CN109978009A - Behavior classification method, device and storage medium based on wearable intelligent equipment - Google Patents
Behavior classification method, device and storage medium based on wearable intelligent equipment Download PDFInfo
- Publication number
- CN109978009A CN109978009A CN201910146841.6A CN201910146841A CN109978009A CN 109978009 A CN109978009 A CN 109978009A CN 201910146841 A CN201910146841 A CN 201910146841A CN 109978009 A CN109978009 A CN 109978009A
- Authority
- CN
- China
- Prior art keywords
- matrix
- classification
- clustering
- physiological characteristic
- graph
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 239000011159 matrix material Substances 0.000 claims abstract description 83
- 230000006399 behavior Effects 0.000 claims description 54
- 239000013598 vector Substances 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 19
- 238000013145 classification model Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 206010000117 Abnormal behaviour Diseases 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000005094 computer simulation Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 208000028017 Psychotic disease Diseases 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The behavior classification method based on wearable intelligent equipment that the invention discloses a kind of, comprising: receive the physiological characteristic data of the target person of wearable intelligent equipment acquisition；The most classes extracted in physiological characteristic data generate canonical matrix, carry out cluster operation to canonical matrix and obtain k cluster group；Most classes in cluster group are extracted, generate classification samples set with the minority class in physiological characteristic data；Classification samples in classification samples set are trained and established with disaggregated model, new physiological characteristic data is inputted into disaggregated model, obtains behavior classification results.A kind of behavior classification method based on wearable intelligent equipment disclosed by the invention can be improved the accuracy rate of behavior classification.The invention also discloses a kind of behavior sorter and storage medium based on wearable intelligent equipment.
Description
Technical Field
The invention relates to the technical field of behavior classification, in particular to a behavior classification method and device based on wearable intelligent equipment and a storage medium.
Background
At present, wearable intelligent equipment is widely applied to the fields of military national defense, environmental monitoring, medical health, industrial and high-risk fields, such as data monitoring, and the application value and scientific research value of the wearable intelligent equipment are highly concerned by countries in the world.
In the prior art, as the supervisors in most cases act normally and regularly, the data acquisition distribution of the supervisory equipment worn by the supervisors has certain similarity. A small number of abnormal data may appear in daily data for a small number of persons with abnormal behaviors, and due to the fact that a large amount of biased historical data appears in the person behavior judgment of the intelligent wearing system, the bias between the normal behavior data volume and the abnormal behavior data volume in the system causes an overfitting phenomenon to appear in the modeling process of the classification system, the number of the small number of abnormal persons is underestimated by the model, and therefore the accuracy of behavior classification is low.
Disclosure of Invention
The embodiment of the invention provides a behavior classification method based on wearable intelligent equipment, which can improve the accuracy of behavior classification.
The embodiment of the invention provides a behavior classification method based on wearable intelligent equipment, which comprises the following steps:
receiving physiological characteristic data of a target person, which is acquired by wearable intelligent equipment;
extracting most types in the physiological characteristic data to generate a standard matrix, and performing clustering operation on the standard matrix to obtain k clustering groups;
extracting a plurality of characteristic classes in the clustering group, and generating a classification sample set with a few classes in the physiological characteristic data;
and training the classification samples in the classification sample set, establishing a classification model, and inputting new physiological characteristic data into the classification model to obtain a behavior classification result.
As an improvement of the above scheme, the extracting a plurality of classes in the physiological characteristic data generates a standard matrix, and performing clustering operation on the standard matrix to obtain k clustering groups specifically includes:
calculating the similarity matrixes of the majority classes, defining a non-directional similarity graph, and calculating a normalized graph matrix according to the weighted connection matrix of the non-directional similarity graph;
calculating the first k eigenvectors of the normalized graph matrix, and performing normalization processing to obtain the standard matrix;
and performing clustering operation on the standard matrix to obtain the k clustering groups.
As an improvement of the above scheme, the calculating of the similarity matrix of the plurality of classes and the defining of the non-directional similarity graph are performed, and a normalized graph matrix is calculated according to the weighted connection matrix of the non-directional similarity graph; calculating the first k eigenvectors of the normalized graph matrix, and performing normalization processing to obtain the standard matrix; performing clustering operation on the standard matrix to obtain the k clustering groups, which specifically comprises:
presetting the classification number k, and forming a similarity matrix S epsilon R based on a Gaussian kernel according to most types of sample datan×nWherein n is the number of the majority samples;
defining the non-directional similarity graph G ═ V, E, and when G is weighted graph, two fixed points V are setiAnd vjIs denoted as wij>0, then the weighted connection matrix W of the non-directional similarity graph is (W)ij)i,j＝1,2,…,n(ii) a If wijWhen 0, then v is representediAnd vjThere is no connection between, and wij＝wji；
Vertex pointDegree of (D) and degree matrix of the graph is D ═ diag (D)1,d2,…,dn) Wherein
obtaining the normalized graph matrix Ls＝I-D-1/2WD-1/2；
Calculating the normalized graph matrix LsThe first k feature vectors, mu*1,μ*2,…,μ*kAnd generating a matrix U epsilon R by taking the feature vector as a columnn×k；
Each row in the matrix U is subjected to standardization processing to generate the standard matrix T epsilon Rn×k(ii) a Wherein,
will ti∈Rn×kA vector defined as the ith row of the criteria matrix T, and i ═ 1,2, …, n;
by using K-means algorithm to pair tiClustering to obtain the k clustering groups C1,C2,…,Ck。
As an improvement of the above scheme, the extracting a plurality of feature classes in the cluster group, and generating a classification sample set with a few classes in the physiological feature data specifically include:
selecting each cluster, beforeAnd taking the sample with the minimum average distance from the minority class sample as the characteristic majority class in the clustering group, and generating a classified sample set with the minority class in the physiological characteristic data.
As an improvement to the above solution, the average distance between the sample in the cluster group and the sample points in the minority class is as follows:
wherein, sizelIs the number size of the clusters;
vector xa,xbIs a distance ofK(xa,xb) Is a vector xa,xbDot product of (1); x is the number ofa,xbRespectively a sample vector and a minority sample point vector in the clustering group;
selecting the number of the characteristic majority classes in the cluster groupThe following formula:
wherein,
correspondingly, an embodiment of the present invention provides a behavior classification device based on wearable intelligent devices, including:
the data acquisition unit is used for receiving physiological characteristic data of the target person acquired by the wearable intelligent equipment;
the clustering calculation unit is used for extracting most types of physiological characteristic data to generate a standard matrix and carrying out clustering operation on the standard matrix to obtain k clustering groups;
the classification sample generating unit is used for extracting a plurality of characteristic classes in the clustering group and generating a classification sample set with a few classes in the physiological characteristic data;
and the behavior classification unit is used for training the classification samples in the classification sample set, establishing a classification model, and inputting new physiological characteristic data into the classification model to obtain a behavior classification result.
Correspondingly, a third embodiment of the present invention provides a behavior classification device based on wearable intelligent devices, including: the wearable intelligent device behavior classification method comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the behavior classification method based on the wearable intelligent device according to an embodiment of the invention when executing the computer program.
Correspondingly, the fourth embodiment of the present invention provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, and when the computer program runs, the device where the computer-readable storage medium is located is controlled to execute the behavior classification method based on the wearable intelligent device according to the first embodiment of the present invention.
The behavior classification method based on the wearable intelligent device provided by the embodiment of the invention has the following beneficial effects:
by generating a cluster group and extracting a plurality of characteristic classes with local space representative significance in the cluster, the influence of the quantity deviation of the classified samples on system modeling can be reduced; the method has the advantages that the noise samples and a large amount of repeated information are prevented from influencing the classification effect of the model, and the accuracy of behavior classification is improved; by adopting an algorithm of directly standardizing the graph matrix, the calculation process is more efficient, and the pretreatment of most types of physiological characteristic data is more effectively carried out in a system with large real-time data volume; the behavior classification model of the target person on the living habits can be accurately identified and established by combining the wearable intelligent equipment; and the new physiological characteristic data can be input into the behavior classification model to identify the behavior state of the target person and detect abnormal behavior conditions in time.
Drawings
Fig. 1 is a schematic flowchart of a behavior classification method based on a wearable smart device according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a behavior classification apparatus based on a wearable smart device according to a second embodiment of 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. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, which is a schematic flow chart of a behavior classification method based on a wearable smart device according to an embodiment of the present invention, including:
s101, receiving physiological characteristic data of a target person, which is acquired by wearable intelligent equipment;
s102, extracting most types in the physiological characteristic data to generate a standard matrix, and performing clustering operation on the standard matrix to obtain k clustering groups;
s103, extracting most types of features in the clustering group, and generating a classification sample set with a few types of physiological feature data;
and S104, training the classification samples in the classification sample set, establishing a classification model, and inputting new physiological characteristic data into the classification model to obtain a behavior classification result.
Further, for step S102, a plurality of classes in the physiological characteristic data are extracted to generate a standard matrix, and the standard matrix is subjected to clustering operation to obtain k clustering groups, which specifically includes:
calculating the similarity matrixes of a plurality of classes, defining a non-directional similarity graph, and calculating a normalized graph matrix according to the weighted connection matrix of the non-directional similarity graph;
calculating the first k eigenvectors of the normalized graph matrix, and performing normalization processing to obtain a standard matrix;
and performing clustering operation on the standard matrix to obtain k clustering groups.
Further, calculating a plurality of similar matrixes and defining a non-directional similar graph, and calculating a normalized graph matrix according to the weighted connection matrix of the non-directional similar graph; calculating the first k eigenvectors of the normalized graph matrix, and performing normalization processing to obtain a standard matrix; performing clustering operation on the standard matrix to obtain k clustering groups, specifically:
presetting the classification number k, and forming a similarity matrix S epsilon R based on a Gaussian kernel according to most types of sample datan×nWherein n is the number of the majority samples;
defining the non-directional similarity graph G ═ V, E, and when G is weighted graph, two fixed points V are setiAnd vjIs denoted as wij>0, then the weighted connection matrix W without directional similarity graph is equal to (W)ij)i,j＝1,2,…,n(ii) a If wijWhen 0, then v is representediAnd vjThere is no connection between, and wij＝wji；
Vertex pointDegree of (D) and degree matrix of the graph is D ═ diag (D)1,d2,…,dn) Wherein
obtaining a normalized graph matrix Ls＝I-D-1/2WD-1/2；
Calculating a normalized graph matrix LsThe first k feature vectors, mu*1,μ*2,…,μ*kAnd generating a matrix U epsilon R by taking the feature vector as a columnn×k；
Each row in the matrix U is subjected to standardization processing to generate a standard matrix T belonging to Rn×k(ii) a Wherein,
will ti∈Rn×kA vector defined as the ith row of the norm matrix T, and i ═ 1,2, …, n;
by using K-means algorithm to pair tiClustering to obtain k clustering groups C1,C2,…,Ck。
In a specific embodiment, the algorithm calculation process of the invention adopting the direct standardization graph matrix is more efficient, and the preprocessing of most types of physiological characteristic data is more effectively carried out in a system with large real-time data volume.
Further, for step S103, extracting a majority of features in the cluster group, and generating a classification sample set with a minority of the physiological feature data, specifically:
selecting each cluster, beforeAnd taking the sample with the minimum average distance from the few classes of samples as the characteristic multi-class in the clustering group, and generating a classification sample set with the few classes in the physiological characteristic data.
Further, the average distance between the sample in the cluster group and the sample point of the minority class is as follows:
wherein, sizelIs the number size of the clusters;
vector xa,xbIs a distance ofK(xa,xb) Is a vector xa,xbDot product of (1); x is the number ofa,xbRespectively a sample vector and a minority sample point vector in the clustering group;
selecting the number of the majority of the features in the cluster groupThe following formula:
wherein,
preferably, the selected most types of characteristics are samples with local space representative significance in clustering, and the influence of the quantity deviation of the classified samples on system modeling can be reduced; the method prevents the existence of noise samples and a large amount of repeated information from influencing the classification effect of the model.
Preferably, for step S104, training is performed by SVM algorithm and a classification model is established. And the kernel parameters are consistent with those of the similarity matrix S, and new samples are waited and the classes of the new samples are identified according to the classification model established by the training samples.
In another specific embodiment, the target person may be a psychotic disorder patient and the wearable smart device may be a smart watch.
The behavior classification method based on the wearable intelligent device provided by the embodiment of the invention has the following beneficial effects:
by generating a cluster group and extracting a plurality of characteristic classes with local space representative significance in the cluster, the influence of the quantity deviation of the classified samples on system modeling can be reduced; the method has the advantages that the noise samples and a large amount of repeated information are prevented from influencing the classification effect of the model, and the accuracy of behavior classification is improved; by adopting an algorithm of directly standardizing the graph matrix, the calculation process is more efficient, and the pretreatment of most types of physiological characteristic data is more effectively carried out in a system with large real-time data volume; the behavior classification model of the target person on the living habits can be accurately identified and established by combining the wearable intelligent equipment; and the new physiological characteristic data can be input into the behavior classification model to identify the behavior state of the target person and detect abnormal behavior conditions in time.
Referring to fig. 2, a schematic structural diagram of a behavior classification apparatus based on a wearable smart device according to a second embodiment of the present invention is shown, including:
the data acquisition unit 201 is used for receiving physiological characteristic data of a target person acquired by the wearable intelligent device;
a clustering calculation unit 202, configured to extract a plurality of classes in the physiological characteristic data to generate a standard matrix, and perform clustering operation on the standard matrix to obtain k clustering groups;
a classification sample generating unit 203, configured to extract a feature majority class in the cluster group, and generate a classification sample set with a minority class in the physiological feature data;
and the behavior classification unit 204 is configured to train the classification samples in the classification sample set and establish a classification model, and input new physiological characteristic data into the classification model to obtain a behavior classification result.
Correspondingly, the third embodiment of the present invention provides a behavior classification device based on a wearable intelligent device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the behavior classification method based on the wearable intelligent device according to the first embodiment of the present invention is implemented. The behavior classification device based on the wearable intelligent device can be computing equipment such as a desktop computer, a notebook computer, a palm computer and a cloud server. The wearable smart device-based behavior classification apparatus may include, but is not limited to, a processor, and a memory.
Correspondingly, the fourth embodiment of the present invention provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, and when the computer program runs, the device where the computer-readable storage medium is located is controlled to execute the behavior classification method based on the wearable intelligent device according to the first embodiment of the present invention.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like. The general processor can be a microprocessor or the processor can be any conventional processor and the like, the processor is a control center of the wearable intelligent device-based behavior classification device, and various interfaces and lines are used for connecting various parts of the whole wearable intelligent device-based behavior classification device.
The memory may be used to store the computer programs and/or modules, and the processor may implement various functions of the wearable smart device-based behavior classification apparatus by executing or executing the computer programs and/or modules stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Wherein, the module/unit integrated by the behavior classification device based on the wearable intelligent device can be stored in a computer readable storage medium if the module/unit is realized in the form of a software functional unit and sold or used as an independent product. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (8)
1. A behavior classification method based on wearable intelligent equipment is characterized by comprising the following steps:
receiving physiological characteristic data of a target person, which is acquired by wearable intelligent equipment;
extracting most types in the physiological characteristic data to generate a standard matrix, and performing clustering operation on the standard matrix to obtain k clustering groups;
extracting a plurality of characteristic classes in the clustering group, and generating a classification sample set with a few classes in the physiological characteristic data;
and training the classification samples in the classification sample set, establishing a classification model, and inputting new physiological characteristic data into the classification model to obtain a behavior classification result.
2. The behavior classification method based on the wearable intelligent device as claimed in claim 1, wherein the extracting of the majority of the physiological characteristic data generates a standard matrix, and the standard matrix is subjected to clustering operation to obtain k clustering groups, specifically:
calculating the similarity matrixes of the majority classes, defining a non-directional similarity graph, and calculating a normalized graph matrix according to the weighted connection matrix of the non-directional similarity graph;
calculating the first k eigenvectors of the normalized graph matrix, and performing normalization processing to obtain the standard matrix;
and performing clustering operation on the standard matrix to obtain the k clustering groups.
3. The behavior classification method based on the wearable intelligent device as claimed in claim 2, wherein the similarity matrix of the majority class is calculated and a non-directional similarity graph is defined, and a normalized graph matrix is calculated according to the weighted connection matrix of the non-directional similarity graph; calculating the first k eigenvectors of the normalized graph matrix, and performing normalization processing to obtain the standard matrix; performing clustering operation on the standard matrix to obtain the k clustering groups, which specifically comprises:
presetting the classification number k, and forming a similarity matrix S epsilon R based on a Gaussian kernel according to most types of sample datan×nWherein n is the number of the majority samples;
defining the non-directional similarity graph G ═ V, E, and when G is weighted graph, two fixed points V are setiAnd vjIs denoted as wij>0, then the weighted connection matrix W of the non-directional similarity graph is (W)ij)i,j＝1,2,…,n(ii) a If wijWhen 0, then v is representediAnd vjThere is no connection between, and wij＝wji；
Vertex pointDegree of (D) and degree matrix of the graph is D ═ diag (D)1,d2,…,dn) Wherein
obtaining the normalized graph matrix Ls＝I-D-1/2WD-1/2；
Calculating the normalized graph matrix LsThe first k feature vectors, mu*1,μ*2,…,μ*kAnd generating a matrix U epsilon R by taking the feature vector as a columnn×k；
Each row in the matrix U is subjected to standardization processing to generate the standard matrix T epsilon Rn×k(ii) a Wherein,
will ti∈Rn×kA vector defined as the ith row of the criteria matrix T, and i ═ 1,2, …, n;
by using K-means algorithm to pair tiClustering to obtain the k clustering groups C1,C2,…,Ck。
4. The behavior classification method based on the wearable intelligent device as claimed in claim 3, wherein the extracting of the feature multi-class in the cluster group and the generating of the classification sample set with the feature data sub-class are specifically:
selecting each cluster, beforeTaking the sample with the minimum average distance from the sample of the minority class as the characteristic majority class in the cluster group and generating the sample with the minority class in the physiological characteristic dataThe sample set is classified.
5. The method of claim 4, wherein the average distance between the samples in the cluster group and the minority sample points is as follows:
wherein, sizelIs the number size of the clusters;
vector xa,xbIs a distance ofK(xa,xb) Is a vector xa,xbDot product of (1); x is the number ofa,xbRespectively a sample vector and a minority sample point vector in the clustering group;
selecting the number of the characteristic majority classes in the cluster groupThe following formula:
wherein,
6. a behavior classification method based on wearable intelligent equipment is characterized by comprising the following steps:
the data acquisition unit is used for receiving physiological characteristic data of the target person acquired by the wearable intelligent equipment;
the clustering calculation unit is used for extracting most types of physiological characteristic data to generate a standard matrix and carrying out clustering operation on the standard matrix to obtain k clustering groups;
the classification sample generating unit is used for extracting a plurality of characteristic classes in the clustering group and generating a classification sample set with a few classes in the physiological characteristic data;
and the behavior classification unit is used for training the classification samples in the classification sample set, establishing a classification model, and inputting new physiological characteristic data into the classification model to obtain a behavior classification result.
7. An apparatus for classifying behaviors based on a wearable smart device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements a method for classifying behaviors based on a wearable smart device according to any one of claims 1 to 5 when executing the computer program.
8. A computer-readable storage medium, comprising a stored computer program, wherein when the computer program runs, the computer-readable storage medium controls a device to execute a method for behavior classification based on a wearable smart device according to any one of claims 3 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910146841.6A CN109978009A (en) | 2019-02-27 | 2019-02-27 | Behavior classification method, device and storage medium based on wearable intelligent equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910146841.6A CN109978009A (en) | 2019-02-27 | 2019-02-27 | Behavior classification method, device and storage medium based on wearable intelligent equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109978009A true CN109978009A (en) | 2019-07-05 |
Family
ID=67077459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910146841.6A Pending CN109978009A (en) | 2019-02-27 | 2019-02-27 | Behavior classification method, device and storage medium based on wearable intelligent equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109978009A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112001425A (en) * | 2020-07-29 | 2020-11-27 | 中国银联股份有限公司 | Data processing method and device and computer readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485188A (en) * | 2015-08-27 | 2017-03-08 | 桂林信通科技有限公司 | A kind of industrial exchanger user anomaly detection method |
| CN107239789A (en) * | 2017-05-09 | 2017-10-10 | 浙江大学 | A kind of industrial Fault Classification of the unbalanced data based on k means |
| CN107330477A (en) * | 2017-07-24 | 2017-11-07 | 南京邮电大学 | A kind of improvement SMOTE resampling methods classified for lack of balance data |
| CN109033148A (en) * | 2018-06-11 | 2018-12-18 | 广州大学 | One kind is towards polytypic unbalanced data preprocess method, device and equipment |
-
2019
- 2019-02-27 CN CN201910146841.6A patent/CN109978009A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485188A (en) * | 2015-08-27 | 2017-03-08 | 桂林信通科技有限公司 | A kind of industrial exchanger user anomaly detection method |
| CN107239789A (en) * | 2017-05-09 | 2017-10-10 | 浙江大学 | A kind of industrial Fault Classification of the unbalanced data based on k means |
| CN107330477A (en) * | 2017-07-24 | 2017-11-07 | 南京邮电大学 | A kind of improvement SMOTE resampling methods classified for lack of balance data |
| CN109033148A (en) * | 2018-06-11 | 2018-12-18 | 广州大学 | One kind is towards polytypic unbalanced data preprocess method, device and equipment |
Non-Patent Citations (1)
| Title |
|---|
| 陶新民等: ""基于谱聚类欠取样的不均衡数据SVM分类算法"", 《控制与决策》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112001425A (en) * | 2020-07-29 | 2020-11-27 | 中国银联股份有限公司 | Data processing method and device and computer readable storage medium |
| CN112001425B (en) * | 2020-07-29 | 2024-05-03 | 中国银联股份有限公司 | Data processing method, device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lu et al. | Dense and sparse reconstruction error based saliency descriptor | |
| JP7266674B2 (en) | Image classification model training method, image processing method and apparatus | |
| CN109242002A (en) | High dimensional data classification method, device and terminal device | |
| CN109918498B (en) | Problem warehousing method and device | |
| CN112084856A (en) | Face posture detection method and device, terminal equipment and storage medium | |
| CN109117857B (en) | Biological attribute identification method, device and equipment | |
| CN109726391B (en) | Method, device and terminal for emotion classification of text | |
| CN112990318B (en) | Continuous learning method, device, terminal and storage medium | |
| CN114419378B (en) | Image classification method and device, electronic equipment and medium | |
| US11080551B2 (en) | Proposal region filter for digital image processing | |
| CN108388869B (en) | Handwritten data classification method and system based on multiple manifold | |
| CN109978009A (en) | Behavior classification method, device and storage medium based on wearable intelligent equipment | |
| CN113507447B (en) | Self-adaptive enhancement method and device for network flow data | |
| CN111930935B (en) | Image classification method, device, equipment and storage medium | |
| CN113011968B (en) | Account state detection method and device, storage medium and electronic equipment | |
| CN111767710B (en) | Indonesia emotion classification method, device, equipment and medium | |
| CN111325225B (en) | Image classification method, electronic device and storage medium | |
| CN114548262A (en) | Feature level fusion method for multi-modal physiological signals in emotion calculation | |
| CN109614854B (en) | Video data processing method and device, computer device and readable storage medium | |
| CN110717359B (en) | Counter propagation optimization method and device based on mathematical statistics and electronic equipment | |
| Abed et al. | Machine learning algorithms for distributed operations in internet of things IoT | |
| CN111708884A (en) | Text classification method and device and electronic equipment | |
| CN108108763B (en) | Electroencephalogram classification model generation method and device and electronic equipment | |
| CN110852767A (en) | Passenger flow volume clustering method and terminal equipment | |
| CN114036982B (en) | Individual identification method, system, equipment and medium for radar radiation source |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190705 |