基于改进超限学习机的N400诱发电位测谎方法

Lie detection method of N400 evoked potential based on improved extreme learning machine

针对现有测谎方法识别率低的缺陷,将人工免疫算法和超限学习机相结合,提出了一种基于AIA-ELM的N400诱发电位测谎新方法。将24名被试分成犯罪组和对照组,提取多通道的N400峰值、平均幅值、中值频率作为特征向量。采用AIA-ELM算法对被试的探测刺激与无关刺激进行分类,犯罪组被试的识别率为97.60%。实验结果表明,本方法能较有效地进行谎言区分,为N400测谎提供了一种新的参考依据。

Aiming at the defects of the low recognition rate of lie detection, this paper proposes a new method of N400 evoked potential polygraphy based on AIA-ELM, which integrates the artificial immune algorithm and the extreme learning machine. 24 subjects are divided into a crime group and a control group respectively to extract the multi-channel peak value, average amplitude and median frequency of N400, and all of them just constitute the eigenvectors. AIA-ELM algorithm is applied to classify the probe stimulus and the irrelevant stimulus, and the recognition rate of crime group is 97.60%. Experimental results show that this method can distinguish lies effectively and provide a new reference for lie detection based on N400.