CN115778389A - Birth fear detection method and system based on electrocardio and electrodermal joint analysis - Google Patents
Birth fear detection method and system based on electrocardio and electrodermal joint analysis Download PDFInfo
- Publication number
- CN115778389A CN115778389A CN202211543465.2A CN202211543465A CN115778389A CN 115778389 A CN115778389 A CN 115778389A CN 202211543465 A CN202211543465 A CN 202211543465A CN 115778389 A CN115778389 A CN 115778389A
- Authority
- CN
- China
- Prior art keywords
- childbirth
- fear
- electrocardio
- skin
- electric signals
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 21
- 238000004458 analytical method Methods 0.000 title claims abstract description 10
- 230000035606 childbirth Effects 0.000 claims abstract description 61
- 230000008878 coupling Effects 0.000 claims abstract description 25
- 238000010168 coupling process Methods 0.000 claims abstract description 25
- 238000005859 coupling reaction Methods 0.000 claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 18
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 230000015654 memory Effects 0.000 claims abstract description 7
- 238000001914 filtration Methods 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 13
- 238000011176 pooling Methods 0.000 claims description 11
- 239000000126 substance Substances 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 238000005315 distribution function Methods 0.000 claims description 3
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 2
- 230000004913 activation Effects 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 210000002569 neuron Anatomy 0.000 claims description 2
- 230000004927 fusion Effects 0.000 claims 1
- 238000005070 sampling Methods 0.000 claims 1
- 230000008451 emotion Effects 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 230000005611 electricity Effects 0.000 description 5
- 230000008909 emotion recognition Effects 0.000 description 3
- 230000007787 long-term memory Effects 0.000 description 2
- 238000013186 photoplethysmography Methods 0.000 description 2
- 230000035935 pregnancy Effects 0.000 description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000010482 emotional regulation Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 230000036544 posture Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 231100000430 skin reaction Toxicity 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention belongs to the technical field of emotion monitoring and adjustment, and particularly relates to a childbirth fear detection method and system based on electrocardio and electrodermal joint analysis. The invention comprises the following steps: the method comprises the steps that original electric signals of the heart and the skin of a pregnant woman are synchronously collected, and a doctor divides the childbirth fear level of the pregnant woman according to a childbirth attitude questionnaire; signal preprocessing, including filtering, denoising and standardization; extracting coupling characteristics of the standardized electrocardio and skin electric signals; acquiring network learning characteristics of the electrocardio-skin electric signals and the skin electric signals based on the convolutional neural network model, and fusing the network learning characteristics with the coupling characteristics; and inputting the integrated comprehensive characteristics into a bidirectional long-time and short-time memory network model to evaluate the childbirth fear grade, and obtaining a childbirth fear classification result. Compared with the childbirth fear detection based on the subjective scale, the method and the device deeply excavate the information related to the emotion of the pregnant woman contained in the electrocardio-signals and the skin-electric signals, can judge the childbirth fear more timely and accurately, and are beneficial to the pregnant woman to know and adjust the psychological state of the pregnant woman timely.
Description
Technical Field
The invention belongs to the technical field of emotion monitoring and adjustment, and particularly relates to a method and a system for detecting childbirth fear of pregnant women.
Background
Pregnancy is a critical period specific to women during which, in addition to being physiologically variable, a series of psychological changes also occur. Fear of childbirth (FOC) is a common psychological problem in pregnant women and has received much attention in recent years. Fear of childbirth is a negative cognitive assessment of childbirth, and is a negative impact on the quality of childbirth and on the safety of the labor, as regards the impending childbirth being fraught with fear and anxiety, and even the psychological state that one wants to escape. The fear of delivery is identified timely and accurately, so that effective intervention measures are collected, and the method has important significance.
In the field of emotion recognition, an emotion recognition method based on a human physiological signal is considered to be more reliable and more accurate than facial expressions, voices, gestures, postures, and the like. However, at present, the judgment of the fear of delivery of pregnant women is mainly realized by self-measuring scales, including a delivery attitude scale (CAQ), a delivery fear scale (FCQ), a Wijma delivery expectation/experience scale (W-DEQ) and the like. The evaluation of childbirth fear based on physiological signals is lacking in systematic studies.
The physiological signals used for emotion recognition mainly include electroencephalogram (EEG), electrocardiogram (ECG), electromyogram (EMG), galvanic Skin Response (GSR), respiration (RSP), skin temperature (SKT), photoplethysmography (PPG), and the like. Compared with other physiological signals, the electrocardio-signals and the skin electric signals are easier to acquire and are less interfered by noise. Meanwhile, considering the particularity of the body type of the pregnant woman, the two signals have the smallest influence on the pregnant woman, and are most suitable for constructing a childbirth fear evaluation model.
Disclosure of Invention
The invention aims to provide a childbirth fear detection method and a childbirth fear detection system based on electrocardio and electrodermal joint analysis, which can more timely and accurately judge childbirth fear, so that a pregnant woman can timely know and adjust the psychological state of the pregnant woman.
The invention provides a childbirth fear detection method based on electrocardio and skin electricity combined analysis, which comprises the steps of collecting and obtaining an original skin electric signal of a pregnant woman; synchronously collecting electrocardio and skin electric signals of the pregnant woman; filtering, denoising and standardizing the original signal; calculating time domain, frequency domain and nonlinear coupling characteristics of the electrocardio and skin electric signals; network training characteristics of the electrocardio-skin electric signals and the skin electric signals are obtained through a Convolutional Neural Network (CNN), and are fused with the coupling characteristics; and sending the obtained comprehensive characteristics into a bidirectional long-time memory network (biLSTM) to obtain a birth fear classification result. The method comprises the following specific steps:
step (1): synchronously collecting original electric signals of the heart and skin of the pregnant woman, and dividing the childbirth fear level of the pregnant woman by a doctor according to a childbirth attitude questionnaire;
step (2): signal preprocessing, including filtering, denoising and standardization;
and (3): extracting coupling characteristics of the standardized electrocardio and skin electric signals;
and (4): obtaining network learning characteristics of the electrocardio-skin electric signals and the skin electric signals by adopting a Convolutional Neural Network (CNN) model, and fusing the network learning characteristics with the coupling characteristics;
and (5): and inputting the integrated comprehensive characteristics into a bidirectional long-time memory network (biLSTM) model, and carrying out birth fear grade evaluation to obtain a birth fear classification result.
Further, the fear of childbirth grade in step (1) is divided into: no fear of childbirth, mild fear of childbirth, moderate fear of childbirth and severe fear of childbirth.
Further, the signal preprocessing in the step (2) comprises: for the acquired original electrocardiosignals, a second-order Butterworth band-pass filter of 0.05-75Hz is adopted for denoising and baseline drift removal, and a notch filter of 50Hz is used for removing power frequency interference; for the collected original skin electric signals, a second-order Butterworth band-pass filter with the frequency of 0.02-0.5Hz is adopted for denoising and baseline drift removing; then, the filtered skin electric and electrocardio signals are standardized by a Z-score method.
Further, the coupling indexes in the step (3) comprise Pearson correlation coefficients, amplitude square coherence functions, mutual information, mutual sample entropy and mutual fuzzy entropy, and the coupling relation between the skin electricity and the electrocardio electricity is analyzed from three aspects of time domain, frequency domain and nonlinearity respectively. For cardioelectric sequences { X i N = x (i), 1 ≦ i ≦ N } and electrodermal sequence Y j And = y (j), 1 ≦ j ≦ M }, wherein x (i) and y (j) respectively represent each electrocardiogram and skin electrical value in the time sequence, N represents the sequence length, and the coupling index is obtained by the following method:
(1) pearson correlation coefficient:
wherein the content of the first and second substances,andrespectively represent X i And Y j The average value of (a) of (b),andrespectively represent X i And Y j Standard deviation of (2).
(2) Amplitude squared coherence function:
wherein, P XY (f) Representing the cross-spectral density, P, between two time series XX (f) And P YY (f) Respectively represent X i And Y j MSCF represents the degree of linear correlation between the components of the two time series at each frequency.
(3) Given a reconstruction dimension m, X i And Y j Respectively reconstructing as follows:
wherein | represents the maximum norm;
Wherein Θ (-) is a Heaviside function;
(4) given a reconstruction dimension m, X i And Y j Respectively reconstructing as follows:
wherein the content of the first and second substances,is a decreasing half Gaussian distribution function;
further, the Convolutional Neural Network (CNN) model in step (4) is a dual-scale convolutional neural network. Each scale has 4 convolutional layers, 2 pooling layers, 2 dropout layers, 1 flat layer and 1 fully connected layer. The first convolutional layer is used to initially extract features and reduce tensor size, the pooling layer and dropout layer are used to downsample the feature tensor and prevent the over-fitting phenomenon, and the following three identical convolutional layers are used to further refine the filter. Then another pooling layer and a flattening layer are applied to further reduce the size of each tensor, and finally the tensors are connected and then passed through a dropout layer, and the tensor size is further reduced through a fully connected layer. And (4) after the network learning characteristic is obtained, fusing the network learning characteristic with the coupling characteristic in the step (3) to obtain a comprehensive characteristic.
Based on the delivery fear detection method, the invention also comprises a delivery fear detection system based on electrocardio and skin-electricity combined analysis. The system specifically comprises five modules which are respectively: the pregnant woman's original electrocardio and skin electric signal collection module, signal preprocessing module, electrocardio and skin electric signal coupling characteristic extraction module, the characteristic learning, the integration module based on Convolution Neural Network (CNN) model, the fear of childbirth grade evaluation module based on two-way long-and-short term memory network (bilSTM) model. The five modules respectively execute the operation contents of the five steps of the method.
The invention has the characteristics and beneficial effects that:
compared with the childbirth fear detection based on the subjective scale at present, the method and the device deeply excavate the information related to the emotion of the pregnant woman contained in the electrocardio-skin electric signal, can more timely and accurately judge the childbirth fear, and are beneficial for the pregnant woman to timely know and adjust the psychological state of the pregnant woman.
Drawings
Fig. 1 is an overall flowchart of the childbirth fear detection method based on the combined analysis of the electrocardio-signals and the skin electric signals.
Fig. 2 is an overall architecture of a dual scale convolutional neural network.
FIG. 3 is the overall architecture of a bidirectional long-short-term memory network (bilSTM).
Detailed Description
The present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments. The whole process of the childbirth fear detection method provided by the invention is shown in figure 1, and comprises the following steps:
(1) The method comprises the steps of synchronously collecting original electric signals of the heart and the skin of a pregnant woman, and dividing the childbirth fear level by a doctor according to a childbirth attitude questionnaire;
in the embodiment, the portable equipment is used for collecting electrocardio and skin electric signals of 20 pregnant women in 32 weeks, the collection is carried out in a nursing room of an obstetrical department outpatient service, and the signal duration is at least 5 minutes. The pregnant woman fills out a general data survey table and a childbirth attitude scale, and a doctor divides a childbirth fear grade according to the scale. Specifically, the childbirth attitude scale contains 16 entries, with a score of 1-4, with a total score of 16-64, with higher scores indicating more severe childbirth fear, 16-27 scores representing no childbirth fear, 28-39 scores representing mild childbirth fear, 40-51 scores representing moderate childbirth fear, and 52-64 scores representing severe childbirth fear.
(2) And signal preprocessing, including filtering, denoising and normalizing.
In the embodiment, for the acquired original electrocardiosignals, a second-order Butterworth band-pass filter of 0.05-75Hz is adopted for denoising and baseline drift removal, and a notch filter of 50Hz is used for removing power frequency interference; for the collected original skin electric signals, a second-order Butterworth band-pass filter with the frequency of 0.02-0.5Hz is adopted for denoising and baseline drift removal; then, standardizing the filtered skin electric and electrocardio signals by adopting a Z-score method, wherein the calculation method comprises the following steps:
wherein Normalized (X) is the Normalized signal, mean (X) is the mean of the original signal,is the standard deviation of the original signal.
(3) And extracting coupling characteristics of the standardized electrocardio and skin electric signals.
The coupling indexes comprise Pearson correlation coefficients, amplitude square coherence functions, mutual information, mutual sample entropy and mutual fuzzy entropy, and the coupling relation between the skin electricity and the electrocardio electricity is analyzed from the time domain, the frequency domain and the nonlinearity. For electrocardio-sequences { X i N = x (i), 1 ≦ i ≦ N } and electrodermal sequence Y j And j is more than or equal to 1 and less than or equal to N, x (i) and y (j) respectively represent each electrocardio and skin electrometric value in the time sequence, N represents the length of the sequence, and the coupling index is obtained by the following method:
(1) pearson correlation coefficient:
wherein the content of the first and second substances,andrespectively represent X i And Y j The average value of (a) is calculated,andrespectively represent X i And Y j Standard deviation of (2).
(2) Amplitude squared coherence function:
wherein, P XY (f) Representing the cross-spectral density, P, between two time series XX (f) And P YY (f) Respectively represent X i And Y j MSCF represents the degree of linear correlation between the components of the two time series at each frequency.
(3) Given a reconstruction dimension m, X i And Y j Respectively reconstructing as follows:
Where Θ (-) is the Heaviside function; increasing the reconstruction dimension m to m +1, calculatingMutual sample entropy
(4) Given a reconstruction dimension m, X i And Y j Respectively reconstructing as follows:
wherein the content of the first and second substances,is a decreasing half Gaussian distribution function;
in this embodiment, the parameters of XSampEn and XFuzzyEn are set to reconstruction dimension m =2, and the threshold r =0.2.
(4) And obtaining network learning characteristics of the electrocardio-skin electric signals and the skin electric signals based on a Convolutional Neural Network (CNN) model, and fusing the network learning characteristics with the coupling characteristics. A double-scale convolutional neural network is adopted, and each scale comprises 4 convolutional layers, 2 pooling layers, 2 dropout layers, 1 flat layer and 1 full-connection layer. The first convolutional layer is used to initially extract features and reduce tensor size, the pooling layer and dropout layer are used to downsample the feature tensor and prevent the over-fitting phenomenon, and the following three identical convolutional layers are used to further refine the filter. Then another pooling layer and a flattening layer are applied to further reduce the size of each tensor, and finally the tensors are connected and then passed through a dropout layer, and the tensor size is further reduced through a fully connected layer.
In the present embodiment, a dual-scale network architecture is adopted as shown in fig. 2. The pooling type employs maximum pooling, with the addition of a Batch Normalization (BN) operation and a linear rectification unit (ReLU) per convolutional layer. And (4) after the convolutional neural network features are extracted, fusing with the coupling features in the step (3) to obtain comprehensive features.
(5) And inputting the fused comprehensive characteristics into a bidirectional long-term memory network (biLSTM) model for carrying out birth fear level assessment. The model contains three biLSTM layers and one dense layer. The three biLSTM layers contained a number of neurons in the order of 200,100 and 50, using a Sigmoid activation function, an Adam optimizer and a cross entropy loss function.
In this embodiment, the two-way long and short term memory network architecture is shown in fig. 3: sending the comprehensive characteristics acquired based on electrocardio and electrodermal into the network, and adopting five-fold cross validation, namely averagely dividing the data into 5 equal parts, wherein only 1 part is used as a test set each time, the other 4 parts are used as training sets, and the average value of 5 times of validation is used as a final delivery fear evaluation result. The result shows that the identification accuracy rate of the method for the childbirth fear absence and the childbirth fear is 82.05%.
According to the childbirth fear detection method based on electrocardio and electrodermal joint analysis, on one hand, coupling analysis is introduced to obtain the synchronism information of two body surface signals, and the limitation of a single signal is overcome; on the other hand, the information related to the emotion of the pregnant woman contained in the signal is deeply mined by using a deep learning method, so that the detection accuracy is improved. Compared with the conventional delivery fear detection based on the subjective scale, the method can objectively, accurately and timely evaluate the delivery fear, and is beneficial to timely emotion regulation and psychological persuasion of the pregnant woman, so that the precise management of the pregnancy period is realized.
The above embodiments are only for illustrating the present invention, and are not intended to limit the present invention. It will be understood by those skilled in the art that various combinations, modifications and equivalents of the embodiments of the invention described herein may be made without departing from the spirit and scope of the invention as defined in the claims.
Claims (7)
1. A childbirth fear detection method based on electrocardio and skin-electricity combined analysis is characterized by comprising the following specific steps:
step (1): synchronously collecting original electric signals of the heart and skin of the pregnant woman, and dividing the childbirth fear level of the pregnant woman by a doctor according to a childbirth attitude questionnaire;
step (2): signal preprocessing, including filtering, denoising and standardization;
and (3): extracting coupling characteristics of the standardized electrocardio and skin electric signals;
and (4): obtaining network learning characteristics of the electrocardio-skin electric signals and the skin electric signals based on a Convolutional Neural Network (CNN) model, and fusing the network learning characteristics with the coupling characteristics;
and (5): and inputting the integrated comprehensive characteristics into a bidirectional long-short-term memory network (biLSTM) model to evaluate the class of the fear of childbirth to obtain a classification result of the fear of childbirth.
2. The method for fear of childbirth detection according to claim 1, wherein the fear of childbirth in step (1) is graded as: no fear of childbirth, mild fear of childbirth, moderate fear of childbirth and severe fear of childbirth.
3. The method for fear of childbirth detection of claim 2 wherein the signal preprocessing of step (2) comprises: for the acquired original electrocardiosignals, a second-order Butterworth band-pass filter of 0.05-75Hz is adopted for denoising and baseline drift removal, and a notch filter of 50Hz is used for removing power frequency interference; for the collected original skin electric signals, a second-order Butterworth band-pass filter with the frequency of 0.02-0.5Hz is adopted for denoising and baseline drift removing; then, the filtered skin electric and electrocardio signals are standardized by a Z-score method.
4. The fear of childbirth detection method according to claim 3, wherein the coupling indicators in step (3) include Pearson's correlation coefficient, amplitude squared coherence function, mutual information, mutual sample entropy and mutual fuzzy entropy, and the coupling relationship between the skin current and the electrocardiogram is analyzed from three aspects of time domain, frequency domain and nonlinearity; for cardioelectric sequences { X i N = x (i), 1 ≦ i ≦ N } and electrodermal sequence Y j And j is more than or equal to 1 and less than or equal to N, x (i) and y (j) respectively represent each electrocardio and skin electrometric value in the time sequence, N represents the length of the sequence, and the coupling index is obtained by the following method:
(1) pearson correlation coefficient:
wherein the content of the first and second substances,andrespectively represent X i And Y j The average value of (a) of (b),andrespectively represent X i And Y j Standard deviation of (d);
(2) amplitude squared coherence function:
wherein, P XY (f) Representing the cross-spectral density, P, between two time series XX (f) And P γγ (f) Respectively represent X i And Y j The MSCF represents the linear correlation degree between the components of the two time series on each frequency;
(3) given a reconstruction dimension m, X i And Y j Respectively reconstructing as follows:
wherein | represents the maximum norm;
Wherein Θ (-) is a Heaviside function;
(4) given a reconstruction dimension m, X i And Y j Respectively reconstructing as follows:
wherein the content of the first and second substances,is a decreasing half Gaussian distribution function;
5. the fear of childbirth detection method of claim 4 wherein in step (4) the model is a two-scale convolutional neural network; each scale has 4 convolutional layers, 2 pooling layers, 2 dropout layers, 1 flat layer and 1 fully connected layer; the first convolutional layer is used for preliminarily extracting features and reducing tensor size, the pooling layer and the dropout layer are used for down-sampling the feature tensor and preventing the over-fitting phenomenon, and the following three same convolutional layers are used for further improving the filter; then applying another pooling layer and a flattening layer to further reduce the size of each tensor, and finally connecting the tensors together, passing through a dropout layer, and further reducing the tensor size through a full connection layer; and (4) after the network learning characteristic is obtained, fusing the network learning characteristic with the coupling characteristic in the step (3) to obtain a comprehensive characteristic.
6. The fear of childbirth claim 5 wherein the bidirectional stoke network model in step (5) comprises three biLSTM layers and one dense layer; the three biLSTM layers contained a number of neurons in the order of 200,100 and 50, using a Sigmoid activation function, an Adam optimizer and a cross entropy loss function.
7. A childbirth fear detection system based on the method of any one of claims 1-6, comprising five modules, respectively: the pregnant woman's original electrocardio and skin electric signal acquisition module, the signal preprocessing module, the electrocardio and skin electric signal coupling characteristic extraction module, the characteristic learning and fusion module based on the convolutional neural network model, the childbirth fear grade evaluation module based on the bidirectional long-time memory network model; the five modules respectively execute the operation contents of the five steps of the method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211543465.2A CN115778389B (en) | 2022-12-02 | Method and system for detecting fear of delivery based on electrocardio and skin electricity combination analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211543465.2A CN115778389B (en) | 2022-12-02 | Method and system for detecting fear of delivery based on electrocardio and skin electricity combination analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115778389A true CN115778389A (en) | 2023-03-14 |
CN115778389B CN115778389B (en) | 2024-05-28 |
Family
ID=
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012025622A2 (en) * | 2010-08-27 | 2012-03-01 | Smartex S.R.L. | Monitoring method and system for assessment of prediction of mood trends |
WO2017016086A1 (en) * | 2015-07-30 | 2017-02-02 | 华南理工大学 | Depression evaluating system and method based on physiological information |
WO2018120088A1 (en) * | 2016-12-30 | 2018-07-05 | 中国科学院深圳先进技术研究院 | Method and apparatus for generating emotional recognition model |
US20190347476A1 (en) * | 2018-05-09 | 2019-11-14 | Korea Advanced Institute Of Science And Technology | Method for estimating human emotions using deep psychological affect network and system therefor |
KR20190128978A (en) * | 2018-05-09 | 2019-11-19 | 한국과학기술원 | Method for estimating human emotions using deep psychological affect network and system therefor |
US20200085362A1 (en) * | 2017-03-24 | 2020-03-19 | Obshchestvo S Ogranichennoj Otvetstvennost`Yu "Mnogoprofilnoe Predpriyatie "Elsys" | Method of evaluating a psychophysiological state of a person |
CN112998711A (en) * | 2021-03-18 | 2021-06-22 | 华南理工大学 | Emotion recognition system and method based on wearable device |
CN113208593A (en) * | 2021-04-08 | 2021-08-06 | 杭州电子科技大学 | Multi-modal physiological signal emotion classification method based on correlation dynamic fusion |
WO2021233259A1 (en) * | 2020-05-21 | 2021-11-25 | 华为技术有限公司 | Method for evaluating female emotion and related apparatus, and device |
US20220084543A1 (en) * | 2020-01-21 | 2022-03-17 | Rishi Amit Sinha | Cognitive Assistant for Real-Time Emotion Detection from Human Speech |
CN115273904A (en) * | 2022-07-22 | 2022-11-01 | 浙江大学 | Angry emotion recognition method and device based on multi-feature fusion |
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012025622A2 (en) * | 2010-08-27 | 2012-03-01 | Smartex S.R.L. | Monitoring method and system for assessment of prediction of mood trends |
WO2017016086A1 (en) * | 2015-07-30 | 2017-02-02 | 华南理工大学 | Depression evaluating system and method based on physiological information |
WO2018120088A1 (en) * | 2016-12-30 | 2018-07-05 | 中国科学院深圳先进技术研究院 | Method and apparatus for generating emotional recognition model |
US20200085362A1 (en) * | 2017-03-24 | 2020-03-19 | Obshchestvo S Ogranichennoj Otvetstvennost`Yu "Mnogoprofilnoe Predpriyatie "Elsys" | Method of evaluating a psychophysiological state of a person |
US20190347476A1 (en) * | 2018-05-09 | 2019-11-14 | Korea Advanced Institute Of Science And Technology | Method for estimating human emotions using deep psychological affect network and system therefor |
KR20190128978A (en) * | 2018-05-09 | 2019-11-19 | 한국과학기술원 | Method for estimating human emotions using deep psychological affect network and system therefor |
US20220084543A1 (en) * | 2020-01-21 | 2022-03-17 | Rishi Amit Sinha | Cognitive Assistant for Real-Time Emotion Detection from Human Speech |
WO2021233259A1 (en) * | 2020-05-21 | 2021-11-25 | 华为技术有限公司 | Method for evaluating female emotion and related apparatus, and device |
CN112998711A (en) * | 2021-03-18 | 2021-06-22 | 华南理工大学 | Emotion recognition system and method based on wearable device |
CN113208593A (en) * | 2021-04-08 | 2021-08-06 | 杭州电子科技大学 | Multi-modal physiological signal emotion classification method based on correlation dynamic fusion |
CN115273904A (en) * | 2022-07-22 | 2022-11-01 | 浙江大学 | Angry emotion recognition method and device based on multi-feature fusion |
Non-Patent Citations (5)
Title |
---|
A. RAHIM, A. SAGHEER, K. NADEEM: "Emotion Charting Using Real-time Monitoring of Physiological Signals", 2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION IN INDUSTRY (ICRAI), 22 October 2019 (2019-10-22) * |
WEN, W., QIU, Y., LIU, G. ET AL: "Construction and cross-correlation analysis of the affective physiological response database", SCIENCE CHINA INFORMATION SCIENCES, vol. 53, no. 9, 14 May 2010 (2010-05-14) * |
权学良, 曾志刚, 蒋建华, 等: "基于生理信号的情感计算研究综述", 自动化学报, vol. 47, no. 8, 22 January 2021 (2021-01-22) * |
李振齐: "基于脑电时空频多域特征的自动情绪识别研究及系统实现", 中国优秀硕士学位论文全文数据库 基础科学辑, no. 12, 15 December 2018 (2018-12-15) * |
林萍珍, 薛娇美, 杨蓓, 等: "基于Pearson相关系数的癌症患者创伤后成长与心理适应相关性的Meta分析", 山东大学学报(医学版), vol. 55, no. 9, 8 August 2017 (2017-08-08) * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110916631B (en) | Student classroom learning state evaluation system based on wearable physiological signal monitoring | |
Bairy et al. | Automated diagnosis of depression electroencephalograph signals using linear prediction coding and higher order spectra features | |
CN105147248A (en) | Physiological information-based depressive disorder evaluation system and evaluation method thereof | |
CN204931634U (en) | Based on the depression evaluating system of physiologic information | |
CN111466876B (en) | Alzheimer's disease auxiliary diagnosis system based on fNIRS and graph neural network | |
CN111407243B (en) | Pulse signal pressure identification method based on deep learning | |
CN112353391A (en) | Electroencephalogram signal-based method and device for recognizing sound quality in automobile | |
CN107468243A (en) | A kind of method and device for assessing stupor degree | |
CN111860410A (en) | Myoelectric gesture recognition method based on multi-feature fusion CNN | |
CN112190261A (en) | Autism electroencephalogram signal classification device based on resting brain network | |
CN111839506B (en) | Mental load detection method and device | |
CN111544256A (en) | Brain-controlled intelligent full limb rehabilitation method based on graph convolution and transfer learning | |
CN111616681A (en) | Anesthesia state monitoring system based on portable electroencephalogram acquisition equipment and deep learning | |
CN115640827B (en) | Intelligent closed-loop feedback network method and system for processing electrical stimulation data | |
CN113723557A (en) | Depression electroencephalogram classification system based on multiband time-space convolution network | |
CN112541415A (en) | Brain muscle function network movement fatigue detection method based on symbol transfer entropy and graph theory | |
CN115568866A (en) | System and method for evaluating nerve injury | |
CN111783715A (en) | Identity recognition method based on pulse signal feature extraction | |
CN111067513A (en) | Sleep quality detection key brain area judgment method based on characteristic weight self-learning | |
CN114533089A (en) | Lower limb action recognition and classification method based on surface electromyographic signals | |
CN111671421B (en) | Electroencephalogram-based children demand sensing method | |
CN110680285A (en) | Anesthesia degree monitoring device based on neural network | |
CN117281479A (en) | Human lower limb chronic pain distinguishing method, storage medium and device based on surface electromyographic signal multi-dimensional feature fusion | |
CN115778389B (en) | Method and system for detecting fear of delivery based on electrocardio and skin electricity combination analysis | |
CN115778389A (en) | Birth fear detection method and system based on electrocardio and electrodermal joint analysis |
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 | ||
GR01 | Patent grant |