Data augmentation method and system for biomedical signals based on self-training

Abstract

The present invention belongs to the field of data processing technology. A self-training-based data amplification method and system for biomedical signals is proposed. According to any pre-processed real sample and a pre-trained diffusion model, multiple amplified samples corresponding to the real sample are obtained; the similarity between the real sample and each amplified sample is calculated, and a unique amplified sample that is most similar to the real sample is selected based on the similarity, and the amplified samples corresponding to all real samples are calculated; based on the amplified samples and the downstream model preliminarily trained based on the real samples, the pseudo-labels of the amplified samples are calculated, and based on the comparison of the pseudo-labels and the real labels, the unique amplified sample with the consistent label is used as the final amplified sample. The present invention solves the problems of insufficient biomedical signal data volume, insufficient diversity, and data and label noise, and significantly improves the performance of the downstream model.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a data amplification method and system for biomedical signals based on self-training. Background Art

[0002] The statements in this section merely provide background art related to the present invention and do not necessarily constitute prior art.

[0003] Biomedical signals refer to signals spontaneously generated by human physiological processes, such as electrocardiograms (ECGs), electroencephalograms (EEGs), and electromyograms (EMGs). They play a vital role in disease diagnosis, monitoring, and treatment. With the advent of the big data era, biomedical signal data is increasingly stored electronically. Artificial intelligence technology, particularly deep neural networks, has become an important tool for processing these signals. Deep learning models, with their sophisticated function layer design, are able to effectively process and analyze complex biomedical signals, achieving remarkable results in signal classification and diagnosis tasks. However, the performance of deep neural networks typically relies on large amounts of labeled data. Biomedical signal data is not only scarce but also has strict privacy protection requirements, which undoubtedly poses a huge challenge to related research.

[0004] To overcome data scarcity, various data augmentation methods have been proposed to improve the performance of downstream tasks by expanding datasets. Early biomedical signal enhancement methods largely borrowed techniques from image processing, employing basic operations such as simple flipping, segmentation, and reassembly to generate new data samples. However, the samples generated by these methods are limited in diversity and fail to effectively increase data diversity, which can easily lead to overfitting of downstream models. To address this issue, generative models such as generative adversarial networks (GANs) and variational autoencoders (VAEs) have been introduced in recent years for biomedical signal enhancement research. While these generative models can generate more realistic signal samples, they still face several challenges. For example, due to limitations in training data and model design, the generated data often lacks sufficient diversity. Furthermore, models such as VAEs and GANs can introduce structural distortions during the generation process, compromising the quality of the enhanced data.

[0005] Currently, diffusion models, as an emerging data augmentation method, have received widespread attention due to their ability to increase data diversity. In the field of biomedical signals, diffusion models have demonstrated potential in generating diverse signal samples. However, on the one hand, diffusion models may also face the risk of generating false or over-enhanced samples when enhancing biomedical signals. In particular, during signal processing, overemphasizing certain features of the data distribution may introduce additional noise, thereby affecting the training and testing performance of downstream models. On the other hand, the accuracy of data labels has also become a significant issue. The generation process may not perfectly preserve the label information of the original samples, and the labels of the enhanced data may be affected by noise or inconsistency, further exacerbating the noise problem in the data. Summary of the Invention

[0006] To address the shortcomings of the existing technology, the present invention provides a self-training-based data amplification method and system for biomedical signals, which solves problems such as insufficient biomedical signal data volume, insufficient diversity, and data and label noise. It significantly improves the performance of downstream models (such as classification models), assists doctors in completing more accurate classification tasks, and lays the foundation for the integration of deep learning and the medical and health fields.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] In a first aspect, the present invention provides a data amplification method for biomedical signals based on self-training.

[0009] A data augmentation method for biomedical signals based on self-training, comprising the following steps:

[0010] Preprocessing multiple real biomedical sample signals to obtain multiple preprocessed real samples;

[0011] According to any of the real samples and the pre-trained diffusion model, a plurality of amplified samples corresponding to the real sample are obtained;

[0012] Calculating the similarity between the true sample and each of the amplified samples, selecting a unique amplified sample that is most similar to the true sample based on the similarity, and calculating the unique amplified samples corresponding to all the true samples;

[0013] According to the unique amplified sample and the downstream model preliminarily trained based on the real sample, the pseudo label of the amplified sample is calculated. According to the comparison between the pseudo label and the real label, the unique amplified sample with the consistent label is used as the final amplified sample.

[0014] As a further limitation of the first aspect of the present invention, preprocessing the plurality of real biomedical sample signals includes:

[0015] A bandpass filter is used to remove high-frequency noise and low-frequency interference in the real biomedical sample signal, retain the mid-frequency band signal, and perform normalization processing on the retained mid-frequency band signal.

[0016] As a further limitation of the first aspect of the present invention, in the pre-trained diffusion model, a Transformer model with an attention mechanism is used to learn the inverse distribution to predict the amount of noise added at each time step.

[0017] As a further limitation of the first aspect of the present invention, calculating the similarity between the true sample and each of the amplified samples, and selecting a unique amplified sample that is most similar to the true sample according to the similarity, comprises:

[0018] Calculate the cosine similarity between the two-dimensional embedding of the real sample and the two-dimensional embedding of each amplified sample respectively;

[0019] Sorting according to the cosine similarity values, if any cosine similarity value is greater than a set threshold, selecting the amplified sample with the highest cosine similarity value as the only amplified sample of the true sample;

[0020] If the cosine similarity values are all less than or equal to the set threshold, multiple amplified samples are regenerated for the real sample, and the most similar unique amplified sample is reselected until the selection is completed.

[0021] As a further limitation of the first aspect of the present invention, a real training set consisting of each of the real samples is used to train the downstream model to obtain a preliminarily trained downstream model; based on the preliminarily trained downstream model and the unique amplified sample, a pseudo-label of the amplified sample is obtained, and the only amplified sample whose pseudo-label is the same as the real label of the real sample is retained; all the retained unique amplified samples and all the real samples continue to be used as training data for the downstream model to train the downstream model until the training accuracy requirement of the downstream model is met.

[0022] In a second aspect, the present invention provides a data amplification system for biomedical signals based on self-training.

[0023] A data augmentation system for biomedical signals based on self-training, comprising:

[0024] The data preprocessing unit is configured to: preprocess a plurality of real biomedical sample signals to obtain a plurality of preprocessed real samples;

[0025] The data amplification unit is configured to: obtain a plurality of amplified samples corresponding to any one of the real samples and the pre-trained diffusion model;

[0026] a sample selection unit configured to: calculate the similarity between the true sample and each of the amplified samples, select a unique amplified sample that is most similar to the true sample according to the similarity, and calculate unique amplified samples corresponding to all the true samples;

[0027] The self-training amplification unit is configured to: calculate the pseudo label of the amplified sample based on the unique amplified sample and the downstream model preliminarily trained based on the real sample, and based on the comparison between the pseudo label and the real label, take the unique amplified sample with the consistent label as the final amplified sample.

[0028] As a further limitation of the second aspect of the present invention, in the self-training amplification unit, a real training set composed of each of the real samples is used to train the downstream model to obtain a preliminarily trained downstream model; based on the preliminarily trained downstream model and the unique amplified sample, a pseudo-label of the amplified sample is obtained, and the only amplified sample whose pseudo-label is the same as the real label of the real sample is retained; all the retained unique amplified samples and all the real samples continue to be used as training data for the downstream model to train the downstream model until the training accuracy requirement of the downstream model is met.

[0029] In a third aspect, the present invention provides a computer device comprising: a processor and a computer-readable storage medium;

[0030] a processor adapted to execute a computer program;

[0031] A computer-readable storage medium having a computer program stored therein, wherein the computer program, when executed by the processor, implements the self-training-based data amplification method for biomedical signals as described in the first aspect of the present invention.

[0032] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program is suitable for being loaded by a processor and executing the self-training-based biomedical signal-oriented data amplification method as described in the first aspect of the present invention.

[0033] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the self-training-based data amplification method for biomedical signals as described in the first aspect of the present invention.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] 1. This invention innovatively proposes a self-training-based data amplification strategy for biomedical signals. Through data preprocessing, data generation, data selection, and self-training, it addresses issues such as insufficient biomedical signal data volume, insufficient diversity, and data and label noise. It significantly improves the performance of downstream models (such as classification models), assists doctors in completing more accurate classification tasks, and lays the foundation for the integration of deep learning and the medical and health fields.

[0036] 2. The present invention removes inherent noise and interference in biomedical signals through data preprocessing, ensuring the accuracy of subsequent processing. It uses bandpass filters and normalization operations to optimize the quality of original signals and improve processing accuracy.

[0037] 3. The present invention solves the problems of insufficient biomedical signal data volume and lack of diversity through the data generation stage. It adopts the diffusion model for data enhancement. By generating new signal samples, it not only effectively expands the data set, but also ensures the diversity of the enhanced data and enhances the generalization ability of the model.

[0038] 4. To address the problems of false enhancement and data noise that may be introduced by the generative model, the present invention selects the most similar generated sample for each real data sample and ensures the diversity of the samples, thereby reducing the interference of invalid data on model training and optimizing the quality of the dataset.

[0039] 5. The present invention solves the label noise problem caused by inaccurate generated data labels through a self-training mechanism. It can continuously screen out samples with high-confidence labels and add them to the training of downstream models. In the iterative process, it not only optimizes label selection but also improves the performance of downstream models.

[0040] Advantages of additional aspects of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0042] Figure 1 A schematic flow chart of a method for data amplification of biomedical signals based on self-training provided in Example 1 of the present invention;

[0043] Figure 2 A schematic diagram of the process of the self-training phase provided in Example 1 of the present invention;

[0044] Figure 3A schematic diagram of a data amplification system for biomedical signals based on self-training provided in Example 2 of the present invention;

[0045] Figure 4 A schematic diagram of a computer device provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0046] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0047] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0048] In the absence of conflict, the embodiments of the present invention and the features thereof may be combined with each other.

[0049] Example 1:

[0050] This implementation proposes a data amplification method for biomedical signals based on self-training, and designs a self-training enhancement framework. Through a series of precisely designed processing stages, it effectively alleviates the sparsity of biomedical signal data and the need to pay attention to privacy protection, improves data diversity, reduces data noise caused by the diffusion model, and optimizes label accuracy through a self-training mechanism. Specifically, in the data preprocessing stage, bandpass filters and normalization operations are used to eliminate noise interference; in the data generation stage, the diffusion model is used to increase the amount of data and ensure diversity; in the data selection stage, false enhancement is avoided and data noise is reduced by selecting the most similar generated sample for each real sample; in the self-training stage, label noise is reduced by selecting samples with high confidence labels, thereby continuously improving the performance of downstream models. The present invention effectively improves the accuracy and robustness of biomedical signal processing and promotes the application of deep learning technology in the field of medical and health care.

[0051] like Figure 1 As shown, the real biomedical signal samples are band-pass filtered and normalized to obtain a preprocessed data set. The diffusion model is used to generate data according to a 1:N ratio to initially generate a data set. The cosine similarity is calculated between each real sample and each N generated sample to determine whether there is a generated sample with a similarity greater than a threshold λ. If so, the generated sample with the highest similarity is selected to obtain the generated data. If not, the generated data is regenerated and the cosine similarity is calculated again for each real sample and each N generated sample.

[0052] The data augmentation method, more specifically, includes the following steps:

[0053] S1: Data preprocessing phase. This phase aims to mitigate the noise and interference inherent in biomedical signals to improve the accuracy of subsequent processing and ensure the quality of the original signal by removing irrelevant noise and abnormal data.

[0054] S2: Data generation phase. To address the issues of insufficient biomedical signal data volume and lack of diversity, this phase uses a diffusion model for data augmentation. By generating new signal samples, this not only effectively expands the data volume but also ensures the diversity of the enhanced data.

[0055] S3: Data selection stage: This stage aims to alleviate the problems of false enhancement and data noise that may be caused by the generative model. It selects the generated sample that is most similar to each real data sample (i.e., the unique augmented sample) while maintaining the diversity of the data, thereby reducing the interference of invalid data on model training.

[0056] S4: Self-training. This phase addresses the label noise issue that may arise from generating data samples. Through the self-training mechanism, the framework continuously selects samples with accurate labels and feeds them into the training of downstream models. This iterative process optimizes label selection and improves the classification performance of downstream models.

[0057] In step S1 of this implementation method, specifically, it includes: in the process of collecting biomedical signals, various noises and interferences are often inevitably introduced. These non-target signals may significantly affect the accuracy of subsequent signal generation and classification tasks. In order to ensure the reliability of the experimental results, the signal was carefully preprocessed in the early stage. First, a bandpass filter was used to effectively remove high-frequency noise and low-frequency interference in the ECG signal, while retaining the mid-frequency band where the main signal components are located; then, the filtered signal was normalized to limit the numerical range of each sample to the interval [0,1], thereby providing a unified and clear data basis for subsequent analysis.

[0058] Step S2 of this implementation specifically includes: dividing the processed biomedical signal data into a training set, a validation set, and a test set in proportion. The training set is used to train the generative model, while the validation set and the test set are used only to test the performance of downstream models. Compared to other generative models, data enhanced using the diffusion model can exhibit greater diversity. Therefore, the diffusion model is selected to generate more diverse data. The generation phase can be divided into two steps: training and sampling.

[0059] First, the training process can be divided into a forward process and a backward process. The forward process involves adding noise to real data samples until the original data becomes pure noise. The backward process, on the other hand, involves continuous learning to gradually remove the noise and restore the original data.

[0060] Specifically, suppose there is a biomedical signal sample ,pass time steps to gradually add noise, As the sample set, we continuously get , the size of the noise added at each step is determined by the hyperparameter Decided, specifically as follows:

[0061] (1);

[0062] and They are Moment and The sample signal at each moment can be found in the forward process Just and It is related to the time, so it can also be regarded as a Markov process. After derivation, at any time Can be directly and Calculation yields:

[0063] (2);

[0064] in, and , Over time With the increase of t As increases, the original data gradually becomes pure noise.

[0065] Then the reverse reasoning process is carried out to restore the real data sample. Considering that if the noise addition process can be reversed from By sampling in, the real sample data can be restored from pure noise, but it cannot be simply deduced from the formula , so a neural network model is needed to learn such an inverse distribution :

[0066] (3);

[0067] )(4).

[0068] Considering the long sequence characteristics of biomedical signals, the Transformer architecture with attention mechanism is used as the neural network model of the diffusion model. Mean and variance in a distribution , to restore the real data distribution, considering that for DDPM, the fixed variance is The best result is achieved when , for which the variance is also fixed, and the mean is calculated as follows:

[0069] (5);

[0070] Among them, the neural network model can be used to predict the amount of noise added at each time step , the above formula can be rewritten as:

[0071] )(6);

[0072] The diffusion model can then be trained using the following loss function:

[0073] (7).

[0074] in, represents the noise parameter, and are the corresponding noise amounts respectively.

[0075] The sampling process mainly consists of a reverse process, which is to continuously remove noise from the original noise and generate many new samples. Specifically, starting from random noise, the trained neural network model is used to continuously predict the amount of noise added in the previous time step, and then continuously move forward to obtain , for each real data sample, a diffusion model is used to generate The corresponding generated data samples.

[0076] In step S3 of this implementation, if Figure 2 Specifically, considering that the diffusion model is prone to false enhancement and data noise, if all inputs are used as downstream models, the model will be greatly affected by the noise. Therefore, after obtaining the generated data, a data selection stage is added, and cosine similarity is used for selection. The specific process is as follows:

[0077] First, using the trained diffusion model, for each real sample ,generate data samples ; Secondly, flatten the three-dimensional time series data into two-dimensional time series data (flattened in the channel dimension) to prepare for calculating cosine similarity; then calculate the two-dimensional embedding of the real sample and 2D embedding of generated samples Then, the generated samples are sorted according to these cosine similarity values. If any similarity value of the generated samples exceeds the threshold , then the sample with the highest similarity is selected as the generated sample corresponding to the real sample. If no sample meets the conditions, the real sample is regenerated samples, recalculate, compare and select the appropriate sample.

[0078] The specific implementation formula of the above process is as follows:

[0079] (8);

[0080] (9);

[0081] (10);

[0082] in, Indicates the index of the selected generated sample, which ranges from 1 to . The above data selection process includes executing the above three formulas. If no samples consistent with the trend are found in each round of generation, the process is restarted and the above formula is re-executed until a suitable sample is selected. Usually, a trained diffusion model does not require multiple iterations to generate the required data samples. Through this data selection stage, the generated data that is most similar to the real data trend can be identified, thereby ensuring the quality of the generated samples and alleviating the data noise problem caused by false enhancement. Through this step, the same number of generated samples as the real data can be obtained to form a generated data set.

[0083] In step S4 of this implementation, specifically, it includes: after the data selection stage is completed, each real data sample will be matched with a closest generated sample, and this process is not simply repeated, ensuring the diversity of the generated samples. In order to solve the label noise problem that may be caused by the generated data samples, that is, the labels of the generated data may be inaccurate, the framework continuously selects samples with higher label accuracy through the self-training mechanism and puts them into the training of the downstream model. In this cyclic process, both label optimization and the performance of the classification model are improved. The specific cyclic process is as follows:

[0084] First, a real training dataset is used to train the downstream model, resulting in a preliminarily trained downstream model, which already possesses a certain degree of classification capability. The trained downstream model is then used to predict the labels of the generated data, obtaining pseudo-labels. These pseudo-labels are then compared with the original labels of the generated data, assuming that the pseudo-labels and original labels each have a 50% accuracy rate. Based on this criterion, generated samples with consistent labels are retained, effectively reducing label noise. Next, the retained generated data is mixed with real data and used to train the downstream model, further improving the model's classification performance. This process not only enhances the downstream model's ability to process real data but also improves the accuracy of generated sample label predictions in the next cycle. The above steps are iterated continuously until the performance of the downstream model no longer significantly improves. Through this continuous optimization process, a downstream model (e.g., a classification model) with continuously improving performance is ultimately obtained.

[0085] The above is the entire process for a patient sample instance. In actual applications, multiple real data samples are required to generate multiple generated data, and then carry out the subsequent selection process.

[0086] Example 2:

[0087] like Figure 3 As shown, this implementation provides a data amplification system for biomedical signals based on self-training, including:

[0088] The data preprocessing unit is configured to preprocess the plurality of real biomedical sample signals to obtain a plurality of preprocessed real samples. The specific process is described in step S1 of embodiment 1 and will not be repeated here.

[0089] The data amplification unit is configured to: obtain multiple amplified samples corresponding to any one of the real samples and the pre-trained diffusion model; the specific process is described in step S2 of embodiment 1 and will not be repeated here;

[0090] The sample selection unit is configured to: calculate the similarity between the real sample and each of the amplified samples, select a unique amplified sample that is most similar to the real sample based on the similarity, and calculate the unique amplified samples corresponding to all the real samples; the specific process is described in step S3 of embodiment 1 and will not be repeated here;

[0091] The self-training amplification unit is configured to: calculate the pseudo-label of the amplified sample based on the unique amplified sample and the downstream model preliminarily trained based on the real sample, and based on the comparison between the pseudo-label and the real label, use the unique amplified sample with the consistent label as the final amplified sample; the specific process is described in step S4 in Example 1 and will not be repeated here.

[0092] It is understandable that each of the above-mentioned units can be separately or completely combined into one or several other units to constitute, or one (or some) of the units can be further divided into multiple functionally smaller units to constitute, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions. In actual applications, the functions of one unit can also be implemented by multiple units, or the functions of multiple units can be implemented by one unit. In other embodiments of the present application, the system may also include other units. In actual applications, these functions can also be implemented with the assistance of other units, and can be implemented by the collaboration of multiple units.

[0093] According to another embodiment of the present application, the system described in this embodiment can be constructed and the method of Example 1 of the present application can be implemented by running a computer program (including program code) capable of executing the steps involved in the corresponding method described in Example 1 on a general-purpose computing device such as a computer, which includes processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). The computer program can be recorded on, for example, a computer-readable recording medium, and loaded into the above-mentioned computing device through the computer-readable recording medium and run therein.

[0094] Example 3:

[0095] like Figure 4 As shown, this implementation provides an electronic device, which includes a processor 1001, a communication interface 1002, and a computer-readable storage medium 1003. The processor 1001, the communication interface 1002, and the computer-readable storage medium 1003 may be connected via a bus or other means.

[0096] Among them, the communication interface 1002 is used to receive and send data, the computer-readable storage medium 1003 can be stored in the memory of the electronic device, the computer-readable storage medium 1003 is used to store a computer program, the computer program includes program instructions, and the processor 1001 is used to execute the program instructions stored in the computer-readable storage medium 1003.

[0097] The processor 1001 (also called CPU (Central Processing Unit)) is the computing core and control core of the electronic device, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to implement corresponding method processes or corresponding functions.

[0098] The processor 1001 is configured to execute the following process:

[0099] Preprocessing the plurality of real biomedical sample signals to obtain a plurality of preprocessed real samples; the specific process is described in step S1 in Example 1 and will not be repeated here;

[0100] According to any of the real samples and the pre-trained diffusion model, multiple amplified samples corresponding to the real sample are obtained; the specific process is described in step S2 of Example 1 and will not be repeated here;

[0101] Calculate the similarity between the true sample and each of the amplified samples, select a unique amplified sample that is most similar to the true sample based on the similarity, and calculate the unique amplified samples corresponding to all the true samples; the specific process is described in step S3 of Example 1 and will not be repeated here;

[0102] Based on the unique amplified sample and the downstream model preliminarily trained based on the real sample, the pseudo label of the amplified sample is calculated. Based on the comparison between the pseudo label and the real label, the unique amplified sample with the consistent label is used as the final amplified sample. The specific process is described in step S4 in Example 1 and will not be repeated here.

[0103] Example 4:

[0104] This implementation provides a computer-readable storage medium (Memory). This computer-readable storage medium is a memory device within an electronic device that stores programs and data. It should be understood that the computer-readable storage medium herein may include both built-in storage media within the electronic device and, of course, extended storage media supported by the electronic device. The computer-readable storage medium provides storage space that stores the processing system of the electronic device.

[0105] Furthermore, the storage space also stores one or more instructions suitable for being loaded and executed by the processor. These instructions may be one or more computer programs (including program code). It should be noted that the computer-readable storage medium herein may be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage device; alternatively, it may be at least one computer-readable storage medium located remotely from the processor.

[0106] In one embodiment, the computer-readable storage medium stores one or more instructions; the processor loads and executes the one or more instructions stored in the computer-readable storage medium to implement the following process:

[0107] Preprocessing the plurality of real biomedical sample signals to obtain a plurality of preprocessed real samples; the specific process is described in step S1 in Example 1 and will not be repeated here;

[0108] According to any of the real samples and the pre-trained diffusion model, multiple amplified samples corresponding to the real sample are obtained; the specific process is described in step S2 of Example 1 and will not be repeated here;

[0109] Calculate the similarity between the true sample and each of the amplified samples, select a unique amplified sample that is most similar to the true sample based on the similarity, and calculate the unique amplified samples corresponding to all the true samples; the specific process is described in step S3 of Example 1 and will not be repeated here;

[0110] Based on the unique amplified sample and the downstream model preliminarily trained based on the real sample, the pseudo label of the amplified sample is calculated. Based on the comparison between the pseudo label and the real label, the unique amplified sample with the consistent label is used as the final amplified sample. The specific process is described in step S4 in Example 1 and will not be repeated here.

[0111] Example 5:

[0112] This implementation provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the following process:

[0113] Preprocessing the plurality of real biomedical sample signals to obtain a plurality of preprocessed real samples; the specific process is described in step S1 in Example 1 and will not be repeated here;

[0114] According to any of the real samples and the pre-trained diffusion model, multiple amplified samples corresponding to the real sample are obtained; the specific process is described in step S2 of Example 1 and will not be repeated here;

[0115] Calculate the similarity between the true sample and each of the amplified samples, select a unique amplified sample that is most similar to the true sample based on the similarity, and calculate the unique amplified samples corresponding to all the true samples; the specific process is described in step S3 of Example 1 and will not be repeated here;

[0116] Based on the unique amplified sample and the downstream model preliminarily trained based on the real sample, the pseudo label of the amplified sample is calculated. Based on the comparison between the pseudo label and the real label, the unique amplified sample with the consistent label is used as the final amplified sample. The specific process is described in step S4 in Example 1 and will not be repeated here.

[0117] Those skilled in the art will appreciate that the units and algorithmic steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technical personnel may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0118] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted via a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data processing device such as a server or data center that integrates one or more available media. Available media can be magnetic media (e.g., floppy disk, hard disk, tape), optical media (e.g., DVD), or semiconductor media (e.g., solid-state drive (SSD)).

[0119] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A data augmentation method for biomedical signals based on self-training, characterized in that: The following processes are included: Preprocessing multiple real biomedical sample signals to obtain multiple preprocessed real samples; According to any of the real samples and the pre-trained diffusion model, a plurality of amplified samples corresponding to the real sample are obtained; Calculating the similarity between the true sample and each of the amplified samples, selecting a unique amplified sample that is most similar to the true sample based on the similarity, and calculating the unique amplified samples corresponding to all the true samples; Calculate a pseudo-label of the amplified sample based on the unique amplified sample and a downstream model preliminarily trained based on the real sample, and determine the unique amplified sample with the consistent label as the final amplified sample based on a comparison between the pseudo-label and the real label; Calculating the similarity between the true sample and each of the amplified samples, and selecting a unique amplified sample that is most similar to the true sample according to the similarity, including: Calculate the cosine similarity between the two-dimensional embedding of the real sample and the two-dimensional embedding of each amplified sample respectively; Sorting according to the cosine similarity values, if any cosine similarity value is greater than a set threshold, selecting the amplified sample with the highest cosine similarity value as the only amplified sample of the true sample; If the cosine similarity values are all less than or equal to the set threshold, multiple amplified samples are regenerated for the real sample, and the most similar unique amplified sample is reselected until the selection is completed; In the pre-trained diffusion model, a Transformer model with an attention mechanism is used to learn the inverse distribution to predict the amount of noise added at each time step; A real training set consisting of each of the real samples is used to train the downstream model to obtain a preliminarily trained downstream model; a pseudo-label of the amplified sample is obtained based on the preliminarily trained downstream model and the unique amplified sample, and the unique amplified sample whose pseudo-label is the same as the real label of the real sample is retained; all the retained unique amplified samples and all the real samples are continued to be used as training data for the downstream model to train the downstream model, and through loop iteration, samples with high-confidence labels are continuously screened out and added to the training of the downstream model until the training accuracy requirement of the downstream model is met.

2. The method for biomedical signal amplification based on self-training according to claim 1, wherein: Preprocess multiple real biomedical sample signals, including: A bandpass filter is used to remove high-frequency noise and low-frequency interference in the real biomedical sample signal, retain the mid-frequency band signal, and perform normalization processing on the retained mid-frequency band signal.

3. A data augmentation system for biomedical signals based on self-training, characterized in that: include: The data preprocessing unit is configured to: preprocess a plurality of real biomedical sample signals to obtain a plurality of preprocessed real samples; The data amplification unit is configured to: obtain a plurality of amplified samples corresponding to any one of the real samples and the pre-trained diffusion model; a sample selection unit configured to: calculate the similarity between the true sample and each of the amplified samples, select a unique amplified sample that is most similar to the true sample according to the similarity, and calculate unique amplified samples corresponding to all the true samples; The self-training amplification unit is configured to: calculate a pseudo label of the amplified sample based on the unique amplified sample and a downstream model preliminarily trained based on the real sample, and based on a comparison between the pseudo label and the real label, use the unique amplified sample with the consistent label as the final amplified sample; Calculating the similarity between the true sample and each of the amplified samples, and selecting a unique amplified sample that is most similar to the true sample according to the similarity, including: Calculate the cosine similarity between the two-dimensional embedding of the real sample and the two-dimensional embedding of each amplified sample respectively; Sorting according to the cosine similarity values, if any cosine similarity value is greater than a set threshold, selecting the amplified sample with the highest cosine similarity value as the only amplified sample of the true sample; If the cosine similarity values are all less than or equal to the set threshold, multiple amplified samples are regenerated for the real sample, and the most similar unique amplified sample is reselected until the selection is completed; In the pre-trained diffusion model, a Transformer model with an attention mechanism is used to learn the inverse distribution to predict the amount of noise added at each time step; A real training set consisting of each of the real samples is used to train a downstream model to obtain a preliminarily trained downstream model; a pseudo-label of the amplified sample is obtained based on the preliminarily trained downstream model and the unique amplified sample, and the unique amplified sample whose pseudo-label is the same as the real label of the real sample is retained; all the retained unique amplified samples and all the real samples are continued to be used as training data for the downstream model to train the downstream model until the training accuracy requirement of the downstream model is met.

4. The self-training-based data augmentation system for biomedical signals according to claim 3, wherein: In the self-training amplification unit, a real training set consisting of each of the real samples is used to train the downstream model to obtain a preliminarily trained downstream model; based on the preliminarily trained downstream model and the unique amplified sample, a pseudo-label of the amplified sample is obtained, and the only amplified sample whose pseudo-label is the same as the real label of the real sample is retained; all the retained unique amplified samples and all the real samples are continued to be used as training data for the downstream model to train the downstream model until the training accuracy requirement of the downstream model is met.

5. A computer device, characterized in that: include: a processor and a computer-readable storage medium; a processor adapted to execute a computer program; A computer-readable storage medium having a computer program stored therein, wherein the computer program, when executed by the processor, implements the self-training-based data amplification method for biomedical signals according to any one of claims 1 to 2.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which is suitable for being loaded by a processor and executing the self-training-based biomedical signal-oriented data amplification method according to any one of claims 1 to 2.

7. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the self-training-based data amplification method for biomedical signals according to any one of claims 1 to 2.

Images