90 results about "Arousal" patented technology

The invention discloses a skin electric signal multi-task feature fusion-based mixed emotion recognition method, which comprises the following steps of: acquiring a skin electric signal in a mixed emotion state, performing preprocessing such as filtering and baseline correction, extracting time domain, frequency domain and nonlinear manual features, and extracting deep spatial-temporal features in combination with a CNN-LSTM model; a gating network is designed to realize self-adaptive fusion of manual features and deep spatial-temporal features, so that a multi-task collaborative learning framework with emotion classification as a main task and titer / wakeup degree prediction as an auxiliary task is constructed, and accurate distinguishing of positive, negative and mixed emotions is realized through joint optimization of model parameters. According to the method, classification of mixed emotions is realized, and an extensible technical reference can be provided for the fields of emotion calculation, intelligent health monitoring and the like.

Embodiments disclosed include a method comprising building a machine learning (ML) model that includes a digital agent configured to navigate a digital environment, implementing a navigation of the digital agent over a period of time and following a path within the digital environment, that includes a set of states. Upon reaching each state, the digital agent is configured to acquire the value associated with that state. The method includes determining a signal representing an acquisition of values by the digital agent over the period of time, computing an emotive state of the digital agent and an arousal state of the digital agent based on the signal representing the acquisition of values, and determining a goal for the digital agent to achieve an improved overall performance in acquiring cumulative rewards. The method includes implementing a real version of an action of the digital agent in a real environment.

The invention discloses an emotion recognition method based on multi-modal signal fusion, and relates to the technical field of emotion recognition, and the method comprises the steps: obtaining an electroencephalogram signal and a peripheral physiological signal to form a multi-modal signal, and carrying out the preprocessing of down-sampling, baseline correction and band-pass filtering on the multi-modal signal; based on the preprocessed signal, extracting a difference entropy feature and a power spectrum density feature; mapping the extracted features into a standardized space grid to generate a feature tensor with a uniform structure; performing adaptive weighting on the mapped feature tensor by using a frequency band fusion attention mechanism, and generating a frequency band weight through global average pooling and a full connection layer; inputting the weighted features into a full connection layer of the parameterized hypermatrix, and performing feature compression and modeling through matrix decomposition and reconstruction; a multi-task learning framework is adopted, classification results of emotion titer and awakening degree are output at the same time based on compressed features, and multi-task collaboration is optimized through a shared feature layer and a dynamic loss weight.

The invention discloses a music induced emotion recognition method based on EEG and fNIRS fusion, and the method comprises the steps: firstly designing a music library covering different titer-awakening degree dimensions, and achieving the automatic generation of a large number of music clips through constructing a cue word template and innovatively combining with an AIGC technology; then, volunteers are recruited to subjectively score the generated music segments, and segments with good emotion inducing effects are screened out; on the basis, a multi-mode brain signal acquisition normal form is designed, EEG and fNIRS signals of a subject when the subject listens to music are synchronously acquired, and finally effective emotion classification is realized based on a model fusing the EEG and fNIRS signals. Through technical innovation and method integration, a complete closed loop from music generation to brain signal analysis is constructed, and a reproducible research normal form and an effective classification model are provided for the field of emotion calculation.

The present invention relates to a method and system for analysing audio (eg. music) tracks. A predictive model of the neuro-physiological functioning and response to sounds by one or more of the human lower cortical, limbic and subcortical regions in the brain is described. Sounds are analysed so that appropriate sounds can be selected and played to a listener in order to stimulate and / or manipulate neuro-physiological arousal in that listener. The method and system are particularly applicable to applications harnessing a biofeedback resource.

The invention relates to the technical field of brain-computer interaction, in particular to a patient mental state assessment system for a clinician, which comprises a semantic manifold calibration module, a state trajectory projection module, a geometric curvature resolving module and an emotion transformation quantification module. According to the method, electroencephalogram data are collected and deeply analyzed, high-dimensional neural activity characteristics are converted into a visual three-dimensional state track in combination with titer and awakening degree information, continuous dynamic monitoring of the mental state of a patient is achieved, then the emotion conversion process is quantitatively analyzed according to the geometric curvature change rate of the state track, and therefore the mental state of the patient can be rapidly and accurately monitored. According to the method, rapid emotion fluctuation which is difficult to perceive in a traditional evaluation mode can be accurately recognized and marked, objective and fine data support is provided for clinical diagnosis, and the accuracy and instantaneity of mental state evaluation are remarkably improved.

A model may be generated for characterization of a fluctuation in an arousal level based on EEG data for a cohort of subjects. Changes in gamma and delta waves can be used to detect arousal units (AUs) for cortical periods. One or more metrics relating at least in part to gamma and theta waves can be determined for each AU. Centroids for the cortical periods can be used to train the model to generate an arousal index. The model can be used to determinate arousal level in one or more patients. For example, EEG data can be acquired for a subject using a set of sensors. AUs in the EEG data can be detected, and a characterization of a fluctuation in an arousal level of the subject can be generated using the model. The characterization may be used in evaluating and / or treating a health condition, such as a consciousness disorder.

This paper discloses a music-induced emotion recognition method based on the fusion of EEG and fNIRS. The method first designs a music library covering different valence-arousal dimensions. By constructing a prompt word template and innovatively combining AIGC technology, it realizes the automated generation of a large number of music clips. Then, volunteers are recruited to subjectively score the generated music clips, screening out those with good emotion-inducing effects. Based on this, the method designs a multimodal brain signal acquisition paradigm to synchronously collect EEG and fNIRS signals from subjects while listening to music. Finally, based on the model that fuses EEG and fNIRS signals, it achieves effective emotion classification. Through technological innovation and methodological integration, the method constructs a complete closed loop from music generation to brain signal analysis, providing a reproducible research paradigm and effective classification model for the field of emotion computing.

The invention provides a user emotion prediction processing method and device, equipment and a storage medium. The method comprises the following steps: acquiring a face image and audio data of a user; preprocessing the face image and the audio data to obtain an aligned face image and each audio clip; performing visual feature extraction processing on the aligned face image to obtain visual representation features; performing audio feature extraction processing on each audio clip to obtain Mel spectrogram features; preprocessing the visual representation features and the Mel spectrogram features, and determining corresponding final condition features; inputting the final condition features, the current noise value and the time step number into a pre-trained back diffusion process function for processing to obtain a preliminary prediction titer-wake-up value; correcting and updating the preliminary predicted titer-wake-up value to obtain a final titer-wake-up value; and the emotion of the user is predicted according to the final titer-wake-up value, so that the prediction accuracy of the emotion of the user is improved.

The application discloses a kind of induced mood pulse sound feature screening method, belong to cognitive neuroscientific technology field, solve the problem of lack of effective screening in prior art mood pulse sound feature.A kind of induced mood pulse sound feature screening method, the method comprises: under the condition of subject within experiment, according to the scene of inducing mood, set multiple pulse sounds;The independent variable of the pulse sound includes sound frequency, repetition frequency and relative loudness;Different sound frequency, repetition frequency and relative loudness are cross designed, form multiple sound stimuli;Using multiple sound stimuli, a plurality of subjects are experimented respectively;And the physiological signal of each subject under each sound stimulus, emotional valence score and arousal degree score are acquired;Based on the physiological signal of all subjects under all sound stimuli, emotional valence score and arousal degree score, the feature screening result of corresponding induced mood pulse sound is obtained.

To estimate an arousal direction of a driver of a vehicle.SOLUTION: A first derivation unit 41 derives a first index value corresponding to a driver's visual stimulation based on a front image of a vehicle obtained by an imaging unit. A second derivation unit 42 derives a second index value corresponding to a relatively strong visual stimulation among a driver's visual stimuli based on a result of comparing the first index value with a predetermined stimulation threshold. An arousal direction estimation unit 43 estimates an arousal direction, which is a direction of change in the driver's arousal level, based on a correlation between a temporal change in the first index value and a temporal change in the second index value.SELECTED DRAWING: Figure 9

The application belongs to the technical field of biomedical signal processing and computer vision, and specifically discloses a child emotion analysis method and system based on eye movement and micro-expression association, which comprises the following steps: synchronously acquiring an eye movement data stream and a facial video stream, triggering a dynamic analysis process by identifying a mode conflict between high physiological arousal and low emotional expression intensity after generating a physiological arousal and emotion hypothesis through preliminary analysis, generating a guide strategy according to a conflict degree, and enhancing original data in a time domain or a space domain to facilitate deep analysis, capturing suppressed micro-expression signals in the enhanced data to correct the preliminary emotion hypothesis, and finally fusing a physiological arousal level, a corrected emotion category and a quantified expression inhibition degree to output a multi-dimensional psychological state analysis result containing an emotion category, a physiological arousal level and an expression inhibition degree, so as to realize quantitative and multi-dimensional evaluation of real emotions of children.

The application discloses a kind of feature screening systems for evaluating the emotional interference effect of impulse sound, it is related to cognitive neuroscientific technology field, it solves the problem that there is no effective screening impulse sound characteristics affecting emotion in prior art.The system comprises: sound generation module, for the independent variable of impulse sound is cross designed to form multiple sound stimuli, and multiple subjects are respectively experimented using multiple sound stimuli;Data acquisition module is used to collect experimental data in the process of within-subject experiment;The experimental data include the physiological signal of each subject under each sound stimulus, emotional valence score and arousal score;Data processing module is used to process experimental data in the process of within-subject experiment, and the dependent variable of impulse sound under each sound stimulus is obtained;Data analysis module determines the feature screening result of impulse sound inducing emotion by analyzing the correlation between the independent variable and dependent variable of impulse sound under sound stimulus.

The invention discloses a VR psychological intervention method fusing emotion release and wake-up, and relates to the technical field of VR psychological intervention, comprising the following steps: after a user enters a virtual reality psychological intervention environment, a system synchronously collects physiological signals, voice intonation and facial micro-expression information of the user to obtain multi-modal data; the physiological signals comprise galvanic skin response, heart rate and heart rate variability; based on the multi-modal data, the emotional states of the user are classified, emotional state labels are generated, and the emotional state labels comprise three types of high-negative emotions, low-negative emotions and positive emotions; when the emotional state label indicates that the user is in a high-negative emotional state, an emotional release stage is triggered, the user captures a dark energy ball appearing in a virtual space through gesture interaction and executes a throwing-out action, and the energy ball moves along with a gesture track of the user and explodes and dissipates after the release action of the user is completed.

The application relates to a medical engineering technology, in particular to a control method and system of a diagnosis and treatment robot for autistic children. The control method comprises the following steps: analyzing a human face video by using a deep learning model; generating a next-step intervention action recommendation list by using an LSTM state prediction model and a CPT action decision model; selecting or modifying one of the recommendation items and executing; retraining and updating the LSTM state prediction model and the CPT action decision model by using new interaction data. The control system comprises an execution module, a perception module, a memory module, an evolution module and a decision module. By introducing the quantification calculation of the concentration of the children and the valence and arousal of the facial expression, and by using the LSTM to predict the future state, the strategy can be adjusted in advance when it is predicted that the children will lose interest, so that the children's boredom or escape behavior is not easily caused, and meanwhile, the model is retrained and updated, so that the self-learning and adaptation capability is high, and the auxiliary diagnosis and treatment capability is relatively high.

A method and system for determining a positional sleep disordered breathing (pSDB) status associated with a respiratory device user is disclosed. Airflow data associated with the user is received. The airflow data is analyzed to identify a first time period of suspected arousal and a second time period of suspected arousal. A first time section between the identified first time period and the identified second time period is determined. The airflow data associated with the determined first time section is analyzed to identify (i) an indication of one or more respiratory events and / or (ii) an indication of one or more therapy events. Based at least in part on the (i) identified indication of one or more respiratory events and / or (ii) identified indication of one or more therapy events, the pSDB status of the user is determined, where the pSDB status is indicative of whether or not the user has pSDB.

This invention relates to the field of medical information processing and intelligent decision-making technology, and particularly to an autism decision assessment system based on multivariate data and knowledge graphs. The autism decision assessment system based on multivariate data and knowledge graphs includes the following components: a time-locked random calculation module: collecting endogenous and exogenous data, and determining time lock and random variables based on the endogenous and exogenous data; an arousal graph correction module: obtaining the endogenous arousal level based on the time lock and random variables, constructing a knowledge graph based on the endogenous and exogenous data and combining the endogenous arousal level, and correcting the knowledge graph; and a decision assessment output module: performing autism decision assessment based on the corrected knowledge graph. This invention integrates physiological and environmental time-series data, and through mutual information phase-locked detection, randomized causal graph construction, and individualized extreme value modeling, decouples endogenous and exogenous confusion, improving the accuracy and interpretability of autism assessment.

This document relates to causing computers to perform various actions based on gas sensor readings. Gas sensor readings indicating gas levels of various gases can be employed to predict emotional characteristics of a user. For instance, a gas sensor placed near a user's mouth can obtain gas sensor readings indicating levels of nitrogen dioxide, ethyl alcohol, volatile organic compounds, and / or carbon monoxide in the user's breath. Then, gas sensor readings can be used to obtain gas level features, which are input to a trained machine learning model. The trained machine learning model can output a predicted emotional characteristic of the user, such as valence or arousal. Then, a computer can perform an action based on the predicted emotional characteristic. For instance, the action can include adjusting behavior of an automated agent, e.g., to help a distressed user calm down, outputting an alert when the user is in distress, etc.

Systems, devices, and methods are provided for performing a sleep study of a subject. The methods include obtaining data from one or more body signals, the one or more body signals being non-brain signals, and determining an arousal or arousal-associated event of the subject using the data from one or more body signals. In a preferred embodiment, the one or more body signals include data obtained from one or more RIP belts.

A vibration control device that while responding to music being played, generates a vibration that gives desired arousal effect and / or relaxing effect regardless of the contents is provided, the vibration control device controlling a vibration device that generates vibration according to the music being played and gives a stimulus to a user includes a vibration signal acquisition unit for acquiring a vibration signal representing the vibration in which a stimulus intensity falls within a predetermined stimulus intensity range, and an output unit for outputting the vibration signal acquired by the vibration signal acquisition unit to the vibration device.

The application discloses a method and system for emotion perception and empathetic interaction adjustment of embodied agents. Non-contact acquisition of user physiological signals: millimeter wave radar measures respiratory rate and heart rate, a camera measures heart rate and / or heart rate variability through remote photoplethysmography rPPG, and wearable device signals can be optionally fused; real-time evaluation of signal quality of each mode and adaptive fusion, estimation of emotional / stress state containing physiological arousal based on individualized baseline; adjustment of robot behavior strategy based on the estimation, output of embodied behavior parameters such as speech speed, action amplitude, close distance and dialogue content; the behavior strategy adopts reinforcement learning, and physiological arousal is included in the reward function, so that the robot learns embodied behaviors for reducing user discomfort and improving comfort, and an empathetic interaction closed loop of perception-estimation-decision-execution-re-perception is formed. The application does not need long-term wearing, can more truly reflect the internal state, is robust, safe and privacy-friendly, and is suitable for companion and education robots.

A method and device for arranging a fatigue arousal section in a tunnel, as well as a road tunnel. The method includes: determining a plurality of colors and luminance of fatigue arousal section; based on a plurality of samples, generating a plurality of arousal duration models in which the drivers' arousal duration changes with stimulus quantity at multiple different vehicle speeds, wherein the samples include arousal durations of different drivers under different stimulus quantities at the plurality of colors and luminance; determining length and spacing of fatigue arousal section to be arranged according to a specified speed of the tunnel, using the arousal duration models; and arranging one or more fatigue arousal sections in the tunnel based on the determined length and spacing of the fatigue arousal section.

An arousal state control system includes a sensor, a stimulation control unit, and a stimulator. The sensor acquires biological information of a user. The stimulation control unit determines, based on the biological information, one or more types of stimuli to control a state of arousal of the user. The stimulator applies the one or more types of stimuli determined by the stimulation control unit to the user.

An arousal estimation system is proposed herein that estimates a human psychophysiological state on an arousal scale, using an arousal detection model that outputs a single arousal score characterizing arousal, rather than a particular target state, such as drowsiness, stress, or cognitive load. Based on an estimated arousal score, the human state can be characterized as either within or outside a desired range of arousal levels associated with optimal performance of relevant tasks. The arousal detection model is trained on a wider set of sensor data than may be applicable to a specific mental state. By training the arousal detection model on the wider set of sensor data associated with different arousal levels, an arousal score generated by the arousal detection model may generate a more accurate estimation of the human state than the conventional single state detectors, even when combined.

The wake state control system includes a sensor, a stimulation control unit, and a stimulator. The sensor acquires biological information of a user. A stimulation control unit determines one or more types of stimuli based on the biological information to control a wake-up state of the user. A stimulator applies the one or more types of stimulation determined by the stimulation control unit to the user.

The present invention discloses a street greening quality detection method based on physiological arousal recognition, comprising: establishing a greening quality factor index system according to high-frequency street landscape characteristics, acquiring and uniformly processing street greening images to conduct greening stimulation physiological experiments; collecting original data, reclassifying and performing difference wave processing on the original data according to the greening quality factor index, and obtaining effective physiological data that can be used for greening quality factor arousal feature identification; calculating physiological arousal feature parameters based on the obtained effective physiological data, using transfer learning to fuse and train the physiological arousal feature parameters to achieve physiological arousal feature importance judgment, and identifying the weighted average greening arousal index of the greening quality factor; analyzing the weighted average greening arousal index data of the greening quality factor to form a street greening quality detection model, inputting the labeled street samples to be analyzed into the street greening quality detection model, and obtaining the labeling results of the street greening quality grading detection target data.

To provide a method of evaluating a change in a psychological state of a person due to external stimulation and a creation method of flavor that changes a psychological state.SOLUTION: A change in a psychological state of a person due to external stimulation is objectively evaluated by analyzing evaluation of emotion and arousal factor of an emotion and arousal checklist (EACL) on a coordinate axis on the Russell's circumplex model.SELECTED DRAWING: Figure 6

The application provides a cross-subject electroencephalogram emotion recognition method based on a Riemannian manifold. Current cross-subject emotion recognition models based on electroencephalogram signals have problems such as poor model generalization, low recognition accuracy and the like, and are limited to analyzing amplitude information of the electroencephalogram signals, and cannot effectively reduce the difference between subjects. The application first extracts four frequency bands θ, α, β and γ of the electroencephalogram signals by using an FIR filter, then calculates a PLV matrix between the electroencephalogram signal channels, and aligns the PLV matrix of a task state to the PLV matrix of a resting state on the Riemannian manifold to reduce the difference between different subjects. Finally, the PLV matrix is mapped to a tangent space for classification and recognition. The application performs a valence and arousal two-classification experiment and a valence-arousal space four-classification experiment on a DEAP data set, and the results show that the method is effective.

The present invention discloses an emotion recognition method based on the fusion of EEG spatio-temporal-frequency features, including: S1, performing a series of preprocessing steps on the original EEG signals, including baseline correction, normalization, and adding time windows; S2, performing a form conversion on the EEG signals processed in S1 above to obtain the spatial information and time-frequency information of the EEG signals; S3, extracting features in multiple aspects; S4, fusing the extracted emotion features and performing multi-feature emotion recognition; S5, using BILSTM with added channel attention mechanism to further extract the time features of the EEG signals and perform deep fusion of the features; S6, obtaining the emotion classification result. By adopting the above emotion recognition method based on the fusion of EEG spatio-temporal-frequency features, the present invention fully considers the feature information of the three dimensions of time, frequency, and space of the EEG signals, achieves the highest recognition accuracy in the arousal and valence dimensions, improves the accuracy and robustness of emotion recognition, and verifies the effectiveness of the method.

A system and method for objectively determining interpersonal compatibility by correlating synchronized multimodal biometric responses to humorous stimuli. The system presents categorized media content to a user while simultaneously capturing asynchronous data streams, including facial video, audio vocalizations, and galvanic skin response (GSR). A synchronization engine aligns these streams, applying a latency correction algorithm to correlate delayed physiological arousal peaks (phasic SCR) with antecedent visual micro-expressions (Action Units 6 and 12). By validating visual smiles with physiological arousal, the system distinguishes genuine Duchenne responses from social masking. These validated responses are fused via a tensor network into a multidimensional “Humor Response Vector.” Compatibility is determined by calculating the cosine similarity between users' vectors in a latent space, providing a quantification of psychological alignment that transcends self-reported bias. Embodiments include privacy-preserving edge extraction and homomorphic encryption of profile vectors.