{"title":"基于自适应小波变换Kolmogorov-Arnold的运动图像脑电图分类轻量级神经网络","authors":"Yu Song;Hang Zhang;Janzhi Man;Xiaoqian Jin;Qi Li","doi":"10.1109/TCE.2025.3540970","DOIUrl":null,"url":null,"abstract":"Motor imagery electroencephalography (MI-EEG) is widely used in the neural rehabilitation field, including for hybrid device control, such as robotic arms. However, it is difficult to apply large models with good performance in consumer electronics (CE) with limited computing and memory resources. To address this challenge, this study proposes an adaptive wavelet transform Kolmogorov-Arnold network (KAN) approach named AWKNet, which uses wavelet loss to construct personalized discrete wavelet functions for MI-EEG features suited to different topics to learn an effective multiresolution wavelet transform. Second, a depth-separable convolutional layer is used to decouple the cross-channel and frequency domain features of the EEG data, and the conventional multilayer perceptron (MLP) layer is replaced based on the KAN technique. The proposed model is lightweight and improves the performance of the brain-computer interface (BCI) system. The model was employed to classify EEG signals acquired in the BCI Comparison IV 2a dataset and in a real-world environment. In both tasks, the visualization of model weights showed that the trained AWKNet consistently generates scientifically interpretable lightweight models and outperforms more advanced neural networks in terms of classification performance, which indicates that AWKNet has broader application potential in CE. All the code is deposited on GitHub (<uri>https://github.com/Songyu-EEGsignals/AdaptiveWavelets</uri>).","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"71 1","pages":"1219-1234"},"PeriodicalIF":4.3000,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"AWKNet: A Lightweight Neural Network for Motor Imagery Electroencephalogram Classification Based on Adaptive Wavelet Transform Kolmogorov-Arnold\",\"authors\":\"Yu Song;Hang Zhang;Janzhi Man;Xiaoqian Jin;Qi Li\",\"doi\":\"10.1109/TCE.2025.3540970\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Motor imagery electroencephalography (MI-EEG) is widely used in the neural rehabilitation field, including for hybrid device control, such as robotic arms. However, it is difficult to apply large models with good performance in consumer electronics (CE) with limited computing and memory resources. To address this challenge, this study proposes an adaptive wavelet transform Kolmogorov-Arnold network (KAN) approach named AWKNet, which uses wavelet loss to construct personalized discrete wavelet functions for MI-EEG features suited to different topics to learn an effective multiresolution wavelet transform. Second, a depth-separable convolutional layer is used to decouple the cross-channel and frequency domain features of the EEG data, and the conventional multilayer perceptron (MLP) layer is replaced based on the KAN technique. The proposed model is lightweight and improves the performance of the brain-computer interface (BCI) system. The model was employed to classify EEG signals acquired in the BCI Comparison IV 2a dataset and in a real-world environment. In both tasks, the visualization of model weights showed that the trained AWKNet consistently generates scientifically interpretable lightweight models and outperforms more advanced neural networks in terms of classification performance, which indicates that AWKNet has broader application potential in CE. All the code is deposited on GitHub (<uri>https://github.com/Songyu-EEGsignals/AdaptiveWavelets</uri>).\",\"PeriodicalId\":13208,\"journal\":{\"name\":\"IEEE Transactions on Consumer Electronics\",\"volume\":\"71 1\",\"pages\":\"1219-1234\"},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2025-02-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Consumer Electronics\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10880107/\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Consumer Electronics","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10880107/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
摘要
运动图像脑电图(MI-EEG)广泛应用于神经康复领域,包括机械臂等混合装置的控制。然而,由于计算和存储资源有限,在消费类电子产品中很难应用具有良好性能的大型模型。针对这一挑战,本研究提出了一种自适应小波变换Kolmogorov-Arnold网络(KAN)方法,命名为AWKNet,该方法利用小波损失对不同主题的MI-EEG特征构建个性化离散小波函数,学习有效的多分辨率小波变换。其次,采用深度可分卷积层对脑电数据的跨通道和频域特征进行解耦,并基于KAN技术取代传统的多层感知器层;该模型轻量级,提高了脑机接口(BCI)系统的性能。该模型用于对BCI Comparison IV 2a数据集和现实环境中获取的脑电信号进行分类。在这两项任务中,模型权值的可视化表明,训练后的AWKNet始终能够生成科学可解释的轻量级模型,并且在分类性能上优于更高级的神经网络,这表明AWKNet在CE中具有更广泛的应用潜力。所有的代码都存放在GitHub (https://github.com/Songyu-EEGsignals/AdaptiveWavelets)。
AWKNet: A Lightweight Neural Network for Motor Imagery Electroencephalogram Classification Based on Adaptive Wavelet Transform Kolmogorov-Arnold
Motor imagery electroencephalography (MI-EEG) is widely used in the neural rehabilitation field, including for hybrid device control, such as robotic arms. However, it is difficult to apply large models with good performance in consumer electronics (CE) with limited computing and memory resources. To address this challenge, this study proposes an adaptive wavelet transform Kolmogorov-Arnold network (KAN) approach named AWKNet, which uses wavelet loss to construct personalized discrete wavelet functions for MI-EEG features suited to different topics to learn an effective multiresolution wavelet transform. Second, a depth-separable convolutional layer is used to decouple the cross-channel and frequency domain features of the EEG data, and the conventional multilayer perceptron (MLP) layer is replaced based on the KAN technique. The proposed model is lightweight and improves the performance of the brain-computer interface (BCI) system. The model was employed to classify EEG signals acquired in the BCI Comparison IV 2a dataset and in a real-world environment. In both tasks, the visualization of model weights showed that the trained AWKNet consistently generates scientifically interpretable lightweight models and outperforms more advanced neural networks in terms of classification performance, which indicates that AWKNet has broader application potential in CE. All the code is deposited on GitHub (https://github.com/Songyu-EEGsignals/AdaptiveWavelets).
期刊介绍:
The main focus for the IEEE Transactions on Consumer Electronics is the engineering and research aspects of the theory, design, construction, manufacture or end use of mass market electronics, systems, software and services for consumers.