Biomonitoring devices, methods, and systems for use in bathroom setting

Abstract

To provide a biomonitoring device for measuring parameters of substances excreted into a toilet bowl by users.SOLUTION: A biomonitoring device is provided, comprising an electromagnetic radiation source disposed to be above excretion and configured to emit electromagnetic radiation into a toilet bowl, and a sensor comprising a lens positioned to be above excretion and configured to detect electromagnetic radiation or analyte chemicals in the toilet bowl. The electromagnetic radiation source and the sensor are located behind a sitting portion of a toilet seat, and the lens is arranged such that the position thereof relative to the toilet bowl does not change when the toilet seat is lifted.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] This application claims the benefit of U.S. Provisional Application No. 62 / 482,912, filed April 7, 2017.

[0002] This application relates generally to biomonitoring and, more specifically, to biomonitoring devices and methods for measuring medically significant waste and health-related characteristics to assist with health-related tasks. [Background technology]

[0003] Examination of human excreta is recognized to provide insight into human health. Self-reporting via diaries is possible but is subject to interpretation and bias. The ability to objectively and consistently assess excreta on a regular basis can help track symptoms of functional disorders and determine the effectiveness of medications, diet, lifestyle, supplements, and other interventions.

[0004] The major components of the American bathroom, including toilets and mirrors, have remained fundamentally unchanged for over 100 years. In the United States, toilets most often have no electrical, sensor, or connected features. In Japan, toilet seats are widely used as powered bidets for hygiene reasons. Most bathroom mirrors around the world have no electrical sensors or connected features specifically related to health or wellness.

[0005] Therefore, there is a need for accurate, convenient, and unbiased electronic biomonitoring capabilities to analyze waste and other health-related characteristics in a bathroom environment. The present invention addresses that need. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] U.S. Pat. No. 4,697,656 [Patent Document 2] U.S. Patent No. 6,077,222 [Patent Document 3] U.S. Pat. No. 9,416,524 [Patent Document 4] U.S. Pat. No. 9,592,034 [Patent Document 5] U.S. Pat. No. 9,595,185 [Patent Document 6] U.S. Pat. No. 9,671,343 [Patent Document 7] U.S. Pat. No. 9,737,181 [Patent Document 8] U.S. Pat. No. 9,755,586 [Patent Document 9] U.S. Pat. No. 9,757,097 [Patent Document 10] U.S. Pat. No. 9,766,257 [Patent Document 11] U.S. Pat. No. 9,801,508 [Patent Document 12] U.S. Pat. No. 9,810,686 [Patent Document 13] U.S. Pat. No. 9,822,519 [Patent Document 14] U.S. Pat. No. 9,845,593 [Patent Document 15] U.S. Pat. No. 9,867,513 [Patent Document 16] U.S. Pat. No. 9,880,138 [Patent Document 17] US Patent Application Publication No. 2006 / 0155175 [Patent Document 18] US Patent Application Publication No. 2017 / 0135677 [Patent Document 19] US Patent Application Publication No. 2010 / 0170722 [Patent Document 20] US Patent Application Publication No. 2010 / 0205722 [Patent Document 21] US Patent Application Publication No. 2016 / 0374619 [Patent Document 22] US Patent Application Publication No. 2017 / 0198464 [Patent Document 23] US Patent Application Publication No. 2017 / 0198466 [Patent Document 24] US Patent Application Publication No. 2017 / 0198466 [Patent Document 25] US Patent Application Publication No. 2017 / 0204595 [Patent Document 26] US Patent Application Publication No. 2017 / 0251996 [Patent Document 27] US Patent Application Publication No. 2017 / 0254060 [Patent Document 28] US Patent Application Publication No. 2017 / 0254526 [Patent Document 29] US Patent Application Publication No. 2017 / 0322197 [Patent Document 30] US Patent Application Publication No. 2018 / 0000417 [Patent Document 31] US Patent Application Publication No. 2018 / 0020889 [Patent Document 32] US Patent Application Publication No. 2018 / 0020984 [Patent Document 33] US Patent Application Publication No. 2018 / 0052955 [Non-patent literature]

[0007] [Non-Patent Document 1] Gruber et al. (2016). Gas monitoring during a glucose challenge by a combined PTR-QMS / GCxGC-TOFMS approach for the verification of potential volatile biomarkers. Journal of breath research. 10:036003 [Non-Patent Document 2] Janssen et al. (2000) Estimation of skeletal muscle mass by bioelectrical impedance analysis. Journal of Applied Physiology 89:465-471 [Non-Patent Document 3] Kushner (1992). Bioelectrical impedance analysis: a review of principles and applications. Journal of the American College of Nutrition 11:199-209 [Non-Patent Document 4] Kushner and Schoeller (1986). Estimation of total body water by bioelectrical impedance analysis. American Journal of Clinical Nutrition 44:417-424 [Non-Patent Document 5] Zheng et al. (2011) The footprints of gut microbial-mammalian co-metabolism. Journal of proteome research. 10:5512-22 Summary of the Invention [Problem to be solved by the invention]

[0008] The present invention is directed to devices, systems and methods for electronic biomonitoring of fecal waste characteristics in a bathroom environment. [Means for solving the problem]

[0009] Thus, in some embodiments, a biomonitoring device is provided that measures a parameter of a substance expelled by a user while using a toilet, the device comprising a sensor that detects electromagnetic radiation or analyte chemicals in the toilet bowl.

[0010] Also provided is an example of a biomonitoring device that is a bathroom mirror, which identifies the user, detects febrile illness in the user, doses medications / supplements, connects to electrical device accessories in the bathroom, and provides an interactive user interface.

[0011] Further, there is provided a system for measuring parameters of substances excreted during use of a toilet by a user, the system comprising the biomonitoring device as described above.

[0012] In another embodiment, a method of determining a physiological parameter of a user is provided, the method comprising expelling a substance into a toilet bowl in the presence of the biomonitoring device described above. [Brief description of the drawings]

[0013] [Figure 1] FIG. 1 is a perspective view of a system of the present invention. [Figure 2A] FIG. 2 is a top perspective view of the integrated seat toilet device of the present invention. [Figure 2B] FIG. 2 is a bottom view of the device. [Figure 2C] An exploded view of the image sensor within the device. [Figure 2D] FIG. 13 shows a portion of the interior of the device from a top perspective cross-sectional view. [Figure 2E] A close-up view of the load cell within the device. [Figure 2F] FIG. 1 illustrates spectroscopic components within the device. [Figure 3A] FIG. 2 is a perspective view of an air duct system in an integrated seat toilet device of the present invention, the air duct system being located at the bottom of the device. [Figure 3B] An enlarged view of the air exit path from the air duct system. [Figure 3C] A close-up view of the array of gas sensors in the air duct system. [Figure 4A] FIG. 2 is an exploded perspective view of an image sensor embodiment of the present invention. [Figure 4B] FIG. 2 is an exploded view of an image sensor embodiment. [Figure 5A] FIG. 2 is an exploded perspective view of another image sensor embodiment of the present invention. [Figure 5B] FIG. 2 is an exploded view of an image sensor embodiment. [Figure 6A] FIG. 1 illustrates a stool collection embodiment of the present invention. FIG. 2 is a bottom perspective view of one embodiment. [Figure 6B] FIG. [Figure 6C] FIG. 13 is a bottom perspective view of an alternative attachment method for a fecal collection embodiment. [Figure 7] FIG. 2 is an exploded view of a foot scale embodiment of the present invention. [Figure 8] FIG. 1 is a perspective view of a wall console of the present invention. [Figure 9A] FIG. 2 is a front perspective view of a wall-mounted mirror embodiment of the present invention; [Figure 9B] FIG. 2 is an exploded perspective view of a wall mirror embodiment. [Figure 9C] FIG. 13 is a perspective view of accessories associated with the wall mirror embodiment. [Figure 9D] A diagram showing the touch screen user interface. [Figure 10A] FIG. 2 is a perspective view of a portable embodiment of the device of the present invention. [Figure 10B] FIG. 2 illustrates components of an embodiment. [Figure 10C] FIG. 13 shows the device with wings at 90 degrees. [Figure 10D] FIG. 13 shows the device with wings at 180 degrees. [Figure 10E] FIG. 2 illustrates the device being opened and taken out of sleep mode. [Figure 10F] FIG. 1 illustrates typical steps in using the device. [Figure 10G] FIG. 1 illustrates typical steps in using the device. [Figure 10H] FIG. 1 illustrates typical steps in using the device. [Figure 10I] FIG. 1 illustrates typical steps in using the device. [Figure 11A] FIG. 1 shows an embodiment of the device of the present invention that clips onto a toilet seat. FIG. 1 is a perspective view of the device clipped onto the seat. [Figure 11B] FIG. 2 is a cutaway view of the device. [Figure 11C] FIG. 2 is a cross-sectional view of the device. [Figure 11D] FIG. 13 is an additional cross-sectional view of the device. [Figure 12A] FIG. 1 illustrates an embodiment of a device of the present invention that fits between the bottom of a toilet seat and the edge of a toilet bowl. FIG. 2 is a perspective view of the device installed on a toilet. [Figure 12B] FIG. 2 is a cutaway view of the device. [Figure 12C] FIG. 2 is a cross-sectional view of the device. [Figure 13] FIG. 1 illustrates an example of a general-purpose computing device that can be used to store, transmit, and process data from the devices of the present invention. [Figure 14] FIG. 1 is a block diagram illustrating an exemplary communication network architecture, devices, and components for operating the devices of the present invention. [Figure 15A] FIG. 2 is a block diagram illustrating an exemplary image processing and classification method for processing data from the device of the present invention, showing exemplary image pre-processing tasks. [Figure 15B] FIG. 1 illustrates one image classification method for classifying stool consistency. [Figure 15C] FIG. 1 illustrates one image classification method for detecting color in feces. [Figure 15D] FIG. 1 shows a set of labels for stool and urine classification. [Figure 15E] FIG. 1 illustrates a workflow for estimating human excretion. [Figure 16] FIG. 1 is a block diagram illustrating an exemplary set of steps taken by a user, device, software, and / or user interface during use of a device of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. Furthermore, the use of "or" is intended to include "and / or" unless the context clearly indicates otherwise.

[0015] The present invention is directed to devices, systems and methods for electronic biomonitoring of fecal waste characteristics in a bathroom environment.

[0016] Thus, in some embodiments, a biomonitoring device is provided that measures parameters of substances expelled by a user while using a toilet, the device comprising one or more sensors that detect electromagnetic radiation or analyte chemicals within the toilet bowl.

[0017] These embodiments are not narrowly limited to any particular biomonitoring device, nor are they limited to the measurement of any particular parameter or any particular excreted substance. In various embodiments, the substance is feces, urine, flatus, or gases emitted from feces or urine.

[0018] 1 shows an exemplary system of the present invention in a bathroom environment, comprising a toilet 200 with various sensors integrated into the seat, a foot scale 300, a wall console 400, and a mirror 500. These various components of the system are discussed further below.

[0019] FIG. 2A shows an exemplary toilet 200 from FIG. 1. A conductive material 201 is provided on the device to function as a bioelectrical impedance analysis electrode. Bioelectrical impedance is determined by applying a sinusoidal current into the body through the electrodes, indicated by reference number 201. The sinusoidal current is generated by an internal pattern generator and a digital-to-analog converter. A voltage-to-current converter applies this sinusoidal current into the body between a pair of two terminals. The voltage generated between these two terminals by the impedance of the body is measured by a differential amplifier, rectified, its amplitude is extracted, and measured by an analog-to-digital converter (ADC). The measured voltage is directly related to the body impedance. General calibration methods and established formulas that can be used to derive body composition are described in Kushner (1982), Kushner and Schoeller (1986), and Janssen et al. (2000), to name a few examples.

[0020] The conductive material can be applied to the seat by any method known in the art or hereafter discovered. In some embodiments, a pad-printable, B-stageable, two-part conductive epoxy adhesive containing carbon filler is applied to the fixed device by tampography and cured at 100°C for 1 hour. The sheet resistance of the epoxy adhesive is 140-200 ohms / sq / mil. The epoxy adhesive has elongation properties that provide flexibility, for example when a user sits on the device, and is resistant to solvents such as common toilet cleaning chemicals and abrasives.

[0021] 2A also shows a nozzle 202 for dispensing a liquid operably connected to a container 203, which may be replaceable, for containing the liquid to be dispensed into the toilet bowl, such as a deodorant, chemical reagent, or cleaning agent. A charging port 204 is operably connected to the battery for recharging the battery.

[0022] FIG. 2B illustrates an exemplary toilet in a bottom perspective view. A low distortion lens 205 is provided, which may further include hydrophobic and antimicrobial coatings. Electromagnetic radiation may travel from inside the toilet bowl through the lens 205 to the image sensor. An additional or alternative lens 206 made of a material similar to lens 205 may be utilized in a position that does not change when the seat is lifted. Behind the lenses 205 and 206 is a light source that projects electromagnetic radiation in the visible and / or invisible ranges of the electromagnetic spectrum. A load cell 207 is for capturing the weight of a user. In some embodiments, the load cell 207 pivots to accommodate contact with non-flat surfaces and / or includes a non-slip material where it contacts the toilet bowl.

[0023] FIG. 2C shows an exploded view of the image sensor, light source, and lens in an exemplary toilet. The image sensor is in a housing 208. A lens 209, which may be coated with a hydrophobic and antimicrobial coating, allows the passage of electromagnetic radiation of various frequencies and wavelengths. An electromagnetic radiation source 210 may emit electromagnetic radiation in the visible and invisible ranges of the electromagnetic spectrum into the toilet bowl. Visible and / or invisible light captured by the lens may be measured electronically by any means known in the art, for example using an active pixel sensor such as a charge-coupled device (CCD) or a complementary metal-oxide semiconductor (CMOS) 211. Light passing through the lens may also be measured using a thermography array consisting of a focal plane array responsive to longer wavelengths (mid-wave and long-wave infrared). Illumination of the image is performed by switching on the electromagnetic radiation source 210. Image capture is performed by a sensor 211, which acquires an illuminated image of the inside of the toilet bowl at configurable time intervals.

[0024] 2D illustrates a top perspective cutaway view of a portion of the interior of an exemplary toilet apparatus. Load cells 212 capture forces in multiple vectors. Load cells that capture forces in one vector, such as thin film load cells, can also be used. Capacitive sensors 213 detect the presence of a user while the user is seated on the device. The user's presence initiates a sensor measurement that can be used to determine the length of time the user is seated.

[0025] 2E is a close-up view of an exemplary load cell. An additional strain gauge 214 is added to the conventional single sensor bending moment force gauge 215. The addition of the strain gauge 214 allows for the capture of torque around the sensing beam. This bending moment can be provided by the beam 216 capturing the force across the uneven toilet bowl edge. The device algorithmically combines the torque and bending inputs from the four load cells to calculate the user's weight.

[0026] FIG. 2F shows the components involved in spectroscopy-based detection of objects such as blood and urine. Reference number 217 is a laser diode or photodiode array. Reference number 218 is a laser diode, reference number 219 is a prism-shaped member, which can be repositioned depending on the optical requirements, reference number 220 is the top surface of the water in the toilet bowl, reference number 211 is a CMOS sensor, reference number 221 is a light sensor or photodetector, and reference number 222 is a distance sensor, which is intended to reflect the top surface of the water in the toilet bowl. Depending on the object to be detected, the laser diode 218 can emit light at a specific wavelength. The characteristic spectral signature of blood along the near infrared range (760-1500 nm) offers higher selectivity than using only the visible range (400-780 nm). By utilizing the distance sensor 222 as a power meter and utilizing Snell's law of reflection due to the change in refractive index, the presence and concentration of urine can be measured. The CMOS sensor 211 can be monochromatic with the infrared filter removed. The optical sensor or photodetector 221 can detect target objects in the near infrared spectrum using single pixel imaging. The use of laser diodes provides a narrower wavelength bandwidth spread and is therefore more object specific than light sources such as light emitting diodes (LEDs). Laser diodes are wavelength specific, with a full width at half maximum of ±5 nm, and require a prism or lens to disperse the laser over the target area (i.e. the water table).

[0027] The device can be used with or without additional chemicals that manipulate the chemicals in and on the biological cells in the waste. Such additional chemicals may be useful in detecting the presence or quantifying blood, which may be associated with conditions such as ulcers, colitis, colorectal cancer, Crohn's disease, urinary tract infections, and bladder cancer. Such chemicals may be combinations of reagents, buffers, oxidizers, or other chemical agents, and may be liquid or deposited on a substrate that is metered into the toilet bowl prior to defecation or urination and optically indicates a color change relative to the substrate or provides a photoluminescent glow that can be detected by the sensor 211 or 221. One example of such a substrate and color-based blood detection system that has been approved by the U.S. Food and Drug Administration for use in colorectal cancer screening is EZ Detect (Biomerica, Inc., Irvine, Calif., USA).

[0028] In various embodiments, gaseous chemicals are detected by gas sensors. Figure 3A shows an exemplary air fan and duct that draws air from inside the toilet bowl through the gas sensor. The path that air is drawn from inside the toilet bowl 223 and the path that air exits through the toilet seat 224 is shown. A set of gas sensors 225 can be calibrated to detect volatile organic compounds. The mean free path that air travels through the gas sensor 225 may be constrained by walls.

[0029] 3B is a close-up view of the air path. Filter 226 purifies the air before it enters the bathroom. The filter can be made of any suitable material, such as charcoal.

[0030] Any suitable gas sensor known in the art may be utilized to detect gaseous chemicals, hi some embodiments, the gas sensor is a micro-hotplate metal oxide sensor.

[0031] FIG. 3C is a close-up view of an exemplary gas sensor. A combination of three micro-hotplate metal oxide sensors 227 (where each blade can have a different spectrum), with temperature and humidity sensors and a microcontroller, a transimpedance amplifier 228, and a control circuit board 229 is shown. Electrochemical gas sensors can also be used. Some metal oxides can behave as semiconductors at high temperatures. Metal oxide sensors are designed with a heater element and a sensor element (sintered metal oxide with or without catalyst) separated by a very thin insulating film. Redox reactions occurring at the sensor surface cause a change in resistance that can be measured. These redox reactions depend on the nature of the metal oxide / catalyst, the reacting gas, and the temperature. Depending on the type and temperature of the sensor, a very wide range of objects can cause redox reactions. A gas sensor assembly consists of one or more gas sensors, which can be broadband sensors that respond to a mixture of gases or narrowband sensors that respond only to the concentration of a specific gas. The actual concentration can then be calculated using a Gaussian mixture model. Since many of the sensors operate at low currents and are sensitive to temperature changes, the assembly incorporates a temperature sensor and a chemical sensing front-end consisting of a transimpedance amplifier and a cell bias generator. Additionally, to keep the analog sensing paths short, a microcontroller is incorporated into the assembly, using an ADC to convert the readings from the sensors into digital signals that can be further communicated and processed through a digital interface as shown.

[0032] In these examples, any gaseous chemical present in the toilet bowl can be detected. In some of these examples, the gaseous chemical is a volatile organic compound. Volatile organic compounds found in the gut include short-chain and branched-chain fatty acids (Gruber et al., 2016). Carbohydrates in the gut are fermented by various bacteria to produce ethanoic acid, propionic acid, butanoic acid, pentanoic acid, and hexanoic acid. Hydrogen sulfide and methanethiol are produced from sulfur-containing objects in the diet. Fermentation of tyrosine and tryptophan leads to the production of phenols and indoles (Zheng et al., 2011). The relative proportions of these various VOCs may reflect the composition of bacteria present in the gut.

[0033] In some embodiments, the device can be attached to an existing toilet seat (i.e., there is no need to replace the toilet seat). These embodiments are not limited to any particular design and include, for example, connectors that connect a camera or cell phone to the seat or edge, or other designs. Figures 4 and 5 provide exemplary examples.

[0034] 4A and 4B are perspective and exploded views of another embodiment of an image sensor that can work with an existing toilet seat (e.g., without requiring replacement of the toilet seat). An attachment point 230 is bolted into place with an existing bolt 231 and covered by an existing seat 232. An attachment point that does not require bolting can also be used. A wire 233 is provided that can transmit power and communications. Power can be provided by a battery or communications can be wireless. Processing and communications circuitry 234 is also provided, which may or may not be separate from the image sensor. Also shown is a housing 235 for the CMOS sensor 211 and an electromagnetic radiation source 210 that provides light in various spectrums into the toilet bowl. In some embodiments, multiple CMOS sensors may be used. Components related to spectroscopic based detection of objects can also be used.

[0035] 5A and 5B are perspective and exploded views of another embodiment of an image sensor that can interface with an existing toilet seat. A tray-like device 236 snaps into place over the edge of the toilet bowl and is covered by the existing seat 232. Also included are wires 233 capable of transmitting power and communications, and processing and communications circuitry 234, along with a top cover 237. Power can also be provided by a battery, and communications can be wireless. An electromagnetic radiation source 210 provides light in various spectrums into the toilet bowl, which is captured by a CMOS sensor 211. The CMOS sensor is carried by the device 238. Components related to object detection based on spectroscopy, such as those described above, can also be used. The device may be partially or fully encapsulated.

[0036] A flushable feces collection system is also provided. Figures 6A and 6B show bottom and cross-sectional views of an exemplary such system with a toilet seat. The feces collector 239 is constructed of a water-soluble material such as polyvinyl alcohol. Holes 240 in the feces collector cooperate with modified feet on the toilet seat 241 to attach the feces collector to the toilet seat, where the holes hook over the modified feet. Another view of the feet 242 shows exemplary locations where the feces collector 239 may be secured.

[0037] Alternative embodiments of fasteners 243 in the feces collection system are shown in Figure 6C. These fasteners can be used as an alternative to the fasteners in the toilet seat foot shown in Figures 6A and 6B.

[0038] In additional embodiments, the system further comprises a foot scale designed to be placed on a floor, the foot scale performing any or all of the functions of calculating, measuring, assessing, and / or determining physiological data.

[0039] FIG. 7 is an exploded view of an exemplary scale or foot rest 300. The mat 301 is close to the ground and has sloping edges that can prevent the user from injuring themselves when using the device, and also includes guides on which the user can place their feet. A thin film pressure sensor 302 is placed on the guide area, indicated by reference number 301, and can capture weight transmitted through member 303. In another embodiment, reference number 302 is a load cell. The conductive material 304 acts as a bioelectrical impedance electrode and measures the bioelectrical impedance through the foot. The base 305 can be placed on the bathroom floor. The processing and communication circuitry 306 includes a battery holder.

[0040] In further embodiments, the system includes an electronic console that performs any or all of the functions of measuring ambient light, determining the presence of a user, identifying the user, and / or has a user interface for displaying the physiological information. In various embodiments, the displayed physiological information is any or all of current information, historical information, and / or current information taking into account the historical information.

[0041] FIG. 8 is a perspective view of an exemplary console system 400. An electronic display 401 provides real-time information to the user, such as weight and body composition, while the user is seated on the toilet. An ambient light detection sensor 402 is also included in these embodiments. A speaker 403 is also present through which audio feedback can be provided to the user indicating, for example, that the user has been successfully identified. A fingerprint sensor 404 is one example of an identification method to uniquely identify a user. A passive infrared sensor 405 can be used to detect the presence of a user.

[0042] Any of the above devices may also include any other bathroom-related components, including but not limited to: electric or non-electric bidets, motion-activated night lights, different colored ambient lighting, heated toilet seats, foot warmers, voice or gesture-activated toilet flushes, toilet covers that open and close automatically, and networked speakers for playing music.

[0043] Also provided is a bathroom mirror device, which may be non-portable or portable in nature, and which performs any or all of the following functions: identifying a user through facial recognition; detecting a febrile illness in a user; dispensing oral medications and supplements; collecting data from portable electronic device accessories, which may include a deep body thermometer, a toothbrush, a shaver, a respiratory sensor, an otoscope, an ophthalmoscope, a stethoscope, a pulse oximeter, a blood pressure monitor; and providing an interactive user interface.

[0044] FIG. 9A shows a front view of an exemplary wall mirror 500 powered by a public power source and connected to a private network 20 (FIG. 14). An ambient light sensor 501 detects ambient light conditions. A passive infrared sensor 502 detects the presence of a user. LED lighting 503 illuminates the user's face and body. An array of laser diodes 504 in combination with an image sensor 505 is used to identify the user in a bathroom environment based on facial recognition techniques. A thermal sensor 506 is used to detect the elevated body temperature of a user with a fever. A screen 507 functions as both a mirror and a touch display. A microphone and speaker 508 provide voice input that can capture the user's voice and voice output, such as from an artificial intelligence agent that can interact with the user. There is a power output 509, such as a universal serial bus or an AC socket. A pill pack cartridge 510 contains medications and / or supplements. The pills are combined and dispensed in predetermined doses through a pill dispenser 511. A storage section 512 and a charging dock 513 for accessories are provided.

[0045] 9B shows an exploded perspective view of the components of the mirror 500. A touch screen display 514 is placed over a one-way or transmissive mirror 515. A charger 516 for accessories connects to the mirror 500 and may be inductive or wireless in nature. The charging embodiments described herein are not narrowly limited to any particular mechanism or device used for charging.

[0046] 9C shows a more detailed view of the pill dispensing system and exemplary accessories. Pills of a particular medication or supplement are sealed in a pack 517 and placed in a cartridge 518. The pills can be combined to facilitate dispensing of the correct dose. Toothpaste 519 and mouthwash 520 are stored in storage 512. Exemplary electrical devices shown that connect to the system include a thermometer 521, a toothbrush 522, a respiration sensor 523, and a blood pressure monitor 524.

[0047] FIG. 9D shows an interactive user interface 525 where the user can use a touch screen to interact with current and / or historical information, such information being collected from the toilet apparatus 200, the scale 300, the console 400, the mirror 500, electrical devices / accessories that connect to the system, the user himself, or any type of data source that can be connected to the system. The user can also interact with the system by voice. The interface can perform the following functions, without limitation: obtain information from the user; provide current / historical information to the user; alert the user; dispense medication / supplements to the correct user; determine user compliance in taking medication / supplements; facilitate dosage of medication / supplements at recommended times; change dosage of medication / supplements; share information about the user with others; and facilitate remote consultations and the provision of telemedicine with information collected by the system.

[0048] 10A shows an exemplary portable device 600 comprised of a body 601 made from a polymer that is sealed against liquid ingress, is smooth with minimal cracks for easy cleanability, and has antibacterial properties. The movable wings 602 are comprised of a textured elastomeric material that allows for a secure grip.

[0049] FIG. 10B shows the components of the portable device 600 with the wings 602 in a lowered position, ready to transport the device. The top area consists of a capacitive touch screen panel 603. The middle area includes a fingerprint sensor 604, where the user is intended to place his finger for identification, a printed circuit board assembly 605, a module chip 606 containing logic and communication hardware and components, a three-axis accelerometer 607, a battery 608, an image sensor assembly 609, and a data storage unit 610. At the bottom there is an electromagnetic radiation source 611 capable of emitting electromagnetic radiation in the visible and invisible ranges of the electromagnetic spectrum into the toilet bowl, a low distortion lens 612 that may be coated with a hydrophobic and antibacterial coating, and a CMOS sensor 613. The CMOS sensor 613 may be a thermographic array consisting of a focal plane array responsive to longer wavelengths (mid and long wavelength infrared). It may also include components for spectroscopic detection and analysis, for example as described above.

[0050] In some embodiments, placing the wings 602 of the device in this down position switches the device off, for example when the user has finished defecating and / or urinating and wishes to set the device down to free up their hands. Speaker 614 allows for sound to be played and haptic feedback is provided by element 615. Microphone 616 allows for the capture of the user's voice.

[0051] Figure 10C shows the device with wings 602 in a 90 degree position, so that it can be placed on a user's lap with the body of the device extending under the user's legs and facing the drain hole of the toilet bowl, and Figure 10D shows the device with wings 602 in a 180 degree position, so that it can be held in a user's hand.

[0052] Figures 10E-I show the steps involved in switching on and using the device. Figure 10E shows the wings 602 being moved up from a lowered position (also a sleep state intended to conserve battery power) towards a 90 degree position (which wakes up the device and prompts the user to identify themselves via the fingerprint sensor 617). Figure 10F shows the device in use with the wings 602 in the 90 degree position and resting on the lap of a female user. Figure 10G shows the device in use with the wings 602 in the 180 degree position and held in the hand of a male user. Figure 10H shows the camera viewfinder in the top region of the device with guide elements 618 and 619 that help the user to correctly position the device and manually initiate image capture 620. Sound from speaker 614 or haptic feedback from element 615 is used to notify the user after a single or series of images have been captured. 10I shows a question 621 with an area for answering 622, a means for capturing additional images if the user needs to relieve themselves again 623, and a means for advancing or returning to a different screen 624. The questions or questionnaire presented to the user can be customized with regard to topics such as urgency, satisfaction, pain, and difficulty with bowel movements and / or urination related to the particular disease or condition being tracked.

[0053] The device can be used with or without additional chemicals that manipulate the chemicals in and on the biological cells in the waste stream. Such additional chemicals may be useful in detecting the presence of blood or quantifying blood, which may be associated with conditions such as ulcers, colitis, colorectal cancer, Crohn's disease, urinary tract infections, and bladder cancer. Such chemicals may be combinations of reagents, buffers, oxidizers, or other chemical agents, and may be liquid or deposited on a substrate that is metered into the toilet bowl prior to defecation or urination and optically indicates a color change relative to the substrate or provides a photoluminescent glow that can be detected by a sensor 613. One example of such a substrate and color-based blood detection system that has been approved by the U.S. Food and Drug Administration for use in colorectal cancer screening is the EZ Detect (Biomerica, Inc., Irvine, CA, USA).

[0054] Figure 11A shows an alternative embodiment of a portable device 700 placed on a toilet seat 232. The device can be conveniently mounted at various locations around the circumference of the seat due to the conformal nature of the features shown in Figures 11B-D.

[0055] FIG. 11B shows the components of the device in FIG. 11A. There is a printed circuit board assembly 701, a module chip 702, an image sensor assembly 703, which in these examples comprises a light source and a CMOS sensor, and a storage 704. On the interior side of the toilet bowl is an image sensor including an electromagnetic radiation source 705 that provides light in various spectra into the toilet bowl, a low distortion lens 706 that may be formed from a hydrophobic and / or antibacterial material that allows the passage of light in the visible, near infrared, and ultraviolet spectrums, and a housing 707. The sensor 708 may be a thermographic array made up of a focal plane array that responds to longer wavelengths (mid and long infrared). On the front side of the toilet bowl is a battery 709 and a spring loaded mechanism 710, shown in an uncompressed position, that fits multiple seat widths to hold the device securely in place while still allowing easy and quick removal by the user.

[0056] 11C and 11D show cross-sectional views identifying mechanisms that allow the device shown in FIG. 11A to adapt to various widths and thicknesses of toilet seats. A sliding plunger 711 is shown in uncompressed and compressed positions and is supported by a spring 712, which exerts pressure on the outside of the toilet seat 716 and provides a constant force against a surface 713 to hold the device in place. Mechanism 714 serves to resist upward forces to keep the device in place. Mechanism 715 is positioned above the toilet seat 716 to resist downward forces.

[0057] FIG. 12A shows an alternative embodiment of the device 800 in a position of use, installed below the toilet seat 716 and above the toilet bowl 801, with the optical head manually rotated to point at waste in the bowl.

[0058] FIG. 12B shows the device 800 of FIG. 12A, consisting of an optical head positioned above the toilet bowl and an angled body intended to fit over the edge of the bowl under the closed seat, with a tapered design 802 to accommodate various height gaps between the top of the toilet bowl and the bottom of the seat. The design 802 is molded or coated with a conformal elastomeric material, which may also be antimicrobial, to provide a grip to aid in retention. Additionally, a rotation mechanism 803 allows the optical head to be positioned for optimal alignment with the waste in the toilet bowl. Inside is a printed circuit board assembly 804, a module chip 805, a battery 806, an image sensor assembly 807, and storage 808. On the interior side of the toilet bowl is a light source 809 that provides light in various spectra into the toilet bowl, a low distortion lens 810 that may be formed from a hydrophobic material that allows the passage of light in the visible, near infrared, and ultraviolet spectrums, a housing 811 for the image sensor assembly, and an image sensor that includes a CMOS sensor 812. The sensor 812 may also be a thermographic array made up of a focal plane array that is responsive to longer wavelengths (mid and long wavelength infrared). A flushable sanitary bag 813 can be used to protect the device 800 from direct contact with the edge and seat of the toilet bowl when the device is used in a toilet that may not be clean.

[0059] Figure 12C shows the device 800 of Figure 12A utilising the wedge configuration 814 of design 802 to fit securely between the bottom of a toilet seat 815 and the top of the toilet bowl edge 816. An optical head 817 is shown above the toilet bowl. The wedge shape is covered by a sanitary bag over its entire surface, indicated by reference number 818, providing a sufficient barrier to prevent the device from touching the toilet seat 815 or the toilet bowl edge 816.

[0060] The embodiments described herein are not narrowly limited to the use of any particular power source, and thus any of these embodiments may use a utility power source, an electric battery, solar energy, etc.

[0061] In most embodiments, the device and / or system of the present invention further comprises a data storage and / or transmission unit that stores and / or transmits data from the sensor via wireless, optical or wired communication to a computing unit, which analyzes the data from the sensor.

[0062] 13 illustrates an example of a general-purpose computing device 900 that can be used with the techniques described in this disclosure. In various embodiments, any or all of the components featured therein and the functions performed thereby can be incorporated into any of the devices described above.

[0063] Computing device 900 includes, among other components, a processor 901, a memory 902, an input / output device 903 such as a display, a communication interface 904, and a transceiver 905. Computing device 900 may also be provided with a storage device such as a microdrive or other device to provide additional storage. Each of components 900, 901, 902, 903, 904, and 905 may be interconnected using various buses, and some of the components may be mounted on a common motherboard or otherwise as appropriate.

[0064] The processor 901 can execute instructions within the computing device 900, including instructions stored in the memory 902. The processor can be implemented as a chipset of chips including multiple separate analog and digital processors. The processor can coordinate other components of the computing device 900, such as controlling a user interface, applications run by the computing device 900, and wireless communications by the computing device 900.

[0065] The processor 901 may communicate with a user via a control interface 906 and a display interface 907 coupled to a display 903. The display 903 may be, for example, a thin film transistor liquid crystal display (TFT LCD), an organic light emitting diode (OLED) display, or other suitable display technology. The display interface 907 may comprise suitable circuitry for driving the display 903 to present graphical and other information to the user. The control interface 906 may receive commands from a user and translate and submit those commands to the processor 901. Additionally, an external interface 908 may be provided in communication with the processor 901 to enable short-range communication between the computing device 900 and other devices. The external interface 908 may, for example, provide for wired communication in some implementations and wireless communication in other implementations, and multiple interfaces may be used.

[0066] The memory 902 stores information within the computing device 900. The memory 902 may be implemented as one or more of a computer readable medium, a volatile memory unit, or a non-volatile memory unit. Also, an expansion memory 909 may be provided and connected to the computing device 900 via an expansion interface 910, which may include, for example, a Single In Line Memory Module (SIMM) card interface. Such expansion memory 909 may provide additional storage space for the computing device 900 or may store applications or other information for the computing device 900. In particular, the expansion memory 909 may include instructions for implementing or complementing the processes described above, and may include secure information. Thus, for example, the expansion memory 909 may be provided as a security module for the computing device 900 and may be programmed with instructions that enable secure use of the computing device 900. Furthermore, secure applications may be provided by SIMM cards along with additional information, such as placing identifying information on the SIMM card in an unhackable manner.

[0067] The memory may include, for example, flash memory and / or NVRAM memory, as discussed below. In one implementation, the computer program product is tangibly embodied in an information carrier. The computer program product includes instructions that, when executed, perform one or more methods, such as those described above. The information carrier is a computer or machine-readable medium, such as the memory 902, the expansion memory 909, memory on the processor 901, or a propagated signal that may be received, for example, via the transceiver 905 or the external interface 908.

[0068] The computing device 900 may communicate wirelessly via a communication interface 904, which may include digital signal processing circuitry if necessary. The communication interface 904 may be a cellular modem in some cases. The communication interface 904 may enable communication under various modes or protocols, such as GSM voice calls, SMS, EMS, or MMS messaging, CDMA, TDMA, PDC, WCDMA, CDMA2000, or GPRS, among others. Such communication may occur, for example, via a radio frequency transceiver 1268. Additionally, short-range communication may occur, such as using Bluetooth, WiFi, or other such transceivers (not shown). Additionally, a GPS (Global Positioning System) receiver module 911 may provide additional navigation and location related wireless data to the computing device 900, which may be used as appropriate by applications operating on the computing device 900.

[0069] The computing device 900 may also communicate voice using an audio codec 912, which may receive speech information from a user and convert that information into usable digital information. Similarly, the audio codec 912 may generate audible sounds for a user, for example, via a speaker in a handset of the computing device 900. Such sounds may include sounds from a voice call, may include recorded sounds (e.g., voice messages, music files, etc.), and may include sounds generated by applications running on the computing device 900.

[0070] The computing device 900 may be implemented in a number of different forms.

[0071] Implementations of the subject matter and operations described herein may be implemented in digital electronic circuitry, or computer software, firmware, or hardware, including the structures disclosed herein and their structural equivalents, or any combination or combinations thereof. Implementations of the subject matter described herein may be implemented as one or more computer programs, i.e., one or more modules of computer program instructions, encoded in a computer storage medium for execution by or control of the operation of a data processing apparatus. Alternatively or additionally, the program instructions may be encoded in an artificially generated propagated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, which is generated to encode information such that it can be transmitted to a suitable receiver apparatus for execution by a data processing apparatus. The computer storage medium may be, or may be included in, a computer readable storage device, a computer readable storage substrate, a random or serial access memory array or device, or any combination or combinations thereof. Furthermore, the computer storage medium is not a propagated signal, and the computer storage medium may be the source or destination of computer program instructions encoded in an artificially generated propagated signal. A computer storage medium may also be, or be contained in, one or more separate physical components or media (eg, multiple CDs, disks, or other storage devices).

[0072] The operations described herein may be implemented as operations performed by a data processing apparatus on data stored in one or more computer-readable storage devices or data received from other sources.

[0073] The term "data processing apparatus" includes all kinds of apparatus, devices, and machines for processing data, including, by way of example, a programmable processor, a computer, a system on a chip, or a combination or combinations of the above. The apparatus may include special purpose logic circuitry, such as a field programmable gate array (FPGA) or an application-specific integrated circuit (ASIC). In addition to hardware, the apparatus may also include code that creates an execution environment for a subject computer program, such as code constituting a processor firmware, a protocol stack, a database management system, an operating system, a cross-platform runtime environment, a virtual machine, or one or more combinations thereof. The apparatus and execution environment may implement a variety of different computing model infrastructures, such as web services, distributed computing, and grid computing infrastructures.

[0074] A computer program (also called a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and can be deployed in any form, for example as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program can be stored in part of a file that holds other programs or data (e.g., one or more scripts stored in a markup language resource), in a single file dedicated to the program in question, or in several coordinated files (e.g., files storing one or more modules, subprograms, or portions of code). A computer program can be deployed to be executed on one computer or on several computers at one site or distributed across several sites and interconnected by a communication network.

[0075] The processes and logic flows described herein may be implemented by one or more programmable processors executing one or more computer programs to perform actions by processing input data and generating output. The processes and logic flows may also be implemented by, and an apparatus may be implemented as, special purpose logic circuitry, such as an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit).

[0076] Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer.

[0077] Generally, a processor receives instructions and data from a read-only memory or a random access memory, or both. The essential elements of a computer are a processor for performing actions in accordance with the instructions and one or more memory devices for storing instructions and data.

[0078] A computer also typically includes one or more mass storage devices (e.g., magnetic, magneto-optical, or optical disks) for storing data, or is operatively coupled to receive data from or transfer data to a mass storage device, or both. However, a computer need not have such devices. Additionally, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device (e.g., a universal serial bus (USB) flash drive), to name a few. Devices suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, including, by way of example, semiconductor memory devices, such as EPROM, EEPROM, and flash memory devices; magnetic disks, such as internal hard disks or removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0079] To provide for interaction with a user, implementations of the subject matter described herein may implement a computer having a display device, such as a CRT (cathode ray tube) or LCD (liquid crystal display) monitor for displaying information to the user, and a keyboard and pointing device (e.g., a mouse or trackball) that allows the user to provide input to the computer.

[0080] Other types of devices can also be used to provide interaction with a user. For example, feedback provided to a user can be any form of sensory feedback, e.g., visual feedback, auditory feedback, or haptic feedback. Input from a user can be received in any form, including acoustic, voice, or haptic input. Additionally, a computer can interact with a user by sending resources to and receiving resources from a device used by the user, e.g., by sending a web page to a web browser on a user's client device in response to a request received from that web browser.

[0081] Implementations of the subject matter described herein may be implemented in a computing system that includes a back-end component, e.g., as a data server, or includes a middleware component, such as an application server, or includes a front-end component, such as a client computer having a graphical user interface or a web browser through which a user can interact with an implementation of the subject matter described herein, or includes any combination of one or more such back-end, middleware, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication, e.g., a communication network.

[0082] Examples of communication networks include local area networks ("LAN") and wide area networks ("WAN"), internetworks (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks).

[0083] A computing system may include clients and servers. Generally, clients and servers are remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. In some implementations, a server sends data (e.g., HTML pages) to a client device (e.g., for the purposes of displaying the data to a user interacting with the client device and receiving user input from the user). Data generated at the client device (e.g., the result of a user interaction) can be received from the client device by the server.

[0084] One or more computer systems may be configured to perform particular operations or actions by having software, firmware, hardware, or a combination thereof installed on the system that, when operated, causes the system to perform the actions. One or more computer programs may be configured to perform particular operations or actions by including instructions that, when executed by a data processing device, cause the device to perform the actions.

[0085] FIG. 14 is a block diagram illustrating exemplary communication network architectures, devices, and components, including a representation of communication circuitry that may be incorporated into an exemplary biometric monitoring device according to at least some embodiments of the present invention. In particular, the communication circuitry may implement or employ any form of communication (e.g., wireless, optical, or wired) and / or protocol (e.g., standard or proprietary) now known or later developed, with all forms of communication and protocols being contemplated as falling within the scope of the present invention (e.g., Bluetooth, ANT, WLAN, Wi-Fi, power line networking, all types and forms of Internet-based communication, and / or SMS). Large files may be distributed using a peer-to-peer distributed file sharing protocol that improves the scalability of the throughput of the networked system as more nodes are added, and adds security through fingerprinting for data integrity verification, inter-node consensus, and cryptographic shared secrets exchanged as an essential aspect of the protocol. In some cases, encrypted virtual private networks are utilized to provide an additional level of security for all communications, particularly management, maintenance, and metric collection functions.

[0086] In a non-portable image sensor embodiment, before image classification takes place, the images are prepared for classification. The unit acquires several non-sample images (baseline images) during the day for calibration. Once the presence of a user is detected, the unit can capture several images per second. Each image is then assessed for motion. To do so, corners in each image are found using a Harris & Stephens corner detector or similar. The detected corners for each image are then assessed for motion by comparing a block of pixels around the corner of the current image to the next block in sequence using a motion detector such as the Sum of Absolute Differences (SAD) process. The number of flows that exceed a set displacement threshold are then counted. If flows are counted above a set threshold, the image is deemed suboptimal and removed from further processing. The purpose of this step is to restrict the classification to images with stationary samples. The images are then analyzed for indicator features depending on the purpose of the analysis.

[0087] To accommodate different toilets (including their unique shapes, cleaning agents, water color conditions, materials and porcelain colors) and lighting conditions, a baseline model of an empty toilet bowl can be obtained from baseline images. To do so, a training period of sample images is conducted during a training period when no waste is in the toilet bowl. These baseline images are taken with and without illumination to create a robust background model that generates a moving average baseline. The background can be excluded from detection by frame differencing, pixel-wise Gaussian mixture models, or pixel-wise average filters. In frame differencing, the values ​​of successive images that do not contain the sample are subtracted from the pixel values ​​of the images that contain the sample. In the case of Gaussian mixture models, a confidence band is created about each pixel value for the background. As part of the preprocessing, pixels that fall within the confidence interval of the modeled mixture are ignored. In the case of average filters, the arithmetic mean of each pixel value is calculated from the images that do not contain the sample. This value is subtracted from the pixels of the images that contain the sample. All pixels that are close to the threshold of zero, including glare spots and static artifacts that are typical of the environment, are ignored from the classification. Additionally, histogram equalization is performed to be invariant to illumination changes. This procedure improves image contrast and makes classification robust across different illumination conditions. Upon completion of defecation and / or urination, as detected by software-based image detection, sample collection is released and the image is processed locally or sent via access point 30 to networked computing resources in cloud computing environment 50. The image is then analyzed by memory 51 and processor 52, either locally or remotely.

[0088] FIG. 15A is an image classification method for the portable device 600 after a user is identified, sits on the toilet, and then points the device at the toilet bowl just before or during defecation and / or urination. As soon as sample imaging is started, the light source is switched on and the application processor continuously samples the image sensor for frames, and the pan, tilt, and rotation angles are measured for each image captured from the image sensor 613. The electromagnetic radiation source 611 projects light in various spectra into the toilet bowl. The 3-axis accelerometer that samples the pan, tilt, and rotation angles of the unit can be a MEMS-based accelerometer (such as an Invensense MPU-60x0) or a solid-state accelerometer. The image sensor is a color CCD or CMOS-based image sensor. Additionally, the optical stack includes a non-wide angle lens (FOV less than 90°). This combination of sensor and lens reduces image distortion. The sensor has a minimum resolution of 500x500 pixels at a minimum. Frames and angles are sampled at a rate of over 2 frames per second and stored locally on the device until sample collection is terminated.

[0089] Once defecation and / or urination is complete (which may be detected by software-based image detection, sound detection, and / or possibly completion of a questionnaire as shown in FIG. 10I and / or the unit being ready for transport), sample collection is released and the images are processed locally or sent via access point 40 to networked computing resources in cloud computing environment 50. The images are then analyzed by memory 51 and processor 52, either locally or remotely.

[0090] In the device 600 of the present invention (FIG. 10), the first step of image processing is to rectify the image flat to the sample surface. Thus, the sampled pan, tilt and rotation angles and the intrinsic camera parameters are used to calculate the affine transformation of the image to the planar sample for each image. The images are then transformed individually to the perspective of the planar sample. The positions of known glare reflections of the luminaire are blacked out. Each image is then assessed for motion. As with the stationary unit, corners are found in each image using, for example, a Harris & Stephens corner detector. The detected corners for each image are then assessed for motion by comparing a block of pixels around the corner of the current image with the next block in sequence using a motion detector such as a SAD process. The number of flows that exceed a set displacement threshold are then counted. If flows are counted above a set threshold, the image is deemed suboptimal and is removed from further processing. The purpose of this step is to restrict the classification to images with stationary samples. The images are then analyzed for indicator features depending on the purpose of the analysis.

[0091] FIG. 15B is an image classification method for determining stool consistency. In an embodiment where the image is captured in color, the first step is to convert the captured color image to a grayscale image. The gradient magnitude of the image is then calculated using an operator such as the Sobel-Feldman operator. The gradient magnitude is sorted into histogram bins of fixed step size. Each image is encoded as a feature as a quantized histogram of gradients. These features are then fed into a pre-trained classifier, such as a support-vector machine (SVM), which classifies the features into labels according to the Bristol Stool Consistency Scale, or other similar clinically accepted scales known in the art. The classifier that assigns the labels is trained on a set of labeled images. Each image in the training set is assigned a distinct label that is assigned as ground truth. The SVM is trained to minimize classification error relative to these ground truth labels. This classification method determines stool consistency, from hard and lumpy to not fully formed and liquid, using standard clinical labels used in clinical studies to assess bowel consistency. However, rather than relying on patient self-report, this method automates or semi-automates classification using objective images captured from identified individuals. An alternative method for determining stool consistency is to use a shallow neural network (NN). The first few layers of the neural network naturally evolve with training into feature detectors that are more accurate than hand-crafted features such as histograms of gradients, so with more data the NN becomes more accurate. The output of the NN is modeled as an independent matrix function for each desired class label. The rectified linear units at the individual outputs can be like a sigmoid function. The independent outputs are guided to a "meta-class label" such as healthy or unhealthy.

[0092] FIG. 15C is an image classification method for blood and urine color. In preprocessing, pixels that match the color distribution of stool or known toilet fixtures are blackened. From the remaining pixels, a color histogram is calculated for the red channel for blood, and a joint red and green histogram is calculated for urine. The two histograms form the features for blood and urine classification, respectively. From the expert-labeled data, limiting thresholds are obtained for each color channel for blood and urine, and the histograms for the color channels are cropped accordingly. Here, the total number of values ​​in the histograms is normalized to the total number of pixels in the remaining image. From the same historical data set, thresholds are obtained for the normalized counts per channel for true blood and urine samples, respectively. Classification is then performed based on these thresholds. Alternatively, the normalized histograms of the historical data are used to train an SVM. The pre-trained SVM provides a model for classifying the histograms into known class labels. The blood and urine features are classified using a pre-trained classifier, such as an SVM. The SVM is pre-trained with features from images that have been labelled by experts for the desired class labels. For computational efficiency, the SVM is trained to classify samples into categories. The images used to train the SVM are labelled by experts and features are extracted as well as samples for each type of analysis. Representative labels are shown in Figure 15D.

[0093] FIG. 15E shows a workflow for estimating a person's urine and feces output. Temporal changes in water level are used to estimate the output for urine and feces. Temporal changes in water level are an important indicator of the density or porosity of the sample. Density estimation provides another input to the machine learning method, which when combined with optical features, achieves high classification accuracy compared to the Bristol Stool Condition Scale or related methods. Average invariant output rate in milliliters per second can be specified for each demographic and gender type. To estimate the output, the start and end times of urination are performed using an image sensor. When a user urinates, a water table inside the toilet shows movement. Optical motion sensing from consecutive frame pairs flags if the person is still urinating. The sum of the interframe capture times of the frame pairs showing movement, factored with a constant flow rate, models the output. Related motion sensing techniques are sum of absolute differences based background subtraction, average background subtraction based motion sensing, and background subtraction Gaussian mixture model based motion sensing. Techniques that do not rely on a background model, such as thresholding the sum of absolute differences of paired frames, can also be used.

[0094] To further improve the accuracy of the system, the urine output estimates can be monitored by user detection using other means, such as capacitive sensors that can detect when a user is sitting on the toilet seat, or ultrasonic sensors that can detect a user standing in front of the toilet, e.g., a man urinating while standing. This monitoring of the estimation process can rule out sources of erroneous movement and also resets the urine output estimates across different users and urination periods.

[0095] The presented image classification methods and systems can be applied to obtain results from tests that can be performed in a restroom environment that involve colorimetric changes, including urine test strips, lateral flow tests or immunochromatographic assays, or other currently available or future tests that can obtain quantitative or semi-quantitative results using the rigorous measurement of color changes.

[0096] The information may be provided interactively on a personal mobile device 60, which may be a smartphone or a connected device worn on the body such as a wristwatch. After the data is stored, analysis may also be performed by human review, such as verification of flagged images and using information such as weight, body composition, stool consistency, stool frequency, urine color, stool volume, urinary frequency, and the presence of visible blood to make recommendations or provide alerts. In non-portable embodiments of image sensor devices, control of the lighting and imager parameters and geometry means that the system does not need to take perspective distortion into account, as with mobile cameras. Furthermore, the fixed setup provides the opportunity to add polarizing and wavelength filters to the imager to limit the captured light to a spectrum that more prominently displays the features required for classification. By using polarized lenses, the effects of glare and unwanted reflections can be reduced, which provides significant noise reduction and improves the overall quality of the classifiable features.

[0097] In another embodiment, a method for determining a physiological parameter of a user is provided, the method comprising expelling a substance into a toilet bowl in the presence of the biomonitoring device described above. Figure 16 illustrates an exemplary workflow for these methods.

[0098] In view of the above, it will be seen that the several objects of the invention are achieved and other advantages attained.

[0099] Because various changes can be made in the methods and compositions described above without departing from the scope of the invention, it is intended that all matter contained in the above description and shown in the accompanying drawings be interpreted as illustrative and not limiting.

[0100] All references cited herein are hereby incorporated by reference. The discussion of references herein is intended only to summarize the assertions made by the authors and is not an admission that the references constitute prior art. Applicants reserve the right to challenge the accuracy and pertinence of the cited references.

Claims

1. 1. A biomonitoring device for measuring parameters of substances expelled into a toilet bowl by a user, comprising: (i) a source of electromagnetic radiation on the material, the source emitting electromagnetic radiation into the toilet bowl; and (ii) a sensor that detects electromagnetic radiation or an analyte chemical in the toilet bowl, the sensor including a lens on the material; and Equipped with A device, wherein the electromagnetic radiation source and the sensor are behind a seating portion of the toilet seat, and the lens is positioned such that it does not change position relative to the toilet bowl when the toilet seat is lifted.

2. The device of claim 1 , wherein the sensor is an image sensor comprising the lens.

3. The device of claim 2 , wherein the sensor further comprises a complementary metal oxide semiconductor.

4. The device of claim 1 further comprising components for spectroscopic detection including a laser diode and a photodiode.

5. The device of claim 1 , wherein the sensor detects an analyte chemical in the toilet bowl.

6. The device of claim 1 further comprising a polarizing filter.

7. 10. The device of claim 1, further comprising a capacitive sensor for detecting the presence of the user while seated on the toilet seat.

8. The device of claim 1 , further comprising a data storage unit for storing data from the sensor and / or a transmission unit for transmitting data from the sensor.

9. The device of claim 8 , further comprising a transmission unit for transmitting data to the computing unit via wireless, optical or wired communication.

10. 10. The device of claim 9, wherein the device undergoes a training period during which data is analyzed when no waste is in the toilet bowl, the training period including obtaining baseline sample images when no waste is in the toilet bowl, and obtaining a baseline model of the empty toilet bowl from the baseline sample images.

11. 10. The device of claim 9, wherein the computing unit analyzes the data to determine stool consistency, presence of blood, urine color, urine output, weight, body composition, stool frequency, urinary frequency, or any combination thereof.

12. The device of claim 1 , further comprising a scale or foot rest including a thin film pressure sensor that captures the user's body weight.

13. The device of claim 1 , wherein the substance is urine or feces.

14. 10. The device of claim 1, further comprising a nozzle capable of dispensing liquid into the toilet bowl.

15. 1. A biomonitoring device for measuring parameters of substances expelled into a toilet bowl by a user, comprising: (i) a source of electromagnetic radiation on the material, the source emitting electromagnetic radiation into the toilet bowl; and (ii) a sensor that detects electromagnetic radiation or an analyte chemical in the toilet bowl, the sensor including a lens on the material; and (iii) a transmission unit for transmitting data to the computation unit; Equipped with The biomonitoring device comprises a training period during which data is analyzed when no feces is in the toilet bowl, the training period including obtaining baseline sample images when no feces is in the toilet bowl, and obtaining a baseline model of the empty toilet bowl from the baseline sample images.

16. 16. The biomonitoring device of claim 15, wherein the lens is positioned such that it does not change position relative to the toilet bowl when the toilet seat is lifted.

17. 16. The biomonitoring device of claim 15, wherein the electromagnetic radiation source and the sensor are behind a seating portion of the toilet seat.

18. The biomonitoring device of claim 15 further comprising a polarizing filter.

Images