Systems, devices and methods for the identification of users on a seat

Abstract

Systems, devices, and methods are disclosed herein for measuring sensor data of a user seated on a toilet and detecting / identifying the user based on the measured sensor data using statistical models and / or machine learning. In some embodiments, the systems described herein can include multiple sensors including force sensor(s), ECG sensor(s), PPG sensor(s), and other sensor(s), disposed in and / or integrated to a toilet. The sensors can measure and / or record sensor data including loads and forces, BCG-data, ECG-data, PPG data, bioimpedance, or the like, and determine, based on the sensor data, one or more physiological parameters and / or characteristics about the user. The systems can be further configured to associate the measured sensor data and the biological conditions and / or characteristics with a user identifier such that the user can be identified by comparing the user identifier with sensor data measured when a subject (e.g., an unidentified subject) is seated on the toilet.

Description

Attorney Docket No.: HHII-007 / 01 WO 341530-2055SYSTEMS, DEVICES AND METHODS FOR THE IDENTIFICATION OF USERS ON A SEATCross-Reference to Related Applications

[0001] This application claims priority to and the benefit of U.S. Provisional Patent Application No. 63 / 681,012, filed August 8, 2024, and titled, “SYSTEMS, DEVICES AND METHODS FOR THE IDENTIFICATION OF USERS ON A SEAT,” the disclosure of which is incorporated by reference herein in its entirety.Background

[0002] Patient health monitoring is an important tool in tracking physiological conditions of patients and to provide early warnings or guidance to individuals and healthcare providers in cases of patient health deterioration. Oftentimes, patient monitoring is obtrusive and requires individuals to actively wear certain devices or change their routine to be able to measure certain vital signs or characteristics of the patient. Unobtrusive systems and / or devices for monitoring individuals are limited. Furthermore, in multiple instances these systems and / or devices are used and / or shared between multiple subjects, individuals, and / or users as for example, in a group and / or household. Consequently, each subject, individual and / or user included in the group and / or household may be required to routinely identify him or herself prior to monitoring and / or measuring his / her vital signs and / or characteristics. Therefore, there exists a need to develop more accurate approaches to identify and then monitor multiple subjects, individuals and / or users using unobtrusive systems.Summary

[0003] In accordance with one aspect of the present disclosure, a sensing system includes a set of sensors disposed on a seat coupled to a waste receptacle and including a surface on which an unidentified user can be seated, the set of sensors configured to measure sensor data of the unidentified user present on the seat when the unidentified user is seated on the seat. The sensing system includes a processor operatively coupled to the set of sensors, the processor can be configured to receive signals indicative of the measured sensor data. In some aspect, the sensing system can further be configured to generate a set of features of the unidentified user from the measured sensor data. The sensing system can be configured to determine, for each known user of a plurality of known users, a measure of similarity between the set of features of the unidentified user and a set of features of that known user stored in a memory. In some aspects, the sensingAttorney Docket No.: HHII-007 / 01 WO 341530-2055 system can be configured to compute p-values for the unidentified user with respect to the plurality of known users based on the measure of similarity and determine for each known user of the plurality of known users; and determine whether the unidentified user is a known user from the plurality of known users or a new user based on the p-values for the unidentified user.

[0004] In accordance with another aspect of the present disclosure, a sensing system includes a set of sensors disposed on a seat coupled to a waste receptacle and including a surface on which an unidentified user can be seated, the set of sensors configured to measure sensor data of an unidentified user present on the seat when the unidentified user is seated on the seat; and a processor operatively coupled to the set of sensors, the processor configured to: receive signals indicative of the measured sensor data; extract physiological parameters of the unidentified user from the measured sensor data; store the physiological parameters of the unidentified user as reference data in a memory; determine, for each known user of a plurality of known users, a measure of similarity between the physiological parameters of the unidentified user and reference data of that known user stored in the memory; compute p-values for the unidentified user with respect to the plurality of known users based on the measure of similarity determined for each known user of the plurality of known users; compare the p-values with detection thresholds for the plurality of known users; determine whether the user is a known user or a new user based on the comparing of the p-values detection thresholds.

[0005] In accordance with another aspect of the present disclosure, a method includes receiving signals indicative of the measured sensor data, the measured sensor data being measured by a set of sensors disposed on a seat coupled to a waste receptacle and including a surface on which an unidentified user is seated; extracting physiological parameters of the unidentified user from the measured sensor data; storing the physiological parameters of the unidentified user as reference data; determining, for each known user of a plurality of known users, a measure of similarity between the physiological parameters of the unidentified user and reference data of that known user; computing p-values for the unidentified user with respect to the plurality of known users based on the measure of similarity determined for each known user of the plurality of known users; comparing the p-values with detection thresholds for the plurality of known users; and determining whether the user is a known user or a new user based on the comparing of the p-values detection thresholds.

[0006] In accordance with another aspect of the present disclosure, a method includes receiving signals indicative of measured sensor data, the measured sensor data being measured by a set of sensors disposed on a seat coupled to a waste receptacle and including a surface on which an unidentified user is seated; generating a set of features of the unidentified user from theAttorney Docket No.: HHII-007 / 01 WO 341530-2055 measured sensor data; determining, for each known user of a plurality of known users, a measure of similarity between the set of features of the unidentified user and a set of features of that known user; computing p-values for the unidentified user with respect to the plurality of known users based on the measure of similarity determine for each known user of the plurality of known users; and determining whether the unidentified user is a known user from the plurality of known users or a new user based on the p-values for the unidentified user.Brief Description of the Drawings

[0007] FIG. 1 illustrates a schematic illustration of a sensing system for identifying a user based on one or more physical and / or physiological characteristics measured from the user, according to an embodiment.

[0008] FIG. 2A schematically depicts a network of devices for identifying a user based on one or more physical and / or physiological characteristics measured from the user, according to an embodiment.

[0009] FIG. 2B schematically depicts a network of devices for identifying multiple users based on physical and / or physiological characteristics measured from each user, according to an embodiment.

[0010] FIGS. 3A, 3B, and 3C are a top, side, and bottom view, respectively, of a toilet seat including a set of sensors for monitoring signals associated with one or more physical and / or physiological characteristics of a user including photoplethysmogram (PPG) signals, electrocardiogram (ECG) signals, and loads, forces and / or ballistocardiogram (BCG) signals, according to an embodiment.

[0011] FIGS. 4 and 5 are top side views of a toilet seats including a set of sensors for monitoring signals associated with one or more physical and / or physiological characteristics of a user, including PPG signals, bioimpedance electrode signals, and / or ECG signals, according to different embodiments.

[0012] FIGS. 6A, 6B, and 6C present a flow chart of an example process for identifying a user using a sensing system, according to an embodiment.

[0013] FIGS. 7 is a flow chart of an example method of processing sensor data recorded with a sensing system to determine a set of features of a user, according to an embodiment.

[0014] FIG. 8 is a flow chart of an example method of determining the identity of a user based on a set of features extracted from sensor data recorded with a sensing system, according to an embodiment.Attorney Docket No.: HHII-007 / 01 WO 341530-2055

[0015] FIG. 9 is a flow chart of an example method of updating a state of a known user based on a set of features extracted from data recorded with a sensing system, according to an embodiment.

[0016] FIG. 10 is a chart depicting a distribution of data points corresponding to two features and / or biomarkers recorded for one or more users, according to embodiments.

[0017] FIG. 11 is a chart depicting changes in data points of a user over time and schematically indicating the adaptability of a sensing system to such changes, according to embodiments.

[0018] FIGS. 12A and 12B are schematic graphs showing the distribution of a variable or feature and the expansion of a variance term for that feature, e.g., for adjusting an identification scheme for identifying the user, according to embodiments.Detailed Description

[0019] The embodiments described herein relate generally to health monitoring systems and devices, and more particularly to systems, devices, and methods for measuring sensor data (e.g., electrical signals such as voltages and / or electrical current, light signals, and / or forces and loads) when users are using a toilet, urinal, or other lavatory device. Such systems, devices, and methods can provide accurate measurements of sensor data including, for example, weight, a ballistocardiogram (BCG), an electrocardiogram (ECG), a photoplethysmogram (PPG), body temperature, and / or a bioimpedance of a user, which can be used to monitor certain physiological data or conditions of the user and to inform the user and / or healthcare providers of changes in such data or conditions necessitating certain therapies, treatments, lifestyle changes, etc.

[0020] Most individuals use toilets, urinals, or other defecation or urination devices on a daily basis. Accordingly, health monitoring that can be conducted while an individual is defecating and / or urinating into such devices can provide an unobtrusive way of regularly monitoring information about that individual. Measures such as a seated weight, BCG, ECG, PPG, body temperature, and / or bioimpedance of an individual can be useful for monitoring information about that individual. For example, such measures can be useful for monitoring certain conditions of the individual, such as, for example, a cardiac or vascular heath of the individual, fever, menstrual health, circadian rhythm, insomnia and sleep disturbances, and / or overall health and wellbeing.

[0021] Various sensing or monitoring systems can be used to measure one or more physical and / or physiological characteristics of a user. For example, scales can be used to measure a body weight or a body mass index (BMI) of a subject. Wearable devices can be used to measure heartbeat, oxygen level, movement, and / or other data of a subject. Such devices, however, may be obtrusive, e.g., requiring a user to incorporate the use of a device into their daily routine.Attorney Docket No.: HHII-007 / 01 WO 341530-2055However, many sensing or monitoring devices are limited to measuring one or a few different physical and / or physiological characteristics of a user, and therefore lack the comprehensive data capture for being able to effectively or accurately identify different users. In private and public settings, multiple users may also use or interact with the same sensing devices. Therefore, it can be desirable to have systems and devices that can not only measure physical and / or physiological characteristics of users but also identify and adapt with different users. The systems, devices and methods described herein facilitate measuring multiple physical and / or physiological characteristics of one or more users, enabling the accurate identification of each user based on one or more features extracted from the measured physical and / or physiological characteristics.

[0022] In some embodiments, systems, devices, and methods described herein can be implemented using a toilet. The toilet can include, for example, one or more sensors configured to measure physical and / or physiological characteristics of users that use or interact with the toilet. In some embodiments, systems, devices, and methods described herein can be implemented using a toilet and / or one or more other sensing devices, e.g., a scale device or a temperature measurement device. The combination of physical and / or physiological characteristics of users that can be measured by such systems and devices can provide more comprehensive assessments of an individual’s health. For example, such physical and / or physiological characteristics can be used to monitor and assess conditions including, for example, an individual’s respiration, body weight, body temperature, BCG, pulse wave velocity (PWV), stroke volume, cardiac output, weight of or urination or defecation and / or a weight change associated therewith, etc. Examples of sensing devices are described in U.S. Patent No. 10,292,658, titled “Apparatus, System, and Method for Mechanical Analysis of Seated Individual,” issued May 21, 2019 (the ’658 patent); U.S. Patent Application Publication No. 2022 / 0378373, titled “Systems, Devices, and Methods for Monitoring Loads and Forces on a Seat,” published December 1, 2022 (the ’373 application); U.S. Patent No. 11,650,094, titled “Systems, Devices, and Methods for Measuring Loads and Forces of a Seated Subject Using Scale Devices,” issued May 16, 2023 (the ’094 patent); U.S. Patent No. 11,969,229, titled “Systems, Devices, and Methods for Measuring Body Temperature of a Subject Using Characterization of Feces and / or Urine,” issued April 30, 2024 (the ’229 application); International Patent Application No. PCT / US2023 / 075553, titled “Photoplethysmography Sensing Module, Systems and Devices Thereof,” filed September 29, 2023 (the ’553 application), and U.S Provisional Patent Application No. 63 / 573,822, titled “Photoplethysmography Sensing Devices with Light Guiding Components, and Systems and Methods Thereof,” filed April 3, 2024 (the ’822 application). The disclosures of each of the foregoing are incorporated herein by reference in their entirety.Attorney Docket No.: HHII-007 / 01 WO 341530-2055

[0023] FIG. 1 shows a schematic illustration of a sensing system 100, according to embodiments. In some embodiments, the sensing system 100 can be implemented as and / or coupled to a toilet, such as, for example, a toilet seat or a ring of a toilet. The sensing system 100 can be configured to measure one or more physical and / or physiological characteristics of users seated on the toilet seat. In some embodiments, the sensing system 100 can identify which user is seated on the toilet seat out of a plurality of different users based on physical and / or physiological characteristics measured of that user and / or features extracted from the measured physical and / or physiological characteristics. FIG. 1 shows the sensing system 100 can include one or more sensor(s) 110, a processor 120, a memory 122, and a communication interface 126.

[0024] The sensor(s) 110 can be configured to measure data that is indicative of one or more physical and / or physiological characteristics of a user. In some embodiments, the sensor(s) 110 can be coupled to or integrated with a toilet seat and / or disposed near a toilet; and be configured to measure data about a user when the user is seated on the toilet seat. Alternatively, or additionally, the sensor(s) 110 can be coupled to, integrated with, or disposed near other lavatory devices, and be configured to measure data about a user when that user is using such devices and / or near such devices. The sensor(s) 110 can include one or more force sensor(s) 130, electrocardiogram (ECG) sensor(s) 140, and / or photoplethysmogram (PPG) sensor(s) 150. Optionally, in some embodiments, the sensor(s) 110 can also include other types of sensor(s) 160, as further described herein.

[0025] The force sensor(s) 130 of the sensing system 100 can be any suitable sensing device that can measure, record, and / or collect forces or loads, e.g., present on a toilet seat when a user is seated on the toilet seat. The measured forces can be used to determine one or more physical or physiological characteristics of the user. The force sensor(s) 130 can be disposed on, integrated, and / or coupled to a ring of a toilet (a toilet seat and / or other waste receptacle). For example, in some embodiments, a ring can include or be coupled to one or more supports (e.g., bumpers), which can be configured to accommodate the force sensor(s) 130 and support the ring on a top portion of a toilet bowl. Alternatively or additionally, the force sensor(s) 130 can be disposed in or adjacent to a hinge or coupler between the ring and a base of the toilet. The force sensor(s) 130 can include load cells (e.g., pneumatic load cells, hydraulic load cells, piezoelectric crystal load cells, inductive load cells, capacitive load cells, magneto strictive load cells, strain gauge load cells), strain gages, force sensing resistors (FSR) or printed or flexible force sensors, optical force sensors, etc.

[0026] The force sensor(s) 130 can be configured to measure force data, which can provide information regarding a weight or BCG of a seated user and / or subject (e.g., by accounting forAttorney Docket No.: HHII-007 / 01 WO 341530-2055 static and / or dynamic loads or forces present on the ring due to the weight of the subject seated on the ring of the toilet). The force sensor(s) 130 can be configured to measure changes in loads and / or forces, that can be used to calculate, for example, a weight change due to defecation or urination. In some embodiments, information collected by the force sensor(s) 130 can be used to determine the forces generated by the cardiac cycle of the seated user and / or subject. In particular, as the heart forcefully ejects fluid into the aorta of the user, the body of the user undergoes a downward and upward force in a repeating pattern, which can cause changes in forces and / or loads exerted by the user on the ring of the toilet. The force sensor(s) 130 can be configured to measure these changes and to provide BCG data for the user over time. In some embodiments, the force sensor(s) 130 can be independent sensors configured to each measure changes in forces and loads exerted by the user seated on the ring of the toilet and generate independent force data. The independent signals can be used to improve signal quality, which can enable more accurate and repeatable measurements.

[0027] In some embodiments, signals from multiple force sensor(s) 130 can be used to determine a seated posture of the user. For example, in some embodiments, the seat of the toilet can include a first number of force sensors 130 disposed on a front portion of the ring of the toilet (e.g., forward force sensors) and a second number of force sensors 130 disposed on the rear portion of the seat of the toilet (e.g., back force sensors). Higher relative signals on the forward force sensors can be indicative of the user leaning forward, with the ratio of the forward to back force sensors being indicative of a posture angle of the user. In some instances, the user weight, age gender, and / or a dimensional measurement associated with the user such as, for example, the user’ s height, a feet to waist length, or a seat to sternal notch distance can be used in conjunction with the static signals described above for a more accurate determination of the posture of the user.

[0028] In some embodiments, the force sensor(s) 130 described herein can be similar to the force sensor(s) described in U.S. Patent Application Publication No. 2022 / 0378373, incorporated above by reference.

[0029] The ECG sensor(s) 140 of the sensing system 100 can be configured to measure an ECG of a subject, such as, for example, a user seated on a toilet. In particular, the ECG sensor(s) 140 can be configured to measure signals representative of the electrical activity of the heart of a user and / or subject originating from the depolarization of the conductive pathway of the heart and the cardiac muscle tissues during each cardiac cycle. In some embodiments, the ECG sensor(s) 140 can include one or more electrodes or conductive elements disposed on, integrated, and / or coupled to a surface of the seat of a toilet (or other waste receptacle). In some embodiments, the ECG sensor(s) 140 can include two or more electrodes or conductive elements for measuring aAttorney Docket No.: HHII-007 / 01 WO 341530-2055 user’s ECG. The electrodes can be disposed on or integrated into a toilet seat, as shown for example, in FIGS. 3 A, 4, and 5 such that the electrodes can be placed in direct contact with skin or tissue of a user, when the user is seated on the toilet. In some embodiments, a processor (e.g., processor 120) operatively coupled to the ECG sensor(s) 140 can be configured to extract one or more features or characteristics from the ECG data, including, for example, heart rate, a R-peak amplitude, a PR interval, a QRS duration, a QT interval, etc.

[0030] The PPG sensor(s) 150 of the sensing system 100 can be any suitable sensing device that can be configured to measure a PPG of a subject, such as, for example, a user seated on a toilet. The PPG sensor(s) 150 can include an electromagnetic radiation source (e.g., a light source) that is configured to generate and direct an electromagnetic radiation signal (e.g., light signal) to a region and / or a tissue of a user, and the PPG sensor(s) 150 can include electromagnetic radiation sensors such as photodetectors, photodiodes, photoresistors, photovoltaic cells, etc. that can measure light reflected by, scattered, and / or transmitted through a region of skin or tissue of the user. The amount of light absorbed, reflected, scattered, and / or transmitted by the region of tissue can be associated with volumetric blood flow variations of the user. In some embodiments, the electromagnetic radiation source can include a light-emitting diode (LED), a Xenon Energy discharge lamp (XED), a fluorescent light source and or lamp, a mercury light source, an incandescent light source, a Laser diode, or the like. In some embodiments, the electromagnetic radiation source of the PPG sensor(s) 150 can be configured to generate electromagnetic radiation having one or more predetermined characteristics, such as, for example, a predetermined frequency or range thereof. For example, the electromagnetic radiation source of the PPG sensor(s) 150 can be configured to generate visible light, infrared (IR) light, ultraviolet (UV) light, etc. In some embodiments, the PPG sensor(s) 150 can include multiple electromagnetic radiation sources that can generate light having different characteristics. In some embodiments, the light source(s) of the PPG sensor(s) 150 can be coupled to one or more filters and / or lenses designed to change, manipulate and / or precondition the electromagnetic radiation (e.g., light) generated by the light source. For example, the one or more filters and / or lenses can be coupled to a light source to control a half-angle a of the light source (also referred to as the cone half angle). The half-angle a of the light source describes the extent to which a light beam generated by the light source is converging or diverging. The PPG sensor(s) 150 can be disposed on, integrated, and / or coupled to the seat of a toilet (or other waste receptacle). In some embodiments, the PPG sensor(s) 150 can be disposed on or integrated into a toilet seat such that the PPG sensor(s) 150 can emit and capture reflected light or other electromagnetic radiation from a user, when that user is seated on the toilet seat.Attorney Docket No.: HHII-007 / 01 WO 341530-2055

[0031] In some embodiments, the PPG sensor(s) 150 described herein can be similar to the PPG sensor(s) described in U.S Provisional Patent Application No. 63 / 573,822 and International Patent Application No. PCT / / US2023 / 075553, incorporated above by reference.

[0032] In some embodiments, the sensing system 100 can include one or more other types of sensors, such as sensor(s) 160. The sensor(s) 160 can be configured to measure one or more properties or characteristics of a user, a toilet or other lavatory device to which the sensor(s) 160 is coupled, and / or an environment near the user or toilet. In some embodiments, the measured data can be used to determine or evaluate one or more physical or physiological parameters and / or characteristics of a user.

[0033] For example, in some embodiments, the sensor(s) 160 of the sensing system 100 can include a temperature sensor. The temperature sensor can be integrated and / or coupled to a toilet and configured to measure, record, and / or collect temperature of a urine stream or feces excreted by a user. In some embodiments, the temperature sensor can be coupled to a toilet seat. The housing can be sufficiently small such that the temperature sensor can fit within a toilet bowl (or other excretion collection device) without interfering with a user and / or individual’s use of the toilet (or other excretion collection device). The temperature sensor may either be static or movable, e.g., in a linear motion and / or rotationally about an axis to span the opening of the toilet bowl (or other excretion collection device) through which urine and / or feces may be collected. As such, the temperature sensor can be used to capture a temperature of urine and / or feces regardless of the exact location where such urine and / or feces is received into the toilet bowl (or other excretion collection device). In an embodiment, the temperature sensor(s) can include one or more heat flux sensors integrated into the toilet seat to measure body core temperature. The heat flux sensor includes a thermal insulator disposed on a top surface of the toilet seat such that a first side and / or surface of the thermal insulator can be in direct contact with a portion of the skin of a user (e.g., a skin surface) when the user is seated on the toilet. The thermal insulator can be covered from a second side and / or surface by an electric heater that can be controlled and / or used to eliminate flow of heat through the insulator, until the temperature of the heater and the skin surface are equal (e.g., Zero heat flux conditions). At the zero heat flux conditions an isothermal tunnel is generated between the skin surface and subdermal tissue located a short distance below the skin surface, which approximates the temperature of the skin of the user (e.g., skin temperature). Additionally or alternatively, in some embodiments the thermal insulator can be coupled to a temperature sensor configured to measure and / or sense a temperature of the first side and / or surface of the thermal insulator, which facilitates measuring heat flux (e.g., by measuring the temperature of the first side and / or surface of the thermal insulator and the temperature of theAttorney Docket No.: HHII-007 / 01 WO 341530-2055 heater) and skin temperature of the user (e.g., at Zero heat conditions). In some embodiments, the sensor(s) 160 of the system 100 can include one or more temperature and heat flux sensors integrated into a toilet seat, and operably coupled to the processor 120 and / or a processor of user device or a third-party device such as those described with reference to FIGS. 2 A and 2B. The temperature and heat flux sensors can be used to sense and / or detect heat flux conditions, measure a temperature of a portion of the skin of a user (e.g., a skin surface) in direct contact with the heat flux sensors when the user is seated on the toilet. The measured temperature (or a signal associated with the measured temperature) and heat flux data can be transmitted to the processor 120 and be fed to a machine learning-based algorithm or an artificial intelligence model to determine a core body temperature of the user. In an embodiment, the temperature sensor(s) can include a noncontact infrared (IR) thermometer or temperature sensor, which can measure temperature based on the thermal radiation or black-body radiation emitted by the object being measured. In some embodiments, the temperature sensor described herein can be similar to the temperature sensors described in U.S. Patent No. 11,969,229, incorporated above by reference.

[0034] In some embodiments, the sensor(s) 160 of the sensing system 100 can include a camera and / or a spectrometer (with optional light source) integrated into a toilet seat such that the camera and / or spectrometer can be used in addition to the other sensors 110 to determine the identity of the user, or to gather additional physiological data such as a speckle plethysmogram. For example, in some embodiments the sensor(s) 160 can include a camera disposed and / or integrated on a surface of the toilet seat which is in direct contact with skin of a user when the user is seated on the toilet. In use, a processor (e.g., the processor 120) can be configured to activate the camera to collect one or more images and determine, from the images, information associated with, for example, a tone and / or other characteristic of the skin of the user seated on the toilet. In some embodiments, the camera can be an infrared skin penetrating camera and / or spectrometer. The images collected by the camera can be used to determine the identity of the user seated on the toilet.

[0035] Additionally or alternatively, the sensor(s) 160 of the sensing system 100 can include two or more electrodes that function as impedance sensor(s). The impedance electrodes and / or sensors can be integrated and / or coupled to a surface of a toilet seat. In some embodiments the impedance sensor(s) can include two impedance sensors: a first impedance sensor disposed on a first side of the toilet seat (e.g., a left side or a right side), and a second impedance sensor disposed on a second side of the toilet seat opposite to the first side, a shown, for example, in FIG. 3 A. The first and second impedance sensors can be disposed on the toilet seat such that the impedance sensors can be placed in direct contact with the buttocks (or any adjacent skin surface) of a userAttorney Docket No.: HHII-007 / 01 WO 341530-2055 when the user is seated on the toilet (e.g., the first impedance sensor being in contact with a first buttock and the second impedance sensor being in contact with the second buttock). The two impedance sensors can be coupled such that the first and second impedance sensors can form a closed-loop circuit. The current and / or voltage associated with the closed-loop circuit can be measured (e.g., the voltage between the impedance sensors can be measured), processed (e.g., amplified, filtered, digitized) and send to a processor (e.g., processor 120). The first and second impedance sensors can be operatively coupled to a processor (e.g., the processor 120) that can receive signals from the first and second impedance sensors to determine a bioimpedance. When a user places his buttocks on the toilet seat (e.g., the left and right buttock in direct contact with the first and second impedance sensors), the first impedance sensor and / or electrode can send a signal (e.g., a current) to the second impedance sensor and / or electrode, and a resulting voltage can be measured between the two electrodes to determine a buttock-to buttock bioimpedance of the user

[0036] In some embodiments, the sensor(s) 160 of the sensing system 100 can include three electrodes that can be configured to function as impedance sensors or as ECG sensors. For example, the three electrodes can be configured as a 3-electrode system. The 3-electrode system can include a first and a second electrode which can be and / or function as single lead signal ECG electrodes; and a third electrode which can be a driven-right-leg (DRL) electrode that functions as a reference point for the ECG signal(s). The first, second, and third electrodes can be operatively coupled (e.g., via an onboard chip or integrated circuit) to a processor (e.g., the processor 120) that can determine ECG data and / or a bioimpedance of a user when the user is seated on the toilet. The onboard chip can be an auxiliary processor configured to receive raw ECG data from the first, second, and third electrode, conduct one or more pre-processing steps to the raw ECG data (e.g., amplify, filter, and / or digitize the raw ECG data recorded by the first, second and third electrode) and then send the pre-processed ECG data to the processor 120. In some embodiments, the onboard chip can be a multi-channel ECG chip.

[0037] In some embodiments, the sensor(s) 160 of the sensing system 100 can include four electrodes that function as impedance sensor(s). The electrodes and / or sensors can include: a first and a second impedance sensor disposed on a first side of the toilet seat (e.g., a left side or a right side), and a third and a fourth impedance sensor disposed on a second side of the toilet seat opposite to the first side, as shown, for example in FIGS. 4 and 5. The first and second impedance sensors can be disposed on the toilet seat such that the first and second impedance sensors can be placed in direct contact with a buttock (or any adjacent skin surface including for example a thigh) of a user when the user is seated on the toilet (e.g., the first and the second impedance sensor being inAttorney Docket No.: HHII-007 / 01 WO 341530-2055 contact with a first buttock of the user). The third and fourth impedance sensor can be disposed on the toilet seat such that the third and fourth impedance sensors can be placed in direct contact with the other buttock (or an adjacent skin surface including for example a thigh) of the user when the user is seated on the toilet (e.g., the third and the fourth impedance sensors being in contact with the second buttock of the user). The four impedance sensors can be coupled such that the first, second, third, and fourth impedance sensor form and / or constitute a kelvin-like drive circuit and / or a four-electrode configuration. The kelvin-like drive circuit configuration can facilitate eliminating resistive voltage losses and / or drops caused by the current source, resulting in more accurate impedance measurement. Additionally, the kelvin-like drive circuit can exhibit reduced sensitivity to the specific characteristics and geometry of the electrical connections, as well as to contact impedance (or a changing contact impedance which would cause your measured impedance to drift over time).

[0038] In some embodiments, the first and the third impedance sensors (e.g., one impedance sensor disposed on each side of the toilet seat) can be configured to act and / or operate as excitation electrodes, which deliver an excitation signal (e.g., apply an excitation current trough the first and the third impedance sensors) when the user is seated on the toilet. The second and the fourth impedance sensors (one impedance sensor disposed on each side of the toilet seat) can be configured to act and / or operate as sensing electrodes, which sense and / or measure a response signal in response to the excitation signal (e.g., measure a voltage difference, loss, and / or drop across the first and the third impedance sensor caused by the excitation current). The first, second, third, and fourth impedance sensor can be operably coupled to a processor (e.g., the processor 120) that can receive signals from the first, second, third, and fourth impedance sensors to determine a buttock-to-buttock bioimpedance of the user.

[0039] Additionally and / or alternatively, in some embodiments the first and the second impedance sensors (e.g., the two impedance sensors disposed on a side of the toilet seat, either the first side or the second side of the toilet seat) can be disposed such that tissue of a thigh of the user seated on the toilet can be placed in contact with the first and the second impedance sensors. That is to say, a first portion of a thigh of the user can be placed in direct contact the first impedance sensor and / or electrode while a second portion of that thigh of the user can be placed in direct contact with the second impedance sensor and / or electrode, as shown, for example in FIG. 5. The first and second impedance sensors can be coupled such that the first and second impedance sensors can form a closed-loop circuit. The current and / or voltage associated with the closed-loop circuit can be measured (e.g., the voltage between the impedance sensors can be measured), processed (e.g., amplified, filtered, digitized) and send to a processor (e.g., processor 120). AsAttorney Docket No.: HHII-007 / 01 WO 341530-2055 described above, the processor can be configured to determine a bioimpedance based on the measured current and / or voltage. When a user places one of the user’s thigh (a left or a right thigh of the user) in contact with the first and second impedance sensor disposed on the toilet seat such that a first portion of the thigh of the user placed in contact with the first impedance sensor and a second portion of that thigh of the user in contact with the second impedance sensor, the first impedance sensor can send a signal (e.g., a current) to the second impedance sensor, and a resulting voltage can be measured between the first and the second impedance sensor to determine a bioimpedance of the thigh of the user. Similarly, the third and fourth impedance sensors can be disposed such that tissue of a thigh of the user seated on the toilet can be placed in contact with the third and the fourth impedance sensors, and a bioimpedance of the thigh of the user can be measured. In some embodiments the sensor(s) 160 of the sensing system 100 can be configured to determine a buttock-to-buttock bioimpedance of the user as well as a thigh impedance of the user.

[0040] In some embodiments, the impedance sensors and / or electrodes described above can be configured to generate an excitation signal and measure a response signal to determine a bioimpedance of the user at a predetermined frequency. In some embodiments the impedance electrodes and / or sensors described above can be configured to determine a bioimpedance of the user at multiple frequencies. For example, in some embodiments the impedance electrodes and / or sensors can be configured to determine a bioimpedance of a user at multiple frequencies between 40 Hz and 10 MHz. In some embodiments, the impedance electrodes and / or sensors can be configured to determine bioimpedance data of the user sequentially (e.g., one frequency at a time producing a frequency sweep). Alternatively, the impedance electrodes and / or sensors can be configured to determine bioimpedance data of the user at different frequencies simultaneously. In some embodiments the impedance electrodes and / or sensors can be configured to determine bioimpedance data of the user continuously while the user is seated on the toilet. In other embodiments the impedance electrodes and / or sensors can be configured to determine bioimpedance data of the user throughout random periods of time while the user is seated on the toilet

[0041] In some embodiments, the force sensor(s) 130, ECG sensor(s) 140, PPG sensor(s) 150 and / or other sensor(s) 160 can be disposed in spaced relation to one another, e.g., at different locations along a toilet ring. In some embodiments, one or more sensors can be disposed adjacent to or near a toilet ring or other component of a toilet, while other sensors are disposed on the toilet ring or other toilet component. For example, one or more force sensors in a scale can be disposed adjacent to a toilet, while other force sensors can be disposed in the toilet (e.g., in a ring or aAttorney Docket No.: HHII-007 / 01 WO 341530-2055 coupler attached to the ring). In some embodiments, one or more of the force sensor(s) 130, ECG sensor(s) 140, and / or PPG sensor(s) 150 can be disposed together on a single circuit board or housing.

[0042] In some embodiments, the data measured, recorded, and / or collected by one or more of the sensor(s) 110 can be used alone or in combination with other information to identify a user, e.g., when the user is seated on a toilet. Because individual users tend to have physical and / or physiological characteristics that are different from that of other users, the sensing system 100 can be configured to analyze data indicative of the physical and / or physiological characteristics of a user to identify that user. In some embodiments, the sensor(s) 130, 140, 150, 160 can collectively measure data associated with a plurality of physiological characteristics of a user and provide this measured data to a processor (e.g., processor 120 or a processor of a separate compute device (see FIGS.2A-2B)). The processor 120 can be any suitable processing device configured to run and / or execute a set of instructions or code. The processor 120 may be, for example, a general purpose processor, a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), and / or the like. The processor 120 may be configured to run and / or execute application processes and / or other modules, processes and / or functions associated with the system 100 and / or a network associated therewith (see FIGS. 2A-2B). In some embodiments, the processor 120 can be coupled to processing circuitry, e.g., electronic components and / or systems configured to process a signal, such as, for example, an ECG waveform, a PPG waveform, a BCG waveform, etc. The processing circuitry can include, for example, an analog-to-digital converter (ADC), a filter, an amplifier, and / or other circuit components configured to process signals and / or inputs.

[0043] In some embodiments, the processor 120 can be configured to analyze data measured by the one or more sensor(s) 110 to identify a user. For example, the processor can be configured to process the measured data, e.g., to remove noise, artifacts, and / or other compromised data. The processor can also be configured to extract one of more features from the measured data and / or to determine one or more physiological characteristics of the user (e.g., core body temperature, weight, BCG, ECG, posture, impedance, or other physiological parameters and / or characteristics) based on the measured data. The processor can be configured to compare the measured data (or extracted features of the data) with reference data (e.g., previously measured or stored data of one or more users) to determine whether the measured data is similar to the reference data. Based on the comparison, the processor may be able to identify the user associated with the measured data. For example, if the measured data is substantially similar to a reference data set associated with User A, then the processor can determine that the measured data is of User A. In some instances,Attorney Docket No.: HHII-007 / 01 WO 341530-2055 where the measured data may not be similar to any reference data, then the processor may indicate that the user associated with the measured data is a new user. Further details of this process are provided below with reference to FIGS. 6A-C, 7, and 8.

[0044] In some embodiments, the system 100 may implement a method and / or process for identifying a user. In some instances, the user may be a new user (e.g., unknown user). In such instances, a new user of a toilet may indicate via an input / output device (e.g., an input / output device coupled to communications interface 126) that the user is a new user. The system 100, via the one or more sensor(s) 110, can record sensor data of the user when the user is seated on the toilet, including, for example, core body temperature, weight, BCG, ECG, posture, impedance, or other physiological parameters and / or characteristics. The system can then associate recorded sensor data with the new user and store the recorded sensor data as reference data and / or a state of the user. The state of the user can then be used for identifying that user during that user’s subsequent uses of the toilet. Further details of this process are provided below with reference to FIGS. 6A-6C, 7, and 8.

[0045] In some embodiments, the processor 120 can be configured to analyze data measured by one or more sensor(s) 110 to monitor and / or evaluate various physiological data or conditions of the subject. For example, the processor can be configured to process and / or analyze sensor data (e.g., received from the force sensor(s) 130, the ECG sensor(s) 140, the PPG sensor(s) 150, and / or the other sensor(s) 160) to determine a temperature, weight, BCG, ECG, posture, impedance, or other physiological parameters and / or characteristics of an individual or subject. The processor can be configured to monitor these physiological characteristics of the user and / or compare them to predetermined metrics associated with certain conditions. The processor can inform the user (or the user’s healthcare providers or caretakers) of changes in such data or conditions necessitating certain therapies, treatments, lifestyle changes, etc. Examples of processing and / or evaluating sensor data to determine physiological parameters and / or characteristics about a user and / or subject are described in U.S. Patent No. 10,292,658, U.S. Patent Application Publication No. 2022 / 0378373, U.S. Patent No. 11,650,094, U.S. Patent No. 11,969,229, and International Patent Application No. PCT / US2023 / 075553, incorporated above by reference.

[0046] The processor 120 can be coupled to the communication interface 126, which can be used to send information to and / or receive information from other devices, as further described herein. The communication interface can be configured to allow two-way communication with an external device, including, for example, the compute device 270, one or more user device(s) 280, and / or one or more third-party device(s) 290, as depicted in FIGS. 2A-2B. The communicationAttorney Docket No.: HHII-007 / 01 WO 341530-2055 interface can include a wired or wireless interface for communicating over a network (e.g., the network 204).

[0047] The processor 120 can be operatively coupled to the memory 122. The memory 122 can be, for example, a random-access memory (RAM), a memory buffer, a hard drive, a database, an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), a read-only memory (ROM), and / or so forth. In some embodiments, the memory 122 stores instructions that cause processor 120 to execute modules, processes, and / or functions associated with processing and / or analyzing sensor data from sensor(s) 110, identifying a subject seated on the toilet based on data measured, recorded, and / or collected by the sensor(s) 110, and / or sending sensor data to other devices via communications interface 126.

[0048] FIG. 2A depicts a block diagram illustrating a sensing system 200 in communication with other devices via a network 204, according to embodiments. In some embodiments, the sensing system 200 can be configured to measure physiological data and / or characteristics of a subject seated on a toilet or other lavatory device. For example, the sensing system 200 can be configured to measure one or more of load or force data indicative or a weight or seated weight, BCG data, ECG data, PPG data, core body temperature, bioimpedance, or the like. In some embodiments, the sensing system 200 can be operatively coupled to one or more of a compute device 270, a user device 280, or a third-party device 290, and to send the measured data to such devices for further processing and / or analysis. In some embodiments, the sensing system 200 or one or more devices coupled to the sensing system (e.g., a compute device 270, a user device 280, or a third-party device 290) can be configured to associate the data measured by the sensing system 200 with a particular individual or subject. In some embodiments, the sensing system 200 or one or more devices coupled to the sensing system (e.g., a compute device 270, a user device 280, or a third-party device 290) can be configured to identify an individual or subject based on the data measured by the sensing system 200.

[0049] The sensing system 200 can include component(s) that are structurally and / or functionally similar to those of other sensing systems and devices described herein, including, for example, sensing system 100. For example, sensing system 200 can have one or more sensors 210. The sensor(s) 210 can include force sensor(s), ECG sensor(s), PPG sensor(s), and / or other sensor(s), similar to those described with reference to sensing system 100. The sensor(s) 210 can be disposed on, integrated, and / or coupled to a seat of a toilet to measure sensor data representative of physiological parameters and / or characteristics about a subject.Attorney Docket No.: HHII-007 / 01 WO 341530-2055

[0050] In some embodiments, the sensing system 200 can be configured to communicate with a compute device 270, one or more user device(s) 280, and / or one or more third-party device(s) 290, via a network 204. The network 204 can include one or more network(s) that may be any type of network (e.g., a local area network (LAN), a wide area network (WAN), a virtual network, a telecommunications network) implemented as a wired network and / or wireless network and used to operatively couple to any compute device, including the sensing system 200, the compute device 270, the user device(s) 280, and the third-party device(s) 290.

[0051] In some embodiments, the sensing system 200 can be configured to send data measured by the sensor(s) 210 to the compute device 270, one or more user device(s) 280, and / or one or more third-party device(s) 290, via a communication interface 226. In some embodiments, the sensing system 200 can include onboard processing, such as, for example, a processor 220 implemented as a microprocessor and / or processing circuitry (e.g., analog-to-digital converter, filter, amplifier, etc.), to process (e.g., filter, convert, etc.) sensor data prior to sending the sensor data to the compute device 270, one or more user device(s) 280, and / or one or more third-party device(s) 290. Alternatively, the sensing system 200 can be configured to send raw sensor data to the compute device 270, one or more user device(s) 280, and / or one or more third-party device(s) 290. In some embodiments, the processor 220 can be configured to analyze the data measured by the sensor(s) 210 and / or determine information such as a seated weight, BCG data, ECG data, PPG data, or other physiological parameters and / or characteristics of a subject seated on a toilet. In some embodiments, the sensing system 200 can be configured to recieve information from a user device 280, which can be used to determine the identity of the user. For example, in some instances, an unknow user can be seated on the toilet while having with him a user device 280. The user device 280 can include a mobile phone or other portable device, a wearable device such as a necklace, a ring, or the like, a tablet, a laptop, a personal computer, a smart device, etc. The user device 280 can be configured to communicate with the compute device 270 via the network 204 to send information and / or data of the user such that the compute device 270 can determine the identity of the user seated on the toilet. The sensing system 200 can be configured to receive from the compute device 270 the identity of the user seated on the toilet. Additionally, or alternatively, in some embodiments the user device 280 can be configured to communicate with the processor 220 of the sensing system 200 to send information and / or data of the user. The sensing system 200 can use the received information and / or data from the user device 280 to determine the identity of the user seated on the toilet.

[0052] In some embodiments, the processor 220 can be configured to associate the measured data and / or physiological parameters extracted and / or obtained from the measured data (e.g., a setAttorney Docket No.: HHII-007 / 01 WO 341530-2055 of features) with a particular individual or subject. In some embodiments, the measured data and / or physiological parameters can be stored as reference data in a memory of the sensing system 200 (not shown). Alternatively, in some embodiments, the measured data and / or physiological parameters can be stored as reference data in a memory or database coupled to the sensing system 200, such as a memory of an external compute device (e.g., compute device 270, user device(s) 280, third-party device(s) 290, and / or other compute device). In some embodiments, the processor 220 can be configured to store reference data of a plurality of known subjects (i.e., subjects with known identities), where the reference data of each subject is associated with that subject and can be used to uniquely identify that subject. In particular, the processor 220 of the sensing system 200 can be configured to receive new data measured by the sensor(s) 210 of an unidentified subject seated on the toilet and to analyze the new data to determine an identity of the unidentified subject. For example, the processor 220 can be configured to compare the new data (or information determined or extracted from the new data) with the data and / or physiological parameters previously stored (e.g., the reference data) to determine whether the unidentified subject is one of the plurality of subjects with which the processor 220 is familiar or knows (e.g., a plurality of known users). In some embodiments, in instances where the processor 220 determines that there is a sufficient degree of similarity or overlap between the new measured data of the unidentified subject and the reference data of a known subject, the processor 220 can determine that the unidentified subject and the known subject have the same identity. For example, the processor 220 can perform cluster analysis or clustering and determine that the new data of the unknown subject belongs to the same cluster as the data associated with one of the known subjects. In some embodiments, the processor 220 can determine whether a set of features of the unidentified user are less than a predetermined distance (e.g., Mahalanobis distance) from the set of features of a known user, and based on such determination, determine the identity of the unidentified user. When the processor 220 can identify the unidentified subject based on the comparison, the processor 220 can associate the new measured data with the identity of the known subject and store such data as future reference data (e.g., in an onboard memory or an external memory). In instances where the processor 220 cannot identify the unidentified subject (e.g., due to lack of similarity with data of a known subject, or a distance that is greater than a predefined threshold), the processor 220 can indicate that the unidentified subject cannot be identified and / or prompt the unidentified subject to provide identifying information. Furthermore, in some embodiments when the new data measured by the sensor(s) 210 of an unidentified subject seated on the toilet cannot lead to identifying the user, the sensing system 200 may be configured to store this new data measured in a memory of the sensing system 200, the memory 274 of the compute device 270,Attorney Docket No.: HHII-007 / 01 WO 341530-2055 and / or a memory of a third-party device 290 as measured data of unrecognized users. In instances where the processor 220 receives new data measured by the sensor(s) 210 of an unidentified subject, the processor can be configured to compare the new data (or information determined or extracted from the new data) with the data and / or physiological parameters previously stored (e.g., the reference data or state of known users), as well as with the data of the unrecognized users. When the processor 220 can identify the unidentified subject based on a comparison with data of unrecognized users, the processor can be configured prompt the unrecognize user to provide identifying information.

[0053] In some embodiments, the processor 220 can be configured to present and / or communicate to a subject the data measured and analyzed by the sensor(s) 210 and / or information extracted from that data (e.g., the seated weight, BCG data, ECG data, PPG data, or other physiological parameters and / or characteristics) via an onboard display, audio device, or other output device. In some embodiments, the processor 220 can be configured to present and / or communicate to the subject the determined identity of the subject and / or user seated on a toilet. In some embodiments, the processor 220 can be configured to present and / or communicate to the subject that the processor was unable to identify the subject and / or prompt the subject to provide identifying information.

[0054] While the functions and processes described above are described with reference to the processor 220 of the sensing system 200, in some embodiments, such functions and processes can wholly or partially be performed or implemented by a separate compute device (e.g., compute device 270, user device(s) 280, and / or third-party device(s) 290). In particular, in some embodiments, the processor 220 can be configured to send the data measured by the sensor(s) 210 (or information extracted or determined from the data measured by the sensor(s) 210) to an external device, e.g., via the communication interface 226. The communication interface 226 can be configured to allow two-way communication with one or more external devices, including, for example, the compute device 270, one or more user device(s) 280, and / or one or more third-party device(s) 290. The communication interface 226 can include a wired or wireless interface for communicating over the network 204.

[0055] The compute device 270 can be configured to perform a variety of processing tasks, including, for example, processing and / or analyzing the sensor data measured by the sensor(s) 210 (or information extracted or determined from the data measured by the sensor(s) 210), determining an identity of an unidentified subject based on the measured sensor data (or information extracted or determined from the measured sensor data), etc. The compute device 270 can include aAttorney Docket No.: HHII-007 / 01 WO 341530-2055 processor 272, a memory 274, and an input / out device (I / O) 276 (or a multiplicity of such components).

[0056] The memory 274 can be, for example, a random-access memory (RAM), a memory buffer, a hard drive, a database, an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), a read-only memory (ROM), and / or so forth. In some embodiments, the memory 274 stores instructions that cause processor 272 to execute modules, processes, and / or functions associated with processing and / or analyzing sensor data from sensing system 200, identifying a subject seated on the toilet, etc.

[0057] The processor 272 of compute device 270 can be any suitable processing device that can execute the modules, processes, and / or functions stored in the memory 274. For example, the processor 272 can be configured to process and / or analyze sensor data (e.g., measured by sensor(s) 210), to determine a weight, BCG, or other physiological data or conditions of an individual. The processor 272 can be configured to associate the sensor data and / or determined physiological data or conditions with a particular individual or subject and to store this data as reference data. The processor 272 can be configured to identify unidentified subjects based on sensor data, e.g., by comparing the measured data of the unidentified subject with the reference data. The processor 272 can be a general-purpose processor, a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), and / or the like.

[0058] The I / O device 276 of the compute device 270 can include one or more components (e.g., a communication or network interface) for receiving information and / or sending information to other devices (e.g., sensing system 200, user device(s) 280, third-party device(s) 290). In some embodiments, the VO device 276 can optionally include or be operatively coupled to a display, audio device, or other output device for presenting information and / or communicating with a user. For example, in some embodiments the I / O device 276 can include a vibration motor disposed in the toilet seat to enable haptic communication with a user. In some embodiments, the I / O device 276 can optionally include or be operatively coupled to a touchscreen, a keyboard, or other input device or receiving information from a user.

[0059] In some embodiments, the compute device 270 can be a nearby compute device (e.g., a local computer, laptop, mobile device, tablet, etc.) that includes software and / or hardware for receiving the sensor data and processing and / or analyzing the sensor data. In some embodiments, the compute device 270 can be a server that is remote from the sensing system 200 but can communicate with the sensing system 200 via the network 204 and / or via another device on the network 204 (e.g., a user device 280). For example, the sensing system 200 can be configured toAttorney Docket No.: HHII-007 / 01 WO 341530-2055 transmit sensor data to a nearby device (e.g., a user device 280), e.g., via a wireless network (e.g., Wi-Fi, Bluetooth®, Bluetooth® low energy, a 2G, 3G, 4G / LTE, 5G, and / or other cellular network, Zigbee and the like), and then that device can be configured to transmit the sensor data to the compute device 270 for further processing and / or analysis.

[0060] The user device(s) 280 can be a compute device(s) that is associated with a user or subject that uses a toilet or other lavatory device equipped with the sensing system 200. Examples of user device(s) 280 can include a mobile phone or other portable device, a wearable device such as a necklace, a ring, or the like, a tablet, a laptop, a personal computer, a smart device, etc. In some embodiments, a user device 280 can receive sensor data from the sensing system 200 and process that sensor data before passing the sensor data to the compute device 270. For example, a user device 280 can be configured to reduce noise (e.g., filter, time average, etc.) raw sensor data. In some embodiments, a user device 280 can be configured to analyze the sensor data and present (e.g., via a display) information representative of or summarizing the sensor data, a determined identity of the subject, and / or other information (e.g., a confidence of the determined identity, alerts for failing to determine the identity of a user, alerts for detecting significant changes in the physiological data of a user, etc.). For example, the user device 280 can present weight information, ECG information, BCG information, bioimpedance information, etc. to a user. In some embodiments, a user device 280 can transmit the sensor data to the compute device 270 or other external devices, which can analyze the sensor data and send information representative of or summarizing the sensor data or identifying the user back to the user device 280 for presenting (e.g., via a display) to a user. For example, in some embodiments the user device 280 can present to a user information about the user such as heart rate, heart rate variability, left ventricular ejection time, pre-ejection period, flow velocity, pulse transit time (e.g., based on ECG or BCG data), blood pressure, cardiac output, cardiac contractility, abnormal heart function, blood oxygenation levels (e.g., SpO2), respiration rate, stress levels (e.g., via heart rate variability), body weight, and / or cardiac waveform characteristics (e.g., magnitudes and / or intervals).

[0061] The third-party device(s) 290 can be compute device(s) associated with other individuals or entities that have requested and / or been provided access to a user’s data. For example, the third-party device(s) 290 can be associated with healthcare professionals (e.g., physicians, nurses, therapists) and / or caregivers of the user. The user can select to have certain third parties have access to the user’s health data (e.g., including health data obtained from sensor data collected by sensing system 200). The third parties can then track the user’s health information to determine whether the user is at risk for certain conditions and / or needs certain interventions, treatments, or care.Attorney Docket No.: HHII-007 / 01 WO 341530-2055

[0062] While the user device(s) 280, and third-party-device(s) 290 are not depicted with any onboard memory, processing, and / or I / O devices, it can be appreciated that any one of these devices can include components (e.g., a memory, a processor, a I / O device, etc.) that enable it to perform functions such as, for example, processing and / or analyzing the sensor data, or using the sensor data to determine physiological information about an individual, and / or identifying an individual based on the determined physiological information (e.g., seated weight, ECG, PPG, BCG, body core temperature, posture, impedance, etc.)

[0063] FIG. 2B schematically illustrates an instance in which a sensing system 200 is placed in communication with a compute device 270 to identify multiple unknown and / or unidentified users based on data measured by the sensing system 200. More specifically, FIG. 2B depicts a room where there is a first unidentified user (e.g., user A) optionally associated with a first user device 280 (e.g., user A device), a second unidentified user (user B) optionally associated with a second user device 280 (e.g., user B device), and a toilet equipped with the sensing system 200. Although not shown in FIG. 2B, the sensing system 200 includes the sensor(s) 210, the processor 220, and the communications interface 226 described above with reference to FIG. 2A. The sensing system 200 can measure new sensor data of one of the unidentified user via the sensor(s) 210 when said unidentified user is seated on the toilet (e.g., user A or user B). The sensing system 200 can be configured to send the new sensor data measured by the sensor(s) 210 to the compute device 270, and / or one or more third-party device(s) 290, via the communication interface 226. In some embodiments, the processor 220 can be configured to pre-process (e.g., filter, convert, etc.) the new sensor data prior to sending the new sensor data to the compute device 270, and / or one or more third-party device(s) 290. Alternatively, in some embodiments the sensing system 200 can be configured to send raw new sensor data to the compute device 270, and / or one or more third- party device(s) 290. The compute device 270 can be configured receive the new sensor data and analyze the new sensor data to determine an identity of the unknow user. For example, in some embodiments the compute device 270 can be configured to receive the new sensor data measured by the sensor(s) 210 and obtain and / or extract a set of features from the measured data such as an ECG waveform, an ECG power, a R-peak amplitude, a PPG waveform, a DC level associated with the PPG waveform (e.g., a slow-varying or non-pulsatile level of the PPG waveform), a seated weight, a ratio of the forward to back forces, a posture, a BCG waveform, bioimpedance, or other physiological parameters and / or characteristics of the unknow user seated on the toilet. The compute device 270 can be further configured to compare the new sensor data (or the set of features determined or extracted from the new measured sensor data) with data and / or physiological parameters of a plurality of user previously stored (e.g., the reference data and / or states of knownAttorney Docket No.: HHII-007 / 01 WO 341530-2055 users) either in the memory 274 of the compute device 270, or in a memory of a third-party device 290. The compute device 270 can compare the new sensor data with the reference data to determine whether the unidentified user seated on the toilet is one of the plurality of users with which the compute device 270 is familiar, as further described herein with reference to FIG. 8. In instances where the compute device 270 determines that there is a sufficient degree of similarity or overlap between the new sensor data of the unidentified user and the reference data of a known user, the compute device 270 can determine that the unidentified user and the known subject have the same identity. That is to say, the compute device 270 can determine whether the unidentified user seated on the toilet is either user A or user B. Optionally, in some embodiments the processor 220 of the sensing system 200 can be configured to receive the new sensor data measured by the sensor(s) 210 and analyze the new sensor data to determine an identity of the unidentified user as described above.

[0064] FIG. 2B shows the compute device 270 can optionally be coupled to multiple user devices 280 such as the user A device and / or to the user B device. In such embodiments, the processor 272 of the compute device 270 can be configured to determine whether the unidentified user seated on the toilet is either user A or user B, and then communicate via the network 204 with the user device 280 of the identified user (e.g., user A device or user B device) and prompt the identified user to confirm the user’s identity. Alternatively, in some embodiments the processor 220 of the sensing system 200 can be configured to communicate via the network 204 with the user device 280 of the identified user (e.g., user A device or user B device) and prompt the identified user to confirm the user’s identity.

[0065] FIGS. 3A-3C 3C show a top, side, and bottom view, respectively, of a sensing device or system 300 for monitoring signals associated with various physiological data or conditions of an individual, according to embodiments. The sensing system 300 shown in FIGS. 3A-3C can be similar in at least form and / or function to the sensing system 100 and 200 described above with reference to FIGS. 1 and 2A-2B. Accordingly, portions of the sensing system 300 that are similar to portions of the sensing system 100 and / or 200 are not described in further detail herein. As shown in FIGS. 3 A-3C, the sensing system 300 is implemented as a toilet seat 301. The toilet seat 301 can be a toilet ring or other component of a toilet on which an individual or subject sits. The toilet seat 301 can be positioned on top of a base (e.g., a top portion of a toilet bowl), such that the toilet seat 301 defines a centrally disposed opening 312 therethrough, e.g., for receiving bodily fluids, defecation, etc. The shape and / or the dimensions of the toilet seat 301 can be circular, oval, elliptical, and / or any other closed annular shape (e.g., a round or “o” shaped toilet seat). Alternatively, in some embodiments the shape and / or dimensions of the toilet seat 301 canAttorney Docket No.: HHII-007 / 01 WO 341530-2055 correspond to an open shape such as, for example, a “U” shape toilet seat (not shown in FIGS. 3 A- 3C. In such embodiments, the toilet seat 301 can include one or more openings that provide and / or generate spaces and / or gaps between the seat and the bowl of the toilet that facilitate a user to sit on the toilet without directly contacting the bowl with their private parts, particularly in the case of male users. For example, in some embodiments the toilet seat 301 can include an opening disposed on a front portion of the toilet seat 301. This opening, which can also be referred to as a front opening of the toilet 301, can create a place where urine may splash, facilitating rapid cleaning of the toilet when the toilet is installed in, for example, a public washroom and / or bathroom.

[0066] The toilet seat 301 can include multiple sensors including, for example, one or more force sensor(s) 330, ECG sensors 340, and a PPG sensor 350. These sensor(s) can be the same or similar in form and / or function to the sensor(s) 110 and 210 described above with reference to FIGS. 1 and 2A-2B. The sensor(s) included and / or incorporated in the toilet seat 301 can be configured to measure multiple signals (e.g., PPG signals, ECG signals, bioimpedance, temperature, and loads and / or forces) present on the toilet seat 301, e.g., when an individual is seated on the toilet seat 301. While not depicted, the toilet seat 301 can also include a processor, a memory, and a communication interface, similar to those described with reference to FIGS. 1 and 2A-2B. Alternatively, the toilet seat 301 can be operatively coupled to a processor, a memory, and / or a communication interface that is not located in the toilet seat, such as that disposed within another component of the toilet (e.g., a base of the toilet) or disposed in an external device (e.g., compute device 270). In some embodiments, the toilet seat 301 can be configured to transmit sensor data collected by the force sensor(s) 330, ECG sensors 340, and PPG sensor 350 to a processor (e.g., processor 120, 220, 272), such that the processor can process and / or analyze the sensor data, as described above with reference to FIGS. 2 A and 2B. In some embodiments, the sensing device 300 depicted in FIGS. 3A-3C can be installed on an existing toilet, e.g., by retrofitting an existing toilet.

[0067] FIG. 4 show the top view of an example sensing device or system 400 for monitoring signals associated with various physiological data or conditions of an individual, according to an embodiment of the present disclosure. As shown in FIG. 4, the sensing system 400 is implemented as a toilet seat 401. The toilet seat 401 can be a toilet ring or other component of a toilet on which an individual or subject sits. The toilet seat 401 can be positioned on top of a base (e.g., a top portion of a toilet bowl), such that the toilet seat 401 defines a centrally disposed opening 412 therethrough, e.g., for receiving bodily fluids, defecation, etc. The shape and / or the dimensions of the toilet seat 401 can be circular, oval, elliptical, and / or any other closed annular shape (e.g., aAttorney Docket No.: HHII-007 / 01 WO 341530-2055 round or “o” shaped toilet seat). The sensing system 400 can be similar in at least form and / or function to the sensing system 100, 200 and 300 described above with reference to FIGS. 1, 2A- 2B, and 3A-3C. Accordingly, portions of the sensing system 400 shown in FIG. 4 that are similar to portions of the sensing system 100, 200 and / or 300 are not described in further detail herein.

[0068] The toilet seat 401 can include multiple sensor(s) including a PPG sensor 450, and four sensors 460 which can be four electrodes. The four sensors and / or electrodes 460 can be configured to function as impedance sensor(s) and / or ECG sensor(s). The PPG sensor 450 shown in FIG. 4 can be the same or similar in form and / or function to the PPG sensor(s) 150 and 350, described above with reference to FIGS. 1, and 3A-3C, respectively. Additionally, and / or alternatively, in some embodiments the toilet seat 401 can also include one or more force sensors configured to record, and / or collect forces or loads, e.g., present on the toilet (not shown in FIG. 4). The sensor(s) included and / or incorporated in the toilet seat 401 can be configured to measure multiple signals (e.g., PPG signals, bioimpedance signals, ECG signals, and loads and / or forces) present on the toilet seat 401, e.g., when an individual is seated on the toilet seat 401. While not depicted, the toilet seat 401 can also include a processor, a memory, and a communication interface, similar to those described with reference to FIGS. 1, and 2A-2B.

[0069] FIG. 4 shows the toilet seat 401 includes four sensors and / or electrodes 460 which can be configured to function as impedance sensor(s). The four impedance sensors 460 can be coupled such that the first, second, third, and fourth impedance sensor 460 form and / or constitute a kelvinlike drive circuit and / or a four-electrode configuration. FIG. 4 shows a first and a second impedance sensor 460 can be disposed on a first side of the toilet seat 401. More specifically, the first impedance sensor can be disposed on a rear portion of the first side of the toilet (e.g., see impedance sensor A), while the second impedance sensor is disposed on a front portion of the first side of the toilet (e.g., see impedance B). In use, the first and second impedance sensors are placed in direct contact with a buttock (or any adjacent skin surface including for example, a thigh) of a user when the user is seated on the toilet. FIG. 4 also shows a third and a fourth impedance sensor 460 can be disposed on a second side of the toilet seat opposite to the first side toilet. The third impedance sensor can be disposed on a rear portion of the second side of the toilet (e.g., see impedance sensor C), while the fourth impedance sensor is disposed on a front portion of the second side of the toilet (e.g., see impedance D). In use, the third and fourth impedance sensors are placed in direct contact with the other buttock (or an adjacent skin surface including for example, a thigh) of the user when the user is seated on the toilet. In some implementations the first and third impedance sensors (e.g., the rear impedance sensors A and C) can be configured to act and / or operate as excitation electrodes, which deliver an excitation signal by applying anAttorney Docket No.: HHII-007 / 01 WO 341530-2055 excitation current trough the first and the third impedance sensors when the user is seated on the toilet. In such implementations, the second and the fourth impedance sensors (e.g., the front impedance sensors B and D) can be configured to act and / or operate as sensing electrodes, which sense and / or measure a response signal in response to the excitation signal (e.g., measure a voltage difference, loss, and / or drop across the first and the third impedance sensor caused by the excitation current). Alternatively, in some implementations the first and third impedance sensors (e.g., the rear impedance sensors A and C) can be configured to act and / or operate as the sensing electrodes, while the second and fourth impedance sensors (e.g., the front impedance sensors B and D) care configured to act and / or operate as the excitation electrodes. The kelvin-like drive circuit configuration described above can facilitate eliminating resistive voltage loses and / or drops caused by the current source, resulting in more accurate impedance measurement. The first, second, third, and fourth impedance sensors described above can be operatively coupled to a processor (e.g., the processor 120, 220, and / or 272) that can receive signals from the first, second, third, and fourth impedance sensors to determine a buttock-to buttock bioimpedance of the user

[0070] Additionally, or alternatively, in some embodiments, the first and the second impedance sensors 460 (e.g., impedance sensor A and B) shown in FIG. 4 can disposed such that tissue of a thigh of the user seated on the toilet can be placed in contact with the first and the second impedance sensors. That is to say, a first portion of a thigh of the user can be placed in direct contact with the first impedance sensor (impedance sensor A) while a second portion of that thigh of the user can be placed in direct contact with the second impedance sensor (impedance sensor B). The first and second impedance sensors can be coupled such that the first and second impedance sensors can form a closed-loop circuit. The current and / or voltage associated with the closed-loop circuit can be measured (e.g., the voltage between the first and second impedance sensors can be measured), processed (e.g., amplified, filtered, digitized) and send to a processor (e.g., processor 120, 220, and / or 272). As described above, the processor can be configured to determine a bioimpedance based on the measured current and / or voltage. When a user places one of the user’s thigh in contact with the first and second impedance sensor disposed on the toilet seat such that a first portion of the thigh of the user placed in contact with the first impedance sensor (impedance sensor A) and a second portion of that thigh of the user in contact with the second impedance sensor( impedance sensor B), the first impedance sensor can send a signal (e.g., a current) to the second impedance sensor, and a resulting voltage can be measured between the first and the second impedance sensor to determine a bioimpedance of the thigh of the user. Similarly, the third and fourth impedance sensors (e.g., impedance sensor C and D) can be disposed such that tissue of a thigh of the user seated on the toilet can be placed in contact with the third and theAttorney Docket No.: HHII-007 / 01 WO 341530-2055 fourth impedance sensors, and a bioimpedance of the thigh of the user can be measured. In some embodiments, the impedance sensors 460 shown in FIG. 4 can be configured to determine a buttock-to-buttock bioimpedance of the user as well as a thigh impedance of the user

[0071] FIG. 5 show the top view of an example sensing device or system 500 for monitoring signals associated with various physiological data or conditions of an individual, according to an embodiment of the present disclosure. As shown in FIG. 5, the sensing device 500 is implemented as a toilet seat 501. The toilet seat 501 can be a toilet ring or other component of a toilet on which an individual or subject sits. The toilet seat 501 can be positioned on top of a base (e.g., a top portion of a toilet bowl), such that the toilet seat 501 defines a centrally disposed opening 512 therethrough, e.g., for receiving bodily fluids, defecation, etc. The shape and / or the dimensions of the toilet seat 501 can be circular, oval, elliptical, and / or any other closed annular shape (e.g., a round or “o” shaped toilet seat). The sensing system 500 can be similar in at least form and / or function to the sensing system 100, 200, 300, and 400 described above with reference to FIGS. 1, 2A-2B, 3A-3C, and 4. Accordingly, portions of the sensing system 500 that are similar to portions of the sensing system 100, 200, 300 and / or 400 are not described in further detail herein.

[0072] The seat 501 can include multiple sensor(s) including a PPG sensor 550, and four sensors 560 which can be four electrodes. The four sensors and / or electrodes 560 can be configured to function as impedance sensor(s) and / or ECG sensor(s). The PPG sensor 550 shown in FIG. 5 can be the same or similar in form and / or function to the PPG sensor(s) 150, 350, and / or 450 described above with reference to FIGS. 1, 3A-3C, and 4 respectively. Additionally, and / or alternatively, in some embodiments the toilet seat 501 can also include one or more force sensors configured to record, and / or collect forces or loads, e.g., present on the toilet (not shown in FIG. 5). The sensor(s) included and / or incorporated in the toilet seat 501 can be configured to measure multiple signals (e.g., PPG signals, bioimpedance signals, ECG signals, and loads and / or forces) present on the toilet seat 501, e.g., when an individual is seated on the toilet seat 501. While not depicted, the toilet seat 501 can also include a processor, a memory, and a communication interface, similar to those described with reference to FIGS. 1, and 2A-2B.

[0073] FIG. 5 shows the toilet seat 501 include four sensors and / or electrodes 560 which can be configured to function as impedance sensor(s). The four impedance sensors 560 can be coupled such that the first, second, third, and fourth impedance sensor 560 form and / or constitute a kelvinlike drive circuit and / or a four-electrode configuration. FIG. 5 shows a first and a second impedance sensor 560 can be disposed on a first side of the toilet seat 501 side by side. That is to say, the first impedance sensor can be disposed on an outer region close to the exterior edge of the first side of the toilet seat 501 (e.g., see impedance sensor A), while the second impedance sensorAttorney Docket No.: HHII-007 / 01 WO 341530-2055 can be disposed on an interior region close to the opening 512 (e.g., see impedance sensor B). In use, the first and second impedance sensors are placed in direct contact with a buttock (or any adjacent skin surface, including for example, a thigh) of a user when the user is seated on the toilet. FIG. 5 also shows a third and a fourth impedance sensor 560 can be disposed on a second side of the toilet seat opposite to the first side toilet side by side. The third impedance sensor can be disposed on an interior region close to the opening 512 (e.g., see impedance sensor C), while the fourth impedance sensor can be disposed on an outer region close to the exterior edge of the second side of the toilet seat 501 (e.g., see impedance sensor D). In use, the third and fourth impedance sensors are placed in direct contact with the other buttock (or an adjacent skin surface, including, for example a thigh) of the user when the user is seated on the toilet.

[0074] In some implementations the first and fourth impedance sensors (e.g., the outer region impedance sensors A and D in FIG. 5) can be configured to act and / or operate as excitation electrodes, while the second and third impedance sensors (e.g., the interior region impedance sensors B and C in FIG. 5) are configured to act and / or operate as sensing electrodes. Alternatively, in some implementations the location of the excitation and sensing electrodes can be reversed. That is to say, the first and fourth impedance sensors (e.g., the outer region impedance sensors A and D in FIG. 5) can be configured to act and / or operate as sensing electrodes, while the second and third impedance sensors (e.g., the interior region impedance sensors B and C in FIG. 5) are configured to act and / or operate as excitation electrodes. In yet other implementations, the first and third impedance sensors (e.g., impedance sensors A and C in FIG. 5) can be configured to act and / or operate as the excitation electrodes, while the second and fourth impedance sensors (e.g., impedance sensors B and D in FIG. 5) are configured to act and / or operate as the sensing electrodes. Additionally, in some implementations the location of the excitation and sensing electrodes can be reversed. For example, the first and third impedance sensors (e.g., impedance sensors A and C in FIG. 5) can be configured to act and / or operate as the sensing electrodes, while the second and fourth impedance sensors (e.g., impedance sensors B and D in FIG. 5) are configured to act and / or operate as the excitation electrodes. The kelvin-like drive circuit configuration(s) described above can facilitate eliminating resistive voltage loses and / or drops caused by the current source, resulting in more accurate impedance measurement. The first, second, third, and fourth impedance sensors described above can be operatively coupled to a processor (e.g., the processor 120, 220, and / or 272) that can receive signals from the first, second, third, and fourth impedance sensors to determine a buttock-to buttock bioimpedance of the user.

[0075] Additionally or alternatively, in some embodiments, the first and the second impedance sensors 560 (e.g., impedance sensor A and B) shown in FIG. 5 can disposed such that tissue of aAttorney Docket No.: HHII-007 / 01 WO 341530-2055 thigh of the user seated on the toilet can be placed in contact with the first and the second impedance sensors. That is to say, a first portion of a thigh of the user can be placed in direct contact with the first impedance sensor (impedance sensor A) while a second portion of that thigh of the user can be placed in direct contact with the second impedance sensor (impedance sensor B). The first and second impedance sensors can be coupled such that the first and second impedance sensors can form a closed-loop circuit. The current and / or voltage associated with the closed-loop circuit can be measured (e.g., the voltage between the first and second impedance sensors can be measured), processed (e.g., amplified, filtered, digitized) and send to a processor (e.g., processor 120, 220, and / or 272). As described above, the processor can be configured to determine a bioimpedance based on the measured current and / or voltage. When a user places one of the user’s thigh in contact with the first and second impedance sensor disposed on the toilet seat such that a first portion of the thigh of the user placed in contact with the first impedance sensor (impedance sensor A) and a second portion of that thigh of the user in contact with the second impedance sensor( impedance sensor B), the first impedance sensor can send a signal (e.g., a current) to the second impedance sensor, and a resulting voltage can be measured between the first and the second impedance sensor to determine a bioimpedance of the thigh of the user. Similarly, the third and fourth impedance sensors (e.g., impedance sensor C and D) can be disposed such that tissue of a thigh of the user seated on the toilet can be placed in contact with the third and the fourth impedance sensors, and a bioimpedance of the thigh of the user can be measured. In some embodiments, the impedance sensors 560 shown in FIG. 5 can be configured to determine a buttock-to-buttock bioimpedance of the user as well as a thigh impedance of the user.

[0076] In some embodiments the impedance sensors and / or electrodes described above with reference to FIGS. 4 and 5 can be configured to generate an excitation signal and measure a response signal to determine a bioimpedance of the user at a predetermined frequency. In some embodiments the impedance electrodes and / or sensors described above can be configured to determine a bioimpedance of the user at multiple frequencies. For example, in some embodiments the impedance electrodes and / or sensors can be configured to determine a bioimpedance of a user at multiple frequencies between 40 Hz and 10 MHz. In some embodiments, the impedance electrodes and / or sensors can be configured to determine bioimpedance data of the user sequentially (e.g., one frequency at a time producing a frequency sweep). Alternatively, the impedance electrodes and / or sensors can be configured to determine bioimpedance data of the user at different frequencies simultaneously. In some embodiments the impedance electrodes and / or sensors can be configured to determine bioimpedance data of the user continuously while the user is seated on the toilet. In other embodiments the impedance electrodes and / or sensors can beAttorney Docket No.: HHII-007 / 01 WO 341530-2055 configured to determine bioimpedance data of the user throughout random periods of time while the user is seated on the toilet.

[0077] In some embodiments, two of the sensors 460 or 560 shown in FIGS. 4 and 5, respectively, can be configured to function as ECG sensors. In such embodiments, the two sensors 460 / 560 (e.g., sensor A and C, sensor B and D, sensor A and D, or sensor B and C) can be configured to measure signals representative of the electrical activity of the heart of a user and / or subject originating from the depolarization of the conductive pathway of the heart and the cardiac muscle tissues during each cardiac cycle, as described above with reference to the ECG sensors 140 and 340 in FIGS. 1 and 3A-3C.

[0078] In some embodiments, three of the sensors 460 or 560 shown in FIGS. 4 or 5, respectively, can be configured to function as ECG sensors. In such embodiments, the three sensors and / or electrodes 460 / 560 can be configured as a 3-electrode system. The 3-electrode system can include a first and a second electrode (e.g., electrode A and C) which can be and / or function as single lead signal ECG electrodes; and a third electrode (electrode B) which can be a driven right leg electrode that functions as a reference point for the ECG signal(s). The first, second, and third electrodes can be operatively coupled to a processor (e.g., the processor 120) that can receive signals from the first, second, and third electrode to determine ECG data and / or a bioimpedance of a user when the user is seated on the toilet.

[0079] Systems and devices described herein, including those described in FIGS. 1-5, can actively and / or passively determine an identity of an individual or subject seated on a toilet seat or other lavatory device. In some embodiments, systems and devices described herein may be configured to store information of users that sit on a toilet and be able to identify those users during subsequent sits on the toilet. In particular, systems and devices described herein may obtain and / or record sensor data of a user (during a regular sit or under different conditions, e.g., during an onboarding or initialization process where the user may be asked to undergo a specific onboarding protocol) and associate that sensor data with a subject. Such associated data can then be stored and used as reference data at future times to identify a user. In some embodiments, the systems and devices described herein may record sensor data of a user sitting on a toilet, and process, via a processor, the recorded sensor data to obtain a set of features of the user. The user may be initially unidentified. The set of features obtained of the user can then be compared to reference data and / or a reference set of features of one or more known users. In some embodiments, the reference data and / or reference set of features of a known user can be referred to as or be included in a state of the user. In some embodiments, the state of a user can represent a biological profile or bio- identification of the user, which can be referenced at future times to identify the user.Attorney Docket No.: HHII-007 / 01 WO 341530-2055

[0080] FIGS. 6A-6C provide an example of a method and / or process 600 for identifying an unidentified user, according to an embodiment. In some instances, the process 600 can be used to identify a user (e.g., an existing and / or known user) based on sensor data collected of the user when the user is seated on the toilet, e.g., biometric data. In other instances, the process 600 can be used to onboard a new user by recording sensor data of the new user when the new user is seated on the toilet and associate the recorded data with an identity of the new user, thus generating a state for the new user. For illustrative purposes, the user that is being identified (e.g., either as a known user or a new user) is referred to as an unidentified user. That is, the identity of the user is initially unknown or not yet identified when the user is seated at the toilet, and therefore in the context of the flows that follow, this user is identified as an unidentified user. The process 600 can be implemented by a processor, including, for example, a processor included in a sensing system or device (e.g., a processor similar to processor 120 and / or 220 described above with reference to FIGS. 1 and 2) or a processor of a remote compute device to which a sensing system or device is coupled (e.g., processor 272 of a compute device 270 described above with reference to FIGS. 2A-2B). In some embodiments, the processor can be coupled to processing circuitry, such as, for example, electronic components and / or systems configured to process a signal (e.g., a ECG waveform, a PPG waveform, a BCG waveform, etc.) The processing circuitry can include, for example, an ADC, a filter, an amplifier, and / or other circuit components configured to process signals and / or inputs. The processing circuitry can be configured to implement portions of process 600, including the processing of one or more signal waveforms, and to generate outputs that can be provided to the processor.

[0081] The process 600 can begin when the unidentified user sits on the toilet. In some embodiments, the sensing system can be operating under a low power consumption mode and can be transitioned to an activated mode once the user is seated on the toilet. In some embodiments, one or more sensors included in the sensing system (e.g., the sensor(s) 110 and / or 210 described above with reference to FIGS. 1 and 2) can sense and / or detect the presence of a user seated on the toilet and send one or more signals to the processor (e.g., the processor 120 and / or 220), such that the processor transitions the sensing system from the low power consumption mode to the activated mode. In the activated mode, the one or more sensors included in the sensing system can be used to record data of the user seated on the toilet. For example, in some embodiments, one or more force sensor(s) 130, ECG sensor(s) 140, PPG sensor(s) 150, or other sensor(s) 160, can sense and / or detect when a user is seated on the toilet and send signals to the processor such that the processor transitions the sensing system from the low power consumption mode to the active mode. Alternatively, and / or additionally, in some embodiments, a proximity sensorAttorney Docket No.: HHII-007 / 01 WO 341530-2055 operably coupled to the sensing system and disposed near the toilet seat can be used to detect when a user is seated on the toilet, and then send the one or more signals to the processor to transition the sensing system from the low power consumption mode to the active mode.

[0082] When the sensing system is activated (e.g., in the active mode), the process 600 can optionally begin by prompting the unidentified user to provide identification information at 601. In some embodiments, the processor can communicate with the user via a communications interface (e.g., communications interface 126 or 226) of the sensing system. For example, the communications interface can include an output device that can present (e.g., via audio or video) a prompt or instruction to the user. Alternatively, the communications interface can communicate the prompt or instruction to an external device (e.g., a user device 280, a compute device 270, and / or a third-party device 290) to have the external device present the prompt or instruction to the user. The processor can prompt the user to provide identification information such as, for example, a name, a birthdate, a username or user identifier, or other information that can be used to identify the user. In instances where the user is a new user, the new user can create a user account and associate their identity to a username or user identifier of the account. Alternatively, in some embodiments the processor can communicate with a caretaker, a healthcare worker, and / or a third party associated with the user via the communications interface (e.g., communications interface 126 or 226) of the sensing system, to prompt and / or request the caretaker, healthcare worker, or third party to provide the identification information of the user. In some instances, the caretaker can remotely (e.g., at a location different from the location in which the user and the sensing system is located) enter all the identification information on behalf of the user of the sensing system. Furthermore, in some embodiments, the caretaker, healthcare worker, or third party can populate the information of the user prior to the user being introduced to the sensing system. In some embodiments, the processor can be configured to automatically obtain information of the user from an external device (e.g., a smartphone or other personal user device), e.g., after the user provide permission for the processor to receive such information.

[0083] At 602, the process 600 includes recording sensor data of the unidentified user seated on the toilet for N seconds and / or for a suitable or predetermined period of time. For example, a sensing system (e.g., sensing system 100, 200, 300, 400 or 500 described above with reference to FIGS. 1-5) can measure and / or record sensor data when a user is seated on a toilet. As described above, the sensing system can include sensors that are configured to measure and record data of the user. The recorded data can be stored as a local file in a memory of the sensing device (e.g., the memory 122 of the sensing system 100 described above with reference to FIG. 1). Additionally, and / or optionally, the recorded data can be transferred via the communicationsAttorney Docket No.: HHII-007 / 01 WO 341530-2055 interface to a memory of a compute device (e.g., memory 274 of compute device 270) for storage after the N seconds and / or the suitable period of time has passed. The sensor data, can include, for example, recording force data, BCG data, ECG data, PPG data, bioimpedance data, and / or temperature data of the user seated on the toilet.

[0084] At 603, the process 600 includes receiving at a processor (e.g., an onboard processor similar to processor 120 and / or 220, or a remote processor such as a processor 272 of a compute device 270, a processor of a user(s) device 280 or a processor of a third-party device 290) the measured and / or recorded data from the sensing system. In some embodiments, the processor can be configured to analyze the recorded sensor data and determine physical and / or physiological information of the user based on the recorded sensor data. For example, the processor can be configured to extract information associated with a set of features of the user. In some embodiments, the processor can be configured to receive the measured and / or recorded data and obtain a set of features of the recorded data including, for example, an ECG waveform, an ECG power, a R-peak amplitude, a PPG waveform, a DC level associated with the PPG waveform, a seated weight, a ratio of the forward to back forces, a posture, or a BCG waveform. Further details of the processing of recorded sensor data to obtain a set of features of a user seated on the toilet are described below with reference to FIG. 7.

[0085] In some embodiments, the processor can compare the sensor data recorded at 602 to previously collected and stored sensor data of known users. In some embodiments the processor can compare one or more features from the set of features obtained at 603, with multiple sets of features of known users of the sensing system. That is to say, the set of features obtained at 603 can be compared to the states of known users at 604. Further details of how this comparison can be implemented is described with reference to FIG. 8 below.

[0086] If, based on the comparison at 604, the processor determines that the sensor data of the user is similar to that of a known user, thereby determining that the user is a known user, the processor can proceed to 606-608. As shown in FIG. 6B, when the processor determines that the set of features obtained at 603 are similar to and / or correspond to the state of a known user, the processor can optionally, at 606, associate and store the set of features obtained at 603 with the known user. For example, the processor can associate and store the set of features in a profile associated with the user, e.g., as maintained in a database or other data structure. Alternatively, and / or additionally, in some embodiments the processor can delete at least a portion of the past data associated with the known user when including the new set of features obtained at 603. For example, the processor may be configured to overwrite the oldest data associated with the user with the new set of features obtained at 603. That is to say, in some embodiments, the processorAttorney Docket No.: HHII-007 / 01 WO 341530-2055 can store a newly obtained feature (or features) of a user and delete one or more previously obtained and / or stored features of the user. For example, in some embodiments the processor can associate and store a feature such as an ECG waveform obtained at 603, with the known user. The newly stored ECG waveform can be added while a past and / or previous ECG waveform included in the state of the user can then be deleted. This can be beneficial or desirable for avoiding the need for increasing data storage space as more and more data is collected of a user.

[0087] At 607, the process 600 can optionally include updating the state of the known user. The processor can select one or more features from the set of features obtained at 603 and include them as part of the state of the user and / or update the state of the user based on the set of features obtained at 603. Further details on how the state of the user can be updated are described with reference to FIG. 9 below.

[0088] At 608, the process 600 includes determining health information of the user. In some embodiments, the processor can further process the sensor data recorded at 602 to determine additional physical and / or physiological information and / or parameters of the known user. For example, in some embodiments the processor can determine a heart rate, heart rate variability, left ventricular ejection time, pre-ejection period, flow velocity, pulse transit time (e.g., based on ECG or BCG data), blood pressure, cardiac output, cardiac contractility, abnormal heart function, blood oxygenation levels (e.g., SpCh), respiration rate, stress levels (e.g., via heart rate variability), body weight, cardiac waveform characteristics (e.g., magnitudes and / or intervals), a core body temperature, etc.

[0089] If, based on the comparison at 604, the processor determines that the sensor data of the user is not similar to that of a known user, thereby determining that the user is not a known user, the processor can proceed to 609-611. FIG. 6C shows where the processor does not determine that the sensor data and / or the set of features obtained at 603 is similar to and / or corresponds to a state of a known user. At 609, the processor can optionally generate a state for the new user, e.g., using the sensor data obtained at 602 and / or set of features obtained at 603. In some embodiments, the processor can prompt the user (e.g., via the communications interface 16 or 226) to provide identification information such as, for example, a name, a birthdate, a username or user identifier, or other information that can be used to identify the new user. Alternatively or additionally, the processor can automatically generate a new identifier for the user and associate the sensor data obtained at 602 and / or set of features obtained at 603 with the new user identifier. In some embodiments, the processor can generate and store a state of the new user, which can include, for example, the sensor data obtained at 602 and / or set of features obtained at 603 associated with a user identifier.Attorney Docket No.: HHII-007 / 01 WO 341530-2055

[0090] Optionally, after determining that the unidentified user is a new user (e.g., not associated with a known user at 605), the processor can initiate an onboarding process, e.g., for capturing additional information of the user so that a state or profile of the user can be created and stored for later use in identifying the user during subsequent sits. In some embodiments, the onboarding process can involve collecting additional senor data of the new user when the new user is seated at different patterns or postures on the toilet seat. These patterns, which can also be referred to as landing patterns correspond to the different positions and / or orientations that the new user may assume when siting on the toilet. The new user can be instructed (e.g., via the communications interface) to adjust his posture and to remain in each posture for a predetermined period of time (e.g., seconds, a minute, or minutes) so that the sensing system can measure data of the user in each posture. In some embodiments, the processor can communicate with the user via the communication interface of the sensing system, to instruct the user to hold each of a plurality of postures for a predetermined period of time. In some embodiments, the processor can transmit a message to an external device (e.g., a user device 280, compute device 270, and / or third-party device 290), instructing the user to hold each of a plurality of postures for a predetermined period of time. The external device can be configured to receive the message from the sensing system and present it to the user e.g., via a display, audio device, or other output component of the external device. Examples of postures that the user may be instructed to be in include: sitting on the toilet with upper body leaning forward such that the weight of the user is closer to the front side of the toilet, sitting on the toilet with upper body leaning backward, sitting on the toilet with upper body leaning to a right or left side, sitting on the toilet with upper body being erect or as straight as possible, etc. In other instances, the sensing system can present a message to the user to instruct the user to seat on the toilet with the user’s upper body leaning forward. In some embodiments, the onboarding process may involve having the user sit multiple times on the toilet, with no particular instruction on pattern or posture.

[0091] Optionally, in some embodiments, the processor can be configured to collect sensor data associated with different patterns or postures of the new user when sitting on the toilet. In some embodiments, the landing patterns of a new user can be recorded by the processor and used to determine a set of features that may be included in the state of the new user. The processor can be configured to collect sensor data of the landing patterns of the new user when the new user sits on the toilet seat. The new user can be instructed (e.g., via the communications interface) to stand up and then sit on the toilet approaching the toilet according to different orientations, positions and / or postures. For example, the new user can be instructed to approach the toilet from the front of the toilet and sit on the toilet while assuming a leaning forward orientation. Alternatively, theAttorney Docket No.: HHII-007 / 01 WO 341530-2055 new user may be instructed to approach the toilet from different orientations (e.g., at an angle, or sideways) while assuming different orientation. The new user can be instructed to repeat instructing the user to stand up and sit on the toilet multiple times so that the sensing system can measure sufficient data of the user in each landing, which can then be processed as further described below with reference to FIG. 7, to generate a set of features that can be included and / or associated with a state of the user. At 611, the process 600 includes determining health information of the user, e.g., similar to that previously described above with reference to FIG. 6B at 608.

[0092] FIG. 6C shows that alternatively, in instances where the processor does not determine that the sensor data obtained at 602 and / or the set of features obtained at 603 is similar to and / or corresponds to a state of a known user, the processor may be configured to discard the sensor data obtained at 602 and / or set of features obtained at 603. In such embodiments, the processor may optionally inform the subject seated at the toilet via the communications interface that a positive identification of a known user was not successfully determined. In some embodiments, the processor may provide additional instructions to the subject to provide identification as described at step 601.

[0093] While the onboarding process can involve collecting a single measurement of a user, or collecting multiple measurements at different postures or patterns, it can be appreciated that any number of measurements of a user can be collected during an onboarding process. For example, a user may be instructed to sit on the toilet for an extended period of time so that n measurements of the data can be taken during that period of time. In some embodiments, the onboarding process may last over a few sitting sessions. For example, a user may be asked to identify himself during multiple sitting sessions on a toilet (such as, for example, the first 3-10 sessions), such that the processor can associate the data measured during those multiple sessions with the user. Having multiple sets of data be collected of a user can increase the robustness of the processor in identifying the user at later times.

[0094] FIG. 7 shows a flow chart of an example method of processing sensor data recorded with a sensing system, according to embodiments. The method depicted in FIG. 7 can be an example of how sensor data can be processed in FIG. 6A at 603. The method can be used to determine and / or obtain a set of features of a user, according to an embodiment. The recorded data can be implemented by a processor included in a sensing system or device (e.g., a processor similar to processor 120 and / or 220 described above with reference to FIGS. 1 and 2) or a processor of a remote compute device to which a sensing system or device is coupled (e.g., processor 272 of a compute device 270 described above with reference to FIGS. 2A-2B).Attorney Docket No.: HHII-007 / 01 WO 341530-2055

[0095] In some embodiments, the processing of sensor data can be different based on the type of sensor data. The processing can be implemented by the processor and / or using processing circuitry, as described above. With respect to ECG data, the processing can include, at 710, determining and / or obtaining an ECG waveform of the user seated at the toilet. As described above, the systems and devices described herein, including those described in FIGS. 1-5, can be used to record sensor data of a user seated on a toilet. The sensor data can include ECG data or signal(s) recorded with a sensor such as the ECG sensor(s) 140, 340 and / or the sensors 160, 460 and / or 560 described above. In some embodiments, the ECG signal (e.g., as measured by the ECG sensor(s)) can be received by the processor and / or processing circuitry, and be processed to obtain, extract, or otherwise determine an ECG waveform, at 710. The processor can subsequently obtain or determine one or more features based on the ECG waveform, including ECG power, at 712, the R-peak amplitude, at 714, and / or a segment or portion of the ECG waveform, at 716. In some embodiments, processing circuitry for receiving and / or processing the raw ECG data from the ECG sensor(s) (e.g., ECG sensor(s) 140, 340) can include electrical components, such as, for example, analog-to-digital converters or sampling devices, that can digitize the analog electrical signals from the ECG sensor(s). The processing circuitry can be configured to sample the raw ECG signals at a rate sufficient to capture a shape of the ECG waveform, such as between about 250 Hertz (Hz) and about 1000 Hz, or any discrete value or range between the range of about 250 Hz to about 1000 Hz. The sampling of the ECG signal captures details of the waveform while the processor applies digital filtering and other signal processing to remove noise and / or artifacts, such as, for example, baseline wander and muscle noise. A signal may also undergo signal processing to be normalized to a standard range. In some embodiments, the ECG signal can be plotted for visualization after signal processing is performed. Alternatively and / or additionally, in some embodiments the ECG signal may be charted, tabulated, listed, or represented in ordered or timeseries data in any other form for further processing.

[0096] In some embodiments, the ECG waveform is processed and / or analyzed to determine or extract features, such as, for example, one or more of ECG power, R-peak amplitude, or other ECG-related characteristics. At 712, ECG power may be calculated or determined, e.g., using algorithms for determining the power of a ECG waveform. For example, calculating and / or determining the ECG power can include determining a measure of the power of the ECG waveform, and can include, for example, determining a mean squared value (MSV) of the ECG waveform or portion thereof, a root mean square (RMS) of the ECG waveform or portion thereof, a power spectral density (PSD) of the ECG waveform or portion thereof, a total harmonic distortion (THD) of the ECG waveform or portion thereof, a short-time Fourier transform (STFT)Attorney Docket No.: HHII-007 / 01 WO 341530-2055 of the ECG waveform or portion thereof, a wavelet transform of the ECG waveform or portion thereof, etc. and / or applying bandpass filtering, energy calculations or other processing to the ECG waveform. In an embodiment, the processor can determine the MSV of the ECG waveform by calculating the mean of the squared ECG signal values over a specified time window. In an embodiment, the processor can determine the RMS of the ECG waveform by calculating the square root of the mean squared value of the ECG signal over a specified time window, such as, for example, the time window defined by the QRS complex of the ECG. In an embodiment, the processor can determine the PSD of the ECG signal by determining the power distribution of the ECG signal as a function of frequency using a Fast Fourier Transform or other similar technique. In an embodiment, the processor can determine the THD of the ECG signal by calculating the ratio of the sum of the powers of harmonic components of the ECG signal to the power of the fundamental frequency of the ECG signal. In an embodiment, the processor can determine the STFT of the ECG signal by analyzing the ECG signal in the time domain and the frequency domain. In an embodiment, the processor can apply a wavelet transform to the ECG signal by decomposing the ECG signal into different frequency bands and calculating the power within each band. In an embodiment, the processor can apply bandpass filtering and / or other energy calculations by filtering the ECG signal to isolate specific frequency bands and / or calculating the energy within the specific frequency bands.

[0097] At 714, R-peak amplitude may be determined by analyzing the amplitude of the detected R peak within a QRS complex of the ECG signal or waveform, or by finding the maximum value of the ECG waveform within a predefined time interval, or by any other suitable R-peak detection methods.

[0098] At 716, the processor may select (e.g., extract) a segment or portion of the ECG waveform, e.g., for calculating a cross-correlation with a reference ECG waveform, such as the ECG waveform of a known user. As described below, the cross-correlation can be used to represent a measure of similarity between two waveforms. Further details of determining a crosscorrelation are described below with respect to FIG. 8. In some embodiments, to determine the segment or portion of the ECG waveform to select, the processor can segment the ECG data (e.g., captured by the ECG sensor(s)) into individual beats. The segmentation can involve identifying each R-peak in the ECG data and segmenting the ECG data into individual beats based on the detected R-peaks. For example, the segmentation can involve identifying each R-peak and then sampling a predetermined period of time before and after the R-peak, e.g., to capture the ECG data that correspond to a heartbeat. The segmented ECG data can then be compared, e.g., across beats, to select a ECG portion or segment, e.g., for further analysis, e.g., cross-correlation, etc.Attorney Docket No.: HHII-007 / 01 WO 341530-2055Alternatively, in some embodiments, the processor can be configured to select a segment or portion of the ECG data by selecting the segment around the highest R-peak in the ECG data. For example, the processor can determine the highest value of the ECG data, and based on this highest value, sample a predetermined time period prior to the highest value and a predetermined time period after the highest value, and use this range of ECG data as the segment or portion of ECG data for calculating a cross-correlation. The predetermined time period before and after the highest value (e.g., highest R-peak) can be the same or be different from one another. In some embodiments, the predetermined time periods can be between about 50 to about 100 ms, including any ranges or values therebetween.

[0099] With respect to PPG data, at 720, the recorded sensor data can be processed to determine and / or obtain a PPG waveform of the user seated at the toilet. As described above, the systems and devices described herein, including those described in FIGS. 1-5, can be used to record sensor data of a user seated on a toilet. The sensor data can include PPG data recorded with a sensor such as the PPG sensor(s) 150, 350, 450, and / or 550 described above. The PPG waveform measured by the sensors can including both the DC (non-pulsatile) and AC (pulsatile) components of the PPG signal. In some embodiments, PPG sensor data can be received and used to determine one or more features, such as, for example, a DC level of the PPG waveform. In some embodiments, the PPG sensor(s) 150, 350, 450, and / or 550 can be connected to the processor by processing circuitry (e.g., analog-to-digital converters (ADCs), sampling devices, etc.), which can be configured to digitize and / or otherwise process the analog PPG signals measured by the PPG sensors. The processing circuitry may be configured to sample the PPG signal at a rate sufficient to capture the DC and / or AC levels of the PPG data, such as between about 25 Hz and about 100 Hz, or any discrete rate or range between about 25 Hz and about 100 Hz. In some embodiments, the PPG signal may be normalized to a standard range for further processing and analysis. In some embodiments, digital filters or other processing may be applied to separate the DC component from the AC component of the PPG signal.

[0100] At 722, the processor can be configured to determine the DC level of the PPG signal. In some embodiments, the DC level can be determined by averaging the PPG signal over a predetermined time window to smooth out pulsatile variations representing the AC signal. The predetermined time window can be selected to be a period of time during which the user is expected to have settled down on the toilet seat and may no longer be engaging in gross movements. For example, the time windows used to calculate DC level of the PPG may be between about 1 second and about 60 seconds in length, including all ranges and values therebetween. The time window during which time the PPG signal is acquired may be delayedAttorney Docket No.: HHII-007 / 01 WO 341530-2055 from the start of the signal being acquired (e.g., when the user first sits down on the toilet). For example, if t=0 seconds is the time reference point at which the user initiates a session recording PPG data (e.g., by sitting down at the toilet), the PPG data used to determine the DC level start at least about 2.5 seconds after t=0, at least about 5 seconds after t=0, or at least about 10 seconds after t=0, including all ranges and values therebetween. In some embodiments, the time window can be between about 2.5 seconds and about 30 seconds, including all ranges and values therebetween.

[0101] In some embodiments, the PPG signal can be filtered or processed to remove or smooth out certain data, and then used to determine the DC level. For example, the PPG signal can be processed using moving average filtering, low-pass filtering, bandpass filtering, polynomial fitting, wavelet transformation, spline interpolation, and / or ensemble empirical decomposition (EEMD). In an embodiment, the PPG signal can be filtered to remove higher frequencies of data, and then used to calculate an average indicative of the DC level of the signal. In some embodiments, the processor be configured to determine or extract feature(s) from the AC signal of the PPG waveform. For example, the processor may be configured to identify the peaks of the AC component of the signal to determine related biometric features, such as, for example, the systolic peak, heart rate, pulse rate variability, or other biometric features.

[0102] With respect to force data, at 730, the recorded sensor data can be used to determine and / or obtain seated forces exerted by the user seated on the toilet. As described above, the systems and devices described herein, including those described in FIGS. 1-5, can be used to record sensor data of a user seated on a toilet for a period of time (e.g., N seconds). The sensor data can include static and / or dynamic loads or forces present on the ring and / or toilet when the user is seated on the toilet, measured and / or recorded with the aid of the force sensor(s) 130, and / or 330 described above. In some embodiments the processor can be configured to receive force sensor data and determine, at 732, a seated weight of the user by accounting for static and / or dynamic loads or forces present on the ring of the toilet due to the weight of the individual. In some embodiments, the seated weight of the user can be determined and / or obtained by averaging the loads and forces recorded by the sensing system during the entire period of time that the user is seated (e.g., during the N seconds). In some embodiments, the average can be of an upper percentage of the weight samples, e.g., an upper percentage between about an highest 1% and about an highest 30% of the weight samples, including all ranges and values therebetween. In other embodiments, the seated weight of the user can be determined and / or obtained by averaging a subset of all the loads and forces recorded by the sensing system during a seated session. For example, in some embodiments, the seated weight of the user can be determined and / or obtainedAttorney Docket No.: HHII-007 / 01 WO 341530-2055 by averaging the loads or forces recorded during a time interval within the period of time of the recording (e.g., a subset of the period of time of the recording) selected with respect to the start of the recording. In some embodiments, the seated weight of the user can be determined and / or obtained by averaging an upper percentage of the loads and forces measured during a time interval within the period of time of the recording (e.g., a subset of the period of time of the recording). In some embodiments, the time interval can be toward a beginning of the recording, e.g., to capture the weight of the user prior to urination and / or defecation. In some embodiments, the time interval can be toward an end of the recording, e.g., to capture the weight of the user after urination and / or defecation. In some embodiments, both seated weight toward a beginning of a recording and an end of the recording can be collected and used to identify the user.

[0103] In some embodiments, the processor can receive sensor data recorded with a first number of sensors 130 disposed on a front portion of the ring of the toilet (e.g., forward sensors) and a second number of sensors 130 disposed on the rear portion of the ring of the toilet (e.g., back sensors). Higher relative signals on the forward sensors is indicative of the subject leaning forward, with the ratio of the forward to back sensors indicative of the posture angle. The processor can be configured to receive the force sensor data, determine a ratio of the forward to back sensors signal data, and determine a posture of the user, at 734. In some embodiments, the processor can be configured to determine a ratio of the forward to back sensors signal data by dividing an aggregate value representing the forces or loads measured by the forward sensors (e.g., a mean, median, etc. of the forces or loads measured by the forward sensors) by an aggregate value representing the forces or loads measured by the back sensors (e.g., a mean, median, etc. of the forces or loads measured by the back sensors). In yet other embodiments, statistical analysis (e.g., machine learning) of signals gathered at different postures of users on the toilet across a population can be used to provide a posture estimate from the obtained signals.

[0104] At 740, the static and / or dynamic loads or forces recorded by the force sensors 130 and / or 330 can optionally be used to determine a BCG waveform of the user. In some embodiments, sensor data collected by the sensor(s) 130 and / or 330 can be used to determine the forces generated by a heart of the user seated on the toilet. As described above, as the heart forcefully ejects fluid into the aorta of the individual, the body of the individual undergoes a downward and upward force in a repeating pattern, which can cause changes in forces and / or loads exerted by the individual on the ring 110. The sensor(s) 112 can be configured to measure these changes and provide BCG waveform of the individual. In some embodiments, processing circuitry such as an ADC, filter, etc. can be used to process and / or clean the measured force data to generate a BCG waveform.Attorney Docket No.: HHII-007 / 01 WO 341530-2055

[0105] At 750, the features determined by the processor, including an ECG waveform, ECG power, R-Peak amplitude, PPG waveform, DC level of the PPG signal, seated weight, posture, and / or BCG data of the user can be used as the set of features for identifying the user. In some embodiments, this set of features can be organized in a feature vector, which can subsequently be compared to feature vectors of known users. The process of comparing the set of features of the unidentified user to the feature vectors of known users is further described below with reference to FIG. 8.

[0106] While ECG waveform, ECG power, R-Peak amplitude, PPG waveform, DC level of the PPG signal, seated weight, posture, and BCG data of the user are described with respect to methods described herein, it can be appreciated that other physiological signals and / or data can be used to identify a user. In some embodiments, the features used to identify a user can be selected based on the equal error rate (EER) of each feature. For example, a processor (e.g., such as any of the processors described herein) can be configured to compare the EERs of a plurality of features, e.g., to determine which feature(s) to use to identify users. For each feature, the EER can represent the rate at which the false match rate (FMR) is equal to the false non-match rate (FNMR). The FMR represents the rate at which a feature or features are incorrectly matched to those of a known user, while the FNMR represents the rate at which a feature or features fails to be correctly matched with that of a known user. At the EER, the likelihoods of FMR and FNMR are equivalent. The EER can then be used to evaluate the performance of a feature, as it can provide a quantitative measure of the trade-off between the FMR and the FNMR. The lower the EER of a feature, the better the performance of a feature as being a unique identifying feature of a subject. As such, in some embodiments, a processor can be configured to use EER to select the feature(s) to use to identify one or more subjects. In other embodiments, other methods involving optimization, averaging, or other balancing operations may be performed to identify the features that are most capable of identifying a user. Such features can then be the ones that are included in the feature vector for an unidentified user, e.g., to identify the unidentified user.

[0107] While several types of features, such as the ECG waveform, ECG power, R-Peak amplitude, PPG waveform, DC level of the PPG signal, seated weight, posture, and / or BCG data of the user, are described as being processed and / or determined in FIG. 7, it can be appreciated that embodiments described herein can include a subset of these features. For example, in some embodiments, systems, devices, and methods described herein may process and / or determine one or more of ECG waveform, ECG power, R-Peak amplitude, PPG waveform, DC level of the PPG signal, seated weight, posture, and / or BCG data of the user, but not all of these features. In such embodiments, one or more steps as shown in FIG. 7 may be omitted.Attorney Docket No.: HHII-007 / 01 WO 341530-2055

[0108] FIG. 8 shows a flow chart of an example method of comparing a set of features of an unidentified user (e.g., determined based on sensor data recorded with a sensing system) with sets of features (e.g., states) of known users, according to embodiments. The method depicted in FIG. 8 can be an example of how comparing the set of features of the unidentified user with the states of known users described in FIG. 6A at 604 is implemented. FIG. 8 shows a processor can be used to analyze the set of features of the unidentified user obtained and / or extracted from sensor data recorded by a sensing system when the user is seated at a toilet, such that the processor can determine whether the user is a known user. The processor can be a processor included in a sensing system or device (e.g., a processor similar to processor 120 and / or 220 described above with reference to FIGS. 1 and 2) or a processor of a remote compute device to which a sensing system or device is coupled (e.g., processor 272 of a compute device 270 described above with reference to FIGS. 2A-2B).

[0109] At 802, the processor can be configured to determine a measure or degree of similarity between the set of features obtained and / or extracted as described above with reference to FIG. 6A at 603 and the state of each known user. In some embodiments, the degree of similarity may be represented as a Euclidian distance, an LI distance, a maximum distance, a cosine similarity, a Minkowski distance, a hamming distance, a Mahalanobis distance, etc. In some embodiments, the degree of similarity can be determined or estimated through the use of machine learning, such as autoencoders, support vector machines, k-nearest neighbors, convolutional neural networks, recurrent neural networks, or other machine learning techniques. The method of determining the degree of similarity can be impacted by correlations between the features being compared. Accordingly, it is beneficial that the method of determining the degree of similarity take into account correlation between the features being compared. In other words, the method of determining the degree of similarly can be configured decorrelate the data.

[0110] In an example embodiment, the processor can be configured to determine a Mahalanobis distance between the set of features of the unidentified user and a set of features of each known user. As noted above, the set of features of the known users can be stored as states of the known users. The Mahalanobis distance can be used to account for correlations among variables (e.g., features) while considering differences in their scales. The Mahalanobis distance can be configured to marry signals from multiple sensors together, while also being selfnormalizing and self-whitening (e.g., by decorrelating features to provide robust assessments). When computing the Mahalanobis distance, a covariance matrix may be used. The covariance matrix contains the variances of each variable and the covariances between variables in the dataset.Attorney Docket No.: HHII-007 / 01 WO 341530-2055In particular, the covariance matrix indicates the covariance of each pair of variables (e.g., features) in set of features.[oni] In some embodiments, the diagonal of the covariance matrix, which includes the variance of the features, can be weighted based on the uniqueness of each person’s data relative to a corpus of data (e.g., a population distribution), e.g., to widen the tolerance a specific feature. For example, as schematically depicted in FIGS. 12A and 12B, the variance of a particular feature can be increased, e.g., by a factor a. FIG. 12A depicts the distribution of the feature without adjusting the variance, while FIG. 12B depicts the distribution of the feature after adjusting the variance. Weighting the diagonal of the covariance matrix enables methods and algorithms described herein to adjust for when a user may have a particularly unique feature (e.g., is an outlier for a particular feature, such as an unusually high or unusually low weight, etc.). The covariance matrix allows for scaling and orienting the features while normalizing the influence of different variances and covariances. The Mahalanobis distance, through the usage of weighting of the covariance matrix, can scale the distribution of the features depending on the unique morphologies of a particular user. The adjustment can shorten or reduce the Mahalanobis distance between any two features.

[0112] As described above with reference to FIG. 7, the processor can be configured to generate a set of features including one or more of the ECG waveform, ECG power, R-Peak amplitude, PPG waveform, DC level of the PPG signal, seated weight, posture, and / or BCG data of the user. Some of these features, such as R-peak, ECG power, seated weight, DC level of PPG signal, etc., are fiducial point features, while others, such as the ECG waveform, are non-fiducial features. Non-fiducial features such as the ECG waveform may provide more robust data, e.g., facilitating more accurate user identification. When calculating the degree of similarly based on non-fiducial features, however, it may be necessary to change the non-fiducial feature into another metric that can be used with certain measures or approaches, such as the Mahalanobis distance. In particular, the use of certain processing techniques with an ECG waveform, such as a matched filter, may not integrate well with a classifier that uses the Mahalanobis distance. Therefore, in some embodiments, the processor can be configured to cross-corelate the ECG waveform (e.g., determined at 716) of the unidentified user with the ECG waveform of a known user. The crosscorrelation value or coefficient can be a value between 0 and 1, and can represent the degree of similarity between the ECG waveform of the unidentified user and the ECG waveform of a known user. When the unidentified user and the known user are the same, the cross-correlation coefficient approaches 1 (e.g., is closer to 1 than 0). The processor, after calculating the cross-correlation coefficient, can then use the coefficient as a feature in calculating the Mahalanobis distance. One challenge with doing this, however, is that the cross-correlation coefficient while capable of beingAttorney Docket No.: HHII-007 / 01 WO 341530-2055 a distribution (e.g., between 0 and 1) is not a Gaussian distribution but an exponential distribution, which can present complications when used in a covariance matrix. To address this challenge, a distribution for the cross-correlation coefficient can be defined by mirroring the ECG crosscorrelation data across 1, and computing the standard deviation of the distribution after mirroring for use in the covariance matrix of the Mahalanobis distance. While cross-correlation is described herein for adapting a non-fiducial feature for use in a Mahalanobis-based classifier, it can be appreciated that other suitable statistical methods of treating non-fiducial data can also be used.

[0113] At 804, the processor can be configured to compute a p-value for each determined measure of similarity, e.g., each Mahalanobis distance representing the distance between the set of features of the unidentified user and the state or set of features of a known user. The p-value for each measure of similarity can represent the likelihood that the set of features of the unidentified user belongs to a known user. For example, the p-value can represent the probability of the occurrence of a match between the set of features of the unidentified user and the state of a known user. With respect to the Mahalanobis distance, the p-value corresponds to the Chi-square statistic of the Mahalanobis distance. The Mahalanobis distance, based on the degrees of freedom (number of features), is converted to a p-value.

[0114] Optionally, at 808, the processor can be configured to a determine, for each known user, a detection threshold for the p-value to match a preset false match rate (FMR). The threshold can be set based on a given FMR. For example, for a known user acceptable of a higher FMR, the p-value threshold may be set lower with any p-value that is greater than the set p-value threshold determined to a match (i.e., the unidentified user being identified as the known user). Alternatively, for a known user that desires a lower FMR, the p-value threshold may be set higher with any p-value that is less than the set p-value threshold determined to not be a match (e.g., to be statistically significant and indicative of the unidentified user not being the known user). In some embodiments, the p-value threshold can be set based on a graph or function that defines a relationship between the FMR and the p-value threshold. The graph can be a decreasing function, such that higher FMR is associated with a lower p-value and a lower FMR is associated with a higher p-value. In some embodiments, the p-value threshold can be set based on a look-up table or other aspect that provide a p-value threshold given a target FMR. The effect of setting the p- value based on the FMR allows one to tailor the detection threshold (e.g., identification of the unidentified user being a known user) based on the tolerance of each user to being falsely matched. In some embodiments, the FMR can be set to be between less than about 1% and less than about 10%, including all values therebetween (including, for example, less than about 2%, less than about 3%, less than about 4%, and less than about 5%). The processor may be configured to thenAttorney Docket No.: HHII-007 / 01 WO 341530-2055 compare the p-values calculated at 804 to the p-value threshold to determine whether or not the calculated p-value represents that the unidentified user is a known user. More specifically, the processor can be configured to determine, based on the p-value associated with the measure of similarity (e.g., Mahalanobis distance) between the feature vector of the unidentified user and the feature vector of a known user, whether the feature vector of the identified user exceeds the p- value threshold of the known user and therefore can be identified as the known user.

[0115] In some embodiments, the FMR for any given known user can be set by the processor or can be selected (and modified) based on user input. For example, a physician, individual, patient, caretaker, etc. can set the FMR to different values, e.g., based on the health condition of that user, whether a user is an outlier, etc. In some embodiments, if a doctor has fewer patients, the doctor may set the FMR to be higher, whereas if the doctor has more patients, the doctor may set the FMR to be lower.

[0116] Other statistical methods may be used to determine whether a given feature vector matches or exceeds a detection threshold associated with a state (e.g., set of features) of a known user. Additionally, detection thresholds may be determined through a corresponding FMR or through other known methods.

[0117] FIG. 9 shows a flow chart of an example method of updating a state of a known user, e.g., based on a set of features extracted from data recorded with a sensing system, according to embodiments. The method shown in FIG. 9 can be an example of updating the state of a known user, as described in FIG. 6B at 607. The method shown in FIG. 9 can be conducted and / or executed by any processor as those described herein.

[0118] The method can include different approaches or processes for updating different types of data, including for example fiducial point features (e.g., ECG power, R-peak magnitude, seated weight, etc.) and / or non-fiducial features (e.g., ECG waveform). For example, the method can include updating a non-fiducial feature, such as, for example, the ECG waveform. At 901, the processor can retrieve a plurality of ECG waveforms stored for the known user. In some embodiments, the sensing system can be configured to store in a memory a plurality of ECG waveforms associated with the known user. The memory can be any memory included in a sensing system or device (e.g., a memory similar to memory 122 described above with reference to FIG. 1) or a memory of a remote compute device to which a sensing system or device is coupled (e.g., memory 274 of a compute device 270 described above with reference to FIGS. 2A-2B). The plurality of ECG waveforms may be obtained from ECG data previously recorded by the sensing system when the user is seated at a toilet. In some embodiments, the memory can store any suitableAttorney Docket No.: HHII-007 / 01 WO 341530-2055 quantity of ECG waveforms, including for example, at least 1 ECG waveform, at least 1 ECG waveform, at least 1 ECG waveform, at least 2 ECG waveform, at least 3 ECG waveform, at least 5 ECG waveform, at least 8ECG waveform, at least 10 ECG waveform, at least 20 ECG waveform, at least 50 ECG waveform, or any suitable number of ECG wave forms.

[0119] At 902, a processor may be configured to arbitrate among the stored ECG waveforms, e.g., to select a most representative waveform. The processor may be configured to arbitrate using statistical methods, machine learning methods, or any other suitable arbitration methods. For example, in an embodiment, the processor may have retrieved a plurality of the most recent ECG waveforms of the known user at 901. At 902, the processor may then arbitrate among the plurality of recent ECG waveforms to select a most representative waveform. In some embodiments, the most representative waveform may be selected based on determining cross-correlation coefficients between each waveform and the other waveforms, and then selecting the waveform that has the greatest cross-correlation coefficients (e.g., greatest average of the cross-correlation coefficients, greatest sum of the cross-correlation coefficients, or other aggregate measure of the crosscorrelation coefficients). Additionally, or alternatively, other metrics can be used to select a most- representative waveform. For example, a representative waveform can be selected based on the presence of a defining characteristic, through the absence of a defining characteristic, through a mathematical or statistical calculation, or through a machine learning method.

[0120] The method can also include updating one or more fiducial point features, e.g., ECG power, R-peak magnitude, seated weight, DC level of the PPG waveform, etc. For example, at 904, the processor may be configured to retrieve stored data of one or more fiducial point feature(s) of the known user. For such features, the processor may be configured to calculate an average or aggregate value of the feature, based on the most recent measured data points or values for the feature, at 905.

[0121] In some embodiments, the processor can calculate at 905 an updated average of the feature(s) of the known user retrieved at 904. For example, the processor can calculate a simple average (e.g., mean, median, etc.) of the data points for the feature(s). In some embodiments, the processor can be configured to apply a weighting function (e.g., an exponential filter) or weights to the data points, and to calculate a weighted average. For example, the processor can be configured to apply greater weights to more recent values, such that more recent values have a greater impact on the averaged value. In some embodiments, the processor can be configured to update a feature or set by features by weighting a new value (or more recent values) for the feature(s) by a predefined percentage relative to a current average value of the feature. TheAttorney Docket No.: HHII-007 / 01 WO 341530-2055 predefined percentage can be, for example, between about 5% and about 20%, inclusive of all values and ranges therebetween.

[0122] At 907, the processor may be configured to generate an updated state of the known user, where the updated state includes the most representative ECG waveform determined at 902 and / or the updated averages of the feature(s) determined at 905. The updated state can be stored in memory, e.g., for use in identifying an unidentified user in a subsequent sit. The updating performed herein can be used to account for changes in biological data over time, as described with reference to FIG. 11 below.

[0123] For illustrative purposes, FIG. 10 depicts an example of data points of different users plotted on a scatter plot, according to embodiments. Each data point can represent or be indicative of one or more physiological characteristics, conditions, and / or features of a user obtained and / or determined from recorded sensor data during multiple sittings of the user. For example, the scatter plot can represent a way to visualize the physiological characteristics, conditions, and / or features of users, where multiple features associated with the physiological characteristics, conditions, and / or other information of the users are assigned different axes and data of each user is plotted accordingly on those axes. Each data point may be associated with a different measurement taken of the user, e.g., using sensing systems or devices as described herein. For example, each data point may be associated with a measurement taken of a user at different times he has used a toilet or other lavatory device (e.g., during differing sitting sessions at a toilet). Alternatively or additionally, for users that may have been instructed to undergo a method and / or process for identifying a user as described above in FIGS. 6A-6C, one or more data points of that user may be associated with recordings of the user under different conditions (e.g., when the user is instructed to sit holding a plurality of postures for a predetermined period of time at different postures, or when the user is instructed to take n measurements, as described above). As shown in FIG. 10, a first user may have a plurality of data points that can be grouped together, e.g., based on a cluster analysis. Similarly, a second user may have a plurality of data points that can be grouped together, e.g., based on cluster analysis. Given the grouping of the data points for both users, systems and devices described herein can be configured to determine whether a new data point of an unidentified user is sufficiently similar to (e.g., correlated with) the data points of either user to identify the unidentified user as the first user, the second user, or a new user. It can be appreciated that while the data of two users is depicted in FIG. 10, the data of any number of users can be stored by systems and devices described herein and referenced, when new data is measured of a user, to identify that user.Attorney Docket No.: HHII-007 / 01 WO 341530-2055

[0124] In some embodiments, the sensor data and / or one or more features from the set of features that is obtained from a user during a live session (e.g., when the user is seated on the toilet for a period of time) can be associated with an state of a user, and stored to be used as future reference data or references set of features of that user. For many users, their physiological data may change over time, e.g., based on changing circumstances and / or health. As such, unobtrusive health monitoring systems that a user would commonly interface with, e.g., such as a toilet or other lavatory device, can be well suited to track the changes in physiological data of such users.

[0125] FIG. 11 schematically shows chart depicting changes in data points (e.g., sensor data recorded with a sensing system and / or features obtained from the recorded sensor data of a user overtime) schematically indicating the adaptability of a sensing system to such changes, according to embodiments. For example, as illustratively shown in FIG. 11, the data points and / or features associated with a user may migrate over time. FIG. 11, similar to FIG. 10, depicts an example of data points of users plotted on a scatter plot. Each data point can represent or be indicative of one or more physiological characteristics, conditions, and / or features of a user. Over time (e.g., over a plurality of sitting sessions), a user may change state, e.g., due to weight low, new medication, new environment, etc. These changes are reflected in the data points of that user. The processor can be configured to track these physiological changes of a user over time and to update one or more reference features of the user, as described above with reference to FIG. 9. The processor of the sensing system can track the data of a user to passively adapt a biological profile or bioidentification of the user over time. By constantly or repeatedly associating new sensor data of a user with the state of the user the processor can be configured to adapt a biological profile or bioidentification of the user over time. That is to say, the processor can be configured to update the reference data and / or reference features of the user over time, as described above with reference to FIG. 9.

[0126] In some instances the processor can be configured to compare the user’s sensor data (or information and / or features extracted therefrom) to predetermined metrics indicative of various health conditions. As a user’s data migrates towards a predetermined threshold or other metric that is indicative of a health condition, the processor can be configured to alert a user of such migration. In some embodiments, the processor can be configured to communicate with one or more other compute devices (e.g., a user device or a third-party device) to inform a user or third- party clinicians or caregivers of the user’s condition.

[0127] While systems, devices, and methods are described herein with respect to a toilet seat or lavatory, it can be appreciated that systems, devices, and methods described herein can be implemented in other types of devices. For example, systems, devices, and methods can performAttorney Docket No.: HHII-007 / 01 WO 341530-2055 user identification with other types of sensing systems, including, wearable devices (e.g., armbands, wristbands, headbands, glasses, etc.), scales, exercise equipment, etc

[0128] While various inventive embodiments have been described and illustrated herein, those of ordinary skill in the art will readily envision a variety of other means and / or structures for performing the function and / or obtaining the results and / or one or more of the advantages described herein, and each of such variations and / or modifications is deemed to be within the scope of the inventive embodiments described herein. More generally, those skilled in the art will readily appreciate that all parameters, dimensions, materials, and configurations described herein are meant to be exemplary and that the actual parameters, dimensions, materials, and / or configurations will depend upon the specific application or applications for which the inventive teachings is / are used. Those skilled in the art will recognize or be able to ascertain using no more than routine experimentation, many equivalents to the specific inventive embodiments described herein. It is, therefore, to be understood that the foregoing embodiments are presented by way of example only and that, within the scope of the appended claims and equivalents thereto; inventive embodiments may be practiced otherwise than as specifically described and claimed. Inventive embodiments of the present disclosure are directed to each individual feature, system, article, material, and / or method described herein. In addition, any combination of two or more such features, systems, articles, materials, and / or methods, if such features, systems, articles, materials, and / or methods are not mutually inconsistent, is included within the inventive scope of the present disclosure.

[0129] Also, various inventive concepts may be embodied as one or more methods, of which an example has been provided. The acts performed as part of the method may be ordered in any suitable way. Accordingly, embodiments may be constructed in which acts are performed in an order different than illustrated, which may include performing some acts simultaneously, even though shown as sequential acts in illustrative embodiments

Claims

1. Attorney Docket No.: HHII-007 / 01 WO 341530-2055Claims1. A sensing system, comprising: a set of sensors disposed on a seat coupled to a waste receptacle and including a surface on which an unidentified user can be seated, the set of sensors configured to measure sensor data of the unidentified user present on the seat when the unidentified user is seated on the seat; and a processor operatively coupled to the set of sensors, the processor configured to: receive signals indicative of the measured sensor data; generate a set of features of the unidentified user from the measured sensor data; determine, for each known user of a plurality of known users, a measure of similarity between the set of features of the unidentified user and a set of features of that known user stored in a memory; compute p-values for the unidentified user with respect to the plurality of known users based on the measure of similarity determine for each known user of the plurality of known users; and determine whether the unidentified user is a known user from the plurality of known users or a new user based on the p-values for the unidentified user.

2. The sensing system of claim 1, wherein the processor further configured to: determine a detection threshold for each known user of the plurality of known users to match a preset false match rate (FMR), the FMR being a rate at which the set of features of the unidentified user is incorrectly matched to each known user of the plurality of known users, wherein the processor is configured to determine whether the unidentified user is a known user by: comparing the p-values for the unidentified user with the detection threshold of each known user of the plurality of known users; determining the unidentified user is a known user, when the p-value is greater than the detection threshold for a known user of the plurality of known users; and determining the unidentified user is a new user, when the p-value is below the detection threshold for each known user of the plurality of known user.Attorney Docket No.: HHII-007 / 01 WO 341530-20553. The sensing system of claim 1, wherein the set of sensors includes force sensors configured to collectively measure forces present on the seat when the unidentified user is seated on the seat.

4. The sensing system of claim 3, wherein the set of sensors further includes a scale device configured to measure forces present on the scale device when the unidentified user is seated on the seat and one or more feet of the unidentified user is placed on the scale device.

5. The sensing system of claim 1, wherein the set of sensors includes at least one of a electrocardiogram (ECG) sensor , (photoplethysmogram) PPG sensor, body temperature sensor, and a bioimpedance sensor.

6. The sensing system of claim 1, wherein the measure of similarity is a Mahalanobis distance.

7. The sensing system of claim 6, wherein the processor is configured to determine the measure of similarity by: cross-correlating an ECG waveform of the unidentified user with the ECG waveform of each known user of the plurality of known users; and determining a cross-correlation value based on the cross-correlating.

8. The sensing system of claim 7, wherein the cross-correlation value is used as a feature to calculate the Mahalanobis distance.

9. The sensing system of claim 8, wherein the cross-correlation value is closer to 1 when the unidentified user is the same as a known user of the plurality of known users.

10. A sensing system, comprising: a set of sensors disposed on a seat coupled to a waste receptacle and including a surface on which an unidentified user can be seated, the set of sensors configured to measure sensor data of an unidentified user present on the seat when the unidentified user is seated on the seat; andAttorney Docket No.: HHII-007 / 01 WO 341530-2055 a processor operatively coupled to the set of sensors, the processor configured to: receive signals indicative of the measured sensor data; extract physiological parameters of the unidentified user from the measured sensor data; store the physiological parameters of the unidentified user as reference data in a memory; determine, for each known user of a plurality of known users, a measure of similarity between the physiological parameters of the unidentified user and reference data of that known user stored in the memory; compute p-values for the unidentified user with respect to the plurality of known users based on the measure of similarity determined for each known user of the plurality of known users; compare the p-values with detection thresholds for the plurality of known users; determine whether the user is a known user or a new user based on the comparing of the p-values detection thresholds.

11. The sensing system of claim 1, wherein the processor further configured to: determine a detection threshold for each known user of the plurality of known users to match a preset false match rate (FMR), the FMR being a rate at which the set of features of the unidentified user is incorrectly matched to each known user of the plurality of known users, wherein the processor is configured to determine whether the unidentified user is a known user by: comparing the p-values for the unidentified user with the detection threshold of each known user of the plurality of known users; determining the unidentified user is a known user, when the p-value is greater than the detection threshold for a known user of the plurality of known users; and determining the unidentified user is a new user, when the p-value is below the detection threshold for each known user of the plurality of known user.

12. The sensing system of claim 11, wherein the FMR can be set based on a tolerance of each known user of the plurality of known users to be matched.Attorney Docket No.: HHII-007 / 01 WO 341530-205513. The sensing system of claim 11, wherein the processor is configured to associate and store the set of features of the unidentified user as a state for a known user of the plurality of known users when the p-value is greater than the detection threshold.

14. The sensing system of claim 10, wherein the set of sensors includes force sensors configured to collectively measure forces present on the seat when the unidentified user is seated on the seat.

15. The sensing system of claim 10, wherein the set of sensors further includes a scale device configured to measure forces present on the scale device when the unidentified user is seated on the seat and one or more feet of the unidentified user is placed on the scale device.

16. The sensing system of claim 10, wherein the measure of similarity is a Mahalanobis distance.

17. The sensing system of claim 16, wherein the processor is configured to determine the measure of similarity by: cross-correlating an ECG waveform of the unidentified user with the ECG waveform of each known user of the plurality of known users; and determining a cross-correlation value based on the cross-correlating.

18. The sensing system of claim 17, wherein the cross-correlation value is used as a feature to calculate the Mahalanobis distance.

19. The sensing system of claim 18, wherein the cross-correlation value is closer to 1 when the unidentified user is the same as a known user of the plurality of known users.

20. A method, comprising: receiving signals indicative of measured sensor data, the measured sensor data being measured by a set of sensors disposed on a seat coupled to a waste receptacle and including a surface on which an unidentified user is seated; generating a set of features of the unidentified user from the measured sensor data;Attorney Docket No.: HHII-007 / 01 WO 341530-2055 determining, for each known user of a plurality of known users, a measure of similarity between the set of features of the unidentified user and a set of features of that known user; computing p-values for the unidentified user with respect to the plurality of known users based on the measure of similarity determine for each known user of the plurality of known users; and determining whether the unidentified user is a known user from the plurality of known users or a new user based on the p-values for the unidentified user.

21. The method of claim 20, further comprising: determining a detection threshold for each known user of the plurality of known users to match a preset false match rate (FMR), the FMR being a rate at which the set of features of the unidentified user is incorrectly matched to each known user of the plurality of known users, wherein determining whether the unidentified user is a known user includes: comparing the p-values for the unidentified user with the detection threshold of each known user of the plurality of known users; determining the unidentified user is a known user, when the p-value is greater than the detection threshold for a known user of the plurality of known users; and determining the unidentified user is a new user, when the p-value is below the detection threshold for each known user of the plurality of known user.

22. The method of claim 21, wherein determining, for each known user of a plurality of known users, a measure of similarity between the set of features of the unidentified user includes: cross-correlating an ECG waveform of the unidentified user with the ECG waveform of each known user of the plurality of known users; and determining a cross-correlation value based on the cross-correlating.

23. The sensing system of claim 22, wherein the cross-correlation value is used as a feature to calculate the Mahalanobis distance, the Mahalanobis distance being the measure of similarity.Attorney Docket No.: HHII-007 / 01 WO 341530-205524. The sensing system of claim 23, wherein the cross-correlation value is closer to 1 when the unidentified user is the same as a known user of the plurality of known users.

25. A method, comprising: receiving signals indicative of the measured sensor data, the measured sensor data being measured by a set of sensors disposed on a seat coupled to a waste receptacle and including a surface on which an unidentified user is seated; extracting physiological parameters of the unidentified user from the measured sensor data; storing the physiological parameters of the unidentified user as reference data; determining, for each known user of a plurality of known users, a measure of similarity between the physiological parameters of the unidentified user and reference data of that known user; computing p-values for the unidentified user with respect to the plurality of known users based on the measure of similarity determined for each known user of the plurality of known users; comparing the p-values with detection thresholds for the plurality of known users; and determining whether the user is a known user or a new user based on the comparing of the p-values detection thresholds.

26. The method of claim 25, further comprising: determining a detection threshold for each known user of the plurality of known users to match a preset false match rate (FMR), the FMR being a rate at which the set of features of the unidentified user is incorrectly matched to each known user of the plurality of known users, wherein determining whether the unidentified user is a known user includes: comparing the p-values for the unidentified user with the detection threshold of each known user of the plurality of known users; determining the unidentified user is a known user, when the p-value is greater than the detection threshold for a known user of the plurality of known users; and determining the unidentified user is a new user, when the p-value is below the detection threshold for each known user of the plurality of known user.Attorney Docket No.: HHII-007 / 01 WO 341530-205527. The method of claim 25, wherein determining, for each known user of a plurality of known users, a measure of similarity between the set of features of the unidentified user includes: cross-correlating an ECG waveform of the unidentified user with the ECG waveform of each known user of the plurality of known users; and determining a cross-correlation value based on the cross-correlating.

28. The sensing system of claim 27, wherein the cross-correlation value is used as a feature to calculate a Mahalanobis distance, the Mahalanobis distance being the measure of similarity.

29. The sensing system of claim 28, wherein the cross-correlation value is closer to 1 when the unidentified user is the same as a known user of the plurality of known users.

Images