摘要
为提高飞行员注意力检测准确性、及时性,文中提出一种融合EEG与视觉注视的注意力分析方法。文中以飞行训练实验数据为基础,建立了一种以飞行效果评估与反应时测试融合的注意力评估方法,以此为参考对视觉注视、EEG数据进行分割、筛选制作成数据样本,构建EEG、视觉注视数据集。建立MHA LSTM网络模型对融合EEG、视觉注视的多通道数据进行分类分析。实验表明,网络模型平均准确率达到93.56%,比LSTM模型准确率提升了4.6%,可见文中方法在检测性能上具有明显提高。
In order to detect the pilots’attention more accurately and timely,the paper presents an attention analysis method which combines EEG and visual gaze.Firstly,on the basis of the flight training experimental data,an attention evaluation method is proposed which integrates flight effect evaluation and reaction time test.With this as a reference,the visual fixation and EEG data are segmented,screened and then made into data samples,with which the EEG and visual fixation data sets are constructed.Then the MHA LSTM network model is established for classifying and analyzing the multi channel data fused with EEG and visual gaze.The experiment shows that the average accuracy of the network model is 93.56%,4.6%higher than the LSTM model,which indicating that the detection performance of this method has been significantly improved.
作者
蒋光毅
陈桦
王长元
薛鹏翔
JIANG Guangyi;CHEN Hua;WANG Changyuan;XUE Pengxiang(School of Mechatronic Engineering,Xi’an Technological University,Xi’an 710021,China;School of Computer science and Engineering,Xi’an Technological University,Xi’an 710021,China)
出处
《西安工业大学学报》
CAS
2023年第1期48-55,共8页
Journal of Xi’an Technological University
基金
国家自然科学基金(52072293)
西安市科技计划项目(2020KJRC0036)
基础强化计划技术基金(2020 JCJQ JJ 430)。
关键词
脑电图
视觉注视
神经网络
注意力分析
Electroence phalogram(EEG)
visual perception
neural network
attention analysis
