CN110037694A - One kind judging automatically feed system and method - Google Patents
One kind judging automatically feed system and method Download PDFInfo
- Publication number
- CN110037694A CN110037694A CN201910244516.3A CN201910244516A CN110037694A CN 110037694 A CN110037694 A CN 110037694A CN 201910244516 A CN201910244516 A CN 201910244516A CN 110037694 A CN110037694 A CN 110037694A
- Authority
- CN
- China
- Prior art keywords
- stomach
- intestine
- electric signal
- signal
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- A61B5/389—Electromyography [EMG]
- A61B5/392—Detecting gastrointestinal contractions
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Abstract
The present invention relates to one kind to judge automatically feed system and method, it is related to a kind of medical therapy technical field, the treatment for solving current stomach and intestine electro photoluminescence is mainly opened before diet in user, to effectively improve the satiety before user's diet, to reduce food intake when really starting diet, but in actual application, often there is the case where user forgets to turn on stomach and intestine electrical stimulation apparatus before its diet, so that the problem of seriously affecting the therapeutic effect of user, it includes being implanted to mucous layer or the placenta percreta of stomach to record the Gastroenteric Electrical recording electrode of stomach and intestine electric signal, Gastroenteric Electrical recording electrode is connected to receive stomach and intestine electric signal and in response to stomach and intestine electric signal to analyze and determine whether human body has the signal processing module of feed.The present invention has the effective analytical judgment realized and whether have feed to patient, and stomach and intestine electrical stimulation apparatus is opened when judging that user starts diet really, improves the effect of user's stomach and intestine electronic stimulation.
Description
Technical field
The present invention relates to a kind of medical therapy technical fields, judge automatically feed system and side more particularly, to one kind
Method.
Background technique
Diabetes and obesity are the common public health problems in the whole world, and disease incidence is just in troubling speed
It rises.Type-2 diabetes mellitus case accounts for the overwhelming majority of all diabetes, and most of type 2 diabetes patient is by obesity
Cause.The drug therapy of two kinds of diseases because side effect or lack long-term efficacy due to prospect it is not good enough.
By the investigation of obesity potential treatment scheme, it was determined that weight can be caused to subtract by stomach and intestine electro photoluminescence
Gently, because it changes gastroenteritic power, increase satiety, reduce food intake.The treatment of stomach and intestine electro photoluminescence at present mainly with
Family is opened before diet, so that the satiety before user's diet is effectively improved, to reduce food when really starting diet
Object intake, but in actual application, often there is user and forgets to turn on stomach and intestine electrical stimulation apparatus before its diet
Situation, so that seriously affecting the therapeutic effect of user, there is room for improvement.
Summary of the invention
The object of the present invention is to provide a kind of effective analytical judgments for whether having feed to patient with realization, and are judging
At once stomach and intestine electrical stimulation apparatus is opened when user starts diet really, improves the effect of user's stomach and intestine electronic stimulation
Judge automatically feed system and method.
Foregoing invention purpose of the invention has the technical scheme that
One kind judging automatically feed system, and judging automatically feed system includes being implanted to mucous layer or the placenta percreta of stomach to record stomach
The Gastroenteric Electrical recording electrode of intestines electric signal is connected to Gastroenteric Electrical recording electrode to receive stomach and intestine electric signal and in response to stomach and intestine telecommunications
Number to analyze and determine whether human body has the signal processing module of feed, is connected to signal processing module to receive signal processing signal
And carry out artificial intelligence neural networks training with analyze artificial intelligence neural networks training analysis module that whether human body feed,
And be connected to artificial intelligence neural networks training analysis module and be controlled by artificial intelligence neural networks training analysis module with
Realize the stomach and intestine electrical stimulation treatment device of stomach and intestine electronic stimulation.
By using above-mentioned technical proposal, the Gastroenteric Electrical of patient can be effectively acquired by the setting of Gastroenteric Electrical recording electrode
Signal carries out corresponding signal processing to stomach and intestine electric signal by signal processing module, to facilitate subsequent artefacts' intelligence nerve net
Network training analysis module makees further judgement to human body feed, effectively increases the accurate judgement for whether having feed to user,
Really judge that user has under the precondition of feed, accordingly will start stomach and intestine electrical stimulation treatment device, to effectively increase
To the effect of user's stomach and intestine electronic stimulation.
The present invention is further arranged to: judging automatically feed system further includes being set at Gastroenteric Electrical recording electrode and signal
It manages between module with the signal amplification module for amplifying stomach and intestine electric signal.
By using above-mentioned technical proposal, stomach and intestine electric signal can effectively be amplified by the setting of signal amplification module, from
And avoid stomach and intestine electric signal by external interference signal weaker so that it cannot normal transmitting.
One kind judging automatically eating method, which comprises the following steps:
S1: the Gastroenteric Electrical signal condition of current individual is obtained in real time；
S2: the analytical judgment whether human body feeds is carried out by artificial intelligence neural networks training analysis module.
It, can be based on the personal Gastroenteric Electrical of acquisition by the setting of step S1, step S2 by using above-mentioned technical proposal
Whether signal condition has feed to make accurate judgement human body by artificial intelligence neural networks training analysis module.
The present invention is further arranged to: S2 the following steps are included:
S2.1: the stomach and intestine electric signal of several experimental subjects feeds front and back is obtained；
S2.2: the time domain for obtaining several experimental subjects by time-domain analysis based on the stomach and intestine electric signal of several experimental subjects is special
A is collected, while obtaining the frequency domain character collection B of several experimental subjects by frequency-domain analysis；
S2.3: using all features in temporal signatures collection A and frequency domain character collection B as input layer, whether experimental subjects have feed
Result as output layer, construct artificial neural network；
S2.4: based on the stomach and intestine electric signal of current individual, the temporal signatures of current individual are analyzed by time-domain analysis,
The frequency domain character that current individual is obtained by frequency-domain analysis is brought into the input layer of constructed artificial neural network, passes through classification
Device analyzes and determines out whether current individual has feed.
By using above-mentioned technical proposal, if the setting by step 2.1, step 2.2 can be obtained by time-domain analysis
The time-domain analysis result of dry experimental subjects forms temporal signatures collection A, similar, can obtain experiment accordingly by frequency-domain analysis
Individual frequency-domain analysis result formed frequency domain character collection B, finally using temporal signatures collection A, frequency domain character collection B all features as
Input layer, test it is personal whether fed state as output layer, constructs corresponding artificial neural network, and constructed by set
Artificial neural network and current individual Gastroenteric Electrical signal condition, effectively analyze and determine out whether current individual has feed.
The present invention is further arranged to: constructed artificial neural network is BP neural network, input layer in step S2.3
Number of plies range be [3,15], output layer is two, and 0 represents on an empty stomach, and 1 represents and has a meal, and the range of hidden layer is [1,3].
By using above-mentioned technical proposal, BP nerve net is set by artificial neural network constructed by step S2.3 herein
Network effectively increases the accuracy of building neural network building the known input layer and output layer the case where.
The present invention is further arranged to: step S2.2 is previously mentioned the fast wave constituent analysis that time-domain analysis is stomach and intestine electric signal,
Basic frequency and main power analysis of the frequency-domain analysis for stomach and intestine electric signal.
By using above-mentioned technical proposal, the object of step S2.2 time-domain analysis and frequency-domain analysis is disclosed.
Detailed description of the invention
Fig. 1 is the system block diagram that the present invention judges automatically feed system.
Fig. 2 is the framework schematic diagram for judging automatically neural network constructed by eating method
Fig. 3 is the step schematic diagram for judging automatically eating method.
Fig. 4 is the schematic diagram of step S2 in Fig. 3.
In figure, 1, Gastroenteric Electrical recording electrode；2, signal processing module；3, signal amplification module；4, artificial intelligence nerve net
Network training analysis module.
Specific embodiment
Below in conjunction with attached drawing, invention is further described in detail.
Referring to Fig.1, one kind judging automatically feed system, including being implanted to mucous layer or the placenta percreta of stomach to record Gastroenteric Electrical
The Gastroenteric Electrical recording electrode 1 of signal is connected to Gastroenteric Electrical recording electrode 1 to receive stomach and intestine electric signal and in response to stomach and intestine electric signal
To analyze and determine whether human body has the signal processing module 2 of feed, is connected to signal processing module 2 to receive signal processing signal
And artificial intelligence neural networks training is carried out to analyze the artificial intelligence neural networks training analysis module whether human body feeds
It 4 and is connected to artificial intelligence neural networks training analysis module 4 and is controlled by artificial intelligence neural networks training analysis module
4 to realize the stomach and intestine electrical stimulation treatment device of stomach and intestine electronic stimulation.
Stomach and intestine change in electric can be bigger before and after feed by known people, compared to its stomach and intestine electric signal before feeding after feed
Frequency and intensity can become larger, in addition stomach and intestine electric signal is further divided into fast wave and slow wave, will increase fast wave component on slow wave
Can effectively judge whether human body has feed at this time.
In view of once by the interference of external environment, its signal can die down when practical stomach and intestine electric signal is in transmitting,
It even can not normally be transmitted, judging automatically feed system further includes being set to Gastroenteric Electrical recording electrode 1 and signal processing
With the signal amplification module 3 for amplifying stomach and intestine electric signal between module 2.
The above are the introductions for judging automatically feed system, describe in detail below for eating method is judged automatically.
One kind judging automatically eating method, comprising the following steps: S1: obtaining the stomach and intestine electric signal feelings of current individual in real time
Condition；S2: the analytical judgment whether human body feeds is carried out by artificial intelligence neural networks training analysis module 4.
Wherein step S2 the following steps are included:
S2.1: obtaining the stomach and intestine electric signal of several experimental subjects feeds front and back, and experimental subjects herein are at least 100.
S2.2: based on the stomach and intestine electric signal of several experimental subjects by time-domain analysis obtain several experimental subjects when
Characteristic of field collection A, while the frequency domain character collection B of several experimental subjects is obtained by frequency-domain analysis, time-domain analysis is stomach and intestine electric signal
Fast wave constituent analysis, frequency-domain analysis be stomach and intestine electric signal basic frequency and main power analysis.
S2.3: using all features in temporal signatures collection A and frequency domain character collection B as input layer, whether experimental subjects have
The result of feed constructs artificial neural network as output layer, and constructed artificial neural network is preferably BP in step S3.3
Neural network can also be feedforward neural network, radial basis function neural network, kohonen self organizing neural network, recurrence mind
Through network, convolutional neural networks, modular neural network, the number of plies range of input layer is [3,15], and output layer is two, 0 generation
Table on an empty stomach, have a meal by 1 representative, and the range of hidden layer is [1,3].
S2.4: based on the stomach and intestine electric signal of current individual, the time domain of current individual is analyzed by time-domain analysis
Feature obtains the frequency domain character of current individual by frequency-domain analysis, brings into the input layer of constructed artificial neural network, passes through
Classifier analyzes and determines out whether current individual has feed, and classifier herein can be linear classifier or Nonlinear Classification
Device, wherein linear classifier is mainly used in the function of constructed hidden layer when be linear function, and Nonlinear Classifier is answered
When function used in constructed hidden layer is nonlinear function.
The embodiment of present embodiment is presently preferred embodiments of the present invention, not limits protection of the invention according to this
Range, therefore: the equivalence changes that all structures under this invention, shape, principle are done, should all be covered by protection scope of the present invention it
It is interior.
Claims (6)
1. one kind judges automatically feed system, it is characterised in that: judge automatically feed system include be implanted to stomach mucous layer or
Placenta percreta is to record the Gastroenteric Electrical recording electrode (1) of stomach and intestine electric signal, be connected to Gastroenteric Electrical recording electrode (1) to receive Gastroenteric Electrical
Signal and in response to stomach and intestine electric signal to analyze and determine whether human body has the signal processing module (2) of feed, is connected at signal
Reason module (2) is to receive signal processing signal and carry out artificial intelligence neural networks training to analyze the people whether human body feeds
Work intelligent Neural Network training analysis module (4) and it is connected to artificial intelligence neural networks training analysis module (4) and controlled
The stomach and intestine electrical stimulation treatment device of stomach and intestine electronic stimulation is realized in artificial intelligence neural networks training analysis module (4).
2. one kind according to claim 1 judges automatically feed system, it is characterised in that: judge automatically feed system and also wrap
It includes and is set between Gastroenteric Electrical recording electrode (1) and signal processing module (2) with the signal amplification for amplifying stomach and intestine electric signal
Module (3).
3. one kind judges automatically eating method, which comprises the following steps:
S1: the Gastroenteric Electrical signal condition of current individual is obtained in real time；
S2: the analytical judgment whether human body feeds is carried out by artificial intelligence neural networks training analysis module (4).
4. one kind according to claim 3 judges automatically eating method, which is characterized in that S2 the following steps are included:
S2.1: the stomach and intestine electric signal of several experimental subjects feeds front and back is obtained；
S2.2: the time domain for obtaining several experimental subjects by time-domain analysis based on the stomach and intestine electric signal of several experimental subjects is special
A is collected, while obtaining the frequency domain character collection B of several experimental subjects by frequency-domain analysis；
S2.3: using all features in temporal signatures collection A and frequency domain character collection B as input layer, whether experimental subjects have feed
Result as output layer, construct artificial neural network；
S2.4: based on the stomach and intestine electric signal of current individual, the temporal signatures of current individual are analyzed by time-domain analysis,
The frequency domain character that current individual is obtained by frequency-domain analysis is brought into the input layer of constructed artificial neural network, passes through classification
Device analyzes and determines out whether current individual has feed.
5. one kind according to claim 4 judges automatically eating method, which is characterized in that constructed people in step S2.3
Artificial neural networks are BP neural network, and the number of plies range of input layer is [3,15] layer, and output layer is two, and 0 represents on an empty stomach, 1 generation
Table is had a meal, and the range of hidden layer is [1,3] layer.
6. one kind according to claim 4 judges automatically eating method, which is characterized in that step S2.2 is previously mentioned time domain point
Analysis is the fast wave constituent analysis of stomach and intestine electric signal, basic frequency and main power analysis of the frequency-domain analysis for stomach and intestine electric signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910244516.3A CN110037694A (en) | 2019-03-28 | 2019-03-28 | One kind judging automatically feed system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910244516.3A CN110037694A (en) | 2019-03-28 | 2019-03-28 | One kind judging automatically feed system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110037694A true CN110037694A (en) | 2019-07-23 |
Family
ID=67275487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910244516.3A Pending CN110037694A (en) | 2019-03-28 | 2019-03-28 | One kind judging automatically feed system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110037694A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115517682A (en) * | 2022-11-25 | 2022-12-27 | 四川大学华西医院 | Cognitive dysfunction prediction system based on gastrointestinal electric signals and construction method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101005799A (en) * | 2004-06-17 | 2007-07-25 | 布卢尔维尔麦克米兰儿童中心 | System and method for detecting swallowing activity |
| JP2008208043A (en) * | 2007-02-23 | 2008-09-11 | Kowa Co | Solid preparation containing carnitines |
| CN101516441A (en) * | 2005-07-13 | 2009-08-26 | 贝塔斯蒂姆有限公司 | GI and pancreatic device for treating obesity and diabetes |
| CN102281817A (en) * | 2008-12-12 | 2011-12-14 | 内测公司 | Detection of food or drink consumption in order to control therapy or provide diagnostics |
| US20120101874A1 (en) * | 2005-02-17 | 2012-04-26 | Metacure N.V. | Charger With Data Transfer Capabilities |
| CN108634948A (en) * | 2018-05-11 | 2018-10-12 | 南京宽诚科技有限公司 | A kind of detection method, device, detection device and the storage medium of stomach and intestine electric signal |
| CN109068983A (en) * | 2016-01-28 | 2018-12-21 | 克鲁有限公司 | For tracking food intake and other behaviors and providing the method and apparatus of relevant feedback |
-
2019
- 2019-03-28 CN CN201910244516.3A patent/CN110037694A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101005799A (en) * | 2004-06-17 | 2007-07-25 | 布卢尔维尔麦克米兰儿童中心 | System and method for detecting swallowing activity |
| US20120101874A1 (en) * | 2005-02-17 | 2012-04-26 | Metacure N.V. | Charger With Data Transfer Capabilities |
| CN101516441A (en) * | 2005-07-13 | 2009-08-26 | 贝塔斯蒂姆有限公司 | GI and pancreatic device for treating obesity and diabetes |
| JP2008208043A (en) * | 2007-02-23 | 2008-09-11 | Kowa Co | Solid preparation containing carnitines |
| CN102281817A (en) * | 2008-12-12 | 2011-12-14 | 内测公司 | Detection of food or drink consumption in order to control therapy or provide diagnostics |
| CN109068983A (en) * | 2016-01-28 | 2018-12-21 | 克鲁有限公司 | For tracking food intake and other behaviors and providing the method and apparatus of relevant feedback |
| CN108634948A (en) * | 2018-05-11 | 2018-10-12 | 南京宽诚科技有限公司 | A kind of detection method, device, detection device and the storage medium of stomach and intestine electric signal |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115517682A (en) * | 2022-11-25 | 2022-12-27 | 四川大学华西医院 | Cognitive dysfunction prediction system based on gastrointestinal electric signals and construction method |
| CN115517682B (en) * | 2022-11-25 | 2023-01-31 | 四川大学华西医院 | Cognitive dysfunction prediction system based on gastrointestinal electric signals and construction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108472489B (en) | Synchronizing multiple sources of physiological data | |
| US7616999B2 (en) | System for generating a cochlear implant program using multi-electrode stimulation to elicit the electrically-evoked compound action potential | |
| CA1157526A (en) | Method and apparatus for transcutaneous electrical stimulation | |
| CN103656855B (en) | For the synchronous diagnostic measures of cochlear implant | |
| CN103987424B (en) | The pacemaker of spastic dysphonia | |
| CN106345034A (en) | Device based on brain electricity acquisition terminal for cognitive emotion regulation | |
| US20040152946A1 (en) | Methods for programming a neural prosthesis | |
| US20080221640A1 (en) | Multi-electrode stimulation to elicit electrically-evoked compound action potential | |
| Tong et al. | Perceptual studies on cochlear implant patients with early onset of profound hearing impairment prior to normal development of auditory, speech, and language skills | |
| CN106377252A (en) | Biologic information feedback system based on virtual reality | |
| CN107029351A (en) | System and method for global LFP parkinsonisms characteristics extraction | |
| WO2009010870A2 (en) | Using interaction to measure neural excitation | |
| CN109391891A (en) | For running the method and hearing device of hearing device | |
| Shah et al. | Computational challenges and opportunities for a bi-directional artificial retina | |
| CN108353236A (en) | Stimulation parameter optimization | |
| CN107847739A (en) | Cochlea implantation system | |
| CN202654544U (en) | Neuromuscular rehabilitation instrument based on electromyographic feedback | |
| CN110037694A (en) | One kind judging automatically feed system and method | |
| Paulraj et al. | A machine learning approach for distinguishing hearing perception level using auditory evoked potentials | |
| CN113260305A (en) | Health monitoring based on body noise | |
| CN201308487Y (en) | Amblyopia detecting system based on P-VEP | |
| CN106667480A (en) | Anthropometric dummy for performance test of wearing type physiological signal detection device | |
| CN116421150A (en) | Obstructive sleep apnea hypopnea syndrome identification and treatment system | |
| CN104873306B (en) | Artificial cochlea's analog neuron telemetry system and method | |
| AU2015387123A1 (en) | EEG monitor |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210914 Address after: 310000 rooms 201, 202, 203, 204, 205 and 206, second floor, building 6, heco science and technology center, No. 500 QiaoXin Road, Xiasha street, Hangzhou Economic and Technological Development Zone, Hangzhou, Zhejiang Province Applicant after: Zhejiang MEDA Perth Medical Technology Co.,Ltd. Address before: 315800-23, building 1, No. 491, Mingzhou West Road, Beilun District, Ningbo City, Zhejiang Province Applicant before: NINGBO BETH TRANSLATIONAL MEDICINE RESEARCH CENTER Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190723 |