CN111466908B - Method for screening audio capable of affecting appetite by utilizing EEG (electroencephalogram) - Google Patents
Method for screening audio capable of affecting appetite by utilizing EEG (electroencephalogram) Download PDFInfo
- Publication number
- CN111466908B CN111466908B CN202010276095.5A CN202010276095A CN111466908B CN 111466908 B CN111466908 B CN 111466908B CN 202010276095 A CN202010276095 A CN 202010276095A CN 111466908 B CN111466908 B CN 111466908B
- Authority
- CN
- China
- Prior art keywords
- audio
- appetite
- testee
- electroencephalogram
- time
- 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
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—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
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
- A61M2021/0005—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus
- A61M2021/0027—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus by the hearing sense
Abstract
The invention discloses a method for screening audio capable of affecting appetite by utilizing EEG. The invention screens out the audio frequency which can influence the appetite by analyzing the EEG generated when listening to the audio frequency, and has good creativity; through the analysis of the first LSTM neural network on the EEG, the trouble of acquiring the appetite data of the test object is avoided when the second LSTM neural network is trained, the brain waves of the test object can be directly acquired and put into the first LSTM neural network for analysis to obtain the appetite data of the test object, the speed of generating the training data of the second LSTM neural network is greatly increased, and the efficiency of influencing the appetite audio screening is improved; compared with the method for suppressing the appetite by using the medicines, the method has extremely high safety, a person to be tested does not need to take any medicines which can cause harm, the person only needs to listen to music to play a certain effect of suppressing the appetite, and the cost is lower when the method is used compared with the method for suppressing the appetite by using the medicines.
Description
Technical Field
The invention relates to the field related to EEG detection technology, in particular to a method for screening audios capable of affecting appetite by utilizing EEG.
Background
The existing methods for controlling appetite physiologically generally comprise two methods, namely drug control. Such as fenfluramine, which acts on the brain feeding center to suppress appetite. But it causes heart valve damage and pulmonary hypertension, depression, nausea, dizziness and sleepiness. There were several fatal medical events, which were released in 1997. Yet another is aversion therapy. The conditioned reflex method is adopted, and target behaviors needing to be abstained are combined with unpleasant or punitive stimulation, so that the target behaviors are removed from the attractiveness of the patient through aversive conditioned reflex, and symptoms are removed. Such as shock, by creating a penalty feedback on appetite, thereby reducing appetite. This method causes intense discomfort to the person.
It is now known that a variety of behaviors can affect appetite in different situations. Such as satiety, and watching a picture of nausea, smelling a flavor of a favorite food, etc. The existing scholars screen the audio capable of suppressing the appetite by analyzing the audio bpm and judging whether the bpm is more than 140, but the problems of low precision and poor effect exist.
To this end, we propose a method for screening for appetites-affecting audio using EEG.
Disclosure of Invention
The present invention is directed to a method for screening audio frequency capable of affecting appetite by using EEG, so as to solve the problems mentioned in the background art.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method of screening for appetite-affecting audio using EEG, comprising the steps of:
s1, a testee wears an electroencephalogram acquisition instrument to acquire electroencephalogram data in real time, time slicing is switched once at fixed time, the testee randomly watches different food pictures on different time slices, the testee scores food eating desire in the pictures according to the testee, then the electroencephalogram sequence signals of each slice are used as input of an LSTM network, the scores are used as corresponding labels, and the accuracy of the predicted score of the LSTM network is continuously improved through training;
s2, constructing a new LSTM model, enabling a testee to wear an electroencephalogram acquisition instrument to acquire electroencephalogram data in real time, enabling the testee to listen to sounds with different frequencies and rhythms in the process, similarly switching a time slice at a fixed time, playing different audios in different time slices, and enabling the audios in the same time slice to correspond to the acquired electroencephalograms one by one, wherein electroencephalogram signals are input into the model in the first step as a label, the audio signals are input into the new LSTM model, the label is an output result of the electroencephalogram signals input into the model in the first step, and the new LSTM model is obtained through training, wherein the input is a section of audio, and the output is a guess of an appetite signal of the user;
s3, the testee wearing the earphone switches a time slice at a fixed time, different audio is played in different time slices, and the played audio is divided into two types, one type is the audio randomly screened from a large amount of open source audio, the other type is the audio with low score obtained in the model of the second step, the two types of audio are randomly played in different time slices, and meanwhile, the testee is allowed to score a picture of random food in each time slice according to the eating desire.
Preferably, the score value ranges from one to ten minutes, one representing the worst desire to eat and one representing the strongest desire to eat.
Preferably, the frequency of the switching time slices is one time slice of five seconds.
Preferably, the electroencephalogram signal is input at a sampling rate of 200Hz or more.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention screens out the audio frequency which can influence the appetite by analyzing the EEG generated when listening to the audio frequency, and has good creativity;
2. through the analysis of the first LSTM neural network on the EEG, the trouble of acquiring the appetite data of the test object is avoided when the second LSTM neural network is trained, the brain waves of the test object can be directly acquired and put into the first LSTM neural network for analysis to obtain the appetite data of the test object, the speed of generating the training data of the second LSTM neural network is greatly increased, and the efficiency of influencing the appetite audio screening is improved;
3. compared with the method for suppressing the appetite by using the medicines, the method has extremely high safety, a person to be tested does not need to take any medicines which can cause harm, the person only needs to listen to music to play a certain effect of suppressing the appetite, and the cost is lower when the method is used compared with the method for suppressing the appetite by using the medicines.
Drawings
FIG. 1 is a flow chart of the method for screening an audio frequency affecting appetite using EEG according to the present invention, wherein an EEG signal is introduced into an LSTM neural network for training;
FIG. 2 is a flow chart of training using a large number of open source audios imported into an LSTM neural network in a method for screening appetite-affecting audios using EEG according to the present invention;
FIG. 3 is a table comparing the impact of random audio and suppressing the appetite audio on appetite in a method of using EEG to screen for appetite-influenceable audio according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
1-3, the present invention also provides a method for screening audio capable of affecting appetite using EEG, comprising the following steps:
s1, a testee wears an electroencephalogram acquisition instrument to acquire electroencephalogram data in real time, time slicing is switched once at fixed time, the testee randomly watches different food pictures on different time slices, the testee scores food eating desire in the pictures according to the testee, then the electroencephalogram sequence signals of each slice are used as input of an LSTM network, the scores are used as corresponding labels, and the accuracy of the predicted score of the LSTM network is continuously improved through training;
s2, constructing a new LSTM model, enabling a testee to wear an electroencephalogram acquisition instrument to acquire electroencephalogram data in real time, enabling the testee to listen to sounds with different frequencies and rhythms in the process, similarly switching a time slice at a fixed time, playing different audios in different time slices, and enabling the audios in the same time slice to correspond to the acquired electroencephalograms one by one, wherein electroencephalogram signals are input into the model in the first step as a label, the audio signals are input into the new LSTM model, the label is an output result of the electroencephalogram signals input into the model in the first step, and the new LSTM model is obtained through training, wherein the input is a section of audio, and the output is a guess of an appetite signal of the user;
s3, the testee wearing the earphone switches a time slice at a fixed time, different audio is played in different time slices, and the played audio is divided into two types, one type is the audio randomly screened from a large amount of open source audio, the other type is the audio with low score obtained in the model of the second step, the two types of audio are randomly played in different time slices, and meanwhile, the testee is allowed to score a picture of random food in each time slice according to the eating desire.
Further, the score value ranges from one to ten minutes, one representing the worst desire to eat and one representing the strongest desire to eat.
Further, the frequency of the switching time slice is five seconds and one time slice.
Further, the electroencephalogram signal is input at a sampling rate of 200Hz or more.
In the invention, two LSTM neural networks are established, wherein in the first LSTM neural network, the input of training data is EEG, and the output of the training data is appetite; in the second LSTM neural network, the training result of the first LSTM neural network is used, the input of the training data is audio, and the output of the training data is the output generated by inputting the electroencephalogram signals generated by the test object when listening to the current audio into the first LSTM neural network, namely, the appetite. Through the analysis of the EEG by the first LSTM neural network, the trouble of acquiring the appetite data of the test object is avoided when the second LSTM neural network is trained, the brain waves of the test object can be directly acquired and put into the first LSTM neural network for analysis to obtain the appetite data of the test object, the speed of generating the training data of the second LSTM neural network is greatly increased, and after the two LSTM neural networks are fully trained (reach enough accuracy), only a large amount of audio needs to be randomly generated and input into the second LSTM neural network, and the predicted influence of the current audio on the appetite is obtained. Then, based on the predicted effect of the current audio on appetite, the more appetite suppressing audio can be selected from the randomly generated plurality of audio. Compared with the method for suppressing the appetite by using the medicines, the method has extremely high safety, and a testee can play a certain effect of suppressing the appetite by only listening to music without taking any medicines which can cause harm. Compared with the method for suppressing the appetite by using medicines, the method has the advantages that the cost is lower, in addition, the method screens out the audios capable of influencing the appetite by analyzing the EEG generated when the audios are listened, the creativity is good, meanwhile, the method not only can be applied to screening the audios influencing the appetite, but also can be used for screening other physiological signals capable of reflecting the appetite of people, and the applicability is good.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (4)
1. A method for screening appetite-affecting audio using EEG, comprising the steps of:
s1, a testee wears an electroencephalogram acquisition instrument to acquire electroencephalogram data in real time, time slicing is switched once at fixed time, the testee randomly watches different food pictures on different time slices, the testee scores food eating desire in the pictures according to the testee, then the electroencephalogram sequence signals of each slice are used as input of an LSTM network, the scores are used as corresponding labels, and the accuracy of the predicted score of the LSTM network is continuously improved through training;
s2, constructing a new LSTM model, enabling a testee to wear an electroencephalogram acquisition instrument to acquire electroencephalogram data in real time, enabling the testee to listen to sounds with different frequencies and rhythms in the process, similarly switching a time slice at a fixed time, playing different audios in different time slices, and enabling the audios in the same time slice to correspond to the acquired electroencephalograms one by one, wherein electroencephalogram signals are input into the model in the first step as a label, the audio signals are input into the new LSTM model, the label is an output result of the electroencephalogram signals input into the model in the first step, and the new LSTM model is obtained through training, wherein the input is a section of audio, and the output is a guess of an appetite signal of the user;
s3, the testee wearing the earphone switches a time slice at a fixed time, different audio is played in different time slices, and the played audio is divided into two types, one type is the audio randomly screened from a large amount of open source audio, the other type is the audio with low score obtained in the model of the second step, the two types of audio are randomly played in different time slices, and meanwhile, the testee is allowed to score a picture of random food in each time slice according to the eating desire.
2. The method of claim 1 wherein the score values range from one to ten minutes, one being the worst desire to eat and one being the strongest desire to eat.
3. The method of claim 1, wherein the switching time slices are at a frequency of five seconds and one time slice.
4. The method of claim 1, wherein the EEG signal is input at a sampling rate of 200Hz or higher.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010276095.5A CN111466908B (en) | 2020-04-09 | 2020-04-09 | Method for screening audio capable of affecting appetite by utilizing EEG (electroencephalogram) |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010276095.5A CN111466908B (en) | 2020-04-09 | 2020-04-09 | Method for screening audio capable of affecting appetite by utilizing EEG (electroencephalogram) |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111466908A CN111466908A (en) | 2020-07-31 |
| CN111466908B true CN111466908B (en) | 2022-08-09 |
Family
ID=71751416
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010276095.5A Active CN111466908B (en) | 2020-04-09 | 2020-04-09 | Method for screening audio capable of affecting appetite by utilizing EEG (electroencephalogram) |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111466908B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116999072B (en) * | 2023-08-23 | 2024-02-27 | 北京理工大学 | Appetite intervention system and method based on individualized brain electrical nerve feedback |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08112182A (en) * | 1994-10-13 | 1996-05-07 | Royal Kogyo Kk | Tableware having vocal function |
| CN103370703A (en) * | 2010-03-08 | 2013-10-23 | 健康看护股份有限公司 | Method and apparatus to monitor, analyze and optimize physiological state of nutrition |
| CN107438398A (en) * | 2015-01-06 | 2017-12-05 | 大卫·伯顿 | Portable wearable monitoring system |
| US10874708B2 (en) * | 2017-01-10 | 2020-12-29 | Nektium Pharma, S.L. | Compositions for reducing appetite and craving, increasing satiety, enhancing mood, and reducing stress |
| WO2019001360A1 (en) * | 2017-06-29 | 2019-01-03 | 华南理工大学 | Human-machine interaction method based on visual stimulations |
-
2020
- 2020-04-09 CN CN202010276095.5A patent/CN111466908B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111466908A (en) | 2020-07-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Staum et al. | The effect of music amplitude on the relaxation response | |
| US7046813B1 (en) | Auditory sense training method and sound processing method for auditory sense training | |
| Hutchinson et al. | The relationship between exercise intensity and preferred music intensity. | |
| US9191764B2 (en) | Binaural audio signal-based applications | |
| CN105930480B (en) | The generation method and managing irritating auditory phenomena system of managing irritating auditory phenomena music | |
| Rao et al. | Neural correlates of selective attention with hearing aid use followed by ReadMyQuips auditory training program | |
| CN102682761A (en) | Personalized system and device for sound processing | |
| CN111466908B (en) | Method for screening audio capable of affecting appetite by utilizing EEG (electroencephalogram) | |
| CN105999509A (en) | A tinnitus treating music generating method and a tinnitus treating system | |
| Ogata | Human EEG responses to classical music and simulated white noise: effects of a musical loudness component on consciousness | |
| Steeve et al. | Mandibular motor control during the early development of speech and nonspeech behaviors | |
| Cantisani et al. | MAD-EEG: an EEG dataset for decoding auditory attention to a target instrument in polyphonic music | |
| Shumov et al. | Comparative analysis of the effect of stimulation with a binaural beat and similar kinds of sounds on the falling asleep process: A brief note | |
| Nittrouer et al. | Measuring the effects of spectral smearing and enhancement on speech recognition in noise for adults and children | |
| Rosenboom | Method for producing sounds or light flashes with alpha brain waves for artistic purposes | |
| Murphy et al. | Voice initiation and termination time in stuttering and nonstuttering children | |
| Wilson et al. | Effects of ear preference and order bias on the reception of verbal materials | |
| Hodgetts et al. | Changing hearing performance and sound preference with words and expectations: Meaning responses in audiology | |
| Rastatter et al. | Quantitative electroencephalogram of posterior cortical areas of fluent and stuttering participants during reading with normal and altered auditory feedback | |
| Levak et al. | Effects of noise on humans | |
| Gygi et al. | Predicting the timing of dynamic events through sound: Bouncing balls | |
| Carraturo et al. | Pupillometry reveals differences in cognitive demands of listening to face mask-attenuated speech | |
| Chen | The impact of different genres of music on teenagers | |
| CN104134000B (en) | Method for optimizing child ability based on current situations of child and music | |
| RU2740255C1 (en) | Creation of music therapy technique |
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 |