480 results about "Biosignal" patented technology

The invention relates to a battle wound field real-time hemostasis method based on a biological information sensing technology, and the technical scheme comprises the steps: introducing a time sequence biological signal for modeling, and carrying out the dynamic prediction of a battle wound state; on the basis of a biosensor data flow, a multi-dimensional time sequence state space is constructed, and the multi-dimensional time sequence state space comprises a nonlinear change trend of a bleeding rate, an evolution mode of tissue physiological parameters and a dynamic evolution process of a blood coagulation process; external intervention requirements are minimized while a hemostasis strategy is dynamically adjusted through active learning; defining multi-objective optimization modeling of key objectives of hemostasis efficiency, tissue damage minimization and pressure adaptability; estimating distribution prediction of success probabilities of different hemostasis strategies; the intelligent response mechanism is composed of a nanoscale blood coagulation factor carrier and a phase change regulation and control network. An environment triggering response model is constructed, and the blood coagulation factor carrier selectively releases blood coagulation factors according to biological signals including the pH value, the temperature and the bleeding rate.

The invention discloses a pneumatic-biological signal feedback cooperative control method based on an anti-gravity rehabilitation treadmill, and the method comprises the steps: synchronously collecting sEMG, IMU and plantar pressure signals, and completing the time-space registration through clock synchronization, time warping and extended Kalman filtering; muscle activation degree, pressure center offset and joint angular velocity are extracted to construct multidimensional features, and gait phase switching is predicted through LSTM-CNN; the TS fuzzy system generates a preliminary control instruction according to expert rules, and Q-learning takes pressure balance and motion smoothing as reward functions to optimize the weight reduction proportion and the treadmill speed online; a waist annular air cavity is driven to be inflated to form a pressure supporting field so as to lift a pelvis and guide a lower limb gait mechanical mode, so that the muscle activation degree, the joint angular motion trail and the pressure center migration characteristic are dynamically influenced, a servo motor tracks phase nodes in a feedforward-feedback mode, and risk early warning and training parameter self-adaptive closed-loop rehabilitation are achieved.

The invention provides a diabetic neuropathy dynamic early warning method based on a multi-modal biological signal, and the method comprises the steps: integrating a multi-modal sensor through an intelligent wearable device, and constructing a personalized prediction model in combination with a deep learning algorithm; through an artificial intelligence algorithm, diabetic neuropathy (DN) development risk prediction and unperceptual hypoglycemia real-time early warning are realized. According to the time-frequency domain characteristics and clinical data of the multi-mode signal, the time window of the DN from the progress to the serious stage can be predicted; recognizing an unperceptual hypoglycemia risk by combining ECG and HR features with a blood glucose trend prediction model, and triggering grading intervention measures; based on the individual physiological response mode of the patient, the algorithm threshold is dynamically optimized, and the accuracy of prediction and early warning is improved. According to the method, HR, BP, ECG and other multi-dimensional signals are integrated, and the prediction precision is improved; continuous monitoring and instant feedback are supported; the self-adaptive algorithm adapts to individual differences of patients, and the limitation of a traditional general model is overcome.

The invention relates to a child attention evaluation and training method and system, and the method comprises the steps: obtaining a brain wave mode, an eyeball movement track, an emotion activation level and autonomic nervous system function data of a child in real time, and generating multi-dimensional biological signal data; based on the multi-dimensional biological signal data, generating evaluation task data; generating dynamic task parameters according to biological signal data and behavior performance data in the evaluation task data; generating an attention feedback signal based on the dynamic task parameters; according to the attention feedback signal, a training task integrating work memory, suppression control and cognitive flexibility is constructed, and cognitive function training data is generated; and based on the cognitive function training data, synchronously sharing the attention performance data of the children to the parent terminal and the teacher terminal, generating life situation intervention suggestions, and iteratively optimizing evaluation parameters according to a long-term effect evaluation result. Therefore, the accuracy of children attention evaluation and training can be improved.

The invention relates to the technical field of medical instruments, and discloses a minimally invasive surgery system based on artificial intelligence. Comprising a target identification and positioning module, a multi-mode sensing module, a self-adaptive control module, a man-machine interaction module and a scene adaptation module. The target recognition and positioning module positions an operation target in real time through image recognition and a deep learning algorithm; the multi-mode sensing module collects the stress and movement track of an instrument and physiological signals of a patient. The self-adaptive control module adjusts movement parameters of the instrument according to the data; the man-machine interaction module displays data and provides an operation interface; the scene adaptation module adjusts the instrument form and function according to the operation type. In addition, the system also comprises an operational stability evaluation module, an instrument life prediction module and a biological signal fusion module. The system can achieve precise positioning, real-time monitoring and intelligent control, and the precision, safety and operation convenience of minimally invasive surgery are improved.

The invention relates to the cross technical field of signal processing and artificial intelligence, in particular to a multi-source noise removal method and system based on DAE, and the method comprises the steps: 1, carrying out the data collection and feature extraction of multi-source noise and pure signals; step 2, constructing a de-noising recognition knowledge base based on feature analysis; step 3, constructing a deep denoising auto-encoder model based on a knowledge base; step 4, hierarchical training and optimization guided by a mixed loss function of the deep denoising model; step 5, denoising processing of a target signal and output evaluation based on a discrimination model; according to the invention, noise data in multiple fields such as electromagnetism, remote sensing and biological signals are integrated, a dynamic mixing strategy and a data enhancement technology are adopted, a training set which highly simulates a real environment is constructed, and a unique cross-scene adaptation module can perform adaptive adjustment according to signal characteristics of different application scenes; the problem that a traditional method is poor in scene adaptability is solved.

The invention belongs to the field of intelligent rehabilitation medical instruments, and particularly relates to a brain-computer interface-based multi-modal child sensory integration training device, which comprises a brain-computer interface head ring, an intelligent touch floor and AR interactive glasses, the brain-computer interface head ring is connected with a biological signal acquisition module, the intelligent touch floor is connected with a motion trail analysis unit, the AR interactive glasses are connected with a universe scene engine, and the biological signal acquisition module, the motion trail analysis unit and the universe scene engine are connected with a digital twin generator. The digital twin generator is connected with a dynamic mode switching decision tree, and the dynamic mode switching decision tree is connected with a multi-mode feedback actuator; the brain-computer interface head ring is located on the head of the child and collects electroencephalogram, myoelectricity and electrocardiosignals through a biological signal collection module; and the biological signal acquisition module sends a signal to the digital twin generator through wireless transmission. According to the invention, the training efficiency can be improved, the evaluation dimension can be expanded, potential safety hazard early warning can be realized, and the compliance can be enhanced.

The disclosed device can receive a biosignal and, using user input predictions based on the biosignal, pre-render a display frame. The device can also subsequently receive a user input, output the pre-rendered display frame based on the user input confirming the user input predictions and flush the pre-rendered display frame otherwise. The device can also modulate computing performance and power based on computing demands predicted from the biosignal. Various other methods, systems, and computer-readable media are also disclosed.

The invention belongs to the technical field of resource management, and relates to a cloud computing-based intelligent agricultural resource optimization scheduling system, which comprises a biological signal acquisition module used for acquiring biological signals of crops in a target area; the environment data acquisition module is used for acquiring environment parameters outside crops; the dynamic demand analysis module is used for fusing the biological signals and the environmental parameters, generating dynamic demand indexes and judging whether a resource cooperation request is triggered or not; the block chain scheduling management module is used for receiving the resource cooperation request and calling surplus resources of the target farm to execute operation; the contribution point management module is used for generating verifiable contribution points and dynamically adjusting the exchange weight; and the intelligent verification module is used for comparing the deviation between the chain record and the local sensor data, triggering an automatic verification mechanism and correcting the account book record. The method can solve the problems that the contribution degree of participants lacks a credible quantitative standard, the benefit distribution contradiction inhibits the resource sharing willingness between farms.

The invention relates to a motion capture optimization method of a tactical AR helmet. Based on a motion model and dynamic changes of muscle activities and biological signals; collecting data in real time through a sensor, and establishing a time-dependent model of motion data by using a time sequence analysis method; in combination with an LSTM (Long Short Term Memory) model in deep learning, capturing head motion and time dynamic change of motion, and predicting and correcting an error in motion capture; intelligent processing is carried out based on continuous time sequence data, and short-term errors of capturing data drift are avoided; designing a multi-level sensor correction algorithm, and performing time alignment and error correction on IMU data and visual data; drift phenomena including position errors and rotation errors in motion capture are eliminated; optimizing the helmet capture system using a ground sensor including a gait monitoring device and external vision calibration data; a target-oriented motion trail optimization algorithm is designed by combining a motion target and a tactical task of a user, and a capture strategy is dynamically adjusted according to the change of the task.

According to various embodiments, an electronic device may include a first communication circuit and at least one first processor. At least one first processor is configured to: obtain, via the communication circuit, a plurality of images including a user's face obtained by using a camera of a first external electronic device; obtain first data obtained based on a first sensor of the first external electronic device contacted with a first portion of a body of the user and second data obtained based on a second external electronic device contacting a second portion of the body of the user while obtaining the plurality of images, while simultaneously acquiring the plurality of images; and obtain a first biometric signal of a specific type based on the images, a second biometric signal of the specific type based on the first data, and a third biometric signal based on the second data.

The invention relates to the technical field of intelligent medical rehabilitation evaluation, and discloses a biological index detection system for orthopedic rehabilitation evaluation. According to the system, biological signals of a patient are collected through a multi-sensor array of a biological signal sensing module to generate an original data stream; the quality self-adaptive evaluation module carries out real-time quality analysis on the data and generates a quality parameter set; the signal intelligent processing module dynamically adjusts a signal processing strategy according to the quality parameter set and then outputs optimized signal data; the feature depth extraction module is used for mining biological features from the optimized signal data and generating feature weight distribution; the rehabilitation dynamic scoring module calculates a rehabilitation evaluation index based on the feature weight distribution; and the intervention strategy generation module automatically adjusts an evaluation strategy according to the rehabilitation evaluation index and outputs a personalized evaluation report. According to the invention, through real-time quality monitoring and adaptive signal processing, the accuracy and reliability of orthopedic rehabilitation evaluation are improved.

The invention relates to a method for controlling a robot, said method including the following method steps: a) detecting a biosignal on a body part of a user; b) deriving a user command ({dot over (x)}usr) for controlling the robot from the detected biosignals; c) deriving a task to be performed from the user command ({dot over (x)}usr) using an intention recognition module; d) calculating an optimal command ({dot over (x)}opt) which is most efficient for performing the task; e) determining a deviation between the user command ({dot over (x)}usr) and the optimal command ({dot over (x)}opt); f) adjusting the decoding algorithm, by means of which the user command ({dot over (x)}usr) is decoded from the biosignal, based on the determined deviation; and g) controlling the robot using the adjusted decoding algorithm.

The invention relates to the technical field of image processing and biological signal detection, discloses a facial physiological detection method and system based on signal quality driven ROI selection, and aims to solve the problem of signal degradation of a traditional fixed geometric ROI in a complex scene. The method comprises the following steps: collecting a user face video stream through a camera and preprocessing the user face video stream; detecting a face bounding box and dividing the face bounding box into a plurality of sub-regions; calculating the signal-to-noise ratio, the periodic intensity and the motion artifact interference degree of each sub-region; screening an optimal sub-region according to a weighted fusion formula to generate a dynamic ROI mask; extracting a pure rPPG signal from the dynamic ROI mask coverage area; detrending and band-pass filtering are carried out on the rPPG signals, and physiological parameters such as the heart rate and the blood oxygen saturation degree are extracted. The system comprises a face video acquisition module, a face region positioning and segmentation module, a signal quality evaluation module, a dynamic ROI selection module, an rPPG signal extraction module and a physiological parameter estimation module. According to the technical scheme, signal degradation caused by local shielding, illumination abrupt change or attitude offset can be effectively avoided, the signal-to-noise ratio and the stability of the rPPG signal are remarkably improved, and the universality and the robustness of the method are enhanced.

The invention relates to the technical field of nervous system dysfunction, in particular to a nerve regulation and control system for degenerative disease treatment based on multi-modal physiological feedback, which comprises a central processing unit, an optical radiation applicator, a mechanical vibration applicator, an integrated biological signal sensing array and a man-machine interaction module, cooperative stimulation is applied by using a multispectral light source and a broadband vibrator, and multi-dimensional physiological signals such as heart rate variability, myoelectricity, galvanic skin and the like are monitored in real time through a sensor array. A multi-parameter adaptive control algorithm built in the central processing unit can dynamically and intelligently adjust stimulation parameters based on the feedback signals to form an accurate personalized treatment closed loop. Meanwhile, the safety monitoring module based on the biological thermal model ensures the safety boundary of the treatment process. According to the invention, intelligent, self-adaptive and non-invasive treatment of nerve dysfunction is realized.

The invention provides an intelligent motion evaluation and damage early warning method and system based on multi-source biological signal fusion, and is applied to the technical field of medical data processing. The method comprises the following steps: acquiring a multi-modal biological signal acquired based on a multi-source sensing node; carrying out self-adaptive preprocessing on the multi-modal biological signals, eliminating motion artifacts by adopting an improved spectral subtraction formula, realizing multi-rate synchronization through a Lagrange kernel, triggering node vibration by virtue of signal quality evaluation to prompt electrode reattachment, and generating preprocessed signal features; and constructing cross-modal fusion features by using multi-scale cavity convolution and the like, and outputting results such as a motion mode and the like. A target depth model is trained in combination with signal optimization and data enhancement and the like, a motion pattern classification result, joint load estimation data and a damage risk scoring result are processed based on the target depth model, damage early warning information is generated, and accurate and dynamic motion evaluation and damage early warning are achieved.

A device 100 for developing the concentration, the device 100 comprising: an optical sensor unit, the optical sensor unit comprising a plurality of one or more lenses 201, 202 capable of holding sensitive elements, the plurality of sensitive elements being configured to detect a user-provided biological signal in at least three operating modes; three switches for switching between the plurality of operating modes; a plurality of illumination units configured to indicate each of the plurality of operating modes by emitting a predetermined light signal; a processing unit for processing information using artificial intelligence.

The present disclosure provides an electronic device. The electronic device includes a flexible element, and a sensing element adjacent to the flexible element and configured to detect a biosignal. The electronic device also includes an active component in the flexible element and electrically connected with the sensing element. A method of manufacturing an electronic device is also disclosed.

A real-time drug interaction alert system using AI-powered analytics, consisting of: a wearable or implantable biosensor device configured to continuously measure physiological parameters of a subject, including at least heart rate, blood pressure, blood oxygen saturation, skin temperature, and biomarkers related to liver and kidney function; a communication module integrated into the device that can securely transmit physiological data to a cloud-based analysis engine via wireless protocols such as Bluetooth Low Energy (BLE), Wi-Fi, or LTE-M; a cloud-hosted artificial intelligence (AI) inference engine configured to perform multimodal drug-drug interaction risk analysis, the engine comprising at least a convolutional neural network (CNN) for time-series analysis of biosignal patterns, a natural language processing (NLP) module for extracting drug information from structured and unstructured medical sources, and a Bayesian reasoning module for modeling probabilistic risk interactions between drugs and patient-specific variables; a pharmaceutical input interface for capturing medication data by at least one of the following methods: manual entry, optical character recognition (OCR) of the packaging, or near field communication (NFC) scanning of embedded tags; an alert dissemination module configured to trigger multi-channel alerts, including haptic signals via the wearable device, audiovisual notifications via a paired smart device, and the secure transmission of interaction reports to designated healthcare professionals based on severity thresholds.

The invention discloses a low-noise and high-precision analog front-end circuit for biological signal acquisition. The low-noise and high-precision analog front-end circuit comprises a chopping capacitance coupling type instrument amplifier circuit, a switched capacitor type programmable gain amplifier circuit and a Sigma-Delta analog-to-digital converter modulator circuit. T-type capacitance feedback, chopping modulation and programmable technologies are introduced on the basis of an existing amplifier, and the low-noise and programmable gain functions of the pre-amplifier are achieved. Through the three-order one-bit quantized feed-forward chopping type Sigma-Delta modulator, the signal to noise ratio and the effective bit number of the signal are improved. Compared with the prior art, the analog front-end circuit not only has the capability of changing the gain multiple according to the bio-electricity signal, but also has the low-noise and high-precision signal processing effect, and the problems that a traditional analog front-end circuit is large in noise and low in signal processing precision are solved. In addition, the biological signal acquisition-oriented circuit provided by the invention can also be used in other analog front ends, such as an audio processor and the like, and is wide in application range.

The invention provides a relaxation and decompression system for relieving juvenile depression based on traditional Chinese medicine five-tone music, and relates to the technical field of five-tone relieving, the relaxation and decompression system comprises an equipment layer and a cloud service layer, the equipment layer comprises an intelligent bracelet module and a multi-mode equipment output module, a user interaction sub-module, an optical heart rate sensing sub-module, a skin electric response sensing sub-module, a body temperature sensing sub-module and a questionnaire survey sub-module are arranged in the intelligent bracelet module, the multi-modal equipment output module comprises an audio conduction unit and a wearable acupuncture point stimulation unit, and a phototherapy control sub-unit is arranged in the wearable acupuncture point stimulation unit. The cloud service layer comprises a traditional Chinese medicine five-tone generation module, a cloud intelligent analysis module and a user feedback module; by introducing the mechanism of five voices of traditional Chinese medicine and combining the theory of traditional Chinese medicine, a three-dimensional synergistic mode of music, acupoint stimulation and phototherapy is provided, and a relieving control scheme is continuously adjusted through real-time biological signal feedback, so that the depressive symptom of teenagers is effectively relieved, and the pressure is relieved.

The invention discloses an intelligent real-time regulation and control foot tub health management system which comprises an automatic water quality purification subsystem, a water temperature regulation and control subsystem, a foot biological signal detection subsystem, a touch-free induction control subsystem and a self-adaptive climate control subsystem. The invention belongs to the technical field of intelligent health, and particularly relates to a double-flow control algorithm combining real-time water temperature control flow and environment adaptation optimization flow in a water temperature regulation and control subsystem in a foot tub, water temperature management combining dynamic and static control is achieved, and on the basis that the double-flow control algorithm is designed in the water temperature regulation and control subsystem, water temperature management is achieved. A time sequence modeling method for power adjustment is provided, a power adjustment model is constructed by using a position Fourier transform bidirectional and conditional generative adversarial network, periodicity and frequency characteristics in time sequence data are extracted from a frequency domain level, heating power is accurately adjusted, unnecessary energy consumption is reduced, and the energy efficiency ratio of a system is improved.

The invention relates to the technical field of image enhancement, in particular to a rhizosphere microflora distribution analysis method based on image enhancement, which comprises the following steps: acquiring a continuous microscopic image sequence of a rhizosphere microenvironment, converting the continuous microscopic image sequence into a gray data space, and constructing a standard input frame set for optical flow calculation. According to the method, the stability score of each feature is calculated by using the signal-to-noise ratio stability measurement function, and the long-life-cycle feature is screened and reserved, so that the random imaging noise of the short life cycle can be filtered fundamentally, and the topological structure of the target community is obtained; and mapping the topological structure back to an original image space by using an inverse persistence mapping algorithm to be fused with a continuous microscopic image sequence, and finally, remarkably enhancing weak biological signals while keeping original form details, thereby realizing high signal-to-noise ratio analysis of microflora spatial and temporal distribution in a complex rhizosphere environment.

To provide information for notifying a user of an appropriate charging timing in a wearable-type biological signal measuring device in which the number of channels to be activated can be dynamically switched.SOLUTION: A wearable-type biological signal measuring device that is capable of measuring the biological signal of a plurality of channels and driven by a battery, includes: an operation mode switching part which can switch between a first operation mode for measuring the biological signal of the plurality of channels by activating the plurality of channels and a second operation mode for measuring the biological signal of a part of the channels by activating the part of the channels; a battery remaining amount acquiring part for acquiring the information of battery remaining amount of the battery; a prediction part for predicting an operable time of the biological signal measuring device based on the consumption power in each of the operation mode and the battery remaining amount; and an output part for outputting the information of the predicted value of the operable time.SELECTED DRAWING: Figure 1

A method for biosignal data transformation can include: determining a set of biosignal data, determining a brain state representation (e.g., an embedding) based on the biosignal data, and determining a biomarker value based on the brain state representation. The method can optionally include training a model (e.g., training a model used to determine the brain state representation), and / or any other suitable steps. A system for biosignal data transformation can include a biosignal device and a computing system.

The invention provides a multi-mode biological signal dynamic fusion fitness guidance method and system. The method comprises the steps that a signal acquisition layer synchronously acquires dynamic force and static pressure through a flexible voltage capacitance sensor; in the feature processing layer, frequency domain energy distribution is extracted from voltage signals through short-time Fourier transform, static pressure gradient is obtained from capacitance signals through wavelet packet decomposition, time-frequency decomposition is carried out, and feature dimensionality reduction is carried out; the fusion modeling layer is used for eliminating time migration of sensor data through dynamic time warping to carry out time alignment and carrying out feature fusion based on a Transform attention mechanism; and the decision generation layer performs incremental learning and large model driven fine tuning to generate a personalized exercise prescription. Based on the technical scheme of the invention, the muscle state analysis precision is effectively improved through the dynamic time-frequency fusion of the dynamic and static signals; real-time dynamic feedback of the system is improved; the model power consumption is reduced, and the noise suppression rate is improved; and the personalized adaptation degree is improved by a dynamic threshold value.

Apparatus and methods detect sleep staging events. The apparatus (100) may be configured to obtain a facial biopotential signal measured between two electrodes connected to a user's face, which may be configured to form a transverse-ocular measurement vector. The biopotential signal may be measured by a biopotential measurement device comprising the two electrodes. The apparatus (100, 200) may be configured to derive, from the facial biopotential signal, a plurality of biosignals suggestive of sleep staging events. The apparatus may be configured to classify individual segments of the plurality of biosignals as belonging to one of a plurality of sleep stating events. The classification may involve using a trained machine learning model, such as a recurrent neural network, to predict sleep staging events for different segments or epochs of the plurality of biosignals.

The invention discloses a foreign language learning and homework doing system and a foreign language learning and homework doing method integrating education artificial intelligence, augmented reality (AR) technology and biological signal perception. A multi-mode biosensor (electrodermal response, heart rate, eye movement and the like) is integrated through customized AR intelligent glasses, and a closed loop of'interest scene triggering-biological signal sensing-personalized content pushing-self-adaptive review planning based on a forgetting curve and real-time emotion data 'is realized in combination with an interest matching algorithm and a dynamic learning engine of an intelligent foreign language learning APP. The system utilizes an artificial intelligence technology to accurately analyze the emotional state of a user, adopts a bidirectional long short-term memory network (Bi-LSTM) personalized forgetting curve algorithm, integrates foreign language words, grammar and other homework contents into an augmented reality or virtual interest scene, and supports on-school students to complete homework tasks and off-school users to autonomously learn. The system covers hardware architecture design, AI algorithm implementation and a data interaction process, foreign language learning and homework doing are completed during playing, the learning efficiency is remarkably improved, and the system has high innovativeness and practicability.

The invention discloses a training system for economic management teaching based on cloud service. The training system comprises a biological signal acquisition module, an electroencephalogram signal processing module and a dynamic difficulty adjustment module, the invention relates to the technical field of educational training. According to the training system for economic management teaching based on the cloud service, the cognitive load degree of a student is clearly judged by collecting electroencephalogram signals of the student, and corresponding intervention of the difficulty of an economic management teaching course is performed according to the cognitive load degree of the student, so that personalized teaching of the student can be realized, and the teaching efficiency is improved. In addition, the system can assist students in high-efficiency learning, achieves the purpose of better adapting to individual differences and teaching stage changes, and provides effective support for improving intervention accuracy, enhancing system adaptability and optimizing learning experience.

The invention relates to the technical field related to intelligent traffic driving safety, in particular to a dangerous driving behavior recognition method and system based on multi-modal data fusion. According to the method, driver behaviors and vehicle operation data are collected in real time through a vehicle-mounted sensing system, hardware-level synchronization of multi-source data is achieved based on GPS-PPS pulses, and a unified timestamp system is established; extracting multi-modal features of vision, vehicle dynamics and biological signals under a unified time sequence; cross-modal feature deep fusion is realized by using a graph neural network and an attention mechanism; performing risk quantification by adopting a secondary decision model in combination with an environment adaptive weight; and finally, according to the risk score, triggering graded early warning and linkage with vehicle control, and meanwhile, generating an event report and uploading the event report to a cloud platform to form closed-loop management. According to the method, the problem of misjudgment caused by data asynchronization in a traditional scheme is effectively solved, and the recognition accuracy and the system reliability in a complex environment are remarkably improved.