CN114202032B - Gait detection method, device and computer storage medium based on reserve pool model - Google Patents
Gait detection method, device and computer storage medium based on reserve pool model Download PDFInfo
- Publication number
- CN114202032B CN114202032B CN202111539098.4A CN202111539098A CN114202032B CN 114202032 B CN114202032 B CN 114202032B CN 202111539098 A CN202111539098 A CN 202111539098A CN 114202032 B CN114202032 B CN 114202032B
- Authority
- CN
- China
- Prior art keywords
- data
- gait
- gait detection
- dimension reduction
- layer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1116—Determining posture transitions
- A61B5/1117—Fall detection
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/112—Gait analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4076—Diagnosing or monitoring particular conditions of the nervous system
- A61B5/4082—Diagnosing or monitoring movement diseases, e.g. Parkinson, Huntington or Tourette
-
- 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
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/245—Classification techniques relating to the decision surface
- G06F18/2453—Classification techniques relating to the decision surface non-linear, e.g. polynomial classifier
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Neurology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Physiology (AREA)
- Public Health (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Dentistry (AREA)
- Neurosurgery (AREA)
- Mathematical Physics (AREA)
- Developmental Disabilities (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Nonlinear Science (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The application relates to a gait detection method, equipment and a computer storage medium based on a reserve pool model, wherein the reserve pool model comprises an input layer, a reserve pool, a dimension reduction layer and an output layer; the gait detection method comprises the following steps: acquiring gait detection data; inputting gait detection data to an input layer to be converted into a multi-dimensional array in a preset format; the multidimensional array enters the reserve pool, and characteristic data are obtained after the reserve pool is calculated; the feature data enter a dimension reduction layer, and dimension reduction processing is carried out on the feature data in the dimension reduction layer; and the feature data after the dimension reduction treatment enters an output layer to obtain gait classification probability of gait detection data. According to the method and the device, gait detection is achieved based on the reserve pool model, and the accuracy of the gait detection is improved.
Description
Technical Field
The present application generally detects the field of classification. More particularly, the present application relates to a method, apparatus, and computer storage medium for gait detection based on a pool model.
Background
Frozen gait (FOG) is a gait disorder characterized by recurrent episodes of transient, delayed cessation of gait, which often occurs in the middle and late stages of parkinson's disease with unknown causes. Falls of parkinson's disease are caused by FOG, which has a serious impact on physical and mental health and quality of life of patients. Studies have shown that parkinson's disease is not completely cured and that treatment with drugs is generally only able to alleviate the symptoms of frozen gait, whereas FOG attacks are random and sensitivity to drugs and the environment makes it clinically difficult to detect FOG and does not allow an accurate assessment of its severity. Therefore, the early detection of the FOG event is the basis of the implementation of the intervention measures, can help the patient suffering from the disease to reduce the falling times, so that the patient can recover to normal activities as soon as possible, and can be used as the basis of disease assessment, thereby having important guiding application to the research and treatment of the frozen gait of the Parkinson.
At present, research on frozen gait is mainly divided into a deep learning-based method and a machine learning-based method, wherein the deep learning-based method is an end-to-end technology, and the classification effect is achieved mainly by training a hidden multi-layer neural network; another machine learning-based method is classified into supervised learning and unsupervised learning. In supervised learning, most of the methods are classified based on the combination of features such as statistical features, freezing indexes, frozen frequency band energy and the like and algorithms of machine learning; in unsupervised learning, features are extracted mainly by PCA principal component analysis and combined with a machine-learned classifier.
The randomness and sensitivity of FOG make the detection result not particularly ideal, and the detection result lacks stability, and the characteristic extraction part is based on the characteristic which is often manually screened and extracted, so that the whole experiment process becomes more complicated,
in deep learning, one obvious but computationally expensive solution (CNN) to this problem is to develop a generic classifier using a large amount of training data recorded from many subjects (with different health or pathological conditions). However, this approach for FOG diagnostic purposes faces several challenges, including data collection, beat annotation, and technical challenges related to hardware implementation.
Disclosure of Invention
The application provides a gait detection method, equipment and a computer storage medium based on a reserve pool model, which are used for solving the problem that the detection result is inaccurate when the existing model detects gait.
In order to solve the technical problems, the application provides a gait detection method based on a reserve pool model, wherein the reserve pool model comprises an input layer, a reserve pool, a dimension reduction layer and an output layer; the gait detection method comprises the following steps: acquiring gait detection data; inputting gait detection data to the input layer to be converted into a multi-dimensional array in a preset format; the multidimensional array enters the reserve pool, and characteristic data are obtained after calculation of the reserve pool; the feature data enter the dimension reduction layer, and dimension reduction processing is carried out on the feature data in the dimension reduction layer; and the feature data after the dimension reduction treatment enter the output layer to obtain gait classification probability of the gait detection data.
In one embodiment, the performing, at the dimension reduction layer, dimension reduction processing on the feature data includes: and carrying out linear transformation on the characteristic data to enable the characteristic data after the dimension reduction processing to be irrelevant in linearity.
In one embodiment, said linearly transforming said feature data comprises: and carrying out linear transformation on the characteristic data by adopting a principal component analysis method.
In one embodiment, the output layer is provided with a plurality of non-linear classifiers; the feature data after the dimension reduction processing enters the output layer to obtain gait classification probability of the gait detection data, which comprises the following steps: and the feature data after the dimension reduction treatment enters a selected nonlinear classifier to obtain gait classification probability of the gait detection data.
In one embodiment, inputting gait detection data into the input layer for conversion into a multi-dimensional array of a preset format includes: gait detection data is input to the input layer for conversion into a multi-dimensional array, the dimensions of which include the number of data segments, the number of data points per data segment, the number of variables per data point.
In one embodiment, the acquiring gait detection data comprises: acquiring gait detection data in a detection time period; utilizing a time window, slipping the time window with a fixed step length, and intercepting gait detection data to obtain a gait detection data segment; more data points of the time window than the fixed step size; the inputting gait detection data to the input layer includes: the gait detection data segment is input to the input layer.
In one embodiment, the output layer in the reservoir model is obtained from gait training data training, including normal gait training data and frozen gait training data.
In one embodiment, the gait detection data and the gait training data each comprise: thigh acceleration data, calf acceleration data, and lower back acceleration data.
To solve the above technical problem, the present application proposes an electronic device, which includes a processor and a memory, where the memory stores a computer program, and the processor is configured to execute the computer program to implement the steps of the above method.
To solve the above technical problem, the present application proposes a computer storage medium storing a computer program that is executed to implement the steps of the above method.
Unlike the prior art, the reservoir model in this application includes input layer, reservoir, dimension reduction layer and output layer, and gait detection method includes: acquiring gait detection data; inputting gait detection data to an input layer to be converted into a multi-dimensional array in a preset format; the multidimensional array enters the reserve pool, and characteristic data are obtained after the reserve pool is calculated; the feature data enter a dimension reduction layer, and dimension reduction processing is carried out on the feature data in the dimension reduction layer; and the feature data after the dimension reduction treatment enters an output layer to obtain gait classification probability of gait detection data. The reserve pool model used in the method only needs to train the output layer, is high in training speed, introduces the dimension reduction layer into the reserve pool model, reduces the collinearity between data, improves the generalization performance of the reserve pool model, and improves the accuracy of gait detection of the reserve pool model.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present disclosure will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which like reference numerals refer to similar or corresponding parts and in which:
FIG. 1 is a schematic diagram of the construction of a reservoir model of the present application;
FIG. 2 is a flow chart of a reservoir model-based gait detection method of the present application;
FIG. 3 is a schematic structural diagram of the electronic device of the present application;
fig. 4 is a schematic structural view of the computer storage medium of the present application.
Detailed Description
The following description of the technical solutions in the embodiments of the present disclosure will be made clearly and completely with reference to the accompanying drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are some embodiments of the present disclosure, but not all embodiments. Based on the embodiments in this disclosure, all other embodiments that a person skilled in the art would obtain without making any inventive effort are within the scope of protection of this disclosure.
Specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings. Referring to fig. 1 and 2, fig. 1 is a schematic structural diagram of a reservoir model of the present application, and fig. 2 is a schematic flow chart of a gait detection method based on the reservoir model of the present application.
The gait detection method of the embodiment is used for detecting normal gait and frozen gait, and specifically is based on a reserve pool model, wherein the reserve pool model comprises an input layer, a reserve pool, a dimension reduction layer and an output layer.
Reservoir computation mimics the circuit structure of recursively connected neurons in the brain, using reservoirs consisting of randomly sparsely connected neurons as hidden layers for high-dimensional, non-linear representation of the input. The reservoir is pre-generated, the generation process being independent of the training process. The reserve pool generated in advance has good attribute, so that good performance can be obtained by only training the weight of the reserve pool to the output layer. Compared with the traditional neural network, the training process of the reserve pool model is simplified, the global optimality and the good generalization capability after weight determination can be realized, and the problems that the training algorithm is complex and is easy to fall into local minimum and the like in the traditional neural network are avoided.
The pool is used to develop the input signal u (t) of the input layer into x (t) in high dimension so that x (t) can be developed by the weight matrix Wout. The pool also has short term memory capability, which can provide time links. The reservoir has adjustable parameters for adjusting the reservoir's performance. Parameters of the reservoir include: pool size, pool sparsity, input scale and internal connection weight spectrum radius.
Reservoir size refers to the number of neurons within the reservoir. The different choices of pool size are not only related to the data of the samples, but also have a large impact on the performance of the pool model. Generally, the larger the pool size, the better the performance of the network, but the larger the pool size, not only the larger the calculation, but also the risk of overfitting, resulting in a reduced model generalization.
Reservoir sparsity refers to the connection between neurons in the reservoir. The reservoir sparsity magnitude may represent the abundance of vectors in the reservoir and also affect the non-linear approximation ability of the reservoir model. The greater the reservoir sparseness, the higher the richness of vectors representing the reservoir, and the higher the nonlinear approximation capability.
The input scale refers to a scale on which the input signal is multiplied before entering the pool neurons. Because of the diversity of the sample data and the choice of the neuron activation function, in order to avoid that the input data is too wide in distribution range, the input data must be limited to a certain range by a scaling scale when the neuron activation function is input. One setting rule for inputting the scaling scale in this embodiment is: the scale determines the degree of nonlinearity of the pool response, the stronger the nonlinearity, the larger the scale.
The internal connection weight spectrum radius refers to the maximum absolute eigenvalue of the inter-neuron connection matrix in the reservoir. The precondition for the stability of the reservoir model is that the echo state properties, i.e. the decay history of the input u (t), define the state x (t) of the reservoir. In most cases, the spectral radius smaller than 1 can ensure the echo state attribute of the reservoir, and the reservoir model tends to be in a stable state.
The parameters of the reserve pool are selected mostly empirically, and in a given parameter space, the optimal parameters are found by adopting a trial and error method. Since the training process of the pool model is simple and the verification time is less expensive, experiments are usually performed using random parameters, from which set of parameters the model is best to choose as the best parameters.
The gait detection method based on the reservoir model in this embodiment includes the following steps.
S11: gait detection data is acquired.
The method of the embodiment mainly detects the gait of the inspector, so that gait detection data of the inspector are firstly acquired, specifically real-time gait data in the walking process of the inspector are acquired, in the embodiment, the acquisition is performed through sensors arranged on the inspector, specifically thigh acceleration data, shank acceleration data and lower back acceleration data related to the gait are acquired through inertial sensors worn on the thigh, the shank and the lower back of the inspector, and each acceleration data comprises acceleration data in X, Y, Z directions.
Further, the frozen gait is not always present for the person who has the frozen gait, so in this embodiment, the obtained real-time gait data during walking is captured and then detected during the detection.
After gait detection data in a detection time period are acquired, utilizing a time window to slide the time window with a fixed step length, and intercepting the gait detection data to obtain a gait detection data period; the time window has more data points than the fixed step size.
For example, the time window has 50 data points and the fixed step size has 5 data points. The data points represent the detection time points, the sensor obtains data every 0.015s, the corresponding time window is 0.8s, and 45 repeated data points are arranged between adjacent gait detection data segments.
In the embodiment, the time window is not more than 1s, if the intercepted data segment is too short, the data points are insufficient, and the characteristics cannot be fully represented; if too long, the problem of difficulty in identifying the mixture of normal features and frozen features occurs.
S12: gait detection data are input to the input layer to be converted into a multi-dimensional array in a preset format.
If the gait detection data segment is obtained in step S11, the gait detection data segment is input to the input layer. The data to the input layer needs to be converted into a multidimensional NumPy array, where the array is in the shape of [ N, T, V ], where N is the number of data segments, T is the number of data points in each data segment, and V is the number of variables in each data point, for example, thigh acceleration data, shank acceleration data, and lower back acceleration data in this embodiment, each acceleration data further includes acceleration data in X, Y, Z directions, and thus the number of variables is 9. The multidimensional array is also converted from the csv format to the mat format during the specific computation.
S13: and the multidimensional array enters a reserve pool, and characteristic data are obtained after the reserve pool is calculated.
The multidimensional array is calculated by each neuron in the reserve pool to obtain characteristic data.
S14: and the feature data enter a dimension reduction layer, and dimension reduction processing is carried out on the feature data in the dimension reduction layer.
Because of multiple collinearity of data in a reserve pool, the solution is unstable in space, dimension disasters and complex in model, and the generalization capability of the model is weak; moreover, the stored Chi Gaowei spatial samples have sparsity, so that the model is difficult to find data features; too many variables can interfere with model finding rules; sometimes, the feature matrix is too large, so that the calculated amount is large and the training time is long.
In order to solve the problem, in the embodiment, a dimension reduction method is adopted, the number of characteristic attributes is reduced, irrelevant or redundant characteristics are removed, the number of the characteristics is reduced, the accuracy of a model is improved, and the running time is shortened.
In the embodiment, the feature data is subjected to linear transformation in the dimension reduction layer to realize dimension reduction, so that the feature data after dimension reduction processing is independent of linearity, and the feature attributes are mutually independent. The method specifically comprises the steps of extracting subspaces of a large-scale reserve pool state matrix, removing linearly related components, solving output weights by the subspaces instead of the original reserve pool state matrix, and avoiding occurrence of pathological solutions, and generalization performance and prediction accuracy of a reserve pool calculation model.
The dimension reduction method can adopt principal component analysis (PCA, tenPCA) to carry out linear transformation on the characteristic data. Principal Component Analysis (PCA) is a data dimension reduction method for continuous attributes that constructs an orthogonal transformation of the original data, with the new spatial basis removing the correlation of the data under the original spatial basis, and requiring only a few new variables to interpret the majority of the variables in the original data. In applications, it is common to select several new variables, so-called principal components, which are fewer than the original variables and which are capable of interpreting the variables in the majority of the data, instead of the original variables for modeling. The raw dataset is changed by linear change into a set of linearly independent representations of the dimensions.
S15: and the feature data after the dimension reduction treatment enters an output layer to obtain gait classification probability of gait detection data.
The output layer is used for classifying the characteristic data to determine the normal gait probability and the frozen gait probability of the gait detection data. The output layer in this embodiment is provided with various non-linear classifiers, such as a multi-layer perceptron (multilayer perceptron), ridge estimate (Ridge estimate), support vector machine (Support Vector Machine), etc.
Specifically, when the reserve pool model is used for detection, a certain adaptive nonlinear classifier can be selected according to data to be detected, so that classification accuracy is ensured. The feature data after the dimension reduction processing enters a selected nonlinear classifier to obtain gait classification probability of the gait detection data.
The step of training the reservoir model is similar to the step of the gait detection method described above, specifically, gait training data is input to the reservoir model for training, and the gait training data includes normal gait training data and frozen gait training data.
In this embodiment, gait training data is gait data of 8 patients, 237 times of frozen gait time occur in the testing process, and finally the intercepted data segments comprise 118656 data segments, wherein 23731 data segments of the testing set and 94925 data segments of the training set are obtained by dividing in a ratio of 2:8.
The gait detection method may be implemented by an electronic device, and thus the present application further proposes an electronic device, referring to fig. 3, fig. 3 is a schematic structural diagram of an embodiment of the electronic device of the present application, and the electronic device 100 of the present embodiment may be a computer, which includes a processor 11 and a memory 12 that are connected to each other, and the electronic device 100 of the present embodiment may implement an embodiment of the method. Wherein the memory 12 stores a computer program, and the processor 11 is configured to execute the computer program to implement the above method.
The processor 11 may be an integrated circuit chip with signal processing capabilities. The processor 11 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
For the method of the above embodiment, which may exist in the form of a computer program, the present application proposes a computer storage medium, please refer to fig. 4, fig. 4 is a schematic structural diagram of an embodiment of the computer storage medium of the present application. The computer storage medium 200 of the present embodiment stores therein a computer program 21 that can be executed to implement the method in the above embodiment.
The computer storage medium 200 of this embodiment may be a medium that may store program instructions, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disc, or may be a server that stores the program instructions, and the server may send the stored program instructions to other devices for execution, or may also self-execute the stored program instructions.
In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interface, indirect coupling or communication connection of devices or units, electrical, mechanical, or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
While various embodiments of the present application have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Many modifications, changes, and substitutions will now occur to those skilled in the art without departing from the spirit and spirit of the application. It should be understood that various alternatives to the embodiments of the present application described herein may be employed in practicing the application. The appended claims are intended to define the scope of the application and to cover such module forms, equivalents, or alternatives falling within the scope of the claims.
Claims (10)
1. The gait detection method based on the reserve pool model is characterized in that the reserve pool model comprises an input layer, a reserve pool, a dimension reduction layer and an output layer; the gait detection method comprises the following steps:
acquiring gait detection data, the gait detection data comprising: thigh acceleration data, shank acceleration data, and lower back acceleration data;
inputting gait detection data to the input layer to be converted into a multi-dimensional array in a preset format;
the multidimensional array enters the reserve pool, and characteristic data are obtained after calculation of the reserve pool;
the feature data enter the dimension reduction layer, and dimension reduction processing is carried out on the feature data in the dimension reduction layer;
and the feature data after the dimension reduction treatment enter the output layer to obtain gait classification probability of the gait detection data.
2. The method according to claim 1, wherein the performing, at the dimension reduction layer, dimension reduction processing on the feature data includes:
and carrying out linear transformation on the characteristic data to enable the characteristic data after the dimension reduction processing to be irrelevant in linearity.
3. The method of detecting according to claim 2, wherein said linearly transforming the feature data includes:
and carrying out linear transformation on the characteristic data by adopting a principal component analysis method.
4. The detection method according to claim 1, wherein the output layer is provided with a plurality of nonlinear classifiers; the feature data after the dimension reduction processing enters the output layer to obtain gait classification probability of the gait detection data, which comprises the following steps:
and the feature data after the dimension reduction treatment enters a selected nonlinear classifier to obtain gait classification probability of the gait detection data.
5. The method according to claim 1, wherein inputting gait detection data to the input layer for conversion into a multi-dimensional array of a predetermined format, comprises:
gait detection data is input to the input layer for conversion into a multi-dimensional array, the dimensions of which include the number of data segments, the number of data points per data segment, the number of variables per data point.
6. The method of claim 1, wherein the acquiring gait detection data comprises:
acquiring gait detection data in a detection time period;
utilizing a time window, slipping the time window with a fixed step length, and intercepting gait detection data to obtain a gait detection data segment; more data points of the time window than the fixed step size;
the inputting gait detection data to the input layer includes: the gait detection data segment is input to the input layer.
7. The method of claim 1, wherein the output layer in the reservoir model is trained from gait training data, the gait training data comprising normal gait training data and frozen gait training data.
8. The method of detecting according to claim 7, wherein the gait training data comprises: thigh acceleration data, calf acceleration data, and lower back acceleration data.
9. An electronic device comprising a processor and a memory, the memory having stored therein a computer program for executing the computer program to perform the steps of the method according to any of claims 1-8.
10. A computer storage medium, characterized in that it stores a computer program that is executed to implement the steps of the method according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111539098.4A CN114202032B (en) | 2021-12-15 | 2021-12-15 | Gait detection method, device and computer storage medium based on reserve pool model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111539098.4A CN114202032B (en) | 2021-12-15 | 2021-12-15 | Gait detection method, device and computer storage medium based on reserve pool model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114202032A CN114202032A (en) | 2022-03-18 |
| CN114202032B true CN114202032B (en) | 2023-07-18 |
Family
ID=80654323
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111539098.4A Active CN114202032B (en) | 2021-12-15 | 2021-12-15 | Gait detection method, device and computer storage medium based on reserve pool model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114202032B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014203039A1 (en) * | 2013-06-19 | 2014-12-24 | Aselsan Elektronik Sanayi Ve Ticaret Anonim Sirketi | System and method for implementing reservoir computing using cellular automata |
| CN104323780A (en) * | 2014-10-30 | 2015-02-04 | 上海交通大学 | Support vector machine-based pedestrian gait classifying system and method |
| CN108090559A (en) * | 2018-01-03 | 2018-05-29 | 华南理工大学 | A kind of construction method of antithesis reserve pool neural network model |
| CN108229661A (en) * | 2018-01-03 | 2018-06-29 | 华南理工大学 | A kind of depth echo state network model building method based on multiple coding re-projection |
| CN108901033A (en) * | 2018-06-20 | 2018-11-27 | 南京邮电大学 | Base station method for predicting based on echo state network |
| CN111241749A (en) * | 2020-01-13 | 2020-06-05 | 广西师范大学 | Permanent magnet synchronous motor chaos prediction method based on reserve pool calculation |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170258390A1 (en) * | 2016-02-12 | 2017-09-14 | Newton Howard | Early Detection Of Neurodegenerative Disease |
| US20170173262A1 (en) * | 2017-03-01 | 2017-06-22 | François Paul VELTZ | Medical systems, devices and methods |
| US20190365287A1 (en) * | 2018-05-30 | 2019-12-05 | Industry-Academic Cooperation Foundation, Dankook University | Apparatus and method for gait type classification using pressure sensor of smart insole |
-
2021
- 2021-12-15 CN CN202111539098.4A patent/CN114202032B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014203039A1 (en) * | 2013-06-19 | 2014-12-24 | Aselsan Elektronik Sanayi Ve Ticaret Anonim Sirketi | System and method for implementing reservoir computing using cellular automata |
| CN104323780A (en) * | 2014-10-30 | 2015-02-04 | 上海交通大学 | Support vector machine-based pedestrian gait classifying system and method |
| CN108090559A (en) * | 2018-01-03 | 2018-05-29 | 华南理工大学 | A kind of construction method of antithesis reserve pool neural network model |
| CN108229661A (en) * | 2018-01-03 | 2018-06-29 | 华南理工大学 | A kind of depth echo state network model building method based on multiple coding re-projection |
| CN108901033A (en) * | 2018-06-20 | 2018-11-27 | 南京邮电大学 | Base station method for predicting based on echo state network |
| CN111241749A (en) * | 2020-01-13 | 2020-06-05 | 广西师范大学 | Permanent magnet synchronous motor chaos prediction method based on reserve pool calculation |
Non-Patent Citations (8)
| Title |
|---|
| Radar Signal Processing for Human Identification by Means of Reservoir Computing Networks;Azarakhsh Jalalvand 等;《2019 IEEE Radar Conference》;1-6 * |
| Yan Yan 等.Topological Descriptors of Gait Nonlinear Dynamics Toward Freezing-of-Gait Episodes Recognition in Parkinson's Disease.《IEEE Sensors Journal》.2022,第22卷(第05期),4294-4304. * |
| 基于储备池主成分分析的多元时间序列预测研究;韩敏 等;《控制与决策》;第24卷(第10期);1526-1530 * |
| 基于压缩感知的回声状态神经网络在时间序列预测中的应用;李莉 等;《软件导刊》;第19卷(第04期);9-13 * |
| 基于无线穿戴式传感系统的智能步态检测研究;黄剑 等;《华中科技大学学报(自然科学版)》(第10期);105-110 * |
| 基于深度学习的步态识别方法;胡靖雯 等;《计算机应用》;第40卷(第S1期);69-73 * |
| 基于神经网络及储备池计算的模拟电路故障诊断的研究与实现;崔珊珊;《中国优秀硕士学位论文全文数据库信息科技辑》(第(2019)06期);I135-89 * |
| 用于小样本人体传感数据机器学习的神经网络表征与拓扑印记分析机理研究;颜延;《中国博士学位论文全文数据库基础科学辑》(第(2021)01期);A006-276 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114202032A (en) | 2022-03-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shoeibi et al. | A comprehensive comparison of handcrafted features and convolutional autoencoders for epileptic seizures detection in EEG signals | |
| Rashed-Al-Mahfuz et al. | A deep convolutional neural network method to detect seizures and characteristic frequencies using epileptic electroencephalogram (EEG) data | |
| Ertuğrul et al. | Detection of Parkinson's disease by shifted one dimensional local binary patterns from gait | |
| Aydemir et al. | A Tunable-Q wavelet transform and quadruple symmetric pattern based EEG signal classification method | |
| Xie et al. | Wavelet-based sparse functional linear model with applications to EEGs seizure detection and epilepsy diagnosis | |
| Acharya et al. | Use of principal component analysis for automatic classification of epileptic EEG activities in wavelet framework | |
| Ilakiyaselvan et al. | Deep learning approach to detect seizure using reconstructed phase space images | |
| Lamba et al. | A systematic approach to diagnose Parkinson’s disease through kinematic features extracted from handwritten drawings | |
| US20210307673A1 (en) | System and method for early and efficient prediction of epilectic seizures | |
| Supakar et al. | A deep learning based model using RNN-LSTM for the Detection of Schizophrenia from EEG data | |
| KR102141185B1 (en) | A system of detecting epileptic seizure waveform based on coefficient in multi-frequency bands from electroencephalogram signals, using feature extraction method with probabilistic model and machine learning | |
| Rout et al. | Multifuse multilayer multikernel RVFLN+ of process modes decomposition and approximate entropy data from iEEG/sEEG signals for epileptic seizure recognition | |
| Rout et al. | An efficient epileptic seizure classification system using empirical wavelet transform and multi-fuse reduced deep convolutional neural network with digital implementation | |
| Deniz et al. | Automated robust human emotion classification system using hybrid EEG features with ICBrainDB dataset | |
| Nahzat et al. | Classification of epileptic seizure dataset using different machine learning algorithms and PCA feature reduction technique | |
| Ramakrishnan et al. | Epileptic eeg signal classification using multi-class convolutional neural network | |
| Hemachandira et al. | A Framework on Performance Analysis of Mathematical Model‐Based Classifiers in Detection of Epileptic Seizure from EEG Signals with Efficient Feature Selection | |
| Saravanakumar et al. | An effective convolutional neural network-based stacked long short-term memory approach for automated Alzheimer’s disease prediction | |
| Bhowmick et al. | Predictive analytics in healthcare epileptic seizure recognition | |
| CN114202032B (en) | Gait detection method, device and computer storage medium based on reserve pool model | |
| Ward et al. | Data balanced bagging ensemble of convolutional-LSTM neural networks for time series data classification with an imbalanced dataset | |
| Wang et al. | An epileptic EEG detection method based on data augmentation and lightweight neural network | |
| Pratiwi et al. | Skin lesion classification based on convolutional neural networks | |
| Fiza et al. | Classification of Parkinson's Disease using CNN and ANN with the aid of Drawing and Acoustic Feature | |
| Sood et al. | Design and Development of Prediction Model to Detect Seizure Activity Utilizing Higher Order Statistical Features of EEG signals. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |