CN116999072B - Appetite intervention system and method based on individualized brain electrical nerve feedback - Google Patents
Appetite intervention system and method based on individualized brain electrical nerve feedback Download PDFInfo
- Publication number
- CN116999072B CN116999072B CN202311063825.3A CN202311063825A CN116999072B CN 116999072 B CN116999072 B CN 116999072B CN 202311063825 A CN202311063825 A CN 202311063825A CN 116999072 B CN116999072 B CN 116999072B
- Authority
- CN
- China
- Prior art keywords
- appetite
- feedback
- tested
- module
- electroencephalogram
- 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.)
- Active
Links
- 235000019789 appetite Nutrition 0.000 title claims abstract description 209
- 230000036528 appetite Effects 0.000 title claims abstract description 209
- 210000004556 brain Anatomy 0.000 title claims abstract description 71
- 210000005036 nerve Anatomy 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000007781 pre-processing Methods 0.000 claims abstract description 34
- 235000019788 craving Nutrition 0.000 claims abstract description 26
- 238000002474 experimental method Methods 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 20
- 230000000007 visual effect Effects 0.000 claims abstract description 20
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 235000013305 food Nutrition 0.000 claims description 29
- 206010056465 Food craving Diseases 0.000 claims description 25
- 239000000463 material Substances 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 abstract description 4
- 235000020980 bad eating habits Nutrition 0.000 abstract description 2
- 230000000638 stimulation Effects 0.000 description 14
- 230000008569 process Effects 0.000 description 13
- 230000003595 spectral effect Effects 0.000 description 12
- 238000001228 spectrum Methods 0.000 description 12
- 208000008589 Obesity Diseases 0.000 description 11
- 235000020824 obesity Nutrition 0.000 description 11
- 239000011159 matrix material Substances 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 230000000694 effects Effects 0.000 description 8
- 239000012634 fragment Substances 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000000737 periodic effect Effects 0.000 description 6
- 230000001105 regulatory effect Effects 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 235000006694 eating habits Nutrition 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 238000011002 quantification Methods 0.000 description 5
- 238000013139 quantization Methods 0.000 description 5
- 238000012937 correction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 229940079593 drug Drugs 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 235000021229 appetite regulation Nutrition 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000002045 lasting effect Effects 0.000 description 2
- 210000001595 mastoid Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008035 nerve activity Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000002560 therapeutic procedure Methods 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 208000004930 Fatty Liver Diseases 0.000 description 1
- 206010019708 Hepatic steatosis Diseases 0.000 description 1
- 206010033307 Overweight Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000004594 appetite change Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000007177 brain activity Effects 0.000 description 1
- 230000003925 brain function Effects 0.000 description 1
- 230000008309 brain mechanism Effects 0.000 description 1
- 230000036624 brainpower Effects 0.000 description 1
- 235000019577 caloric intake Nutrition 0.000 description 1
- 201000011529 cardiovascular cancer Diseases 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 238000009207 exercise therapy Methods 0.000 description 1
- 208000010706 fatty liver disease Diseases 0.000 description 1
- 230000009123 feedback regulation Effects 0.000 description 1
- 235000019680 high-energy food Nutrition 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000000653 nervous system Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000004007 neuromodulation Effects 0.000 description 1
- 230000007171 neuropathology Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 235000019627 satiety Nutrition 0.000 description 1
- 230000036186 satiety Effects 0.000 description 1
- 210000004761 scalp Anatomy 0.000 description 1
- 231100000240 steatosis hepatitis Toxicity 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/372—Analysis of electroencephalograms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/377—Electroencephalography [EEG] using evoked responses
- A61B5/378—Visual stimuli
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4836—Diagnosis combined with treatment in closed-loop systems or methods
-
- 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
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- 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
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- 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
Abstract
The invention discloses an appetite intervention system and method based on individualized brain electricity nerve feedback, comprising the following steps: the electroencephalogram signal acquisition module is used for acquiring electroencephalogram signals in appetite intervention nerve feedback experiments to be tested; the electroencephalogram signal preprocessing module is used for preprocessing electroencephalogram signals; the appetite characteristic extraction module is used for extracting appetite brain characteristics of the preprocessed electroencephalogram signals; the appetite state identification module is used for obtaining the individual appetite state of the tested according to the appetite brain characteristics; and the appetite state feedback module is used for feeding back the appetite craving degree of the tested individual in real time through visual signals according to the tested individual appetite state and performing iterative training intervention adjustment. The technical scheme of the invention can be used for intervention of bad eating habits, and has potential clinical value and social value.
Description
Technical Field
The invention belongs to the technical field of noninvasive nerve intervention, and particularly relates to an individualized appetite intervention system and method based on brain electricity nerve feedback.
Background
Obesity is excessive accumulation of fat caused by long-term imbalance in energy intake and energy expenditure. In recent years, with the development of network self-media, food-related pictures, short videos and live broadcasting are favored and paid attention to by people, but also cause excessive intake of high-energy foods by people, thereby causing overweight caused by poor eating habits. According to world health organization data, the global adult obesity rate has been over 13 hundred million, with over 3 hundred million people in a severely obese state. Obesity increases the risk of various diseases such as diabetes, fatty liver, cardiovascular diseases, cancers and the like, resulting in reduced quality of life and life span of patients, serious threat to human health, and estimated to be death due to obesity-related diseases of over 400 ten thousand people annually.
Based on the current situation, the treatment and rehabilitation industry of obese people is gradually rising, and main means at present comprise diet intervention, exercise therapy, drug treatment, operation treatment and the like, but rebound situations are likely to occur in the traditional means, side effects are likely to occur in the means of drugs, operation and the like, and because of heterogeneity of individuals, the problem of individuation difference cannot be solved in most treatment means, so that the realization of individuation treatment means is needed urgently.
Studies have shown that obese people can have altered brain architecture and that neural network functions that regulate appetite and satiety prior to obesity have been altered, thus exploring the mechanisms of obesity through brain information and performing abnormal neuromodulation would provide a potentially effective new approach to obesity intervention.
The brain-computer interaction intervention therapy is used as a novel non-drug treatment method, and the brain-computer interaction intervention therapy is used for regulating the activities of abnormal nervous systems of human bodies in real time by utilizing an electroencephalogram signal nerve feedback technology, so that the appetite of patients is regulated and controlled to be kept at a relatively normal level, and the obesity problem is improved. The nerve feedback is used for displaying the performance of vision or other forms of activities to the tested person in real time by recording the brain nerve activity, and helping the tested person to autonomously regulate and control the corresponding nerve activity, so that the performance is improved, the advantages of non-invasiveness, individuation, lasting effect and the like are achieved, the treatment side effect can be reduced to the maximum extent by the nerve feedback technology, and individuation effective treatment is carried out on various obese people. Meanwhile, the nerve feedback technology can help us to further know the deep neuropathology mechanism of the disease, thereby providing new direction and means for the treatment of the disease and having important clinical application value.
Therefore, the invention designs an individual appetite intervention system based on the brain-computer interaction technology aiming at the appetite characteristics of people with poor eating habits.
Disclosure of Invention
The invention aims to overcome the defects of the prior obesity intervention technology, and provides an appetite intervention system and method based on individualized brain-computer nerve feedback, which utilize brain-computer interaction technology to objectively quantify appetite states (food craving degree) in real time, adjust appetite changes according to individual needs in a targeted manner and assist clinic or family in performing obesity intervention treatment and the like.
In order to achieve the above purpose, the technical scheme provided by the invention is as follows:
an appetite intervention system based on individualized brain electrical nerve feedback, comprising:
the electroencephalogram signal acquisition module is used for acquiring electroencephalogram signals in appetite intervention nerve feedback experiments to be tested;
the electroencephalogram signal preprocessing module is used for preprocessing electroencephalogram signals;
the appetite characteristic extraction module is used for extracting appetite brain characteristics of the preprocessed electroencephalogram signals;
the appetite state identification module is used for obtaining the individual appetite state of the tested according to the appetite brain characteristics;
and the appetite state feedback module is used for feeding back the appetite craving degree of the tested individual in real time through visual signals according to the tested individual appetite state and performing iterative training intervention adjustment.
Preferably, the method further comprises: the personalized appetite model module is used for calculating and training a personalized appetite state identification model so as to support the online appetite state identification module.
Preferably, the electroencephalogram signal acquisition module sequentially divides and stores food clue prompts serving as events to acquire electroencephalogram signals which are induced by different foods to be tested.
Preferably, the preprocessing of the electroencephalogram signal preprocessing module includes: electrode positioning, re-referencing, signal multi-type filtering and electrooculogram removing processing to obtain the tested pure appetite electroencephalogram signal.
Preferably, the appetite brain features include: appetite related time-frequency domain brain electrical signal characteristics.
Preferably, the appetite state recognition module classifies appetite cravings by using a machine learning algorithm, and predicts the grade calibration of food cravings of the brain electrical characteristics in real time.
Preferably, the appetite state feedback module is used for calibrating the grade of the food craving degree to be corresponding to the stimulus materials of different feedback modes; the visual signal feedback materials are selected from a visual material library by a tested person according to personal preference, and are matched and corresponding to the food craving degree grade, and the visual signal feedback signals provide rewarding and punishing signals to guide the tested person to adjust the individual appetite craving degree.
The invention also provides an appetite intervention method based on the individualized brain electrical nerve feedback, which comprises the following steps:
collecting brain electrical signals in appetite intervention nerve feedback experiments;
preprocessing an electroencephalogram signal;
extracting appetite brain characteristics of the pretreated electroencephalogram signals;
obtaining the individual appetite state of the tested according to the characteristics of the appetite brain;
according to the individual appetite state of the tested person, the appetite craving degree of the tested person is fed back in real time through iterative training intervention adjustment by visual signals.
Preferably, the method further comprises: an individualized appetite state recognition model is calculated and trained to support on-line appetite state recognition.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. the invention builds an individual appetite recognition model, solves the defect of low nerve feedback regulation efficiency caused by neglecting individual physique difference of a single feedback signal, improves the treatment effect, simultaneously provides dynamic multidimensional physiological indexes to evaluate the change of the individual appetite brain state, reveals the appetite brain mechanism of the tested individual, and provides an effective scheme for the tested individual nerve feedback training.
2. According to the invention, the appetite feedback stimulation module is added, the individual food craving degree is quantized to a score between 0 and 1 based on an individual food craving degree model according to the real-time appetite state change of a user, and is combined with visual signals such as a histogram and the like to perform real-time feedback presentation, the abnormal brain characteristic dynamic change related to the appetite is regulated in a targeted manner through closed loop feedback stimulation, and the abnormal brain characteristic dynamic change is regulated in a noninvasive manner based on iterative training of an operational condition reflection and reinforcement learning mechanism, so that the craving degree of the tested food can be regulated to be normalized.
Drawings
For a clearer description of the technical solutions of the present invention, the drawings that are required to be used in the embodiments are briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that, without inventive effort, other drawings may be obtained by those skilled in the art according to the drawings:
FIG. 1 is a schematic diagram of an appetite intervention system based on individualized brain electrical nerve feedback according to an embodiment of the present invention;
fig. 2 is a diagram of an appetite status feedback module according to the present invention: the upper diagram is a control end interface of the appetite state feedback module and is used for monitoring the state of the tested electroencephalogram signals and the experimental process of the main test, and the lower diagram is a user end interface of the appetite state feedback module and is used for visualizing the appetite state of the tested and assisting the tested to conduct appetite regulation;
FIG. 3 is a flow chart of the closed loop real-time data processing of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Example 1:
as shown in fig. 1, an embodiment of the present invention provides an appetite intervention system based on individualized brain electrical nerve feedback, including:
the electroencephalogram signal acquisition module is used for acquiring electroencephalogram signals in appetite intervention nerve feedback experiments to be tested;
the electroencephalogram signal preprocessing module is used for preprocessing electroencephalogram signals;
the appetite characteristic extraction module is used for extracting appetite brain characteristics of the preprocessed electroencephalogram signals;
the appetite state identification module is used for obtaining the individual appetite state of the tested according to the appetite brain characteristics;
and the appetite state feedback module is used for feeding back the appetite craving degree of the tested individual in real time through visual signals according to the tested individual appetite state and performing iterative training intervention adjustment.
As an implementation of the embodiment of the present invention, further includes: the personalized appetite model module is used for calculating and training a personalized appetite state identification model so as to support the online appetite state identification module. Comprising three parts: a food clue response experiment, wherein the craving state of the tested food is induced by picture stimulation; multichannel electroencephalogram feature extraction, namely extracting appetite-related frequency spectrum features of induced electroencephalogram signals through preprocessing and feature extraction processes; building an individuation model, training the individuation appetite prediction model through a support vector machine classification algorithm, and classifying and quantifying real-time appetite states in the feedback intervention process
As one implementation mode of the embodiment of the invention, the electroencephalogram signal acquisition module sequentially divides and stores food clue prompts serving as events to acquire electroencephalogram signals which are tested to be induced by different foods.
As an implementation manner of the embodiment of the present invention, preprocessing of the electroencephalogram signal preprocessing module includes: electrode positioning, re-referencing, signal multi-type filtering and electrooculogram removing processing to obtain the tested pure appetite electroencephalogram signal.
As one implementation of the present embodiment, the appetite brain features include: appetite related time-frequency domain brain electrical signal characteristics.
As an implementation manner of the embodiment of the invention, the appetite state recognition module classifies appetite cravings by using a machine learning algorithm, and predicts the grade calibration of food cravings of the electroencephalogram characteristics in real time.
As an implementation manner of the embodiment of the invention, the appetite state feedback module is used for calibrating the grade of the food craving degree to correspond to the stimulus materials of different feedback modes; the visual signal feedback materials are selected from a visual material library by a tested person according to personal preference, and are matched and corresponding to the food craving degree level, and the visual signal feedback materials provide rewarding and punishing signals to guide the tested person to adjust the individual appetite craving degree, so that the non-invasive intervention of poor eating habits is realized.
The individualized appetite intervention system based on the brain electrical nerve feedback provided by the embodiment of the invention can be used for intervention of bad eating habits, and has potential clinical value and social value.
Example 2:
as shown in fig. 1, an embodiment of the present invention provides an appetite intervention system based on individualized brain electrical nerve feedback, including:
the electroencephalogram signal acquisition module is used for acquiring multichannel electroencephalograms in appetite intervention nerve feedback experiments of the tested person, sequentially dividing and storing food clue prompts serving as events, acquiring electroencephalograms signals of the tested person, which are induced by different foods, and using the electroencephalograms signals as a follow-up electroencephalogram signal preprocessing module;
the electroencephalogram signal preprocessing module is used for preprocessing original electroencephalogram signals, including noise processing such as electrode positioning, re-referencing, signal multi-type filtering, electro-oculogram removing and the like, and acquiring the tested pure appetite electroencephalogram signals for the use of the follow-up appetite brain characteristic extraction module;
the appetite characteristic extraction module is used for extracting real-time characteristics of individual appetite related electroencephalogram signals in real time, including time-frequency domain electroencephalogram signal characteristics related to appetite and the like, and the appetite brain characteristics are used as input of an individual appetite quantification model and used for the use of the subsequent appetite state identification module;
the appetite state recognition module is used for calculating the individual appetite state of the tested in real time, classifying the appetite craving degree by utilizing an individual appetite recognition model trained under the normal of machine learning calculation, predicting the grade calibration of the food craving degree of the brain electrical characteristics in real time, and using the subsequent appetite state feedback module;
the appetite state feedback module is used for feeding back the appetite craving degree of the tested individual in real time through iterative training intervention adjustment, and the grade calibration of the food craving degree corresponds to the stimulation materials of different feedback modes. The visual signal feedback materials are selected from a visual material library by a tested according to personal preference, and are matched and corresponding to the food craving degree grades, and a reward and punishment feedback signal is provided to guide the tested individual appetite craving degree adjustment, so that the non-invasive intervention of poor eating habits is realized;
the personalized appetite model module is used for calculating and training a personalized appetite state recognition model and supporting an on-line appetite state recognition module, and comprises three parts: a food clue response experiment, wherein the craving state of the tested food is induced by picture stimulation; multichannel electroencephalogram feature extraction, namely extracting appetite-related frequency spectrum features of induced electroencephalogram signals through preprocessing and feature extraction processes; and constructing an individuation model, and training the individuation appetite prediction model through a support vector machine classification algorithm for classifying and quantifying the real-time appetite state in the feedback intervention process.
Further, the personalized appetite intervention system implementation comprises 4 modules on-line and 1 off-line module, wherein:
the brain electrical signal acquisition module acquires 32 channel signals in the process of appetite intervention nerve feedback experiments to be tested at a sampling rate of 1000Hz, and the brain electrical signal acquisition module comprises: fp1, fz, F3, F7, FT9, FC5, FC1, C3, T7, CP5, CP1, PZ, P3, P7, O1, oz, O2, P4, P8, TP10, CP6, CP2, cz, C4, T8, FT10, FC6, FC2, F4, F8, fp2 and TP9 channels of electroencephalogram signals are connected with an individualized appetite intervention system through a parallel port line of an electroencephalogram acquisition device, the acquired electroencephalogram signals are stored in a memory, and each 2 seconds of data are used as a segment of electroencephalogram signal for subsequent electroencephalogram data processing.
Furthermore, the electroencephalogram signal preprocessing module carries out real-time preprocessing on the acquired multichannel electroencephalogram signals, TP9 and TP10 channels (mastoid electrodes behind two side ears) in 32 channels are selected as reference electrodes, noises such as 50Hz power frequency interference and the like are removed through band-pass filtering of an infinite-length unit impulse response filter (IIR filter) of 0.5-45Hz, a frequency band of the electroencephalogram signals required by main analysis is reserved, data correction is further carried out on the data through a pseudo shadow space reconstruction method (Artifact Subspace Reconstruction, ASR), and the interference of myoelectricity, oculogram electricity and other artifacts is removed, so that cleaner electroencephalogram signals are obtained. The ASR principle relies primarily on principal component analysis (Principal Components Analysis, PCA), using a sliding window in combination to interpolate high variance signal components that exceed a threshold relative to the covariance of the calibration dataset. Each affected EEG time point is then linearly reconstructed from the remaining signal subspace according to the correlation structure observed in the calibration data, see equation (1).
Wherein S is clean Is the processed signal, S is the input signal, V is the eigenvector of the covariance matrix of the calibration data, and M is the geometric median square root of the covariance matrix. This process involves Moore-Penrose pseudo-inversion, signedAnd (3) representing.
Furthermore, the appetite characteristic extraction module extracts the appetite brain characteristics of the pure electroencephalogram signal fragments related to appetite obtained by the electroencephalogram signal preprocessing module, and can invoke the personalized appetite recognition model constructed by the off-line module to realize classification and quantification of the appetite (food craving degree) of the current electroencephalogram signal fragments. The power spectrum density of the frequency domain energy information of the characteristic brain electrical signals is selected as appetite classification and identification characteristics. Power spectral density (Power spectral density, PSD) characteristics, in particular, 5 frequency bands of interest (Frequency of interest, FOI) were calculated using the whole brain 30 brain electrical channels: delta band (1-3 Hz), theta band (4-7 Hz), alpha band (8-13 Hz), beta band (14-30 Hz), gamma band (31-45 Hz). The specific calculation method of the power spectral density characteristic is based on a welch method of a correction periodic chart to carry out classical power spectral density estimation operation: brain of each channelThe electrical signal is passed through a non-overlapping hanning window of a window length of 2 seconds for a specified number of seconds, and the power spectral density characteristics are calculated using a short-time fourier transform and averaged. Let the length N data x (N), n=0, 1, …, N-1, each segment having M data, the i-th segment data can be expressed as: x is x i (n) =x (n+im-M), 0.ltoreq.n.ltoreq.m, 1.ltoreq.i.ltoreq.l, and then a window function w (n) is added to each segment of data to find the periodic chart of each segment, the periodic chart of the i-th segment can be expressed as formula (2). In equation (3), U is called a normalization factor, and the periodic patterns of each segment are approximately regarded as being uncorrelated with each other, and the final power spectral density can be estimated as equation (4). The power spectral density calculation is implemented by utilizing a pwelch function in MATLAB, wherein window refers to a selected window function type, novelap refers to a segment length (window length), and NFFT refers to the number of FFT data points. Aiming at multichannel appetite related electroencephalogram signals acquired in real time in a feedback experiment process, 2s is used as a step-length sliding window, data are divided into a plurality of data segments (segments), the number of channels of the electroencephalogram signals is recorded as channels, and power spectrum density characteristics of five sub-frequency bands are obtained through calculation of each Segment. And finally, the sample PSD is integrated into a feature matrix with dimension of segment multiplied by channel multiplied by 5, and the matrix is used as a feature to be input into a machine learning model for training a subsequent online individuation model.
Wherein M is the number of data points of each piece of data, and x i (n) is the I-th segment of the processed data, w (n) is the selected window function, the selected window function type of the invention is Hanning window, I i Is a periodic chart of the ith section of data, U is a normalization factor, P xx Is the power spectral density.
Further, the appetite state recognition module performs appetite recognition and quantification on the feature matrix with the dimension of segment multiplied by 30 multiplied by 5 obtained through the frequency spectrum feature extraction module. Firstly, the acquired multi-channel electroencephalogram data of a tested are utilized in the relevant stage of an on-line food cue reaction experiment, the power spectrum density of the whole brain 30 channels is obtained through preprocessing and feature extraction, then the power spectrum density matrix is used as input data, an on-line individualized appetite recognition model is trained by utilizing a LIBSVM tool box svmtrain function in MATLAB, and model parameters are output to default to obtain model decision value data: taking the median of the array as a first reference value and the ninety-five percentile as a second reference value, and taking the median as a reference to quantify the craving degree score of the tested food in the real-time feedback process. And (3) utilizing an off-line individualized appetite recognition model trained based on each tested data to perform appetite recognition and quantification in a real-time recognition feedback module. And acquiring and storing brain electrical data fragments every 2 seconds, obtaining a power spectrum density characteristic matrix representing appetite information through preprocessing and calculating by a characteristic extraction module, inputting the power spectrum density characteristic matrix into a personalized model, and quantifying the appetite state and normalizing the power spectrum density characteristic matrix to a score between 0 and 1.
Further, the appetite state feedback module is mainly implemented through an independently developed high-compatibility data real-time processing platform, and comprises food picture stimulation material presentation and appetite real-time feedback stimulation, wherein: the food picture stimulation material presentation module is used for presenting a picture stimulation area of an appetite intervention nerve feedback experimental program to a user on a display screen, and in the process of appetite nerve feedback, the appetite state is updated once every 2 seconds in a picture and columnar graph mode, and the tested person suppresses the desire of the user for food according to the previous food desire state adjustment strategy and learns and controls the brain activities of appetite. After the nerve feedback experiment is finished, the tested person obtains the preset rest time, the rest is completed, and the tested person can start to carry out the nerve feedback experiment task of the next test time through any key; the appetite real-time feedback stimulation module is used for presenting feedback information and stimulation materials in the nerve feedback training process based on the brain electrical signals to a tested, feeding back food craving degree (0 to 1 and step length 0.2) to the tested in a columnar graph mode, and enabling the platform to call the picture materials corresponding to the craving value to stimulate the tested.
The embodiment provides an appetite intervention system based on individualized brain nerve feedback, which is a depression detection system developed by using QML, C++, javaScript and MATLAB languages and running on a device provided with a Windows system, and comprises: the system comprises an electroencephalogram signal acquisition module, an electroencephalogram signal preprocessing module, an appetite characteristic extraction module, an appetite state recognition module and an appetite state feedback module, wherein the individualized appetite recognition module is realized through three functions of an offline food clue reaction experiment, multichannel electroencephalogram signal acquisition and individualized model construction and is used for supporting the invoking of the individualized SVM classification model and the calculation of a real-time feedback value in the appetite state recognition module in the online module.
Referring to fig. 2, the appetite state feedback module includes a control end and a user end. The control end is realized by QML, C++ and JavaScript based on Qt 5. MatlabEngine components and MatlabScript components are implemented in the experimental part program. The MatlabEngine is responsible for connecting with a MATLAB end sharing engine, and the MatlabScript is responsible for calling an encapsulated individual appetite state model in a program catalog, calculating the acquired electroencephalogram signal fragments in real time and outputting a real-time feedback value to represent food craving degree. The user side is used for presenting the craving degree of the tested food and the feedback stimulation picture correspondingly matched with the craving degree, namely the visual appetite electroencephalogram characteristics, so that the tested understanding and the nerve feedback experiment can be facilitated.
The electroencephalogram signal acquisition module is used for acquiring electroencephalogram signals of a tested person in the process of performing an electroencephalogram appetite nerve feedback experiment, recording cortex electroencephalogram signals by adopting an electroencephalogram amplifier and an EEG electroencephalogram cap with 32 channels, transmitting data to a computer through a parallel port line interface, and storing the electroencephalogram signals as an electroencephalogram signal segment once every 2 seconds for processing by the subsequent electroencephalogram signal preprocessing module. Before the electroencephalogram starts from the beginning of a nerve feedback experiment, the electroencephalogram acquisition process needs to carry out the following preparation work: the tested EEG is firstly seated in front of a display presenting a graphical user interface, the distance between the tested EEG and the display is 50-60cm, the height of the tested EEG is displayed to be adjusted to a head-up level, the tested EEG dry electrode cap is worn, 32-channel EEG electrode caps and amplifiers with national standard 10-20 produced by BrainProducts are used for collecting EEG signals, the EEG signals of all channels are referenced by bilateral post-auricular mastoid electrodes TP9 and TP10, and before the EEG signals are collected, the frosting paste is smeared at the contact position of each electrode and scalp, the impedance value of the electrode is reduced to be below 15 kiloohms, and the EEG signals are set to be sampled at the frequency of 1000 Hz.
The electroencephalogram signal preprocessing module reads the electroencephalogram signal fragments stored by the electroencephalogram signal acquisition module every 2 seconds, performs 0.5-45Hz band-pass filtering on the electroencephalogram signal fragments to remove high-frequency noise and power frequency interference, and ASR correction is used for removing physical motion noise such as electrooculogram, myoelectricity and the like so as to improve the signal-to-noise ratio of the electroencephalogram signals, and invokes the appetite characteristic extraction module after preprocessing is completed.
The appetite characteristic extraction module extracts full brain power spectral density of the pure brain electrical signal fragments obtained by the brain electrical signal preprocessing module to obtain appetite related characteristics of the brain electrical signal fragments, and specifically, calculates 5 FOIs by using 30 brain electrical channels of the whole brain: delta band (1-3 Hz), theta band (4-7 Hz), alpha band (8-13 Hz), beta band (14-30 Hz), gamma band (31-45 Hz). The specific calculation method of the power spectral density characteristic is based on a welch method of a correction periodic chart to carry out classical power spectral density estimation operation: the brain electrical signal of each channel is passed through a non-overlapping hanning window of a window length of 2 seconds for a specific number of seconds, and the power spectral density characteristics are calculated and averaged using a short-time fourier transform. And calling the appetite real-time identification and quantization module after the feature extraction module finishes processing.
The appetite status recognition module is implemented based on the personalized appetite model provided by the offline module. Firstly, the acquired multi-channel electroencephalogram data to be tested is utilized in the relevant stage of a food clue reaction experiment, the power spectrum density of the whole brain 30 channels is obtained through preprocessing and feature extraction, then the power spectrum density matrix is used as input data, a LIBSVM tool kit svmtrain function in MATLAB is utilized to train an under-line personalized appetite recognition model, and model parameters are output to default to obtain model decision value data: taking the median of the array as a first reference value and the ninety-five percentile as a second reference value, and taking the median as a reference to quantify the craving degree score of the tested food in the real-time feedback process. And utilizing an off-line individualized appetite recognition model trained based on each tested data to perform appetite recognition and quantification by the appetite state recognition module.
The appetite state feedback module is used for presenting an appetite state feedback area of an appetite nerve feedback experimental program calculated based on the electroencephalogram to a tested on a display screen, feeding back food craving degree to the tested in the form of a score between 0 and 1 in the appetite feedback area according to the appetite real-time feedback result obtained by the appetite real-time identification and quantization module, and presenting the food craving degree in real time by a bar graph. Each experimental test time (trail) is 2 seconds, the 1 st second is used for calculating the matching result (food craving degree) of the current brain electricity of the tested person and the individuation model, and the 2 nd second feeds back the food craving degree to the tested person in a fractional form and presents the food craving degree in a columnar graph form in real time; the next trail picture stimulus was presented as feedback information from one of the pre-selected 3 food pictures prior to the feedback trial. After each round of experiment is finished, the graphic user interface displays a training result summary, including information such as average food craving degree, task success rate and the like in the experiment, and visual information is presented. To improve the personalized feedback effect, before the neurofeedback experiment starts, the user needs to select 3 photos (high/medium/low craving degree) corresponding to different food craving degrees of the individual from the established 150 food pictures containing various foods, so as to randomly display the photos in the feedback module. During the process of appetite nerve feedback, the test needs to watch randomly presented food picture stimulation materials in a specified time, and during the period, the test needs to adjust the appetite state (the craving degree score of food) so as to reduce the appetite as much as possible. After the picture is subjected to the nerve feedback experiment every time, the picture is tested to obtain the preset rest time for 2 minutes, the rest is completed, and the tested person can start to carry out the nerve feedback experiment task of the next test time through any key.
In conclusion, compared with other obesity intervention means, the system disclosed by the invention is used for improving poor eating habits and regulating brain functions of obese people by designing appetite intervention nerve feedback based on brain electrical signals, provides a potential objective and effective means for mechanism exploration of obese people, and provides a novel brain-computer interaction treatment means with noninvasive and lasting effects. In addition, the system builds an individual appetite recognition model based on the tested electroencephalogram signals, can overcome the defect of low regulation efficiency caused by neglecting individual differences of single feedback signals, improves treatment effects, provides dynamic physiological indexes to objectively evaluate the change of the appetite state of an individual, checks nerve feedback training effects, and helps the tested to feed back the current appetite state in real time, so that the tested appetite state is objectively and accurately reflected. In a word, the invention designs an individual appetite intervention system based on an electroencephalogram appetite neural feedback signal, which has potential clinical value and social value, and is particularly aimed at the unhealthy problem of obese people caused by abnormal appetite regulation.
Example 3:
the embodiment of the invention also provides an appetite intervention method based on the individualized brain electrical nerve feedback, which comprises the following steps:
collecting brain electrical signals in appetite intervention nerve feedback experiments;
preprocessing an electroencephalogram signal;
extracting appetite brain characteristics of the pretreated electroencephalogram signals;
obtaining the individual appetite state of the tested according to the characteristics of the appetite brain;
according to the individual appetite state of the tested person, the appetite craving degree of the tested person is fed back in real time through iterative training intervention adjustment by visual signals.
As an implementation of the embodiment of the present invention, further includes: an individualized appetite state recognition model is calculated and trained to support on-line appetite state recognition.
Example 4:
as shown in fig. 3, an embodiment of the present invention provides an appetite intervention method based on individualized brain electrical nerve feedback, a closed-loop real-time data processing flow, including:
collecting tested brain electrical signals induced by feedback stimulation of different modes;
taking 2 seconds of data after the stimulus trigger point, correcting by using ASR according to FIR filtering, and referring again to perform preprocessing;
calculating the frequency domain PSD characteristics of the preprocessed electroencephalogram signals, and inputting the frequency domain PSD characteristics into an individual recognition quantization model to obtain appetite quantization coefficients;
and presenting feedback stimulus according to the video, the picture and the musical material matched with the quantization coefficients.
The above embodiments are merely illustrative of the preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, but various modifications and improvements made by those skilled in the art to which the present invention pertains are made without departing from the spirit of the present invention, and all modifications and improvements fall within the scope of the present invention as defined in the appended claims.
Claims (3)
1. An appetite intervention system based on individualized brain electrical nerve feedback, comprising:
the electroencephalogram signal acquisition module is used for acquiring electroencephalogram signals in appetite intervention nerve feedback experiments to be tested;
the electroencephalogram signal preprocessing module is used for preprocessing electroencephalogram signals;
the appetite characteristic extraction module is used for extracting appetite brain characteristics of the preprocessed electroencephalogram signals;
the appetite state identification module is used for obtaining the individual appetite state of the tested according to the appetite brain characteristics;
the appetite state feedback module is used for feeding back the appetite craving degree of the tested individual in real time through visual signals according to the tested individual appetite state and performing iterative training intervention adjustment;
the appetite state recognition module classifies appetite craving degrees by utilizing a machine learning algorithm, and predicts the grade calibration of food craving degrees of brain electrical characteristics in real time;
the appetite state feedback module is used for calibrating the grade of the food craving degree to correspond to the stimulus materials of different feedback modes; the visual signal feedback materials are selected from a visual material library by a tested person according to personal preference, and are matched and corresponding to the food craving degree grade, and a reward and punishment feedback signal is provided for guiding the tested person to adjust the individual appetite craving degree;
further comprises: the personalized appetite model module is used for calculating and training a personalized appetite state identification model so as to support the online appetite state identification module;
the electroencephalogram signal acquisition module sequentially divides and stores food clue prompts serving as events to acquire electroencephalogram signals which are tested to be induced by different foods;
the preprocessing of the electroencephalogram signal preprocessing module comprises the following steps: electrode positioning, re-referencing, signal multi-type filtering and electrooculogram removing processing to obtain the tested pure appetite electroencephalogram signals;
the appetite brain features include: appetite related time-frequency domain brain electrical signal characteristics.
2. A method for implementing an individualized brain electrical nerve feedback based appetite intervention using the individualized brain electrical nerve feedback based appetite intervention system of claim 1, comprising:
collecting brain electrical signals in appetite intervention nerve feedback experiments;
preprocessing an electroencephalogram signal;
extracting appetite brain characteristics of the pretreated electroencephalogram signals;
obtaining the individual appetite state of the tested according to the characteristics of the appetite brain;
according to the individual appetite state of the tested person, the appetite craving degree of the tested person is fed back in real time through iterative training intervention adjustment by visual signals.
3. The method of appetite intervention based on individualized brain nerve feedback of claim 2, further comprising: an individualized appetite state recognition model is calculated and trained to support on-line appetite state recognition.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311063825.3A CN116999072B (en) | 2023-08-23 | 2023-08-23 | Appetite intervention system and method based on individualized brain electrical nerve feedback |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311063825.3A CN116999072B (en) | 2023-08-23 | 2023-08-23 | Appetite intervention system and method based on individualized brain electrical nerve feedback |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116999072A CN116999072A (en) | 2023-11-07 |
CN116999072B true CN116999072B (en) | 2024-02-27 |
Family
ID=88563502
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311063825.3A Active CN116999072B (en) | 2023-08-23 | 2023-08-23 | Appetite intervention system and method based on individualized brain electrical nerve feedback |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116999072B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101300045A (en) * | 2005-07-29 | 2008-11-05 | 赛博罗尼克斯公司 | Selective nerve stimulation for the treatment of eating disorders |
CN108271363A (en) * | 2015-02-24 | 2018-07-10 | 伊莱拉股份有限公司 | Use the system and method for the sturdy existing Appetite regulation of electrode-skin and/or improvement compliance of dietary treatment |
CN110772266A (en) * | 2019-10-15 | 2020-02-11 | 西安电子科技大学 | Method for regulating cognitive ability through real-time nerve feedback based on fNIRS |
CN111466908A (en) * | 2020-04-09 | 2020-07-31 | 瘦声(杭州)科技有限公司 | Method for screening audio capable of affecting appetite by utilizing EEG (electroencephalogram) |
CN116139403A (en) * | 2023-04-18 | 2023-05-23 | 中国科学技术大学先进技术研究院 | Control method of transcranial electric stimulation device and transcranial electric stimulation device |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20130018099A (en) * | 2011-08-12 | 2013-02-20 | 한국전자통신연구원 | Apparatus and method for generating of brain wave suppress the appetite for diet |
WO2020021542A1 (en) * | 2018-07-22 | 2020-01-30 | Tal Fass Michal | Means and methods for personalized behavioral health assessment system and treatment |
-
2023
- 2023-08-23 CN CN202311063825.3A patent/CN116999072B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101300045A (en) * | 2005-07-29 | 2008-11-05 | 赛博罗尼克斯公司 | Selective nerve stimulation for the treatment of eating disorders |
CN108271363A (en) * | 2015-02-24 | 2018-07-10 | 伊莱拉股份有限公司 | Use the system and method for the sturdy existing Appetite regulation of electrode-skin and/or improvement compliance of dietary treatment |
CN110772266A (en) * | 2019-10-15 | 2020-02-11 | 西安电子科技大学 | Method for regulating cognitive ability through real-time nerve feedback based on fNIRS |
CN111466908A (en) * | 2020-04-09 | 2020-07-31 | 瘦声(杭州)科技有限公司 | Method for screening audio capable of affecting appetite by utilizing EEG (electroencephalogram) |
CN116139403A (en) * | 2023-04-18 | 2023-05-23 | 中国科学技术大学先进技术研究院 | Control method of transcranial electric stimulation device and transcranial electric stimulation device |
Also Published As
Publication number | Publication date |
---|---|
CN116999072A (en) | 2023-11-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111477299B (en) | Method and device for regulating and controlling sound-electricity stimulation nerves by combining electroencephalogram detection and analysis control | |
Vos et al. | Removal of muscle artifacts from EEG recordings of spoken language production | |
US9999743B2 (en) | Sound-induced sleep method and a system therefor | |
Bidelman | Towards an optimal paradigm for simultaneously recording cortical and brainstem auditory evoked potentials | |
US20160029946A1 (en) | Wavelet analysis in neuro diagnostics | |
CN111110230A (en) | Motor imagery electroencephalogram feature enhancement method and system | |
Sarma et al. | Pre-processing and feature extraction techniques for EEGBCI applications-a review of recent research | |
CN113143293B (en) | Continuous speech envelope nerve entrainment extraction method based on electroencephalogram source imaging | |
Islam et al. | Probability mapping based artifact detection and removal from single-channel EEG signals for brain–computer interface applications | |
Kanoh et al. | A brain-computer interface (BCI) system based on auditory stream segregation | |
CN112426162A (en) | Fatigue detection method based on electroencephalogram signal rhythm entropy | |
CN101052346A (en) | Neural incident process | |
Paulraj et al. | A machine learning approach for distinguishing hearing perception level using auditory evoked potentials | |
Kittilstved et al. | The effects of fluency enhancing conditions on sensorimotor control of speech in typically fluent speakers: an EEG mu rhythm study | |
Islam et al. | Probability mapping based artifact detection and wavelet denoising based artifact removal from scalp EEG for BCI applications | |
CN116999072B (en) | Appetite intervention system and method based on individualized brain electrical nerve feedback | |
CN112861625A (en) | Method for determining stacking denoising autoencoder model | |
Omar et al. | Assessment of acute ischemic stroke brainwave using Relative Power Ratio | |
Yu et al. | Effect of excessive Internet use on the time–frequency characteristic of EEG | |
CN116870360A (en) | Evaluation method of transcranial electrical stimulation effect | |
CN115192907A (en) | Real-time biofeedback percutaneous vagus nerve electronic acupuncture device | |
CN110613446A (en) | Signal processing method and device | |
CN115227263A (en) | Neural stimulation system based on EEG signal theta oscillation regulation and control | |
Gupta et al. | Statistical feature based comparison of EEG in meditation for various wavelet | |
CN115299960A (en) | Electric signal decomposition method and electroencephalogram signal decomposition device based on short-time varying separate modal decomposition |
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 | ||
GR01 | Patent grant |