A novel lie detection method based on extreme learning machine using P300
Yijun Xiong, Yong Yang, Junfeng Gao · 2012
Machine learning-based lie detection has drawn much attention recently. In this paper, we used extreme learning machine (ELM), a recently-proposed machine learning method based on a single layer feedforward network (SLFN), to classify P300 potentials from guilty subject and non-P300 potentials from innocent subject. Back-propagation network and support vector machine classifiers were also used to compare with the proposed method. The number of hidden nodes in ELM was tuned using training with the 10-fold cross validation. The experimental results show that the proposed method reaches the highest classification accuracy with extremely less training and testing time, compared with the other classification models.