CN111513732A - Intelligent psychological stress assessment early warning system for various groups of people under epidemic disease condition - Google Patents
Intelligent psychological stress assessment early warning system for various groups of people under epidemic disease condition Download PDFInfo
- Publication number
- CN111513732A CN111513732A CN202010354393.1A CN202010354393A CN111513732A CN 111513732 A CN111513732 A CN 111513732A CN 202010354393 A CN202010354393 A CN 202010354393A CN 111513732 A CN111513732 A CN 111513732A
- Authority
- CN
- China
- Prior art keywords
- psychological
- early warning
- warning system
- physiological
- intelligent
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Abstract
The utility model provides a mental stress intelligence aassessment early warning system to multiclass crowd under epidemic disease condition belongs to artificial intelligence mode identification field, and the data acquisition module is configured as: acquiring at least one physiological signal of a tested individual and preprocessing the physiological signal; a psychological assessment module configured to: inputting the preprocessed physiological signals into a preset neural network model to obtain the probability of the tested individual in different psychological states, and further determining the current psychological state grade of the tested individual; an alert module configured to: when the psychological state level of the tested individual exceeds the safety level, sending out alarm information; according to the psychological grade classification method and the psychological grade classification system, only relevant physiological signals of the tested individual need to be collected, any inquiry is not needed, the psychological grade classification result can be efficiently and accurately obtained, then the individual with abnormal psychology can be intervened and treated in advance, and the physiological health and the psychological health of the tested person are guaranteed.
Description
Technical Field
The disclosure relates to the field of artificial intelligence mode recognition, in particular to a mental stress intelligent assessment early warning system for various groups of people under epidemic disease conditions.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The sudden epidemic caused by uncontrollable factors can cause serious harm to social and economic life, and simultaneously, regional and group panic is brought, and the social stability is influenced. Different individuals in the society suddenly face serious disasters, so that the living conditions are obviously changed, particularly, difficulties which are difficult to overcome by the existing living conditions and experiences occur, the people concerned suffer from pain and uneasy states, and despair, numbness and anxiety are accompanied by vegetative symptoms and behavioral disorders in serious cases, so that the psychological crisis is called. Under epidemic conditions, medical staff, police officers, government officers and the like need to overcome fear of diseases and anxiety of unknown prospects, bear working pressure which is obviously higher than normal state, continuously fight in front of fighting against epidemic situations, and become high-incidence crowds with psychological crisis. Only if the psychological stress condition of a specific individual is accurately and objectively evaluated, the person in the psychological crisis state can be timely and properly psychologically assisted, so that the person can get rid of mental distress as soon as possible, the healthy life style is restored, the mental stress is relieved, and the working efficiency is improved. In the stage of epidemic disease resistance, timely and effective psychological crisis intervention has important practical significance for gathering people's mind, inspiring morals and maintaining social stability and consolidating the foundation of the masses and establishing a combined efficient combat team, and scientific and accurate psychological pressure assessment is a precondition and a basic approach for obtaining good psychological intervention effect on a micro level and a macro level and is gradually valued by researches in different subject fields of psychology, sociology, neuroscience and the like.
The inventor of the present disclosure finds that (1) the traditional psychological stress assessment is mainly based on subjective statements of target objects, and the obtained answers are subjected to quantization processing and input into various mathematical formulas established in a model-driven manner, and the final scores are used as a diagnosis basis. Different psychological diagnosis scales lack unified standards, and meanwhile, the acquisition process is complicated and is easily influenced by various interference factors such as personal masking, fuzzy subject understanding, unclear self evaluation and the like, so that the accuracy and objectivity of evaluation are reduced. (2) A traditional model-driven mode depends on a small amount of data to carry out certain specific inference and hypothesis, multiple mathematical models such as normal distribution, Rayleigh distribution, Poisson distribution and the like are established, a more suitable model is selected as a data analysis framework in a data fitting model mode, the mode is based on a data adaptation model, the actual problem is difficult to really start, some mathematical models with good self-feeling are often conceived out of the real distribution rule of the data, and when the complex massive data are faced, the existing model cannot process or cannot obtain ideal effects.
Disclosure of Invention
In order to solve the defects of the prior art, the intelligent psychological stress assessment and early warning system for various groups of people under epidemic disease conditions is provided, only relevant physiological signals of tested individuals are needed to be collected, any inquiry is not needed, psychological grade classification results can be obtained efficiently and accurately, then, the individuals with abnormal psychology can be intervened and treated in advance, and the physiological and psychological health of the tested people is guaranteed.
In order to achieve the purpose, the following technical scheme is adopted in the disclosure:
the first aspect of the disclosure provides a mental stress intelligent assessment and early warning system for various groups of people under epidemic disease conditions.
The utility model provides a multiclass crowd's mental stress intelligence aassessment early warning system under towards epidemic disease situation, includes:
a data acquisition module configured to: acquiring at least one physiological signal of a tested individual and preprocessing the physiological signal;
a psychological assessment module configured to: inputting the preprocessed physiological signals into a preset neural network model to obtain the probability of the tested individual in different psychological states, and further determining the current psychological state grade of the tested individual;
an alert module configured to: when the psychological state level of the tested individual exceeds the safety level, sending out alarm information;
the preset neural network model is a single hidden layer neural network comprising a plurality of hidden layer nodes, and when the input weight and the bias of the hidden layer are determined, the output of the hidden layer is uniquely determined.
The second aspect of the disclosure provides an electronic device, which includes the first aspect of the disclosure, and the mental stress intelligent assessment and early warning system for multiple types of people under epidemic disease conditions.
Compared with the prior art, the beneficial effect of this disclosure is:
1. according to the intelligent psychological stress assessment early warning system for the various groups of people under epidemic disease conditions, only relevant physiological signals of tested individuals need to be collected, any inquiry is not needed, psychological grade classification results can be efficiently and accurately obtained, then early intervention treatment can be performed on individuals with abnormal psychology, and the physiological and psychological health of the tested individuals is guaranteed.
2. The mental stress intelligent assessment early warning system for the various crowds under the epidemic disease condition, provided by the disclosure, is provided with a neural network model, specifically is a single hidden layer neural network comprising a plurality of hidden layer nodes, when the input weight and the bias of the hidden layer are determined, the output of the hidden layer is uniquely determined, and the hidden layer can be regarded as the solution of only one linear system, so that the calculation resources consumed in the model training process are effectively saved, the learning precision is further improved, the time complexity of iterative calculation in the learning process is reduced, and the rapidity and the accuracy of assessment are improved.
3. The utility model provides a towards polymorphic crowd's psychological pressure intelligence aassessment early warning system under epidemic disease situation, it is practical to pay close to theoretical innovation simultaneously, no matter to fight in the epidemic situation prevention and control personnel of one line, the back accomplish the work production personnel of logistics support or be in the patient that seals the isolated state, polymorphic crowd such as ordinary uninfected crowd all can realize rapid accurate psychological state early warning, for instant efficient individuation mental health protection work provides reliable support, resist the calamity of helping hand in unusual period and stabilize the civilian mind.
Drawings
Fig. 1 is a general block diagram of an intelligent psychological assessment system based on physiological information according to an embodiment of the present disclosure.
Fig. 2 is a flowchart of a training data collection of an intelligent psychological assessment system based on physiological information according to an embodiment of the present disclosure.
Fig. 3 is a flowchart of feature engineering of an intelligent psychological assessment system based on physiological information according to an embodiment of the present disclosure.
Fig. 4 is a scene diagram of an application of the intelligent psychological assessment system based on physiological information according to an embodiment of the present disclosure.
Fig. 5 is a block diagram of an algorithm of an intelligent psychological assessment system based on physiological information according to an embodiment of the present disclosure.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Example one
The embodiment of the present disclosure provides a mental stress intelligent assessment early warning system for multiple types of people under epidemic disease conditions, including:
a data acquisition module configured to: acquiring at least one physiological signal of a tested individual and preprocessing the physiological signal;
a psychological assessment module configured to: inputting the preprocessed physiological signals into a preset neural network model to obtain the probability of the tested individual in different psychological states, and further determining the current psychological state grade of the tested individual;
an alert module configured to: and when the psychological state level of the tested individual exceeds the safety level, sending out alarm information.
The early warning system described in this embodiment specifically includes three main structural levels, namely, a data set creation layer, an intelligent model building and training layer, and an application layer, as shown in fig. 1, specifically:
(1) a dataset creation layer. The intelligent psychological early warning system under the epidemic disaster condition firstly needs to establish an original data set which is targeted based on human physiological data and marked as a mapping target by different normative psychological states.
As shown in FIG. 2, more than 200 collected volunteers with different sexes and character traits evenly distributed are recruited to ensure the diversity of samples. The method comprises the steps that a virtual reality technology (VR) is utilized to combine video clip creation time with different types of programs which are about ten minutes and reflect natural disasters, epidemic diseases, war states and the like and are close to a real background, a subject randomly selects one of the programs on a VR platform to watch, emotional experience of tension and compression is obtained, a physiological signal acquisition device is synchronously started to obtain physiological information of five different modes of human electrocardio, electrodeionization, respiration, blood oxygen and facial blood oxygen content, refreshing frequency is kept to be 200Hz, and the method has good identification capability in a time dimension.
After the watching is finished, the same testee fills in a psychological state evaluation scale (PSTR), a Chinese soldier psychological health scale (CMMHS) and an on-duty personnel psychological stress measurement scale (WYB) from three different angles, and inquires by combining professional psychologists, and the obtained conclusions are summarized and fused to form three grade representations aiming at the psychological stress bearing degree of the testee, wherein:
high risk means that the mental tolerance is fragile and is in a serious bad emotional state; low risk indicates a general sensitive psychology, in a suppressive emotional state; no risk indicates a healthy mental state, in an emotional phase that can completely innervate self-regulation.
The psychological health degree of the testee is represented as a high, medium and low diagnosis conclusion by a visual and simple psychological state expression means and a psychological evaluation mode of multi-source fusion, and the method is very suitable for scientifically guiding targeted psychological intervention in a clear mode under the condition of lack of medical resources in an epidemic disease period.
And finally, correlating the psychological quantitative label of the same target individual with the physiological data, and storing the psychological quantitative label as an independent sample item in an initial sample space.
As shown in fig. 3, the basic approach of information fusion is followed, physiological signals of different modalities such as electrocardio and pico are uniformly dimensioned in a normalization mode, discrete quantization values of all different units are limited to 0-1, and the phenomenon that too large or too small influence degree is formed in the classification and identification process due to different units is avoided, and the formula is expressed as follows:
according to related research results in the field of computational psychology in recent years, a plurality of human body electric signal characteristics with high correlation degree with psychological state representation are screened out, and an initial characteristic space is formed on the basis of a mean value, a standard deviation, a first derivative, high-frequency power, low-frequency power, multi-scale entropy and the like.
And performing optimized compression on the initial feature space by adopting a sequential backward feature selection algorithm to remove redundancy, deleting the feature with the lowest evaluation value K in the feature set in each step, and enabling the retained feature set K to have the largest value after deleting the feature.
Let n features have been deleted and the remaining set of features be
Will be provided with
Of (2) each feature xjThe K value is arranged according to the following formula:
then:
if the new characteristic subset is superior to the original characteristic subset in recognition performance, continuing to advance or else terminating, and completing the optimization process
As shown in fig. 3, in the present embodiment, a weighted immune clone sample selection algorithm (WICISA) is used to optimize a sample space, and an Adaboost algorithm is first used to calculate an initial weight of each sample, so that the sample is accompanied by a larger classification information amount; further calculating the weighted affinity of the antibody and the antigen in each generation, the affinity among the antibodies and the cloning number, and updating the individual to guide population evolution by cloning operation, immunogene operation and clonal selection operation; the iteration repeats until the termination condition is satisfied.
And (3) performing optimization operation on the characteristic space and the sample space through characteristic engineering to form a high-quality data set capable of providing reliable data support for training an intelligent recognition system.
(2) And an intelligent model training layer. The embodiment adopts an extreme learning machine model based on a neural network as a main algorithm framework of intelligent classification.
As shown in FIG. 5, for a single-hidden-layer network, let N samples in the training set be represented as (X)i,ti) Wherein X isiIs represented by [ x ]i1,xi2......xin]T∈Rn,ti＝[ti1,ti2......tim]T∈Rm. Designing a single hidden layer neural network with L hidden layer nodes, and expressing as follows:
wherein g (x) is an activation function, WiTo input the weights, βiAs output weights, biIs the bias of the ith hidden layer cell. The goal of network training is to minimize the output error, expressed as:
i.e. looking for presence βi、Wi、biAnd realizing that:
the minimization loss function is expressed as:
traditional gradient-based learning algorithms require all parameters to be adjusted in an iterative process, and the algorithm framework once inputs the weight WiSimultaneous random determination of the bias b of the hidden layeriThe output of the hidden layer is uniquely determined, and can be regarded as the solution of only one linear system, so that the computational resources consumed in the model training process are effectively saved. In a real application scene, the physiological data characteristic set of the testee is input into the trained network, an output result processed by adopting an independent thermal expression mode can be obtained in an output layer, the probabilities in different mental health states are displayed, the grade with the maximum probability is a diagnosis conclusion on the mental health degree of the testee, and further mental intervention measures are guided.
(3) And (5) an application layer. As shown in fig. 1, the present embodiment gets rid of the traditional mental health diagnosis and assessment method relying on subject complaints in combination with participation of psychologists, relies on scientific conclusions that the autonomic nervous system of the human body is closely related to the mental state in the neurophysiology, and assesses the mental health grade based on the collection of multi-modal physiological data capable of reflecting the activity rule of the nervous system of the human body. The method is a beneficial attempt for realizing objective evaluation of the psychological state by mutually fusing the disciplines of neuroscience, psychology, artificial intelligence and the like, and solves the problem that the subjective factors are influenced by long-term puzzled in clinical psychological diagnosis for a long time.
As shown in fig. 4, the present embodiment mainly covers two different main application scenarios, which can provide home self-mental health monitoring for independent individuals in an anxious and anxious state during an epidemic disease period, overcome the predicament of medical resource shortage, and prevent the patient from moving excessively to prevent the spread of the epidemic situation; the system can also provide integral remote psychological health real-time monitoring and early warning for the teams in an overload running state, such as a first-line epidemic prevention team and logistics guarantee team, discover high-risk targets and intervene in time, and guarantee the continuous fighting capacity of the teams. By implementing a scientific research concept of four-in-one of theory, practice and application-oriented and social service, a brand-new application field of assessing psychological health support and guaranteeing national epidemic disease resistance by means of physiological indexes is developed.
Compared with the prior art, the embodiment also has the following beneficial effects:
(A) epidemic disease disasters have the characteristics of outbreak, persistence, unknown property and the like, the epidemic period of the epidemic disease is also the high-incidence period of various psychological diseases, various groups bear psychological pressure higher than the normal state in different degrees, and scientific and accurate psychological health assessment is the premise for realizing accurate psychological intervention.
In the embodiment, a scientific and reasonable mapping relation is established between multi-modal human physiological data and psychological stress grade assessment by taking social epidemic disease conditions as an application background and adopting means such as data mining and machine learning. The method changes the mode of taking subjective self-evaluation of a testee as the leading factor in the traditional psychological evaluation process and depends on the basic view of the neurophysiology, develops a new way for evaluating the psychological health degree by exploring the activity rule of the human autonomic nervous system based on physiological data, and effectively overcomes the evaluation error caused by factors such as self-perception blur or camouflage and the like.
Meanwhile, various intelligent means are fused in the evaluation process, and a big data optimization model is utilized, so that the accuracy, robustness, objectivity and the like of classification decision of the system are remarkably improved.
The autonomic nervous system of the human body is dominated by the brain, but has more independence, particularly has autonomic activity which is not dominated by will, and various scientific researches prove that the activity rule of the autonomic nervous system can embody the psychological state characteristics of the human body to a considerable extent. The embodiment collects and integrates multi-mode physiological data of electrocardio, electrodermal, respiratory frequency, blood oxygen and the like which can reflect autonomic nervous activities in real time, fully discovers the activity characteristics of autonomic nervous systems of different individuals, and takes the activity characteristics as an effective means of psychological stress assessment, can overcome the defect that subjective factors of a tested person are dominant in the psychological assessment process, promotes the psychological health assessment to a brand new way of combining human physiological data and data driving by adopting a three-step traditional scheme of questionnaire investigation, subjective review and model driving, and can achieve more ideal height in the aspects of scientificity, accuracy, stability and the like
(B) The operation mode is convenient and fast, and the diagnosis conclusion is intuitive. Traditional mental health assessment needs complex processes such as questionnaire collection, professional physician evaluation, on-site inquiry and the like, is time-consuming and labor-consuming, faces the dilemma of medical resource shortage in an epidemic disease period, develops wide mental health general survey, lacks a considerable number of mental assessment personnel with professional qualifications, and has practical operation difficulty which is difficult to bear in terms of time and material resources.
The embodiment aims at being simple, accurate and applicable, as shown in fig. 4A, self-help psychological diagnosis is realized through a series of software and hardware devices, a user only needs to wear a portable physiological signal acquisition sensor, multi-mode physiological information can be acquired after a rest state lasts for several minutes, data are uploaded to the mental health state intelligent evaluation device through a transmission medium formed by a twisted pair, a coaxial cable or wireless bluetooth, evaluation conclusions of three different psychological pressure state levels of high, medium and low are given by the device, the current-stage psychological health state of the user can be visually displayed in a mode without question and answer or professional psychologist participation in any scene, and a next psychological intervention scheme is guided.
In the epidemic disease resisting period, a medical rescue team, a police service team, a logistics production team and a government function team are all in a high-speed operation state, and the real-time psychological state monitoring and synchronous guidance of team members for psychological intervention is an important guarantee for maintaining the continuous and efficient operation of the team. If the psychological health assessment is performed on team members in a high-intensity working state by using a questionnaire acquisition and physician inquiry mode, firstly, a testee needs to pause the working state, the continuity of team operation is seriously affected, the diagnosis cannot be performed for the same individual for many times, and the real-time effect cannot be achieved. As shown in fig. 4B, in this embodiment, by using the high-sensitivity sensors worn on multiple parts of the body of the team member, physiological data in a continuous time domain can be acquired while maintaining the working state, and the data is transmitted to the remote terminal, the intelligent system gives psychological health evaluation parameters of all team members, screens individuals who break through a warning threshold and are in a high psychological stress state, and can recommend exiting from a first-line position for targeted psychological rehabilitation, thereby effectively avoiding work accidents caused by psychological crisis and mental damage to the individual workers; for general psychological stress individuals, an applicable psychological communication dispersion scheme can be adopted, and the current working position is not withdrawn; for individuals with low psychological stress, intervention measures can be temporarily not taken, and treatment is carried out by people. Through the system, a team manager can establish a four-step efficient cycle mechanism aiming at real-time monitoring of the overall psychological state of the team, early warning of high-risk individuals, withdrawal of the post for physical therapy and recovery and return to the post based on remote monitoring, so that the sustainable operation of the team is guaranteed, and the situation that one computer controls the whole situation is achieved.
For the problems of high network resource occupancy rate and data transmission congestion which are easily caused in an epidemic disease period, the seamless connection between the human body sensor, the remote monitoring equipment and the 5G network is realized by fully utilizing the characteristics of large capacity, high transmission speed, high reliability, low failure rate and the like of the 5G network, so that the reliability of data transmission is effectively guaranteed. The embodiment can be used for individual psychological diagnosis and team psychological health integral monitoring, and establishes a first defense line of psychological early warning for the whole society in a special period of epidemic disease resistance.
(C) Wide applicability. In the sample labeling stage in the data set creating process, a PSTR psychological pressure scale, an on-duty personnel psychological pressure measurement scale (WYB) and a Chinese military psychological health scale (CMMHS) are adopted to quantitatively layer the psychological pressure bearing grade of volunteers in combination with the evaluation of professional psychologists, and labeling is performed in a fusion strategy without depending on a specific population or a single mode based on a specific evaluation angle, so that the intelligent psychological evaluation system based on multi-mode physiological data is suitable for social multi-age and multi-industry populations, can provide self-service psychological diagnosis in a non-medical environment for household isolated populations, can provide instant psychological health monitoring service for workers in different industries, and has good broad spectrum.
(D) High reliability. The embodiment is an artificial intelligence application mode aiming at a medical background, and aims to achieve scientific and rigorous effect, and quality control of the system is completed through two steps of test in a test stage and test in an application stage. The experimental test is carried out in a ten-fold cross validation mode, a data set is divided into 10 parts, 9 parts are used as training data and 1 part is used as test data in turn for testing, the average value of the accuracy of 10 results is used as the estimation of the model precision, and the diagnosis accuracy of the intelligent model is ensured through a quantitative evaluation standard. In the application test stage, aiming at a plurality of types of subjects with a certain scale, the psychological diagnosis conclusion obtained by adopting the intelligent equipment based on the physiological data is compared with the psychological diagnosis conclusion obtained by adopting the traditional means such as questionnaire or physician inquiry, and the like, so that the overall consistency can reach the target value meeting the clinical standard.
(E) A compact and efficient data set. The quality of the data set determines the identification accuracy of an intelligent model trained on the basis of the data set, the embodiment adopts virtual reality and video editing technology to create a nervous atmosphere approaching a real environment, so that collected volunteers can obtain emotional experience under high-intensity psychological pressure, multi-mode physiological data capable of reflecting the activity rule of a human autonomic nervous system under the control of specific emotion are obtained, a multi-source fusion labeling mode is utilized to map and label a physiological data characteristic space, and an initial data set with good association relationship is established.
The embodiment effectively reduces the redundancy of the feature space through a sequential backward feature selection algorithm, improves the separability between classes, and reduces the distance in the classes to ensure higher intra-class aggregation. The weighted immune clone sample selection algorithm (WICISA) has the characteristics of high retrieval speed and strong global and local retrieval capabilities, the embodiment utilizes the WICISA to screen typical samples in a data space, reasonably deletes harmful samples and redundant samples, saves computing resources by optimizing the sample space, and provides more efficient and reliable data support for the training of a classifier.
(F) The artificial neural network has good self-organization and self-adaptive capacity, and the synaptic weight is changed through training to adapt to the requirements of target tasks. In the embodiment, based on various strategies such as optimizing neuron characteristics, improving a neural network topological structure, and making a learning rule close to a target task, an Extreme Learning Machine (ELM) model is constructed on a traditional BP neural network structure to serve as an algorithm rule of intelligent mental health diagnosis, so that on the basis of ensuring the good performance of the traditional neural network for classification problems, the learning precision is further improved, and the time complexity of iterative computation in the learning process is reduced.
Example two
The second embodiment of the present disclosure provides an electronic device, which includes the first embodiment of the present disclosure, and the system for intelligently evaluating and warning psychological stress of multiple groups of people under epidemic disease conditions.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Claims (10)
1. The utility model provides a multiclass crowd's mental stress intelligence aassessment early warning system under towards epidemic disease situation which characterized in that includes:
a data acquisition module configured to: acquiring at least one physiological signal of a tested individual and preprocessing the physiological signal;
a psychological assessment module configured to: inputting the preprocessed physiological signals into a preset neural network model to obtain the probability of the tested individual in different psychological states, and further determining the current psychological state grade of the tested individual;
an alert module configured to: when the psychological state level of the tested individual exceeds the safety level, sending out alarm information;
the preset neural network model is a single hidden layer neural network comprising a plurality of hidden layer nodes, and when the input weight and the bias of the hidden layer are determined, the output of the hidden layer is uniquely determined.
2. The intelligent psychological stress assessment and early warning system for multiple types of people in epidemic situations as claimed in claim 1, wherein the physiological signal at least comprises one of human electrocardio, electrodermal, respiratory, blood oxygen and facial blood oxygen content.
3. The intelligent psychological stress assessment and early warning system for multiple types of people under epidemic conditions as claimed in claim 1, wherein the collected physiological signals are preprocessed in a normalization manner to obtain physiological signal values with unified dimension.
4. The intelligent psychological stress assessment and early warning system for multiple types of people under epidemic disease conditions as claimed in claim 1, wherein the preset neural network model is trained by the collected human physiological signal data set and psychological state information of multiple tested individuals, and the method for acquiring the human physiological signal data set specifically comprises:
preprocessing the acquired human physiological signals, and constructing a feature space;
performing optimized compression on the initial feature space by adopting a sequential backward feature selection algorithm to remove redundancy;
and optimizing the sample space by adopting a weighted immune clone sample selection algorithm to obtain an optimized data set.
5. The intelligent psychological stress assessment and early warning system for multiple types of people under epidemic disease conditions as claimed in claim 4, wherein the initial feature space is optimized, compressed and redundancy removed by using a sequential backward feature selection algorithm, specifically: and deleting the feature with the lowest evaluation value K in the feature set in each step, wherein the deleted feature meets the requirement of maximizing the value of the reserved feature set K.
6. The intelligent psychological stress assessment and early warning system for multiple types of people under epidemic disease conditions, according to claim 4, wherein a sample space is optimized by adopting a weighted immune clone sample selection algorithm, specifically:
calculating the initial weight of each sample by using an Adaboost algorithm, so that the samples are attached with larger classified information quantity;
calculating the weighted affinity of the antibody and the antigen in each generation, the affinity among the antibodies and the cloning number, and updating the individual to guide population evolution by using cloning operation, immune gene operation and cloning selection operation;
the iteration is repeated until a preset termination condition is met.
7. The intelligent psychological stress assessment and early warning system for multiple types of people under epidemic disease conditions, according to claim 4, is characterized in that the acquisition mode of the physiological signals of the tested individual is as follows:
combining a virtual reality technology with video editing to obtain different types of programs with preset duration and reflecting anxiety of people and close to a real background;
the tested individual randomly selects one of the tested individuals on the virtual reality platform to watch, and nervous and oppressive emotional experience is obtained;
the physiological signal acquisition device is synchronously started to acquire five different modal physiological information of the electrocardio, the skin electricity, the respiration, the blood oxygen and the facial blood oxygen content of the tested individual.
8. The intelligent psychological stress assessment and early warning system for multiple groups of people under epidemic disease conditions as claimed in claim 7, wherein after the watching is finished, the same tested individual fills in multiple psychological state evaluation scales and is inquired by professional psychologists, so as to obtain the psychological state grades of high-risk, medium-risk and low-risk types of each tested individual.
9. The intelligent psychological stress assessment and early warning system for multiple groups of people with epidemic disease as claimed in claim 8, wherein the psychological state grade of the same target individual is associated with physiological data and stored as an independent sample item in the initial sample space.
10. An electronic device, comprising the mental stress intelligent assessment and early warning system for multiple groups of people under epidemic conditions as claimed in any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010354393.1A CN111513732A (en) | 2020-04-29 | 2020-04-29 | Intelligent psychological stress assessment early warning system for various groups of people under epidemic disease condition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010354393.1A CN111513732A (en) | 2020-04-29 | 2020-04-29 | Intelligent psychological stress assessment early warning system for various groups of people under epidemic disease condition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111513732A true CN111513732A (en) | 2020-08-11 |
Family
ID=71905895
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010354393.1A Pending CN111513732A (en) | 2020-04-29 | 2020-04-29 | Intelligent psychological stress assessment early warning system for various groups of people under epidemic disease condition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111513732A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112168188A (en) * | 2020-10-09 | 2021-01-05 | 北京中科心研科技有限公司 | Processing method and device for pressure detection data |
| CN112967805A (en) * | 2021-02-03 | 2021-06-15 | 北京好欣晴移动医疗科技有限公司 | Epidemic prevention doctor-patient mental health screening system |
| CN113241178A (en) * | 2021-05-28 | 2021-08-10 | 温州康宁医院股份有限公司 | Method and device for determining severity of depression of tested person |
| CN113255635A (en) * | 2021-07-19 | 2021-08-13 | 中国科学院自动化研究所 | Multi-mode fused psychological stress analysis method |
| CN113707294A (en) * | 2021-08-05 | 2021-11-26 | 沃民高新科技（北京）股份有限公司 | Psychological evaluation method based on dynamic video data |
| CN114617555A (en) * | 2022-03-16 | 2022-06-14 | 山东大学 | Psychological assessment system, medium, and apparatus based on physiological characteristic stability detection |
| CN116616708A (en) * | 2023-05-22 | 2023-08-22 | 深圳市腾进达信息技术有限公司 | Vital sign data processing method and system based on intelligent wearable device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180360371A1 (en) * | 2017-06-14 | 2018-12-20 | International Business Machines Corporation | Analysis of cognitive status through object interaction |
| CN109074510A (en) * | 2016-04-28 | 2018-12-21 | 情感爱思比株式会社 | Emotion determines system, system and program |
| CN109106384A (en) * | 2018-07-24 | 2019-01-01 | 安庆师范大学 | A kind of psychological pressure condition predicting method and system |
| CN109480780A (en) * | 2018-11-14 | 2019-03-19 | 重庆三峡医药高等专科学校 | A kind of cerebral apoplexy early warning system and method |
| CN110123342A (en) * | 2019-04-17 | 2019-08-16 | 西北大学 | A kind of network addiction detection method and system based on brain wave |
| CN110507335A (en) * | 2019-08-23 | 2019-11-29 | 山东大学 | Inmate's psychological health states appraisal procedure and system based on multi-modal information |
-
2020
- 2020-04-29 CN CN202010354393.1A patent/CN111513732A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109074510A (en) * | 2016-04-28 | 2018-12-21 | 情感爱思比株式会社 | Emotion determines system, system and program |
| US20180360371A1 (en) * | 2017-06-14 | 2018-12-20 | International Business Machines Corporation | Analysis of cognitive status through object interaction |
| CN109106384A (en) * | 2018-07-24 | 2019-01-01 | 安庆师范大学 | A kind of psychological pressure condition predicting method and system |
| CN109480780A (en) * | 2018-11-14 | 2019-03-19 | 重庆三峡医药高等专科学校 | A kind of cerebral apoplexy early warning system and method |
| CN110123342A (en) * | 2019-04-17 | 2019-08-16 | 西北大学 | A kind of network addiction detection method and system based on brain wave |
| CN110507335A (en) * | 2019-08-23 | 2019-11-29 | 山东大学 | Inmate's psychological health states appraisal procedure and system based on multi-modal information |
Non-Patent Citations (5)
| Title |
|---|
| 张波云: "《基于监督学习的病毒检测技术研究》", 31 December 2017, 武汉：武汉大学出版社 * |
| 李示勇等: "《智能优化算法原理与应用》", 31 December 2012, 哈尔滨：哈尔滨工业大学出版社 * |
| 杨宏晖等: "融合样本选择与特征选择的AdaBoost支持向量机集成算法", 《西安交通大学学报》 * |
| 王倩: "《CT图像中肺部疾病的计算机辅助诊断方法研究》", 31 December 2015, 华中科技大学出版社（中国武汉） * |
| 黎巎: "《旅游大数据研究》", 31 July 2018, 北京：中国经济出版社 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112168188A (en) * | 2020-10-09 | 2021-01-05 | 北京中科心研科技有限公司 | Processing method and device for pressure detection data |
| CN112168188B (en) * | 2020-10-09 | 2023-07-25 | 北京中科心研科技有限公司 | Processing method and device for pressure detection data |
| CN112967805A (en) * | 2021-02-03 | 2021-06-15 | 北京好欣晴移动医疗科技有限公司 | Epidemic prevention doctor-patient mental health screening system |
| CN113241178A (en) * | 2021-05-28 | 2021-08-10 | 温州康宁医院股份有限公司 | Method and device for determining severity of depression of tested person |
| CN113255635A (en) * | 2021-07-19 | 2021-08-13 | 中国科学院自动化研究所 | Multi-mode fused psychological stress analysis method |
| CN113707294A (en) * | 2021-08-05 | 2021-11-26 | 沃民高新科技（北京）股份有限公司 | Psychological evaluation method based on dynamic video data |
| CN113707294B (en) * | 2021-08-05 | 2023-12-05 | 沃民高新科技（北京）股份有限公司 | Psychological evaluation method based on dynamic video data |
| CN114617555A (en) * | 2022-03-16 | 2022-06-14 | 山东大学 | Psychological assessment system, medium, and apparatus based on physiological characteristic stability detection |
| CN116616708A (en) * | 2023-05-22 | 2023-08-22 | 深圳市腾进达信息技术有限公司 | Vital sign data processing method and system based on intelligent wearable device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111513732A (en) | Intelligent psychological stress assessment early warning system for various groups of people under epidemic disease condition | |
| CN110507335B (en) | Multi-mode information based criminal psychological health state assessment method and system | |
| CN107224291B (en) | Dispatcher capability test system | |
| Yang et al. | IoT structured long-term wearable social sensing for mental wellbeing | |
| CN109009017B (en) | Intelligent health monitoring system and data processing method thereof | |
| AU2016278357A1 (en) | Method and system for monitoring stress conditions | |
| CN112699785B (en) | Group emotion recognition and abnormal emotion detection method based on dimension emotion model | |
| Sharma et al. | Modeling stress recognition in typical virtual environments | |
| Huang et al. | Virtual reality safety training using deep EEG-net and physiology data | |
| Li et al. | Quantification study of working fatigue state affected by coal mine noise exposure based on fuzzy comprehensive evaluation | |
| Harper et al. | End-to-end prediction of emotion from heartbeat data collected by a consumer fitness tracker | |
| CN110755091A (en) | Personal mental health monitoring system and method | |
| Zhao et al. | Data-driven learning fatigue detection system: A multimodal fusion approach of ECG (electrocardiogram) and video signals | |
| Pourmohammadi et al. | Continuous mental stress level assessment using electrocardiogram and electromyogram signals | |
| Feng et al. | Predicting physical fatigue in athletes in rope skipping training using ECG signals | |
| CN111723869A (en) | Special personnel-oriented intelligent behavior risk early warning method and system | |
| CN113143274A (en) | Emotion early warning method based on camera | |
| CN109620263B (en) | Physical sign safety analysis method for post workers in enterprises and public institutions | |
| CN110705413B (en) | Emotion prediction method and system based on sight direction and LSTM neural network | |
| Kalogiannis et al. | Geriatric group analysis by clustering non-linearly embedded multi-sensor data | |
| CN116434979A (en) | Physiological state cloud monitoring method, monitoring system and storage medium | |
| CN113974589B (en) | Multi-modal behavior paradigm evaluation optimization system and cognitive ability evaluation method | |
| CN113963777A (en) | Military net psychological service working platform system | |
| Yashaswini et al. | Stress detection using deep learning and IoT | |
| CN110974215B (en) | Early warning system and method based on wireless electrocardiogram monitoring sensor group |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |