40results about "Person identification" patented technology

Disclosed is an electrocardiogram biometric authentication device and method that allows user addition. An electrocardiogram biometric authentication method performed by a computing device comprising at least a processor includes acquiring a target electrocardiogram signal of a user; generating a plurality of vectors by preprocessing the target electrocardiogram signal; generating an embedding vector by inputting the plurality of vectors to a pretrained embedding model; retrieving a similar embedding vector having a smallest distance from the embedding vector from among prestored embedding vectors; and authenticating the user based on a distance between the embedding vector and the similar embedding vector.

Device (10) for extracorporeal blood treatment, in particular a dialysis device (10) which includes a radar sensor (17) for monitoring a patient (P) located at a treatment station, at least one shut-off device (13, 30) for shutting off a line (23) connected venously to the patient (P) and / or for shutting off an arterial line (22) connected to the patient (P), in particular in the form of a hose clamp (30) clamping an elastic or flexible area of ​​the line (22, 23), a blood pump and has a control unit (14), wherein the control unit (14) is set up and configured to determine a patient's (P) respiratory rate and / or respiratory amplitude based on signals from the radar sensor (17) and to trigger an alarm signal if the respiratory rate and / or respiratory amplitude detected by the radar sensor (17) deviates from one or more preset limit values, the shut-off device (13, 30) can be automatically operated via the control unit (14) in the event of an alarm and The blood pump is stopped in case of an alarm.

A method for patient identification comprises the steps of: determining (S10) initial identification data during an initial measurement of a patient (P) using a first measuring device (1) for determining ophthalmic and / or optometric measurement data; and determining (S30) a patient ID of the patient based on the determined initial identification data. The invention also relates to a system or computer program (product).

By utilizing the existing speaker drivers associated with the dam headphones, smart headphone functionality is enabled without the need for additional auxiliary sensors, providing a peripheral device that excels in terms of weight, volume, cost, and power consumption. [Solution] The zeroing circuit 300, which selectively couples to the magnetic coil driver of the headset, includes a Wheatstone bridge that detects minute fluctuations in the headphone driver voltage caused by the excitation signal, thereby zeroing out the electrical energy associated with the audio input signal. This provides an output signal that mainly consists of the electrical energy associated with the excitation signal generated by the magnetic coil driver in response to external pressure applied to the diaphragm.

The present disclosure provides a task-independent brainprint recognition method based on feature disentanglement by decorrelation. Existing methods fail to mine inherent identity information of a brain, leading to poor robustness of brainprint recognition in a scenario across tasks and difficulty of promotion thereof in practical use. The present disclosure firstly uses two branch networks to perform coarse-grained decomposition of identity information and task related information in an electroencephalogram (EEG). Secondly, in consideration of an influence of a task state on the identity information, a decorrelating method is employed such that the identity information and the task related information are independent as much as possible. Finally, a brainprint feature in the EEG is fully utilized for classification by adversarial self-supervision. The method of the present disclosure is good in performance and capable of realizing efficient task-independent brainprint recognition, and is a brainprint recognition method robustly useful in the real life.

The application discloses a self-supervised cross-period brainprint recognition method and system based on distillation learning. The self-supervised cross-period brainprint recognition method collects electroencephalogram data, pre-processes the collected electroencephalogram data, and divides the electroencephalogram data according to requirements. An electroencephalogram signal sequencer is used to preliminarily encode the electroencephalogram signal. A teacher network and a student network with the same structure are constructed, and the teacher network and the student network are used to extract features of the same electroencephalogram sample under different scales and masks, so as to form global and local two-perspective representations to guide the pre-training process of the student network, and improve the modeling ability of the model to sample consistency and fine-grained differences. A brainprint recognition model based on the student network is fine-tuned by a small number of labeled samples to complete self-supervised cross-period brainprint recognition, and high-precision recognition and robust generalization performance for specific individual characteristics are realized.

A biometric authentication device is provided with: a replay unit for reproducing a sound; an ear authentication unit for acquiring a reverberation sound of the sound in an ear of a user to be authenticated, extracting an ear acoustic feature from the reverberation sound, and calculating an ear authentication score by comparing the extracted ear acoustic feature with an ear acoustic feature stored in advance; a voice authentication unit for extracting a talker feature from a voice of the user that has been input, and calculating a voice authentication score by comparing the extracted talker feature with a talker feature stored in advance; and an authentication integration unit for outputting an authentication integration result calculated based on the ear authentication score and the voice authentication score. After the sound is output into the ear, a recording unit inputs the voice of the user.

A biosignal measurement apparatus of the present invention comprises: a housing comprising a base plate and a column that is coupled to the base plate in a z-axis direction, is formed with an empty interior space, and has one curve-shaped surface; a power supply unit that is provided on one side of the housing and supplies power; a control unit that receives power from the power supply unit and controls operations; an image processing unit that pre-processes and post-processes images; an image determination unit that determines the quality of images; and a control box that is coupled to the other side of the housing, receives power from the power supply unit, and is operated under the control of the control unit, wherein the control box further comprises a plurality of sensor units for measuring biosignals of a user, a display unit that displays biometric measurement data from the sensor units, a data input unit that acquires image or audio data of the user, an illumination unit of which operation is controlled by the control unit, and a light output unit that irradiates the user with light of a specific wavelength. According to these characteristics, the height of a terminal may be adjusted to fit the height of each individual user to reduce errors caused by the angle of image data collection, thereby increasing the reliability of result values.

A method, apparatus, and system for determining a correspondence of physiological data obtained in a physiological study of a subject. The method includes extracting a first signal from the physiological study. A second signal from the physiological study is also extracted. The first signal and the second signal are obtained by one or more biometric sensors. Data of the first signal and data of the second signal are stored on a memory storage. A coherency value is determined between components of the extracted first signal and components of the extracted second signal. And the correspondence of the physiological study data is determined based on the determined coherency value.

The present invention provides a driver information processing device that minimizes the impact on the privacy of registered drivers, even if biometric authentication data is leaked. [Solution] In one embodiment of the present invention, the driver information processing device includes a millimeter-wave radar that irradiates millimeter waves toward the driver of a vehicle and receives reflected waves from the driver, and an ECU that processes and stores the information of the reflected waves. When the ECU determines that the driver's riding posture is in a predetermined state, it irradiates millimeter waves toward the driver from the millimeter-wave radar and stores the driver's physical characteristics as the reflected wave signal characteristics when the millimeter waves are irradiated.

A user identification system for an aerosol provision system, the user identification system comprising: a PPG sensor; and a user identification module configured for providing an indication of the identity of a user of the aerosol provision system, wherein the user identification module is configured to: receive a signal from the PPG sensor, identify a value for one or more identification features from the received signal, compare the identified value for the one or more identification features to a corresponding reference value for the one or more identification features obtained in advance, and output a result of the comparison to a controller of an aerosol provision system, the controller configured to control one or more operations of the aerosol provision system responsive to the result of the comparison.

The invention relates in particular to a radar device (100) comprising a housing (200), suitable for being positioned on the inner wall of a toilet bowl (106) and comprising a radar sensor (202), housed in the housing (200), and suitable for emitting radar waves towards the opening of the toilet bowl, in particular for measuring a physiological data point of a user's body. This physiological data point can be used to identify the user. The invention also relates to associated methods. Abstract figure: Figure 5

A physiological parameter monitoring system adapted to identify a person for monitoring of the identified person's physiological parameters, the system including: one or more sensors for monitoring one or more persons' physiological parameters comprising a cardiac parameter, and one or more processors, the one or more processors configured to process signals from the one or more sensors to identify a person according to an evaluation of a biometric signature, the processing comprising an evaluation of parameters comprising the cardiac parameters, wherein the one or more processors are further configured to determine one or more settings for a respiratory therapy device based on the evaluation of the biometric signature.

Provided is a method including radiating first guide light, which guides a radiation position of a first pulsed beam, onto a suspicious tissue, receiving a first user input for instructing an output of the first pulsed beam while the first guide light is radiated, applying the first pulsed beam to the suspicious tissue to induce plasma ablation in a first target region corresponding to the radiation point of the first guide light, in response to the first user input, wherein the applying of the first pulsed beam is performed after obtaining first image data obtained by capturing an image of the first guide light and a tissue in a periphery the first guide light while the first guide light is radiated to the suspicious tissue, and obtaining target spectrum data on the plasma ablation, obtaining first disease information, and displaying the first image data and the first disease information.

To provide a sensing device, etc. capable of performing sensing of a living body more accurately.SOLUTION: A sensing device 200 includes: an acquisition unit 230 for acquiring wireless machine information acquired from at least one wireless machine of a first wireless machine 100 disposed in an object space 400 capable of performing at least wireless transmission and a second wireless machine 201 disposed in the object space 400 capable of performing at least wireless reception; a determination unit 240 for determining whether or not a movable wireless machine of the first wireless machine 100 and the second wireless machine 201 is standing still; and a sensing unit 250 for performing sensing of a living body 300 in the object space 400 using CSI (channel state information) included in the wireless machine information that is received by the second wireless machine 201 from the first wireless machine 100 when the determination unit 240 determines that the movable wireless machine is standing still.SELECTED DRAWING: Figure 2

A method of managing security of an implanted device including estimating a risk to, or a need of, a user in who the device is implanted; and automatically applying, by the device, a security level regarding communication to the device and / or actions by the device according, to said estimation. In some mebdoimnts, the need is a medical need, such as an emergency situation. In some mebdoimnts the risk is assessed base don a location of the implanted device.

Included are: an image acquisition unit (11) for acquiring a captured image; a detection unit (12) for detecting a skin area of ​​a person from the captured image; a measurement range setting unit (14) for setting measurement ranges that can be used to extract a pulse wave source signal comprising a pulse wave component of the person in an area corresponding to the skin area in the captured image; a face orientation estimation unit (13) for estimating a face orientation of the person based on the captured image; a brightness signal extraction unit (15, 15a) for setting a usage measurement range and for extracting the pulse wave source signal in time series based on a brightness change in the set usage measurement range;a brightness signal selection unit (16, 16a, 16b) for selecting a time-series estimating pulse wave source signal to be used for estimating a person's pulse wave, taking into account the person's face orientation estimated by the face orientation estimating unit (13); and a pulse wave estimating unit (17) for estimating the person's pulse wave based on the time-series estimating pulse wave source signal selected by the brightness signal selection unit (16, 16a, 16b).

Method for determining a color and kinetic assessment tool for cosmetic products. A method for determining an assessment tool for a given population, the given population being characterized by a distribution of skin colors, the method comprising: - determining a group of skin colors from among a set of skin color groups in a colorimetric space, said skin color group being representative of the skin color distribution of the given population and each skin color group defining a range of skin colors in the colorimetric space, the range of skin colors of each skin color group being distinct from the other group(s) of skin colors, - constructing a panel of individuals whose skin colors are representative of the determined skin color groups.- the determination of a protocol for applying cosmetic products to the panel of individuals, the panel of individuals and the protocol forming the evaluation tool, the evaluation tool being used at different times.

A method includes, while a vehicle is restricted to a parked state, presenting a visual tracking application on a display of the vehicle, wherein the visual tracking application includes a moving target user interface element (target UL element) and a tracking UI element, detecting, using a steer-by-wire (SbW) steering system of the vehicle, movements of a steering wheel by an operator of the vehicle, moving based on the detected movements of the tracking UL element in the visual tracking application, and determining a corresponding tracking error between a location of the moving target UL element in the visual tracking application and a location of the tracking UL element in the visual tracking application at multiple time points.The procedure also includes processing the corresponding tracking errors to estimate the operator's visuomotor skills.

A method for identifying patients comprises the following steps: determining (S10) first identification data during a first measurement of a patient (P) by means of a first measuring device (1) for determining measurement data obtained by an ophthalmologist and / or optometrist; and determining (S30) a patient ID of the patient on the basis of the determined first identification data. The invention also relates to a system and to a computer program (product).

A wearable device control method may include: receiving, from a wearable device, first joint angle information about a first joint while the wearable device is controlled on the basis of a bicycle exercise program; determining a first joint angle of the first joint on the basis of the first joint angle information; determining whether the first joint angle corresponds to a first target joint angle; if the first joint angle corresponds to the first target joint angle, determining, on the basis of the bicycle exercise program, a first value of torque provided to the first joint; and controlling the wearable device on the basis of the first value of the torque.

A computer implemented method of determining an identity of a driver is provided. The 5 method comprises: obtaining a first electrocardiogram, ECG, signal for an authorised driver; providing at least part of the first ECG signal to a machine learning algorithm to obtain a first vector representation of features of the first ECG signal; labelling the first vector representation as belonging to the authorised driver, the labelling being based upon an identity token provided by the authorised driver prior to or at the time of 10 obtaining the first ECG signal; obtaining a second ECG signal for a candidate driver; providing at least part of the second ECG signal to the machine learning algorithm to obtain a second vector representation of features of the second ECG signal; comparing the second vector representation to the labelled first vector representation to determine a similarity metric; and if the similarity metric is within a predetermined threshold, 15 providing confirmation that the candidate driver is the authorised driver.

An apparatus including: a housing for containing / protecting / storing a plurality of containers / packages containing pills / medicaments; a power source in the housing; an actuator arrangement powered by the power source and configured to administer / deliver the pills / medicaments for a pre-selected patient; and a sensor powered by the power source to activate the actuator arrangement to allow the at least one package to be opened / accessed manually when the sensor detects a pre-defined identifier of the pre-selected patient.

To improve user's convenience in biometric authentication.SOLUTION: A CPU 11 measures heart beat of a user by means of a heartbeat detection part 15 in the case where an electronic apparatus 1 is attached to the user's body, and makes a locked state by disallowing the operation in the case where the electronic apparatus 1 is removed from the user's body. When a lapse time with the electronic apparatus 1 attached again to the user's body after the locked state is less than a prescribed time, the CPU 11 measures the user's heartbeat by the heartbeat detection part 15. In the case where the degree of coincidence between the heartbeat waveform before the locked state and the heartbeat waveform after the reattachment is within a prescribed range, the locked state is released.SELECTED DRAWING: Figure 1

A system and method are disclosed for hybrid screening in controlled-access environments that enable voluntary preventive medical imaging without interfering with mandatory security screening operations. The system comprises a non-ionizing security screening subsystem configured to perform mandatory security scans, a walk-through low-dose computed tomography (CT) medical imaging subsystem configured for voluntary preventive screening, a biometric identity verification subsystem, and a workflow orchestration and physical routing system. The system further includes automated height and weight measurement synchronized with CT image acquisition and Al-based analysis for cardiopulmonary or cardiometabolic risk assessment. The invention enables high-throughput, low-dose preventive screening in environments such as airports and other controlled-access facilities without degrading security throughput or compromising privacy, regulatory compliance, or operational efficiency.

In an embodiment, a computer-implemented method for decoding neural activity is provided. In the method, at least one machine learning model is trained using a training data set of EEG data and concurrently collected environmental data collected from data collection participants. Once the at least one machine learning model is trained, EEG data measured from sensors attached to or near a user's head is received. Environmental data describing stimulus the user is exposed to concurrently with the measurement of the EEG data is also received. The EEG data and the environmental data is input into the at least one machine learning model to determine an inference related to the neural activity. Based on the inference, an operation of a computer program is altered.