摘要
论文对基于眼电信号(EOG)的扫视角度识别算法进行研究。设计了扫视角度定位和EOG采集实验。提出了联合线性预测系数和波形参数的EOG特征描述新方法;并使用BP神经网络与支持向量机对特征向量进行识别和分类。实验结果表明,本文所提出的方法能较好地识别出不同扫视角度的眼动模式。
This paper researches the saccadic angle recognition algorithm based on electrooculogram（EOG）.The experiment of EOG signal collection at different horizontal saccadic angle is carried out.The linear prediction coefficients（LPC）and waveform features are combined to be the feature vector of EOG signal;then the BP neural network and support vector machine are used to identify and classify the feature vectors.The result of experiment shows that the method proposed can recognize the eye movement with different saccadic angles effectively.
出处
《电子测量技术》
2010年第8期39-42,49,共5页
Electronic Measurement Technology
基金
国家自然科学基金(编号:60771033)资助项目
博士点基金(编号:200803570002)
关键词
眼电
扫视角度
线性预测系数
BP神经网络
支持向量机
electrooculogram
saccadic angle
linear predictive coding
BP neural network
support vector machine
