A method for assessing cognitive state in a closed environment

Abstract

The present disclosure relates to a cognitive state evaluation method and device in a closed environment, electronic equipment and a storage medium. The method comprises: collecting emotion cognitive features and attention cognitive features based on a preset emotion cognitive model and a preset attention cognitive model respectively; performing dimension reduction processing on the emotion cognitive features and the attention cognitive features; taking the dimension-reduced emotion cognitive features and the dimension-reduced attention cognitive features as inputs, learning a cognitive feature model based on a support vector machine (SVM) classifier to evaluate a cognitive state, and generating an evaluation result. The present disclosure uses a self-rating scale and measured electroencephalogram features and behavioral features to evaluate the cognitive state of the brain from subjective and objective perspectives, respectively, uses a machine learning method for identification and classification, realizes the evaluation of the brain evaluation state, and provides a method basis for the detection of the cognitive state of the brain under long-term closed operation conditions.

Description

Technical Field

[0001] This disclosure relates to the field of EEG technology applications, and more specifically, to a method, device, electronic device, and computer-readable storage medium for assessing cognitive states in a closed environment. Background Technology

[0002] Many operations require operators or workers to live and work in a specific, enclosed environment. Studies have shown that enclosed environments differ from normal human living environments, exhibiting social isolation and spatial confinement. Furthermore, prolonged exposure to enclosed environments can lead to abnormal responses in cognitive functions and other areas.

[0003] Electroencephalography (EEG) has recently been used in two closed-environment (space) studies to explore how such environments affect the brain's physiological and emotional states. One study found that three months of isolation led to a general decrease in brain activity, as well as a decline in physical condition and motivation. Another study investigated the effects of closed environments on stress responses. This study assessed the brain activity of six participants from different countries who lived in complete isolation in a simulated spacecraft for 520 days. The study found a significant decrease in global cortical alpha and beta activity from the start to the end of the mission. A recent study on the mental health of soldiers stationed in a fully enclosed environment at high altitudes found that the enclosed environment has a certain impact on the mental health of these soldiers, mainly manifested in irritability, anxiety, and depression.

[0004] A high level of attention is crucial for operators to complete tasks. Posner et al. (2002, 2014) first subdivided the attention network into three subnetworks: Alerting, Orienting, and Executive Control. These three networks reflect an individual's ability to acquire and maintain alertness to a particular type of information or target, selectively attend to useful external information, and process conflicting information. These three components of attention can be measured using the Attention Network Test (ANT) developed by Fan et al. ANT has been widely used by researchers and proven to be an effective tool for measuring the efficiency of different attention networks (Macleod et al., 2010). The experimental paradigm of attention networks has been well-proven through theoretical and experimental studies, and due to its high operability and short testing time, it is widely used in psychology, neuroscience, and medicine. ANT relies on performance measurements of stimuli under different conditions, such as response time and accuracy, and the calculation of differential scores for target alertness, orientation, and executive control.

[0005] Therefore, one or more methods are needed to solve the above problems.

[0006] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] The purpose of this disclosure is to provide a method, apparatus, electronic device, and computer-readable storage medium for assessing cognitive states in a closed environment, thereby overcoming, at least to some extent, one or more problems caused by limitations and defects in related technologies.

[0008] According to one aspect of this disclosure, a method for assessing cognitive states in a closed environment is provided, comprising:

[0009] Based on a preset emotion cognition model and a preset attention cognition model, emotion cognition features and attention cognition features were collected respectively.

[0010] The aforementioned emotion cognition features and attention cognition features are subjected to dimensionality reduction processing;

[0011] Using the dimensionality-reduced emotion and attention cognitive features as input, a cognitive feature model is learned based on a support vector machine (SVM) classifier to evaluate the cognitive state and generate an evaluation result.

[0012] In one exemplary embodiment of this disclosure, the method further includes collecting emotional cognitive features based on a preset emotional cognitive model:

[0013] The scales were assessed using the Self-Rating Anxiety Scale (SAS), Self-Rating Depression Scale (SDS), Self-Rating Stress Questionnaire (PSET), and Symptom Checklist-90 (SCL-90) to obtain SAS scores, SDS scores, PSET scores, and scores for somatization, obsessive-compulsive disorder, interpersonal sensitivity, depression, anxiety, hostility, phobia, paranoia, and psychotic factors in the SCL-90.

[0014] Based on the emotional stroop EEG experiment, behavioral and EEG features were extracted to obtain a preset number of emotional behavioral features and the amplitude of ERP components.

[0015] In one exemplary embodiment of this disclosure, the method further includes collecting attentional cognitive features based on a preset attentional cognitive model:

[0016] The Attention Network (ANT) EEG experiment was designed, and behavioral characteristics of the efficiency of the attention orientation network, attentional alertness network, and attentional executive control network were collected based on the ANT experiment.

[0017] In one exemplary embodiment of this disclosure, the method further includes:

[0018] The emotional and attentional cognitive features were dimensionality reduced using factor analysis.

[0019] In one exemplary embodiment of this disclosure, the method further includes:

[0020] A predetermined number of participants were recruited to participate in emotion and attention experiments.

[0021] In the emotion-inducing experiment, movie clips from a pre-set emotion video database were used to induce specific positive, neutral, and negative emotions in the subjects to complete the collection of training samples.

[0022] In the attention experiment, based on the attention network ANT EEG experiment, after a one-hour simulated driving task, the fatigue self-report results and ANT EEG data of the subjects were collected to complete the training sample collection.

[0023] In one exemplary embodiment of this disclosure, the method further includes:

[0024] The dimensionality-reduced emotion cognitive features and attention cognitive features are learned using multi-kernel learning support vector machines, respectively, to establish classification models for emotion state and attention level, thereby enabling the assessment of emotion state and attention level;

[0025] Calculate the combined kernel vector based on the kernel function vector and its weight vector obtained from the EasyMKL algorithm;

[0026] A classification experiment was conducted by combining an SVM classifier and a test set.

[0027] In one aspect of this disclosure, a cognitive state assessment device for a closed environment is provided, comprising:

[0028] The feature acquisition module is used to collect emotional cognitive features and attentional cognitive features based on the preset emotion cognitive model and the preset attention cognitive model, respectively.

[0029] The dimensionality reduction module is used to reduce the dimensionality of the emotion cognition features and attention cognition features.

[0030] The cognitive state assessment module is used to assess the cognitive state by taking the dimensionality-reduced emotional cognitive features and attention cognitive features as input, learning a cognitive feature model based on a support vector machine (SVM) classifier, and generating assessment results.

[0031] In one aspect of this disclosure, an electronic device is provided, comprising:

[0032] Processor; and

[0033] A memory storing computer-readable instructions that, when executed by the processor, implement the method according to any one of the preceding claims.

[0034] In one aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method according to any one of the preceding claims.

[0035] An exemplary embodiment of this disclosure provides a method for assessing cognitive state in a closed environment. The method includes: collecting emotional cognitive features and attentional cognitive features based on a preset emotional cognitive model and a preset attentional cognitive model, respectively; performing dimensionality reduction processing on the emotional cognitive features and attentional cognitive features; using the dimensionality-reduced emotional cognitive features and attentional cognitive features as input, learning a cognitive feature model based on a support vector machine (SVM) classifier to assess the cognitive state and generate an assessment result. This disclosure uses a self-assessment scale and measured EEG and behavioral features to assess brain cognitive state from subjective and objective perspectives, respectively. Machine learning methods are used for identification and classification to achieve brain cognitive state assessment, providing a methodological basis for detecting brain cognitive state under long-term closed working conditions.

[0036] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0037] The above and other features and advantages of this disclosure will become more apparent from the detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0038] Figure 1 A flowchart is shown for a cognitive state assessment method in a closed environment according to an exemplary embodiment of the present disclosure;

[0039] Figure 2 A schematic diagram of a method for assessing cognitive state in a closed environment according to an exemplary embodiment of the present disclosure is shown.

[0040] Figure 3 A schematic diagram of the ANT experimental paradigm for a cognitive state assessment method in a closed environment according to an exemplary embodiment of the present disclosure is shown.

[0041] Figure 4 A schematic block diagram of a cognitive state assessment device in a closed environment is shown according to an exemplary embodiment of the present disclosure;

[0042] Figure 5 A block diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown schematically;

[0043] Figure 6 The illustration shows a schematic diagram of a computer-readable storage medium according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0044] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted.

[0045] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced without one or more of the specific details described, or other methods, components, materials, apparatuses, steps, etc., can be employed. In other instances, well-known structures, methods, apparatuses, implementations, materials, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0046] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, or in one or more software-hardened modules, or in different network and / or processor devices and / or microcontroller devices.

[0047] In this example embodiment, a method for assessing cognitive state in a closed environment is first provided; refer to Figure 1 As shown, this method for assessing cognitive states in a closed environment may include the following steps:

[0048] Step S110: Collect emotional cognitive features and attentional cognitive features based on the preset emotion cognitive model and the preset attention cognitive model, respectively.

[0049] Step S120: Perform dimensionality reduction processing on the emotion cognition features and attention cognition features;

[0050] Step S130: Using the dimensionality-reduced emotion and attention cognitive features as input, a cognitive feature model is learned based on a support vector machine (SVM) classifier to evaluate the cognitive state and generate an evaluation result.

[0051] An exemplary embodiment of this disclosure provides a method for assessing cognitive state in a closed environment. The method includes: collecting emotional cognitive features and attentional cognitive features based on a preset emotional cognitive model and a preset attentional cognitive model, respectively; performing dimensionality reduction processing on the emotional cognitive features and attentional cognitive features; using the dimensionality-reduced emotional cognitive features and attentional cognitive features as input, learning a cognitive feature model based on a support vector machine (SVM) classifier to assess the cognitive state and generate an assessment result. This disclosure uses a self-assessment scale and measured EEG and behavioral features to assess brain cognitive state from subjective and objective perspectives, respectively. Machine learning methods are used for identification and classification to achieve brain cognitive state assessment, providing a methodological basis for detecting brain cognitive state under long-term closed working conditions.

[0052] The following will further explain a method for assessing cognitive state in a closed environment in this example embodiment.

[0053] Example 1:

[0054] In step S110, emotional cognitive features and attentional cognitive features can be collected based on the preset emotion cognitive model and the preset attention cognitive model, respectively.

[0055] In this example embodiment, the method for collecting emotional cognitive features based on a preset emotional cognitive model further includes:

[0056] The scales were assessed using the Self-Rating Anxiety Scale (SAS), Self-Rating Depression Scale (SDS), Self-Rating Stress Questionnaire (PSET), and Symptom Checklist-90 (SCL-90) to obtain SAS scores, SDS scores, PSET scores, and scores for somatization, obsessive-compulsive disorder, interpersonal sensitivity, depression, anxiety, hostility, phobia, paranoia, and psychotic factors in the SCL-90.

[0057] Based on the emotional stroop EEG experiment, behavioral and EEG features were extracted to obtain a preset number of emotional behavioral features and the amplitude of ERP components.

[0058] In this example embodiment, the method for collecting attentional cognitive features based on a preset attentional cognitive model further includes:

[0059] The Attention Network (ANT) EEG experiment was designed, and behavioral characteristics of the efficiency of the attention orientation network, attentional alertness network, and attentional executive control network were collected based on the ANT experiment.

[0060] In step S120, the emotional cognitive features and attentional cognitive features can be subjected to dimensionality reduction processing.

[0061] In this example embodiment, the method further includes:

[0062] The emotional and attentional cognitive features were dimensionality reduced using factor analysis.

[0063] In step S130, the dimensionality-reduced emotion and attention cognitive features can be used as inputs to learn a cognitive feature model based on a support vector machine (SVM) classifier to evaluate the cognitive state and generate an evaluation result.

[0064] In this example embodiment, the method further includes:

[0065] A predetermined number of participants were recruited to participate in emotion and attention experiments.

[0066] In the emotion-inducing experiment, movie clips from a pre-set emotion video database were used to induce specific positive, neutral, and negative emotions in the subjects to complete the collection of training samples.

[0067] In the attention experiment, based on the attention network ANT EEG experiment, after a one-hour simulated driving task, the fatigue self-report results and ANT EEG data of the subjects were collected to complete the training sample collection.

[0068] In this example embodiment, the method further includes:

[0069] The dimensionality-reduced emotion cognitive features and attention cognitive features are learned using multi-kernel learning support vector machines, respectively, to establish classification models for emotion state and attention level, thereby enabling the assessment of emotion state and attention level;

[0070] Calculate the combined kernel vector based on the kernel function vector and its weight vector obtained from the EasyMKL algorithm;

[0071] A classification experiment was conducted by combining an SVM classifier and a test set.

[0072] Example 2:

[0073] In the embodiments of this example, as Figure 2 As shown, the cognitive assessment of the brain in a closed environment mainly considers two aspects: emotional cognitive function and attentional cognitive function. Emotional assessment employed both scales and electroencephalography (EEG). Four emotion scales were selected, and scale score characteristics were extracted. An EEG experiment using the emotion stroop technique was conducted to obtain EEG ERP amplitude characteristics and reaction time behavioral characteristics. The assessment of attentional cognitive function used an EEG experiment using the attention network test to extract behavioral characteristics related to the efficiency of the attentional alertness network, orientation network, and control network, as well as EEG ERP amplitude characteristics.

[0074] In this example embodiment, the scale assessment includes:

[0075] The scales used in this patent include the Self-Rating Anxiety Scale (SAS), the Self-Rating Depression Scale (SDS), the Psychological Stress Self-Evaluation Test (PSET), and the Symptom Checklist-90 (SCL-90).

[0076] The cutoff score for the SAS standard score is 50. A score of 50-59 indicates mild anxiety, 60-69 indicates moderate anxiety, and ≥70 indicates severe anxiety. A SAS standard score of ≥50 is considered positive.

[0077] The cutoff score for the SDS standard score is 53. A score of 53-62 indicates mild depression, 63-72 indicates moderate depression, and >72 indicates severe depression. An SDS standard score ≥53 is considered positive.

[0078] The PSET scoring system uses the sum of scores for each item as the raw score, which is then converted to a standardized score, T-score. T = 50 + 10(XM) / SD, where X is the raw score, M is the mean, and SD is the standard deviation. A T score < 70 indicates a normal level of psychological stress, while a T score ≥ 70 indicates a high level of psychological stress.

[0079] The SCL-90 consists of 90 items, encompassing nine factors: somatization, obsessive-compulsive disorder, interpersonal sensitivity, depression, anxiety, hostility, phobias, paranoia, and psychoticism. A 5-point scale is used: 1 point for no symptoms, 2 points for mild symptoms, 3 points for moderate symptoms, 4 points for moderate symptoms, and 5 points for severe symptoms. Higher scores indicate more severe symptoms and poorer mental health.

[0080] The parameters obtained from the self-report scale include SAS score, SDS score, PSET score, and scores for somatization, obsessive-compulsive disorder, interpersonal sensitivity, depression, anxiety, hostility, phobia, paranoia, and psychoticism factors in the SCL-90, totaling 12 subjective characteristics.

[0081] In this example embodiment, the emotion stroop EEG experiment and feature extraction include:

[0082] Emotion stroop EEG experimental design:

[0083] The emotional Stroop task used images of superimposed faces and text as experimental materials. The experiment employed a design with two emotion types (pleasure and fear) and two conflict types (consistency and inconsistency). The face images used were from the Chinese Facial Expression Image System (CFAPS), from which five male faces (pleasure and fear) and five female faces (pleasure and fear) were selected, totaling 20 images. The face images were processed, with the words "pleasure" and "fear" labeled onto the face images, resulting in 40 expression images. The experimental task included both consistency and inconsistency conditions. A consistency condition involved stimuli where the valence of the face and the labeled text were consistent, while an inconsistency condition involved stimuli where the valence of the face and the labeled text were inconsistent. The task required judging the emotional valence of the faces. Under inconsistency conditions, the meaning of the words interfered with the judgment of the face's valence; under consistency conditions, the meaning of the words facilitated the judgment of the face's valence. The emotional face images used in the practice were different from those used in the formal experiment, but the processing principles were the same.

[0084] In the experiment, participants were asked to sit approximately 80 centimeters in front of a computer. First, they were shown instructions explaining the experimental conditions. Then, pressing the spacebar displayed a "+" sign on the screen for 500ms, prompting them to concentrate. Next, a stimulus image was displayed along with a timer. When they saw the stimulus image, they were required to quickly and accurately judge the facial emotion: pressing "F" for pleasure and "J" for fear. After pressing the key, the image disappeared. Participants had 1000ms to respond to the facial emotion; after 1000ms, the stimulus image automatically disappeared and was considered an incorrect judgment. After a blank interval of 800-1200ms, the next test would begin. During this time, participants were required to focus on suppressing the distracting signals associated with the words "pleasure" and "fear." There were 15 practice sessions before the formal test, and 120 trials in total. The formal experiment consisted of 120 trials divided into 4 blocks, with the number of trials for both congruent and incongruent cases being equal. After each test, researchers provide a period of rest to reduce fatigue in the participants and thus ensure the reliability of the experiment.

[0085] Behavioral feature extraction:

[0086] The extracted behavioral characteristics included reaction time and accuracy. The experiment was divided into four conditions: "pleasant face matches the labeled text", "pleasant face does not match the labeled text", "fearful face matches the labeled text", and "fearful face does not match the labeled text". The reaction time and accuracy of the participants were recorded when the stimuli were presented under these four conditions, for a total of eight emotion-related behavioral characteristics.

[0087] EEG Feature Extraction:

[0088] The preprocessing of EEG signals was performed using the EEGLAB plugin in MATLAB 2017a (MathWorks, Natick, MA, USA) (http: / / sccn.ucsd.edu / eeglab / ) and a self-written script.

[0089] The acquired raw EEG signals underwent a series of offline preprocessing steps. First, all lead data were rereferenced, and the reference electrodes were reset to whole-brain averaging. Next, the EEG data were bandpass filtered from 0.1Hz to 30Hz using a Basic FIR filter. ICA was used to identify and remove eye movement artifacts from the EEG signals. Finally, the experimental data processing personnel visually reviewed all EEG data, manually removing fluctuations with EEG amplitudes exceeding 100μV as artifacts in their respective experimental trials.

[0090] For each stimulus, EEG data was recorded from 200 ms before stimulus onset to 1000 ms after stimulus presentation. Each ERP segment was extracted, with the first 200 ms used for baseline correction. The ERP segments under four conditioned stimuli were superimposed and averaged to obtain ERP waveforms under four conditions. The amplitudes of four ERP components were extracted: N1 (80-120 ms), P2 (140-220 ms), N2 (220-290 ms), and P3 (300-390 ms), for a total of 16 emotion-related EEG features.

[0091] In this example embodiment, the attention network (ANT) EEG experiment includes:

[0092] Experimental Design:

[0093] like Figure 3As shown, the ANT consists of one practice module (24 trials) and four experimental modules (4 × 96 trials). Participants must complete the practice module before the formal ANT test; the entire test module consists of 408 trials. Data from the practice module is excluded from statistical analysis. Participants are required to respond to the direction indicated by the central target arrow; for example, if the arrow points left, the left index finger presses the "F" key, and if the arrow points right, the right index finger presses the "J" key. The experimental task is presented via E-prime, and test cues are displayed randomly. Each test module lasts approximately 7 minutes. At the start of each trial, a cross-shaped fixation point is displayed in the center of the screen, randomly for 400 to 1600 milliseconds, followed by a 100-millisecond "*" cue. There are four types of cue cues: no cue, double cue, central cue, and spatial cue. This is followed by an 800-millisecond fixation point, and within 1700 milliseconds after the cue disappears, the target stimulus is displayed above or below the fixation point. The test included two scenarios: "target interference consistent" (all five arrows point in the same direction) and "target interference inconsistent" (the middle arrow points in the opposite direction to the other four). Participants had to press the buttons as quickly and accurately as possible. When a button was pressed, the arrow disappeared; if the participant did not respond to the stimulus within 1700 milliseconds, the arrow automatically disappeared. The next step was to display the fixation point, the presentation time of which varied depending on the initial fixation point's presentation duration and the participant's reaction speed. Each trial lasted 4000 ms. Only under the spatial cue condition was the cue and target perfectly matched; under the other three cue conditions, the correspondence between the cue and target was uncertain. This is because the association between the four cue conditions and the target stimulus is not entirely the same.

[0094] Behavioral characteristics:

[0095] First, the reaction time (RT) for each cue condition was obtained, excluding data from erroneous keystrokes, reaction times exceeding 1600 milliseconds, and reaction times below 100 milliseconds. The efficiency of the attentional vigilance network, attentional orientation network, and attentional executive control network were calculated using the following methods, resulting in a total of three attention-related behavioral features.

[0096] Pay attention to network efficiency = RT 无线索条件 —RT 双线索条件Under the uncued condition, subjects experienced the greatest uncertainty regarding the timing of the target's occurrence. According to the testing criteria, any cue can serve as an alert signal, as attention is relatively scattered under both cue conditions. The alertness network score is calculated by subtracting the average reaction time under the uncued condition from the average reaction time under the cue-based condition. However, under the cue-based condition, subjects received more alertness cues than under the uncued condition, focusing their attention on the location of the target stimulus, thus improving reaction efficiency. A higher alertness network efficiency score indicates a more efficient alertness network, meaning the subject can maintain a higher level of alertness based on cues, resulting in more efficient attention processing.

[0097] Note that directional network efficiency = RT 中心线索条件 —RT 空间线索条件 Under central cue conditions, participants can maintain alertness and improve response performance by relying on the spatial location information presented by the stimulus, but central cues do not provide effective information about the target. In contrast, spatial cues can also be used to generate alertness, providing 100% locational information about the target's location. Therefore, orientation scores are obtained by subtracting the average RT under the central cue condition from the average RT under the spatial cue condition. The greater the difference in reaction time between the two cues, the more the subject benefits from reliable spatial cues, and the higher the orientation efficacy.

[0098] Note that the execution control network efficiency = RT 不一致条件 —RT 一致条件 Inconsistent instruction conditions require a higher conflict resolution capability than consistent instruction conditions, so the former has a longer reaction time than the latter. The smaller the difference between the two conditions, the higher the conflict resolution capability and the higher the efficiency of the execution control network.

[0099] In summary, a total of three attention-related behavioral features were extracted.

[0100] EEG characteristics:

[0101] The preprocessing of EEG signals was performed using the EEGLAB plugin in MATLAB 2017a (MathWorks, Natick, MA, USA) (http: / / sccn.ucsd.edu / eeglab / ) and a self-written script.

[0102] The acquired raw EEG signals underwent a series of offline preprocessing steps. First, all lead data were rereferenced, and the reference electrodes were reset to whole-brain averaging. Next, the EEG data were bandpass filtered from 0.1Hz to 30Hz using a Basic FIR filter. ICA (Independent Component Analysis) was used to identify and remove eye movement artifacts from the EEG signals. Finally, the experimental data processing personnel visually reviewed all EEG data, manually removing fluctuations with EEG amplitudes exceeding 100μV as artifacts in their respective experimental trials.

[0103] For "cue" stimuli, the baseline was selected 400ms before the stimulus, and the segment from 400ms before the stimulus to 1000ms after the stimulus presentation was extracted. For "target" stimuli, the baseline was selected 1300ms to 900ms before the stimulus (consistent with the baseline selection of cue stimuli), and the segment from 1300ms before the stimulus to 1700ms after the stimulus presentation was extracted. Subsequently, the four cue stimuli and two target stimuli for each subject were superimposed and averaged to obtain the waveforms of the group level under different conditions. The ERP components were extracted for the following time periods: N1 component after "cue" stimulus (150-230ms), CNV after "cue" stimulus (O wave, 600-800ms; E wave, when the "target" stimulus appears, i.e., 800-1000ms after "cue" stimulus), N200 component after "cue" stimulus (250-400ms); N1 component after "target" stimulus (150-230ms), N200 component after "target" stimulus (300-450ms), and P300 component after "target" stimulus (250-450ms). A total of 22 ERP components were extracted.

[0104] In this example embodiment, feature dimensionality reduction includes:

[0105] The above methods yielded a series of features related to emotion and attention, including subjective evaluation features and objective features acquired from electrophysiological signals, as shown in the table below. Before classification, factor analysis was used to reduce the dimensionality of these features to avoid overfitting in each training iteration, maintaining factors with eigenvalues ​​above 1, thus achieving feature dimensionality reduction. Dimensionality reduction was performed on all features related to emotion and attention, and separately on emotion features and attention features. The dimensionality-reduced features were then used in subsequent classification work.

[0106]

[0107] In this example embodiment, training sample collection includes:

[0108] Thirty healthy participants without mental illness were recruited to participate in emotion and attention experiments.

[0109] In the emotion-inducing experiment, 15 carefully selected Chinese film clips from an emotion video database established by the BCMI Laboratory at Shanghai Jiao Tong University were used to induce specific emotions (positive, neutral, and negative) in the participants. Thirty participants underwent 15 trials. Before each trial, there was a 5-second prompt, followed by watching a film clip lasting approximately 4 minutes. After watching the clip, participants immediately reported their emotional response, underwent self-evaluation of their emotions, completed an emotion scale test, and underwent a Stroop EEG. A 15-second rest period was then followed before watching the next film clip. The order of emotion presentation in the experiment was 1, 0, -1, -1, 0, 1, -1, 0, 1, 0, -1, 0, -1, 0, -1, where 1 represents positive emotion, 0 represents neutral emotion, and -1 represents negative emotion.

[0110] In the attention experiment, participants underwent the aforementioned ANT EEG data collection experiment at the beginning. After a one-hour simulated driving task, participants' self-reported fatigue results were collected, and their ANT EEG data were collected again.

[0111] In this example embodiment, constructing the classification model includes:

[0112] This disclosure uses a Support Vector Machine (SVM) classifier to learn cognitive features and classify different cognitive states in a closed environment. SVM is a classic machine learning algorithm widely used in classification and regression problems. It achieves classification or regression by finding a hyperplane that maximizes the distance between samples. SVM algorithms perform well in many practical applications, such as image recognition, text classification, and bioinformatics. However, with the increasing volume of data and the growing complexity of problems, traditional SVM algorithms face problems such as high computational complexity and poor model generalization ability. To overcome the problems of traditional SVM algorithms, this patent uses a multi-kernel learning method. Multi-kernel learning (MKL) learns a combination of multiple kernel functions, which can better capture the latent structure of the data, thereby improving the learning performance of SVM. By introducing multiple kernel functions, the multi-kernel learning method can better capture the nonlinear relationships in the data, improving the performance of the classifier. Different kernel functions are suitable for different types of data; for example, linear kernels are suitable for linearly separable data, multinomial kernels are suitable for multinomially separable data, and Gaussian kernels are suitable for nonlinearly separable data. By linearly combining multiple kernel functions, a more powerful kernel function can be obtained, improving the classification performance of SVM. The combination of synthetic kernels is shown in the following formula, where η represents the weight coefficient of the kernel function and p represents the number of kernel functions.

[0113]

[0114] Optimization of multi-core learning support vector machines:

[0115]

[0116]

[0117] ξ i ≥0, i=1,2,...,n

[0118] Where C is a regularization parameter used to balance model complexity and error term, ξ i is a slack variable used to handle noise and outliers in the data, and w represents the direction of the classification hyperplane in the high-dimensional feature space. Let be the mapping function. The classification decision function is:

[0119]

[0120] Multi-kernel learning support vector machine was used to learn the dimensionality-reduced emotion-related features and attention-related features respectively, and a classification model of emotion state and attention level was established to realize the evaluation of emotion state and attention level. Specifically, the construction of multi-kernel learning support vector machine was carried out by predefining 10 polynomial kernel functions (poly) and 10 radial basis function kernel functions (rbf) with different parameters to construct kernel vectors, and the weight vectors corresponding to the kernel vectors were learned on the training set by EasyMKL[1]. These two types of kernel functions are commonly used and relatively effective kernel functions when using SVM for EEG classification tasks. Since the parameters of the kernel function actually have a continuous and infinite number of values ​​to choose from, only some commonly used empirical discrete values ​​were selected for research within the commonly used parameter range. The parameter of the polynomial kernel function is the degree of the highest-order term. In this chapter, it is set to 10 values ​​(degree = 1, 2, 3, 4, 5, 6, 7, 8, 9, 10). The parameter gamma of the radial basis function kernel is set to 10 values ​​(gamma = 0.00001, 0.0001, 0.001, 0.01, 0.1, 1, 10, 100, 1000, 10000). Using the kernel function vector and its weight vector obtained through the EasyMKL algorithm, a combined kernel vector can be calculated. This combined kernel vector is then used to complete the classification experiment using an SVM classifier and a test set.

[0121] In this example embodiment, the present disclosure provides a method for assessing the cognitive state of a person's brain in a closed environment. It uses a combination of subjective and objective characteristics to assess the level of cognitive state of the brain, providing a methodological basis for detecting the cognitive state of the brain under long-term closed working conditions.

[0122] It should be noted that although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0123] Furthermore, in this example embodiment, a cognitive state assessment device in a closed environment is also provided. (Refer to...) Figure 4 As shown, the cognitive state assessment device 400 in a closed environment may include: a feature acquisition module 410, a dimensionality reduction processing module 420, and a cognitive state assessment module 430. Wherein:

[0124] The feature acquisition module 410 is used to acquire emotional cognitive features and attentional cognitive features based on a preset emotion cognitive model and a preset attention cognitive model, respectively.

[0125] Dimensionality reduction processing module 420 is used to perform dimensionality reduction processing on the emotion cognition features and attention cognition features;

[0126] The cognitive state assessment module 430 is used to assess the cognitive state by taking the dimensionality-reduced emotional cognitive features and attention cognitive features as input, learning a cognitive feature model based on a support vector machine (SVM) classifier, and generating an assessment result.

[0127] The specific details of the cognitive state assessment device modules in each of the above-mentioned closed environments have been described in detail in the corresponding cognitive state assessment method in a closed environment, so they will not be repeated here.

[0128] It should be noted that although several modules or units of a cognitive state assessment device 400 in a closed environment have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0129] Furthermore, in an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0130] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented as entirely hardware embodiments, entirely software embodiments (including firmware, microcode, etc.), or embodiments combining hardware and software aspects, collectively referred to herein as “circuit,” “module,” or “system.”

[0131] The following reference Figure 5 To describe an electronic device 500 according to such an embodiment of the present invention. Figure 5 The electronic device 500 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0132] like Figure 5 As shown, the electronic device 500 is manifested in the form of a general-purpose computing device. The components of the electronic device 500 may include, but are not limited to: at least one processing unit 510, at least one storage unit 520, a bus 530 connecting different system components (including storage unit 520 and processing unit 510), and a display unit 540.

[0133] The storage unit stores program code that can be executed by the processing unit 510, causing the processing unit 510 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of the present invention. For example, the processing unit 510 can perform actions such as... Figure 1 Steps S110 to S130 are shown in the diagram.

[0134] Storage unit 520 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 5201 and / or cache memory 5202, and may further include a read-only memory (ROM) 5203.

[0135] Storage unit 520 may also include a program / utility 5204 having a set (at least one) program module 5205, such program module 5205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0136] Bus 530 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0137] Electronic device 500 can also communicate with one or more external devices 570 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 500, and / or with any device that enables electronic device 500 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 550. Furthermore, electronic device 500 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 560. As shown, network adapter 560 communicates with other modules of electronic device 500 via bus 530. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0138] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0139] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of the invention may also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the invention described in the "Exemplary Methods" section above.

[0140] refer to Figure 6 As shown, a program product 600 for implementing the above-described method according to an embodiment of the present invention is described. It may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0141] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0142] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0143] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0144] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0145] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0146] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0147] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for assessing cognitive state in a closed environment, characterized in that, The method includes: Emotional cognitive features and attentional cognitive features are collected based on a preset emotion cognitive model and a preset attention cognitive model, respectively; the collection of emotional cognitive features based on the preset emotion cognitive model also includes: The scales were assessed using the Self-Rating Anxiety Scale (SAS), Self-Rating Depression Scale (SDS), Self-Rating Stress Questionnaire (PSET), and Symptom Checklist-90 (SCL-90) to obtain SAS scores, SDS scores, PSET scores, and scores for somatization, obsessive-compulsive disorder, interpersonal sensitivity, depression, anxiety, hostility, phobia, paranoia, and psychotic factors in the SCL-90. Based on the emotional stroop EEG experiment, behavioral features and EEG features ERP were extracted to obtain a preset number of emotional behavioral features and the amplitude of ERP components. Collecting attentional cognitive features based on a pre-defined attentional cognitive model also includes: The Attention Network (ANT) EEG experiment was designed to collect behavioral characteristics and corresponding EEG characteristics of attention orientation network efficiency, attentional alertness network efficiency, and attentional executive control network efficiency after the subjects completed a simulated driving task of a preset duration. The emotion cognition features and attention cognition features are dimensionality reduced by factor analysis to obtain the dimensionality-reduced emotion cognition features and attention cognition features. Multi-kernel learning support vector machines are used to learn the dimensionality-reduced emotion cognitive features and attention cognitive features respectively, and classification models of emotion state and attention level are established to achieve the evaluation of emotion state and attention level; Based on the kernel function vector and its weight vector obtained by the EasyMKL algorithm, a combined kernel vector is calculated, and the combined kernel vector is input into the support vector machine (SVM) classifier. The classification experiment is completed in combination with the test set to obtain the emotion state assessment result and the attention level assessment result. Based on the emotional state assessment results and attention level assessment results, the cognitive state of the subjects in the closed environment is assessed, and assessment results are generated.

2. The method as described in claim 1, characterized in that, The method further includes: A predetermined number of participants were recruited to participate in emotion and attention experiments. In the emotion-inducing experiment, movie clips from a pre-set emotion video database were used to induce specific positive, neutral, and negative emotions in the subjects to complete the collection of training samples. In the attention experiment, based on the attention network ANT EEG experiment, after a one-hour simulated driving task, the fatigue self-report results and ANT EEG data of the subjects were collected to complete the training sample collection.

3. A cognitive state assessment device in a closed environment, based on the method as described in claim 1 or 2, characterized in that, The device includes: The feature acquisition module is used to collect emotional cognitive features and attentional cognitive features based on the preset emotion cognitive model and the preset attention cognitive model, respectively. The dimensionality reduction module is used to reduce the dimensionality of the emotion cognition features and attention cognition features. The cognitive state assessment module is used to assess the cognitive state by taking the dimensionality-reduced emotional cognitive features and attention cognitive features as input, learning a cognitive feature model based on a support vector machine (SVM) classifier, and generating assessment results.

4. An electronic device, characterized in that, include Processor; and A memory storing computer-readable instructions that, when executed by the processor, implement the method according to claim 1 or 2.

5. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method according to claim 1 or 2.

Images