CN106384005A - Incremental neural network model-based depression prediction method and prediction system - Google Patents

Incremental neural network model-based depression prediction method and prediction system Download PDF

Info

Publication number
CN106384005A
CN106384005A CN201610860197.5A CN201610860197A CN106384005A CN 106384005 A CN106384005 A CN 106384005A CN 201610860197 A CN201610860197 A CN 201610860197A CN 106384005 A CN106384005 A CN 106384005A
Authority
CN
China
Prior art keywords
depression
neuron
network model
neural network
data
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
Application number
CN201610860197.5A
Other languages
Chinese (zh)
Inventor
杨滨
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan Old Code Information Technology Co Ltd
Original Assignee
Hunan Old Code Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hunan Old Code Information Technology Co Ltd filed Critical Hunan Old Code Information Technology Co Ltd
Priority to CN201610860197.5A priority Critical patent/CN106384005A/en
Publication of CN106384005A publication Critical patent/CN106384005A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The invention discloses an incremental neural network model-based depression prediction method. The method comprises the following steps of establishing a depression daily data database; training a neural network model; acquiring daily life data, sending the daily life data to a server, and storing the daily life data in a user daily data record table; extracting day data in the user daily data record table to form an n-dimensional vector, performing normalization processing, and inputting the data to a depression pathologic neural network model to perform depression probability prediction; judging whether a depression probability value is greater than 0.5 or not by an intelligent household depression nursing device; if it is judged that a user suffers from depression, enabling the user to go to a hospital for examination, transmitting an examination result back to the server through the intelligent household depression nursing device, and judging whether the examination result is correct or not by the server; and when the examination result is wrong, executing an incremental algorithm and performing dynamic correction on the neural network model. The method is accurate in prediction and the neural network model is customized for each user.

Description

A kind of depression Forecasting Methodology based on increment type neural network model and prognoses system
Technical field
The invention belongs to field of medical technology, more particularly to a kind of depression based on increment type neural network model is pre- Survey method and prognoses system.
Background technology
Currently domestic each health management system arranged be respectively provided with depression prediction and evaluation, its use prediction mode be data Join.Its principle is that by system matches fixed data and then personal lifestyle data entry system is shown ill probability.But due to people The complexity of body and disease, unpredictability, in the form of expression of bio signal and information, Changing Pattern (Self-variation with Change after medical intervention) on, it is detected and signal representation, the data of acquisition and the analysis of information, decision-making etc. are all multi-party All there is extremely complex non-linear relationship in face.So using traditional Data Matching can only be blindness data examination it is impossible to Judge the logic association between data and data and variable, the codomain deviation obtaining is big, causes the specificity ten of system prediction Point poor, domestic health management system arranged effectively Accurate Prediction cannot be carried out to personal depression so current.
Most of before this is all using BP neural network model to depression prediction, but when new detection data generation When it is necessary to train neural network model again, operation efficiency is extremely low.And after system user scale increases, server Will be unable to complete in time training mission.
Content of the invention
The purpose of the present invention is that and overcomes the deficiencies in the prior art, there is provided one kind is based on increment type neural network model Depression Forecasting Methodology and prognoses system, the present invention by neural network model train predict a large amount of patient in hospital pathology numbers According to, find depression pathology and depression earlier life variations in detail, clinical symptoms, examination criteria value, high-risk group's feature, this Logic association between several causes of disease and variable, ultimately form the depression pathology nerve to depression illness probability Accurate Prediction Network model, the present invention passes through to gather user's daily life data, the periodicity of its data of active analysis, regular eventually through Depression pathology Neural Network model predictive user suffers from depression probability, immediately reminds user in the way of visual effect Doctor, constantly revises neural network model when Neural Network model predictive is inaccurate by increasable algorithm, to set for each Standby user sets up the neural network model training for this user, with the increase of use time, to set up to this customer volume Body neural network model customized, accuracy rate is greatly improved.
To achieve these goals, the invention provides a kind of depression prediction side based on increment type neural network model Method, comprises the steps：
Step (1), acquisition hospital's depression etiology and pathology data source and the daily monitoring data of patient, thus set up depression Daily data database；
Step (2), the daily data database of depression set up according to step (1) are off-line manner to neutral net mould Type is trained, to obtain the depression pathology neural network model training；
Step (3), by intelligent monitoring device, the daily life data of user is acquired, and will collection daily life Live data sends to server, and server preserves the daily life data of user to the daily data logger of user；
Step (4), from the daily data logger of user, extract same day data, form n-dimensional vector, and n-dimensional vector is done Carry out depression probabilistic forecasting in the depression pathology neural network model training in input step (2) after normalized, Obtain depression probability, server sends depression probability to wired home depression care appliances；
After step (5), the depression probability of wired home depression care appliances the reception server transmission, judge depression Whether probit is more than 0.5, if greater than 0.5, is then judged to that this user obtained depression, attention device warns to remind user, If less than 0.5, then it is judged to that this user does not have a depression；
Step (6), when user is judged to depression, user voluntarily removes examination in hospital, and inspection result is passed through Wired home depression care appliances send back server, and server judges whether inspection result is correct, if inspection result is wrong By mistake, then explanation depression pathology Neural Network model predictive is inaccurate, if inspection result is correct, depression pathology god is described Through network model's prediction accurately；
Step (7), when inspection result mistake, from the daily data logger of user extract m days in record preserve to In incremental data table, when the record quantity in incremental data table is more than h bar, execute increasable algorithm, to depression pathology god Carry out dynamic corrections through network model；
Step (8), repeat step (3)～(7).
Further, the input layer of neural network model is n node, and hidden layer number is n*2+1, and output layer is 1 Node, extracts k bar record from depression daily data database table and is trained, every record is a n-dimensional vector, owns Data before use first through normalized so as to numerical value is interval in [0,1], then execution following steps are to neural network model It is trained：
1) one n-dimensional vector of input, to neural network model, calculates all of power in neural network model
Vector to the distance of this input n-dimensional vector, as win neuron, its calculating by closest neuron
Formula is as follows：
| | x i - W k | | = min j ( | | x i - W j | | ) ;
Wherein：WkIt is the weight vector of triumph neuron, | | ... | | for Euclidean distance；
2) weight vector of the neuron in adjustment triumph neuron and triumph neuron field, formula is as follows：
Wherein：WjT () is neuron；Wj(t+1) weight vector before being adjustment and after adjustment；J belongs to triumph neuron neck Domain；α (t) is learning rate, and it is as the function that the increase of iterationses is gradually successively decreased, and span is [0 1], through multiple It is 0.62 that Optimal learning efficiency is chosen in experiment；DjIt is the distance of neuron j and triumph neuron；σ (t) is as the letter that the time successively decreases Number；Iteration all input n-dimensional vectors is input in neural network model and is trained each time, when the iteration reaching regulation After number of times, neural network model training terminates.
Further, inspection result is sent back the form of the object information of server by wired home depression care appliances For：{ checking whether correct, blood glucose value }, server, after receiving object information, judges whether inspection result is correct.
Further, the increasable algorithm carrying out dynamic corrections to depression pathology neural network model is：
Vectorial for every in incremental data table V { V1,V2,…,Vn, it is sent in neural network model learning function Row study, learning procedure is as follows：
1) first to output layer, each weight vector is assigned little random number and is done normalized, then utilizes input mode vector V Meansigma methodss Avg (V), be initialized as the weights of unique neuron in the 0th layer of neural network model, and be set to win nerve Unit, calculates its quantization error QE；
2) expand out 2 × 2 structures SOM from the 0th layer of neuron, and its level identities Layer is set to 1；
3) for each 2 × 2 structure SOM subnet expanded out in Layer layer, initialize the power of this 4 neurons Value；The input vector set Ci of i-th neuron is set to sky, main label is set to NULL, the main label ratio r of neuron ii It is set to 0；The abnormity early warning data vector V of new SOM inherits the triumph input vector set VX of his father's neuron；
4) select a vectorial VX from VXiDo following judgement：
If VXiFor the data of not tape label, then calculate its Euclidean distance with each neuron, chosen distance is the shortest Neuron is as triumph neuron；
If VXiFor the data of tape label, then select main label and VXiLabel is identical and riThe maximum neuron of value is made For triumph neuron, update this triumph neuron main label；
If can not find main label and VXiLabel identical neuron, then find and VXiClosest neuron i makees For triumph neuron；
5) weights of neuron in triumph neuron and its neighborhood are adjusted, update the vectorial set W=W ∪ that wins {VXi, calculate main label, the main label ratio r of triumph neuroniWith comentropy EiIf. not up to predetermined frequency of training, Go to step 4)；
6) quantization error QE of each neuron in this neural network model after calculating is adjustedi, neuronal messages entropy Ei With the average quantization error MQE of subnet, formula is as follows：
QE i = Σ X j ∈ C i { | | W i - X j | | } ;
Wherein：WiFor the weight vector of neuron i, CiThe set constituting for all input vectors being mapped to neuron i；
E i = Σ i ∈ T ( - l b n i m ) × n i m ;
Wherein：niRepresent to fall that label is the number of samples of i on neuron, m represents to fall label data on neuron Sum, T represents to fall the sample label species set on neuron；
Then judge：
If MQE>QE × threshold value q of father node, wherein q=0.71, then insert a line neuron in this SOM, turn step Rapid 4)；
If Ei>The E of father nodei× threshold value p, wherein p=0.42, then grow one layer of new subnet from this neuron, will The subnet newly growing increases in the subnet queue of Layer+1 layer；
If being not inserted into new neuron in SOM also do not grow new subnet, illustrate that the training of this subnet completes；
7) for all 2 × 2 structures SOM of the Layer+1 layer newly expanded out, iteration operating procedure 3)～5) to it again It is trained, until neural network model no longer produces new neuron and new layering, whole training terminates.
Further, if user includes health check-up by other means and checks oneself, learn that oneself has suffered from depression, and intelligence The attention device of family's depression care appliances do not warn then it represents that wired home depression care appliances judge inaccurate, this When execution step (6)～(7), wired home depression care appliances are sent to object information on server.
Present invention also offers a kind of prognoses system of described depression Forecasting Methodology, including intelligent monitoring device, intelligence Device data acquisition device, server and wired home depression care appliances, described intelligent monitoring device and described smart machine Data acquisition unit is connected, and described smart machine data acquisition unit passes through communication device one and described server network communication, institute State wired home depression care appliances and pass through communication device two and described server network communication.
Further, described wired home depression care appliances are provided with attention device.
Further, described intelligent monitoring device includes Intelligent worn device, Intelligent water cup, Intelligent weight claim, intelligent horse Bucket and Intelligent light sensing equipment.
Beneficial effects of the present invention：
1st, the present invention by neural network model train predict a large amount of patient in hospital pathological data, find depression pathology with Depression earlier life variations in detail, clinical symptoms, examination criteria value, high-risk group's feature, the logic between this several causes of disease Association and variable, ultimately form the depression pathology neural network model to depression illness probability Accurate Prediction, and the present invention is led to Cross collection user's daily life data, the periodicity of its data of active analysis, regularity are eventually through depression pathology nerve net Network model prediction user suffers from depression probability, reminds user's instant hospitalizing and prevention in the way of visual effect.
2nd, when Neural Network model predictive is inaccurate, neural network model is constantly revised, to be directed to by increasable algorithm Each equipment user sets up the neural network model training for this user, with the increase of use time, to set up to this The neural network model that user makes to measure, accuracy rate is greatly improved.
Brief description
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing Have technology description in required use accompanying drawing be briefly described it should be apparent that, drawings in the following description be only this Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, acceptable Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the flow chart of the embodiment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawings invention is further illustrated, but be not limited to the scope of the present invention.
Embodiment
As shown in figure 1, a kind of depression Forecasting Methodology based on increment type neural network model that the present invention provides, including Following steps：
Step (1), acquisition hospital's depression etiology and pathology data source and the daily monitoring data of patient, thus set up depression Daily data database；
Wherein daily monitoring data is 21 item data, and its 21 item data is the age, sex, heart rate, mental condition, drinking-water frequency Rate, body weight, diet, degree of fatigue, time for falling asleep, sleep quality, smoking capacity (daily), emotional status, somatic reaction speed, from Thing occupation, temperature, humidity, air quality index etc. 21 item data, the present invention sets up 21 dimensional vectors with 21 item data；
Step (2), the daily data database of depression set up according to step (1) are off-line manner to neutral net mould Type is trained, to obtain the depression pathology neural network model training；
Step (3), by intelligent monitoring device, the daily life data of user is acquired, and will collection daily life Live data sends to server, and server preserves the daily life data of user to the daily data logger of user；
Step (4), from the daily data logger of user, extract same day data, form 21 dimensional vectors, and to 21 dimensional vectors Carry out depression probability pre- in the depression pathology neural network model training in input step (2) after doing normalized Survey, obtain depression probability, server sends depression probability to wired home depression care appliances；
After step (5), the depression probability of wired home depression care appliances the reception server transmission, judge depression Whether probit is more than 0.5, if greater than 0.5, is then judged to that this user obtained depression, attention device warns to remind user, If less than 0.5, then it is judged to that this user does not have a depression；
Step (6), when user is judged to depression, user voluntarily removes examination in hospital, and inspection result is passed through Wired home depression care appliances send back server, and server judges whether inspection result is correct, if inspection result is wrong By mistake, then explanation depression pathology Neural Network model predictive is inaccurate, if inspection result is correct, depression pathology god is described Through network model's prediction accurately；
Step (7), when inspection result mistake, from the daily data logger of user extract 7 days in record preserve to In incremental data table, when the record quantity in incremental data table is more than 100, execute increasable algorithm, to depression pathology Neural network model carries out dynamic corrections；
Step (8), repeat step (3)～(7).
The input layer of the neural network model of the present invention is 21 nodes, and hidden layer number is 43, and output layer is 1 node (i.e. the probability of depression), extracts 400000 records from depression daily data database table and is trained, every record 21 dimensional vectors, all data before use first through normalized so as to numerical value is interval in [0,1], then execute such as Lower step is trained to neural network model：
1) one 21 dimensional vector of input, to neural network model, calculate all of weight vector in neural network model defeated to this Enter the distance of 21 dimensional vectors, closest neuron is as won neuron, its computing formula is as follows：
| | x i - W k | | = min j ( | | x i - W j | | ) ;
Wherein：WkIt is the weight vector of triumph neuron, | | ... | | for Euclidean distance；
2) weight vector of the neuron in adjustment triumph neuron and triumph neuron field, formula is as follows：
Wherein：WjT () is neuron；Wj(t+1) weight vector before being adjustment and after adjustment；J belongs to triumph neuron neck Domain；α (t) is learning rate, and it is as the function that the increase of iterationses is gradually successively decreased, and span is [0 1], through multiple It is 0.62 that Optimal learning efficiency is chosen in experiment；DjIt is the distance of neuron j and triumph neuron；σ (t) is as the letter that the time successively decreases Number；Iteration all input n-dimensional vectors is input in neural network model and is trained each time, when the iteration reaching regulation After number of times, neural network model training terminates.
Inspection result is sent back the form of the object information of server by the wired home depression care appliances of the present invention For：{ checking whether correct, blood glucose value }, server, after receiving object information, judges whether inspection result is correct.
The increasable algorithm carrying out dynamic corrections to depression pathology neural network model of the present invention is：
Vectorial for every in incremental data table V { V1,V2,…,Vn, it is sent in neural network model learning function Row study, learning procedure is as follows：
1) first to output layer, each weight vector is assigned little random number and is done normalized, then utilizes input mode vector V Meansigma methodss Avg (V), be initialized as the weights of unique neuron in the 0th layer of neural network model, and be set to win nerve Unit, calculates its quantization error QE；
2) expand out 2 × 2 structures SOM from the 0th layer of neuron, and its level identities Layer is set to 1；
3) for each 2 × 2 structure SOM subnet expanded out in Layer layer, initialize the power of this 4 neurons Value；The input vector set Ci of i-th neuron is set to sky, main label is set to NULL, the main label ratio r of neuron ii It is set to 0；The abnormity early warning data vector V of new SOM inherits the triumph input vector set VX of his father's neuron；
4) select a vectorial VX from VXiDo following judgement：
If VXiFor the data of not tape label, then calculate its Euclidean distance with each neuron, chosen distance is the shortest Neuron is as triumph neuron；
If VXiFor the data of tape label, then select main label and VXiLabel is identical and riThe maximum neuron of value is made For triumph neuron, update this triumph neuron main label；
If can not find main label and VXiLabel identical neuron, then find and VXiClosest neuron i makees For triumph neuron；
5) weights of neuron in triumph neuron and its neighborhood are adjusted, update the vectorial set W=W ∪ that wins {VXi, calculate main label, the main label ratio r of triumph neuroniWith comentropy EiIf. not up to predetermined frequency of training, Go to step 4)；
6) quantization error QE of each neuron in this neural network model after calculating is adjustedi, neuronal messages entropy Ei With the average quantization error MQE of subnet, formula is as follows：
QE i = Σ X j ∈ C i { | | W i - X j | | } ;
Wherein：WiFor the weight vector of neuron i, CiThe set constituting for all input vectors being mapped to neuron i；
E i = Σ i ∈ T ( - l b n i m ) × n i m ;
Wherein：niRepresent to fall that label is the number of samples of i on neuron, m represents to fall label data on neuron Sum, T represents to fall the sample label species set on neuron；
Then judge：
If MQE>QE × threshold value q of father node, wherein q=0.71, then insert a line neuron in this SOM, turn step Rapid 4)；
If Ei>The E of father nodei× threshold value p, wherein p=0.42, then grow one layer of new subnet from this neuron, will The subnet newly growing increases in the subnet queue of Layer+1 layer；
If being not inserted into new neuron in SOM also do not grow new subnet, illustrate that the training of this subnet completes；
7) for all 2 × 2 structures SOM of the Layer+1 layer newly expanded out, iteration operating procedure 3)～5) to it again It is trained, until neural network model no longer produces new neuron and new layering, whole training terminates.
If the user of the present invention includes health check-up by other means and checks oneself, learn that oneself has suffered from depression, and intelligence The attention device of family's depression care appliances do not warn then it represents that wired home depression care appliances judge inaccurate, this When execution step (6)～(7), wired home depression care appliances are sent to object information on server.
Present invention also offers a kind of prognoses system of described depression Forecasting Methodology, including intelligent monitoring device, intelligence Device data acquisition device, server and wired home depression care appliances, described intelligent monitoring device and described smart machine Data acquisition unit is connected, and described smart machine data acquisition unit passes through communication device one and described server network communication, institute State wired home depression care appliances and pass through communication device two and described server network communication.
It is provided with attention device on the described wired home depression care appliances of the present invention.
The described intelligent monitoring device of the present invention includes Intelligent worn device, Intelligent water cup, Intelligent weight claim, intelligent closestool With Intelligent light sensing equipment etc..
The present invention is trained by neural network model and predicts a large amount of patient in hospital pathological data, finds depression pathology and suppression Strongly fragrant disease earlier life variations in detail, clinical symptoms, examination criteria value, high-risk group's feature, the logic between this several causes of disease is closed Connection and variable, ultimately form the depression pathology neural network model to depression illness probability Accurate Prediction, and the present invention passes through Collection user's daily life data, the periodicity of its data of active analysis, regularity are eventually through depression pathology neutral net Model prediction user suffers from depression probability, reminds user's instant hospitalizing and prevention in the way of visual effect.
All data of the present invention preserve to server, can significantly save calculating cost, hardware configuration is low, thus selling Valency is also low.
The present invention carries communication device one and communication device two, by wifi from the Internet that is dynamically connected, and can protect for a long time Hold online.Various intelligent monitoring devices can easily access present device by modes such as network or bluetooths, sets in acquisition The daily life data of the monitoring of intelligent monitoring device, the data that therefore present device obtains can automatically be uploaded after standby mandate It is real-time, accurate, polynary.
Because everyone physical trait is different, the data characteristicses being shown during depression also can be different.Cause This is not conventional high by the method accuracy rate of neural network prediction depression.The present invention is directed to each equipment user and sets up training Go out the neural network model for this user, running after a period of time, by producing to measure neutral net is being made to this user Forecast model, accuracy rate is greatly improved.
When neural network model is judged by accident, error message be will be feedbacked to server by wired home depression care appliances, For this user's dynamic corrections neural network model, when similar characteristics data in this user next, will not judge by accident again.Cause This, with the increase of use time, the judgement of the wired home depression care appliances of the present invention will be more and more accurate.
Ultimate principle, principal character and the advantages of the present invention of the present invention have been shown and described above.The technology of the industry , it should be appreciated that the present invention is not restricted to the described embodiments, the simply explanation described in above-described embodiment and description is originally for personnel Invention principle, without departing from the spirit and scope of the present invention the present invention also have various changes and modifications, these change Change and improvement both falls within scope of the claimed invention.Claimed scope by appending claims and its Equivalent defines.

Claims (8)

1. a kind of depression Forecasting Methodology based on increment type neural network model is it is characterised in that comprise the steps：
Step (1), obtain hospital depression and cure the disease etiology and pathology data source and the daily monitoring data of patient, thus setting up depression Daily data database；
Step (2), off-line manner neural network model is entered according to the daily data database of depression that step (1) is set up Row training, to obtain the depression pathology neural network model training；
Step (3), by intelligent monitoring device, the daily life data of user is acquired, and will collection daily life number According to sending to server, server preserves the daily life data of user to the daily data logger of user；
Step (4), from the daily data logger of user, extract same day data, form n-dimensional vector, and normalizing is done to n-dimensional vector Carry out depression probabilistic forecasting in the depression pathology neural network model training in input step (2) after change process, obtain Depression probability, server sends depression probability to wired home depression care appliances；
After step (5), the depression probability of wired home depression care appliances the reception server transmission, judge depression probability Whether value is more than 0.5, if greater than 0.5, is then judged to that this user obtained depression, attention device warns to remind user, if Less than 0.5, then it is judged to that this user does not have a depression；
Step (6), when user is judged to depression, user voluntarily removes examination in hospital, and by inspection result pass through intelligence Family's depression care appliances send back server, and server judges whether inspection result is correct, if inspection result mistake, Illustrate that depression pathology Neural Network model predictive is inaccurate, if inspection result is correct, depression pathology nerve net is described Network model prediction is accurate；
Step (7), when inspection result mistake, from the daily data logger of user extract m days in record preserve to increment In tables of data, when the record quantity in incremental data table is more than h bar, execute increasable algorithm, to depression pathology nerve net Network model carries out dynamic corrections；
Step (8), repeat step (3)～(7).
2. a kind of depression Forecasting Methodology based on increment type neural network model according to claim 1, its feature exists In the input layer of neural network model is n node, and hidden layer number is n*2+1, and output layer is 1 node, from depression day Extract k bar record in regular data database table to be trained, every record is a n-dimensional vector, all data are first before use Through normalized so as to numerical value is interval in [0,1], then execution following steps are trained to neural network model：
1) one n-dimensional vector of input, to neural network model, calculates all of weight vector in neural network model and ties up to this input n The distance of vector, closest neuron is as won neuron, and its computing formula is as follows：
Wherein：WkIt is the weight vector of triumph neuron, | | ... | | for Euclidean distance；
2) weight vector of the neuron in adjustment triumph neuron and triumph neuron field, formula is as follows：
Wherein：WjT () is neuron；Wj(t+1) weight vector before being adjustment and after adjustment；J belongs to triumph neuron field；α T () is learning rate, it is as the function that the increase of iterationses is gradually successively decreased, and span is [0 1], through many experiments Choosing Optimal learning efficiency is 0.62；DjIt is the distance of neuron j and triumph neuron；σ (t) is as the function that the time successively decreases； Iteration all input n-dimensional vectors is input in neural network model and is trained each time, when the iteration time reaching regulation After number, neural network model training terminates.
3. a kind of depression Forecasting Methodology based on increment type neural network model according to claim 1, its feature exists In the form that inspection result is sent back the object information of server by wired home depression care appliances is：{ just check whether Really, blood glucose value }, server, after receiving object information, judges whether inspection result is correct.
4. a kind of depression Forecasting Methodology based on increment type neural network model according to claim 1, its feature exists In the increasable algorithm carrying out dynamic corrections to depression pathology neural network model is：
Vectorial for every in incremental data table V { V1,V2,…,Vn, it is sent in neural network model learning function and learned Practise, learning procedure is as follows：
1) first to output layer, each weight vector is assigned little random number and is done normalized, then utilizes the flat of input mode vector V Average Avg (V), is initialized as the weights of unique neuron in the 0th layer of neural network model, and is set to triumph neuron, meter Calculate its quantization error QE；
2) expand out 2 × 2 structures SOM from the 0th layer of neuron, and its level identities Layer is set to 1；
3) for each 2 × 2 structure SOM subnet expanded out in Layer layer, the weights of this 4 neurons are initialized；Will The input vector set Ci of i-th neuron is set to sky, and main label is set to NULL, the main label ratio r of neuron iiIt is set to 0；The abnormity early warning data vector V of new SOM inherits the triumph input vector set VX of his father's neuron；
4) select a vectorial VX from VXiDo following judgement：
If VXiFor the data of not tape label, then calculate its Euclidean distance with each neuron, chosen distance nerve the shortest Unit is as triumph neuron；
If VXiFor the data of tape label, then select main label and VXiLabel is identical and riThe maximum neuron of value is as obtaining Victory neuron, updates this triumph neuron main label；
If can not find main label and VXiLabel identical neuron, then find and VXiClosest neuron i is as obtaining Victory neuron；
5) weights of neuron in triumph neuron and its neighborhood are adjusted, update the vectorial set W=W ∪ { VX that winsi, Calculate main label, the main label ratio r of triumph neuroniWith comentropy EiIf. not up to predetermined frequency of training, go to step 4)；
6) quantization error QE of each neuron in this neural network model after calculating is adjustedi, neuronal messages entropy EiAnd son The average quantization error MQE of net, formula is as follows：
Wherein：WiFor the weight vector of neuron i, CiThe set constituting for all input vectors being mapped to neuron i；
Wherein：niRepresent to fall that label is the number of samples of i on neuron, m represents to fall the total of label data on neuron Number, T represents to fall the sample label species set on neuron；
Then judge：
If MQE>QE × threshold value q of father node, wherein q=0.71, then insert a line neuron in this SOM, go to step 4)；
If Ei>The E of father nodei× threshold value p, wherein p=0.42, then grow one layer of new subnet from this neuron, will be new The subnet growing increases in the subnet queue of Layer+1 layer；
If being not inserted into new neuron in SOM also do not grow new subnet, illustrate that the training of this subnet completes；
7) for all 2 × 2 structures SOM of the Layer+1 layer newly expanded out, iteration operating procedure 3)～5) it is re-started Training, until neural network model no longer produces new neuron and new layering, whole training terminates.
5. a kind of depression Forecasting Methodology based on increment type neural network model according to claim 1, its feature exists In, if user includes health check-up by other means and checks oneself, learn that oneself has suffered from depression, and the nursing of wired home depression The attention device of equipment do not warn then it represents that wired home depression care appliances judge inaccurate, now execution step (6)～ (7), wired home depression care appliances are sent to object information on server.
6. a kind of prognoses system of depression Forecasting Methodology described in employing claim 1～6 is supervised it is characterised in that including intelligence Control equipment, smart machine data acquisition unit, server and wired home depression care appliances, described intelligent monitoring device and institute State smart machine data acquisition unit to be connected, described smart machine data acquisition unit passes through communication device one and described server net Network communicates, and described wired home depression care appliances pass through communication device two and described server network communication.
7. according to claim 7 the prognoses system of depression Forecasting Methodology it is characterised in that described wired home depression Attention device is provided with care appliances.
8. according to claim 7 the prognoses system of depression Forecasting Methodology it is characterised in that described intelligent monitoring device bag Include Intelligent worn device, Intelligent water cup, Intelligent weight claim, intelligent closestool and Intelligent light sensing equipment.
CN201610860197.5A 2016-09-28 2016-09-28 Incremental neural network model-based depression prediction method and prediction system Pending CN106384005A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610860197.5A CN106384005A (en) 2016-09-28 2016-09-28 Incremental neural network model-based depression prediction method and prediction system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610860197.5A CN106384005A (en) 2016-09-28 2016-09-28 Incremental neural network model-based depression prediction method and prediction system

Publications (1)

Publication Number Publication Date
CN106384005A true CN106384005A (en) 2017-02-08

Family

ID=57937025

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610860197.5A Pending CN106384005A (en) 2016-09-28 2016-09-28 Incremental neural network model-based depression prediction method and prediction system

Country Status (1)

Country Link
CN (1) CN106384005A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110236572A (en) * 2019-05-07 2019-09-17 平安科技（深圳）有限公司 Depression forecasting system based on body temperature information
WO2020103683A1 (en) * 2018-11-20 2020-05-28 中国科学院脑科学与智能技术卓越创新中心 Method and system for individualized prediction of mental illness on basis of brain function map monkey-human cross-species migration
CN117912640A (en) * 2024-03-20 2024-04-19 合肥工业大学 Domain increment learning-based depressive disorder detection model training method and electronic equipment

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1477581A (en) * 2003-07-01 2004-02-25 �Ϻ���ͨ��ѧ Predictive modelling method application to computer-aided medical diagnosis
US20040054358A1 (en) * 2002-03-28 2004-03-18 Cox Ian G. System and method for predictive ophthalmic correction
CN102647292A (en) * 2012-03-20 2012-08-22 北京大学 Intrusion detecting method based on semi-supervised neural network
CN102789593A (en) * 2012-06-18 2012-11-21 北京大学 Intrusion detection method based on incremental GHSOM (Growing Hierarchical Self-organizing Maps) neural network
CN103324981A (en) * 2013-05-20 2013-09-25 浙江大学 Chemoradiotherapy standardized quality control quantitative method based on neural network
CN104504297A (en) * 2015-01-21 2015-04-08 甘肃百合物联科技信息有限公司 Method for using neural network to forecast hypertension
CN105118010A (en) * 2015-09-30 2015-12-02 成都信汇聚源科技有限公司 Chronic disease management method with functions of real-time data processing and real-time information sharing and life style intervention information

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040054358A1 (en) * 2002-03-28 2004-03-18 Cox Ian G. System and method for predictive ophthalmic correction
CN1477581A (en) * 2003-07-01 2004-02-25 �Ϻ���ͨ��ѧ Predictive modelling method application to computer-aided medical diagnosis
CN102647292A (en) * 2012-03-20 2012-08-22 北京大学 Intrusion detecting method based on semi-supervised neural network
CN102789593A (en) * 2012-06-18 2012-11-21 北京大学 Intrusion detection method based on incremental GHSOM (Growing Hierarchical Self-organizing Maps) neural network
CN103324981A (en) * 2013-05-20 2013-09-25 浙江大学 Chemoradiotherapy standardized quality control quantitative method based on neural network
CN104504297A (en) * 2015-01-21 2015-04-08 甘肃百合物联科技信息有限公司 Method for using neural network to forecast hypertension
CN105118010A (en) * 2015-09-30 2015-12-02 成都信汇聚源科技有限公司 Chronic disease management method with functions of real-time data processing and real-time information sharing and life style intervention information

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
MEHMED KANTARDZIC: "《数据挖掘：概念、模型、方法和算法》", 31 January 2013 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020103683A1 (en) * 2018-11-20 2020-05-28 中国科学院脑科学与智能技术卓越创新中心 Method and system for individualized prediction of mental illness on basis of brain function map monkey-human cross-species migration
CN110236572A (en) * 2019-05-07 2019-09-17 平安科技（深圳）有限公司 Depression forecasting system based on body temperature information
CN117912640A (en) * 2024-03-20 2024-04-19 合肥工业大学 Domain increment learning-based depressive disorder detection model training method and electronic equipment

Similar Documents

Publication Publication Date Title
CN106407699A (en) Coronary heart disease prediction method and prediction system based on incremental neural network model
CN106250712A (en) A kind of ureteral calculus Forecasting Methodology based on increment type neural network model and prognoses system
CN106446552A (en) Prediction method and prediction system for sleep disorder based on incremental neural network model
CN106355035A (en) Pneumonia prediction method and prediction system based on incremental neural network model
CN108366763A (en) Method and system for assessing the state of mind
CN106446560A (en) Hyperlipidemia prediction method and prediction system based on incremental neural network model
CN113241196B (en) Remote medical treatment and grading monitoring system based on cloud-terminal cooperation
CN106384013A (en) Incremental neural network model-based type-II diabetes prediction method and prediction system
CN106650206A (en) Prediction method of high blood pressure based on incremental neural network model and prediction system
CN106384005A (en) Incremental neural network model-based depression prediction method and prediction system
CN106355034A (en) Sub-health prediction method and prediction system based on incremental neural network model
CN106384012A (en) Incremental neural network model-based allergic dermatitis prediction method and prediction system
CN106384008A (en) Incremental neural network model-based allergic rhinitis prediction method and prediction system
CN106295238A (en) A kind of hypertensive nephropathy Forecasting Methodology based on increment type neural network model and prognoses system
CN106446561A (en) Incremental neural network model based urticaria prediction method and system
CN106407693A (en) Hepatitis B prediction method and prediction system based on incremental neural network model
CN106384009A (en) Incremental neural network model-based HIV prediction method and prediction system
CN106250715A (en) A kind of chronic pharyngolaryngitis Forecasting Methodology based on increment type neural network model and prognoses system
CN106407694A (en) Neurasthenia prediction method and prediction system based on incremental neural network model
CN106202986A (en) A kind of tonsillitis Forecasting Methodology based on increment type neural network model and prognoses system
CN106339605A (en) Colonitis prediction method and colonitis prediction system based on incremental nerve network model
CN106407695A (en) Anxiety disorder prediction method and prediction system based on incremental neural network model
CN106446553A (en) Stomach illness prediction method and prediction system based on incremental neural network model
CN106372442A (en) Dental ulcer prediction method and system based on incremental neural network model
CN106295239A (en) A kind of fatty liver Forecasting Methodology based on increment type neural network model and prognoses system

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20170208