摘要
面孔诱发的脑电信号与基函数迭代所构成离散动力系统是混沌的,导致现阶段针对脑电信号的飞行员疲劳评估,存在评估效果不佳等问题。对此,研究混沌脑电信号下的飞行员疲劳评估方法。首先,使用验模态分解的方法,对飞行员脑电信号展开去混沌化处理;然后,通过套袋-正则化空间模式方法,提取飞行员脑电信号特征向量;最后,输入飞行员脑电信号特征向量至隐马尔可夫模型(HMM)与贝叶斯网络结合模型中,完成飞行员疲劳评估。实验结果表明,所提方法的飞行员疲劳评估准确度在91.7%,飞行员疲劳误差在1%~4%,获得了更准确的飞行员疲劳评估结果。
The discrete dynamic system composed of facial evoked EEG signal and basis function iteration is cha-otic,which leads to the poor evaluation effect of pilot fatigue assessment for EEG signal at present.In this regard,the pilot fatigue assessment method under chaotic EEG signals is studied.Firstly,the pilot EEG signals are de-chaotized by using the empirical mode decomposition method.Then,the pilot EEG feature vectors are extracted by the bagging regularized spatial pattern method.Finally,the pilot EEG signal feature vector is input into the hidden Markov model(HMM)and Bayesian network combination model to complete the pilot fatigue assessment.The experimental results show that the accuracy of the pilot fatigue assessment of the proposed method is 91.7%,and the pilot fatigue error is 1%~4%.More accurate pilot fatigue assessment results are obtained.
作者
陈宇亮
李润平
CHEN Yu-liang;LI Run-ping(Special Service Department of the Sixth Medical Center of the General Hospital of the People's Liberation Army,Beijing 100048,China;Diving Medicine Teaching and Research Office of Naval Medical University,Shanghai 200433,China)
出处
《计算机仿真》
2024年第11期443-447,共5页
Computer Simulation
基金
海军装备军内科研计划项目(HJ20172B02012)。
关键词
混沌脑电信号
疲劳评估
经验模态分解
贝叶斯网络
马尔可夫链
Chaotic EEG signals
Fatigue assessment
Empirical modal decomposition
Bayesian network
Markovchain
