Stroke Electroencephalogram Data Synthesizing through Progressive Efficient Self-Attention Generative Adversarial Network

作     者：Suzhe Wang Xueying Zhang Fenglian Li Zelin Wu 

作者机构：College of Electronic Information EngineeringTaiyuan University of TechnologyTaiyuan030024China 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2024年第81卷第10期

页      面：1177-1196页

核心收录：

学科分类：081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the General Program under grant funded by the National Natural Science Foundation of China(NSFC)(No.62171307) the Basic Research Program of Shanxi Province under grant funded by the Department of Science and Technology of Shanxi Province(China)(No.202103021224113) 

主　　题：Data augmentation stroke electroencephalogram features generative adversarial network efficient approximating self-attention 

摘      要：Early and timely diagnosis of stroke is critical for effective treatment,and the electroencephalogram(EEG)offers a low-cost,non-invasive ***,the shortage of high-quality patient EEG data often hampers the accuracy of diagnostic classification methods based on deep *** address this issue,our study designed a deep data amplification model named Progressive Conditional Generative Adversarial Network with Efficient Approximating Self Attention(PCGAN-EASA),which incrementally improves the quality of generated EEG *** network can yield full-scale,fine-grained EEG features from the low-scale,coarse ***,to overcome the limitations of traditional generative models that fail to generate features tailored to individual patient characteristics,we developed an encoder with an effective approximating self-attention *** encoder not only automatically extracts relevant features across different patients but also reduces the computational resource ***,the adversarial loss and reconstruction loss functions were redesigned to better align with the training characteristics of the network and the spatial correlations among *** experimental results demonstrate that PCGAN-EASA provides the highest generation quality and the lowest computational resource usage compared to several existing ***,it significantly improves the accuracy of subsequent stroke classification tasks.