Classification of a Driver's cognitive workload levels using artificial neural network on ECG signals
详细信息 查看全文
- 作者：Amir Tjolleng<sup>asup><sup> ; sup><sup>amirtjoleng@yahoo.co.idsup> ; Kihyo Jung<sup>asup><sup> ; sup><sup>kjung@ulsan.ac.krsup> ; Wongi Hong<sup>bsup><sup> ; sup><sup>wonkiman@naver.comsup> ; Wonsup Lee<sup>csup><sup> ; sup><sup>w.lee@tudelft.nlsup> ; Baekhee Lee<sup>dsup><sup> ; sup><sup>x200won@postech.ac.krsup> ; Heecheon You<sup>dsup><sup> ; sup><sup>hcyou@postech.ac.krsup> ; Joonwoo Son<sup>esup><sup> ; sup><sup>json@dgist.ac.krsup> ; Seikwon Park<sup>fsup><sup> ; sup><sup>ergoparks@gmail.comsup>
- 关键词：Cognitive workload classification ; Heart rate variability ; Artificial neural network
- 刊名：Applied Ergonomics
- 出版年：2017
- 出版时间：March 2017
- 年：2017
- 卷：59
- 期：part_PA
- 页码：326-332
- 全文大小：1569 K
- 卷排序：59
文摘
An artificial neural network (ANN) model was developed to classify the level of cognitive workload. A three-step data processing was performed to compensate for individual differences in heart response. Six ECG measures in time (mean IBI, SDNN, and RMSSD) and frequency (LF, HF, and LF/HF) domains were collected. Accuracy of the ANN model was found satisfactory for learning data (95%) and testing data (82%).