Atterrorism symptom classification method, device and equipment under limited sample condition

Abstract

The invention provides a method, a device and equipment for classifying aterrorism symptoms under a limited sample condition, and the method comprises the steps: reading the multi-modal behavior and physiological signal data of a patient, and extracting the feature representation used for potential category analysis from the data through employing a Bayesian information criterion in combination with an expectation maximization algorithm; the feature representation comprises a timestamp and a spatial distribution characteristic; inputting the feature representation into a potential category analysis module, determining an optimal category number and a boundary through a hierarchical clustering method, and generating candidate sub-clusters; for the candidate sub-clusters, re-evaluating the possibility of each sub-cluster by introducing an information theory enhancement technology to obtain a confidence score of each sub-cluster; according to the confidence score of each sub-group, removing redundant sub-groups by adopting an improved density peak clustering algorithm to obtain a final sub-group; and inputting the final sub-clusters into a trained classification module to estimate the category of the motion terrorism symptom of each sub-cluster so as to realize accurate classification of the motion terrorism symptom according to the category.

Description

Technical Field

[0001] The present invention belongs to the field of machine learning and medical health technology, and specifically relates to a method, device and equipment for classifying atopy under limited sample conditions. Background Art

[0002] Exercise-based cardiac rehabilitation (CR) is a key strategy for the treatment of CVD and is widely recommended by international medical guidelines. However, more than 80% of eligible patients do not participate in CR, especially in the elderly, where fear of movement is common (20%-80%). Therefore, it is necessary to classify fear of movement in order to develop corresponding measures. However, in elderly patients with cardiovascular disease and frailty, the classification of fear of movement faces the challenge of insufficient sample size.

[0003] With the rapid development of machine learning and deep learning technologies, classification tasks under limited sample conditions have gradually become a research hotspot, especially in the fields of medical diagnosis, behavior analysis and emotion recognition. However, due to the difficulty in obtaining samples or the high cost of labeling, how to achieve efficient and accurate classification under limited sample conditions is still a technical problem that needs to be solved urgently. The existing technology has deficiencies in feature extraction capabilities, model generalization, and adaptability to data in specific fields, which limits its performance in actual scenarios. For example, the patent with announcement number CN113378941B proposes a small sample image classification method with multi-decision fusion, which improves the effectiveness and robustness of the model by integrating the decisions of multiple classifiers, and can alleviate the problem of poor adaptability of new categories when training data is limited. However, this method is mainly designed for image classification tasks and relies on the decision fusion strategy of multiple classifiers. It may have limitations when processing non-image data in complex fields (such as behavioral or physiological signals involved in the classification of phobia). In addition, this method does not fully consider the spatial distribution characteristics of sample features, which may lead to a decrease in classification accuracy when the sample size is extremely limited, and is sensitive to noise, making it difficult to adapt to the classification needs of high-dimensional heterogeneous data. The patent with announcement number CN112364747B proposes a target detection method under limited samples. It extracts target features through a backbone neural network and processes candidate regions in combination with a graph structure, thus realizing target detection tasks under few-sample scenarios. However, this technical solution focuses on target detection rather than classification tasks. Its core lies in bounding box regression and candidate region screening, and it pays insufficient attention to the differences between categories that require fine distinction in classification tasks. In addition, this method has high requirements for data preprocessing and does not fully consider the subtle feature differences between categories in small sample scenarios. It may perform poorly when dealing with tasks that require high-precision distinction, such as phobia classification.

[0004] The above problems show that the existing finite sample classification methods still have significant deficiencies in terms of the refinement of feature extraction, adaptability to complex domain data, and generalization ability of classification models. Especially in elderly patients with cardiovascular disease and frailty, existing technologies are difficult to effectively deal with this problem. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a method, device and equipment for classifying atopy under limited sample conditions, so as to solve the problems of insufficient sample size, limited feature extraction ability and insufficient model generalization in the prior art when classifying atopy in elderly patients with cardiovascular disease and frailty.

[0006] The embodiment of the present invention provides a method for classifying phobia under limited sample conditions, which includes: S101, reading multimodal behavior and physiological signal data of the patient, and extracting feature representations for latent class analysis from the data using the Bayesian information criterion combined with the maximum expectation algorithm; S102, inputting the feature representation into a latent class analysis module, determining the optimal number of classes and boundaries through a hierarchical clustering method, and generating candidate sub-clusters; S103, for the candidate subclusters, re-evaluate the possibility of each subclusters by introducing information theory enhancement technology to obtain a confidence score for each subclusters; S104, according to the confidence score of each subgroup, using an improved density peak clustering algorithm to remove redundant subgroups to obtain the final subgroups; S105 , inputting the final sub-clusters into a trained classification module to estimate the kinesiophobia category of each sub-clusters, thereby achieving accurate kinesiophobia classification according to the category.

[0007] Preferably, step S101 specifically includes: Use the feature embedding layer guided by prior knowledge to map the input multimodal data into a high-dimensional feature space and obtain the initial feature tensor R D×N×T ; Where D is the original feature dimension, corresponding to the sampling point value of behavioral signals and physiological signals, N is the number of samples, and T is the length of the time series; The initial feature tensor is optimized by a maximum expectation algorithm based on the Bayesian information criterion to obtain a latent class feature representation; wherein the optimization process includes iteratively updating latent variables and parameter estimates, and calculating information gain after each iteration until convergence conditions are met; the optimization process also includes sparse constraints on the feature representation to reduce noise interference.

[0008] Preferably, the extraction process of the latent class feature representation is expressed as:

[0009] Among them, θ is the feature representation of the latent class, L(θ) represents the objective function, is the prior probability of the kth latent class, is the posterior probability of the kth potential class, K is the optimal number of classes, represents the i-th sample, is the probability density function of the Gaussian distribution, is a sparse regularization term used to control the sparsity of feature representation.

[0010] Preferably, step S102 specifically includes: The latent class feature representation is used as input, and a tree structure is constructed by a hierarchical clustering algorithm; wherein the hierarchical clustering algorithm is based on the Ward variance minimization criterion, and the clusters with the highest similarity are gradually merged; the optimal number of categories K is determined by calculating the silhouette coefficient, and candidate subclusters are generated according to the category boundaries; wherein the silhouette coefficient is defined as:

[0011] Among them, a( ) is a sample The average distance to other samples in its cluster, b( ) is a sample The average distance to the nearest neighbor cluster.

[0012] Preferably, step S103 specifically includes: For each candidate subgroup, the mutual information score is calculated by information theory enhancement technology; where the mutual information score Defined as:

[0013] Where X is the feature distribution of the candidate subgroup, Y is the true label distribution, p(x,y) is the joint probability distribution, and p(x) and p(y) are the marginal probability distributions; The mutual information score is compared with the preset confidence threshold, and the possibility of each subpopulation is re-evaluated to obtain the confidence score of each subpopulation.

[0014] Preferably, in step S104, an improved density peak clustering algorithm is used to remove redundant subgroups; wherein: first, the local density ρ of each subgroup is calculated i and the relative distance δ i , and select the core subpopulation according to the decision diagram; where the local density is defined as:

[0015] in, represents the distance between the i-th subgroup and the j-th subgroup, Scales representing subgroups; The relative distance is defined as:

[0016] Then, the non-core subclusters are merged or eliminated to obtain the final subclusters.

[0017] Preferably, step S105 specifically includes: aligning the time series features of different subgroups along the time dimension using a dynamic time warping algorithm; flattening the aligned features and performing nonlinear transformation through a multi-layer perceptron network to estimate the probability distribution of the phobia category, and then predicting the phobia category of each subgroup; the classification process is defined as:

[0018] in, and b k are the weights and biases for the kth class, is the feature representation of the input sample, P(y=k| ) is the probability that the input sample belongs to category k.

[0019] Preferably, for the classification module, three loss functions are used to optimize its learning parameters, including category balance loss, boundary smoothing loss and classification consistency loss.

[0020] The embodiment of the present invention further provides a device for classifying phobia under limited sample conditions, which includes: A feature extraction unit, used to read the multimodal behavior and physiological signal data of the patient, and extract feature representations for latent class analysis from the data using the Bayesian information criterion combined with the maximum expectation algorithm; the feature representations include timestamps and spatial distribution characteristics; a candidate sub-cluster generation unit, configured to input the feature representation into a latent class analysis module, determine the optimal number of classes and boundaries through a hierarchical clustering method, and generate candidate sub-clusters; A confidence score calculation unit, used for re-evaluating the possibility of each sub-cluster by introducing information theory enhancement technology to obtain a confidence score of each sub-cluster; The final subcluster generation unit is used to remove redundant subclusterings according to the confidence score of each subcluster by using an improved density peak clustering algorithm to obtain the final subclustering; The kinesiophobia classification unit is used to input the final sub-clusters into the trained classification module to estimate the kinesiophobia category of each sub-clusters, thereby achieving accurate kinesiophobia classification according to the category.

[0021] An embodiment of the present invention further provides a device for classifying kinesiophobia under limited sample conditions, which includes a memory and a processor. The memory stores a computer program, and the computer program can be executed by the processor to implement the above-mentioned method for classifying kinesiophobia under limited sample conditions.

[0022] Compared with the prior art, the present invention has at least the following advantages: 1) The present invention significantly improves the refinement of feature extraction under limited sample conditions by introducing prior knowledge and information theory enhancement technology, and can effectively address the problem of insufficient sample size for aphobia classification in elderly patients with cardiovascular disease and frailty; 2) The present invention designs and implements an optimization strategy based on the Bayesian information criterion and the maximum expectation algorithm. Through latent class analysis and hierarchical clustering methods, the potential subgroups of patients are identified and the optimal number of categories and boundaries are determined, thereby improving the classification accuracy and model generalization ability; 3) This paper proposes an improved density peak clustering algorithm, which effectively removes redundant subgroups and improves the robustness and reliability of classification results by combining local density and relative distance. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of a method for classifying atopy under limited sample conditions provided by the first embodiment of the present invention.

[0024] Figure 2 This is a schematic structural diagram of a device for classifying atopy under limited sample conditions provided by a second embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to further understand the content of the present invention, the present invention is described in detail in conjunction with the accompanying drawings and embodiments. The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are only used to explain the relevant inventions, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0026] The present invention provides a method and system for classifying akinesia under limited sample conditions, the core of which is to solve the problems of insufficient sample size, limited feature extraction capability and insufficient model generalization in the classification of akinesia in elderly patients with cardiovascular disease and frailty through feature extraction, latent class analysis, subgroup generation and optimization of multimodal data and design of the final classification module. The specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0027] See also Figure 1The first embodiment of the present invention provides a method for classifying dyspraxia under limited sample conditions, which can be performed by a device for classifying dyspraxia under limited sample conditions (hereinafter referred to as a classification device), and in particular, by one or more processors in the classification device, to implement the following method: S101, reading the patient's multimodal behavior and physiological signal data, and using the Bayesian information criterion combined with the maximum expectation algorithm to extract feature representations for latent class analysis from the data; the feature representations include timestamps and spatial distribution characteristics.

[0028] In practical applications, this embodiment mainly processes multimodal behavior and physiological signal data of elderly patients with cardiovascular disease and frailty to achieve accurate classification of akinesiophobia.

[0029] First, the patient's multimodal data needs to be read, including but not limited to behavioral and physiological signals such as heart rate, blood pressure, gait parameters, and body position changes. The raw data is then mapped to a high-dimensional feature space, and the latent class feature representation is extracted using the Bayesian Information Criterion (BIC) combined with the Maximum Expectation Algorithm (EM). This process first uses a feature embedding layer guided by prior knowledge to convert the input data into an initial feature tensor R D×N×T , where D represents the original feature dimension, N is the number of samples, and T is the length of the time series. The initial feature tensor is optimized by the maximum expectation algorithm based on BIC to obtain the latent class feature representation. The optimization objective function is defined as:

[0030] Among them, θ is the feature representation of the latent class, L(θ) represents the objective function, is the prior probability of the kth latent class, is the posterior probability of the kth potential class, K is the optimal number of classes, represents the i-th sample, is the probability density function of the Gaussian distribution, is a sparse regularization term used to control the sparsity of feature representation. During the optimization process, latent variables and parameter estimation are completed through iterative updates, and information gain is calculated after each iteration until the convergence condition is met.

[0031] S102, inputting the feature representation into a latent class analysis module, determining the optimal number of classes and boundaries through a hierarchical clustering method, and generating candidate sub-clusters.

[0032] In step S102, the classification device uses the extracted latent class feature representation as input and constructs a tree structure through a hierarchical clustering method. The hierarchical clustering algorithm is based on the Ward variance minimization criterion and gradually merges clusters with the highest similarity. In order to determine the optimal number of categories K, the system evaluates by calculating the silhouette coefficient, which is defined as:

[0033] Among them, a( ) is a sample The average distance to other samples in its cluster, b( ) is a sample The average distance to the samples in the nearest neighbor cluster. Based on the calculation results, the system generates candidate subclusters and proceeds to the next step of processing.

[0034] S103, for the candidate sub-clusters, re-evaluate the possibility of each sub-cluster by introducing information theory enhancement technology to obtain a confidence score for each sub-cluster.

[0035] In this embodiment, the possibility of each candidate subgroup is re-evaluated by introducing information theory enhancement technology. Specifically, the system calculates the mutual information score for each candidate subgroup, which is defined as:

[0036] Among them, X is the feature distribution of the candidate subgroup, Y is the true label distribution, p(x,y) is the joint probability distribution, and p(x) and p(y) are the marginal probability distributions.

[0037] The mutual information score is compared with the preset confidence threshold to obtain the confidence score of each subgroup. This process can effectively identify subgroups with higher confidence and provide a basis for subsequent redundancy removal.

[0038] S104, according to the confidence score of each subgroup, using an improved density peak clustering algorithm to remove redundant subgroups to obtain the final subgroups; In step S104, an improved density peak clustering algorithm is used to remove redundant subgroups. First, the local density ρ of each subgroup is calculated. i and the relative distance δ i , and select the core subpopulation according to the decision diagram; where the local density is defined as:

[0039] in, represents the distance between the i-th subgroup and the j-th subgroup, Scales representing subgroups; The relative distance is defined as:

[0040] Then, the non-core subclusters are merged or eliminated to obtain the final subclusters.

[0041] Thus, through comprehensive analysis of local density and relative distance, the system draws a decision diagram and selects core subclusters. For non-core subclusters, the system merges or removes them according to similarity, and finally generates optimized subclusters.

[0042] S105 , inputting the final sub-clusters into a trained classification module to estimate the kinesiophobia category of each sub-clusters, thereby achieving accurate kinesiophobia classification according to the category.

[0043] In step S105, the final sub-clusters are input into the trained classification module to estimate the aphrodisiac category of each sub-cluster. The classification module first aligns the time series features of different sub-cluster along the time dimension using the dynamic time warping algorithm, and then flattens the aligned features and performs nonlinear transformation through a multi-layer perceptron network. The classification process estimates the probability distribution of aphrodisiac categories through the Softmax activation function, and the classification process is defined as: ; in, and b k are the weights and biases for the kth class, is the feature representation of the input sample, P(y=k| ) is the probability that the input sample belongs to category k.

[0044] In order to further improve the classification performance, the system uses three loss functions to optimize the learning parameters, including category balance loss, boundary smoothing loss and classification consistency loss; category balance loss is defined as:

[0045] Among them, α k is the class weight; the boundary smoothing loss is defined as:

[0046] The classification consistency loss is defined as:

[0047] Among them, p i is the generated category label, are pseudo labels generated through data augmentation.

[0048] In actual application scenarios, the embodiments of the present invention have been successfully applied to a group of elderly cardiovascular patients in a hospital. Experimental data show that by introducing prior knowledge and information theory enhancement technology, the system can significantly improve the refinement of feature extraction under limited sample conditions and effectively deal with the problem of insufficient sample size. At the same time, based on the optimization strategy of the Bayesian Information Criterion and the Maximum Expectation Algorithm, combined with latent class analysis and hierarchical clustering methods, it can accurately identify the potential subgroups of patients and determine the optimal number of categories and boundaries, thereby improving classification accuracy and model generalization ability. In addition, the improved density peak clustering algorithm effectively removes redundant subgroups by combining local density and relative distance, thereby improving the robustness and reliability of the classification results.

[0049] In summary, this embodiment solves the key problems in the classification of aphobia under limited sample conditions in the prior art through a series of innovative technical means, and provides strong technical support for the precision medicine of elderly patients with cardiovascular disease and frailty.

[0050] See also Figure 2 The second embodiment of the present invention provides a device for classifying phobia under limited sample conditions, which includes: A feature extraction unit 210 is used to read the multimodal behavior and physiological signal data of the patient, and extract feature representations for latent class analysis from the data using the Bayesian information criterion combined with the maximum expectation algorithm; the feature representations include timestamps and spatial distribution characteristics; A candidate sub-cluster generation unit 220, configured to input the feature representation into a latent class analysis module, determine the optimal number of classes and boundaries through a hierarchical clustering method, and generate candidate sub-clusters; A confidence score calculation unit 230 is used to re-evaluate the possibility of each sub-cluster by introducing information theory enhancement technology to obtain a confidence score of each sub-cluster; A final subcluster generation unit 240 is used to remove redundant subclusterings according to the confidence score of each subcluster using an improved density peak clustering algorithm to obtain a final subclustering; The kinesiophobia classification unit 250 is used to input the final sub-clusters into the trained classification module to estimate the kinesiophobia category of each sub-clusters, thereby achieving accurate kinesiophobia classification according to the category.

[0051] The third embodiment of the present invention further provides a device for classifying kinesiophobia under limited sample conditions, which includes a memory and a processor. The memory stores a computer program, and the computer program can be executed by the processor to implement a method for classifying kinesiophobia under limited sample conditions as described in any of the above embodiments.

[0052] In several embodiments provided in the embodiments of the present invention, it should be understood that the disclosed apparatus and method can also be implemented in other ways. The apparatus and method embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the apparatus, method and computer program product according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0053] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0054] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, electronic device or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code. It should be noted that in this article, the term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or device. Without more constraints, an element defined by the phrase "comprising a..." does not exclude the existence of other identical elements in the process, method, article or apparatus comprising the element.

[0055] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for classifying phobia under limited sample conditions, characterized in that: include: S101, reading multimodal behavior and physiological signal data of the patient, and extracting feature representations for latent class analysis from the data using the Bayesian information criterion combined with the maximum expectation algorithm; S102, inputting the feature representation into a latent class analysis module, determining the optimal number of classes and boundaries through a hierarchical clustering method, and generating candidate sub-clusters; S103, for the candidate subclusters, re-evaluate the possibility of each subclusters by introducing information theory enhancement technology to obtain a confidence score for each subclusters; S104, according to the confidence score of each subgroup, using an improved density peak clustering algorithm to remove redundant subgroups to obtain the final subgroups; S105 , inputting the final sub-clusters into a trained classification module to estimate the kinesiophobia category of each sub-clusters, thereby achieving accurate kinesiophobia classification according to the category.

2. The method for classifying phobia under limited sample conditions according to claim 1, characterized in that: Step S101 specifically includes: Use the feature embedding layer guided by prior knowledge to map the input multimodal data into a high-dimensional feature space and obtain the initial feature tensor R D×N×T ; Where D is the original feature dimension, corresponding to the sampling point value of behavioral signals and physiological signals, N is the number of samples, and T is the length of the time series; The initial feature tensor is optimized by a maximum expectation algorithm based on the Bayesian information criterion to obtain a latent class feature representation; wherein the optimization process includes iteratively updating latent variables and parameter estimates, and calculating information gain after each iteration until convergence conditions are met; the optimization process also includes sparse constraints on the feature representation to reduce noise interference.

3. The method for classifying phobia under limited sample conditions according to claim 2, characterized in that: The extraction process of the latent class feature representation is expressed as: Among them, θ is the feature representation of the latent class, L(θ) represents the objective function, is the prior probability of the kth latent class, is the posterior probability of the kth potential class, K is the optimal number of classes, represents the i-th sample, is the probability density function of the Gaussian distribution, is a sparse regularization term used to control the sparsity of feature representation.

4. The method for classifying phobia under limited sample conditions according to claim 1, characterized in that: Step S102 specifically includes: taking the latent class feature representation as input, constructing a tree structure through a hierarchical clustering algorithm; wherein the hierarchical clustering algorithm is based on the Ward variance minimization criterion, gradually merging clusters with the highest similarity; determining the optimal number of categories K by calculating the silhouette coefficient, and generating candidate subclusters according to the category boundaries; wherein the silhouette coefficient is defined as: Among them, a( ) is a sample The average distance to other samples in its cluster, b( ) is a sample The average distance to the nearest neighbor cluster.

5. The method for classifying phobia under limited sample conditions according to claim 1, characterized in that: Step S103 specifically includes: for each candidate subgroup, calculating its mutual information score by using information theory enhancement technology; wherein the mutual information score Defined as: Where X is the feature distribution of the candidate subgroup, Y is the true label distribution, p(x,y) is the joint probability distribution, and p(x) and p(y) are the marginal probability distributions; The mutual information score is compared with the preset confidence threshold, and the possibility of each subpopulation is re-evaluated to obtain the confidence score of each subpopulation.

6. The method for classifying akinesiophobia under limited sample conditions according to claim 1, characterized in that: In step S104, an improved density peak clustering algorithm is used to remove redundant subgroups; wherein: first, the local density ρ of each subgroup is calculated i and the relative distance δ i , and select the core subpopulation according to the decision diagram; where the local density is defined as: in, represents the distance between the i-th subgroup and the j-th subgroup, Scales representing subgroups; The relative distance is defined as: Then, the non-core subclusters are merged or eliminated to obtain the final subclusters.

7. The method for classifying phobia under limited sample conditions according to claim 1, characterized in that: Step S105 specifically includes: aligning the time series features of different subgroups along the time dimension using a dynamic time warping algorithm; flattening the aligned features and performing nonlinear transformation through a multi-layer perceptron network to estimate the probability distribution of the phobia category, and then predicting the phobia category of each subgroup; the classification process is defined as: in, and b k are the weights and biases for the kth class, is the feature representation of the input sample, P(y=k| ) is the probability that the input sample belongs to category k.

8. The method for classifying phobia under limited sample conditions according to claim 1, characterized in that: For the classification module, three loss functions are used to optimize its learning parameters, including category balance loss, boundary smoothing loss and classification consistency loss.

9. A device for classifying phobia under limited sample conditions, characterized in that: include: A feature extraction unit, used for reading the multimodal behavior and physiological signal data of the patient, and extracting feature representations for latent class analysis from the data using the Bayesian information criterion combined with the maximum expectation algorithm; The feature representation includes a timestamp and a spatial distribution characteristic; a candidate sub-cluster generation unit, configured to input the feature representation into a latent class analysis module, determine the optimal number of classes and boundaries through a hierarchical clustering method, and generate candidate sub-clusters; A confidence score calculation unit, used for re-evaluating the possibility of each sub-cluster by introducing information theory enhancement technology to obtain a confidence score of each sub-cluster; The final subcluster generation unit is used to remove redundant subclusterings according to the confidence score of each subcluster by using an improved density peak clustering algorithm to obtain the final subclustering; The kinesiophobia classification unit is used to input the final sub-clusters into the trained classification module to estimate the kinesiophobia category of each sub-clusters, thereby achieving accurate kinesiophobia classification according to the category.

10. A device for classifying phobia under limited sample conditions, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the computer program can be executed by the processor to implement the method for classifying atopy under limited sample conditions as claimed in any one of claims 1 to 8.

Images