摘要
为了正确地解释大脑活动并对脑电图信号数据进行有效识别,提出一种双通道注意力机制模型,对原始的脑电图信号数据进行分类,从而识别用户的意图。对于公共数据集Eegmmidb,模型在5项识别任务上的平均识别率为99.34%。实验结果表明:所提模型优于现有方法。
To interpret brain activity correctly and classify electroencephalography(EEG)signal data properly,a dual-channel attention mechanism model to classify raw EEG data and is proposed thus users’intents is recognized.The model achieves an average recognition rate of 99.34%over five tasks,on public dataset,eegmmidb.The experimental results show that the model outperforms the state-of-the-art methods.
作者
孙亚东
徐晓涛
章军
陈鹏
SUN Yadong;XU Xiaotao;ZHANG Jun;CHEN Peng(School of Electrical Engineering and Automation,Anhui University,Hefei 230601,China;National and Local Joint Engineering Research Center for Agricultural Ecology Big Data Analysis and Application Technology,School of Internet,Anhui University,Hefei 230601,China)
出处
《传感器与微系统》
CSCD
北大核心
2021年第9期128-131,共4页
Transducer and Microsystem Technologies
基金
国家自然科学基金资助项目(61872004)。
关键词
意图识别
注意力机制
脑电图信号
脑机接口
intent recognition
attention mechanism
electroencephalography(EEG)signals
brain-computer interface(BCI)