基于PCANet和SVM的谎言测试研究

顾凌云, 吕文志, 杨勇, 高军峰, 官金安, 周到

电子学报 ›› 2016, Vol. 44 ›› Issue (8) : 1969-1973.

PDF(722 KB)
PDF(722 KB)
电子学报 ›› 2016, Vol. 44 ›› Issue (8) : 1969-1973. DOI: 10.3969/j.issn.0372-2112.2016.08.028
学术论文

基于PCANet和SVM的谎言测试研究

  • 顾凌云1,2, 吕文志3, 杨勇4, 高军峰1,2,5, 官金安1,2, 周到1
作者信息 +

Deception Detection Study Based on PCANet and Support Vector Machine

  • GU Ling-yun1,2, LV Wen-zhi3, YANG Yong4, GAO Jun-feng1,2,5, GUAN Jin-an1,2, ZHOU Dao1
Author information +
文章历史 +

摘要

主成分分析网络(Principal Component Analysis Network,PCANet)是基于深度学习理论的一种非监督式的特征提取方法,它克服了手工提取特征的缺点,目前其有效性仅仅在图像处理领域中得到了验证.本文针对当前谎言测试方法中脑电信号特征提取困难的缺点,首次将PCANet方法应用到一维信号的特征提取领域,并对测谎实验的原始脑电信号提取特征,然后使用支持向量机(Support Vector Machine,SVM)将说谎者和诚实者的两类信号进行分类识别,将实验结果和其它分类器及未使用特征提取的分类效果进行了比较.实验结果显示相对未抽取任何特征的方法,提出的方法PCANet_SVM可以获得更高的训练和测试准确率,表明了PCANet方法对于脑电信号特征提取的有效性,也为基于脑电信号的测谎提供了一种新的途径.

Abstract

Principal Components Analysis Network (PCANet) is a feature extraction method based on deep learning theory and unsupervised learning modes,which overcomes the shortcoming of hand-crafted features and its efficiency has been only proved in several literatures for picture processing.In this paper,PCANet is applied to process the one dimensional signals for the first time in order to overcome the disadvantages of hand-crafted features from EEG signals in deception detection.PCANet is used to extract features from raw EEG signals in the deception detection experiment.The feature vectors were fed into three classifiers including Support Vector Machine (SVM) to classify the guilty and innocent subjects.The experimental result was compared with the results from other classifiers and the mode of using raw EEG signals as features.The experimental results show that the proposed method PCANet_SVM obtains the highest training and testing accuracy,which indicates the efficiency of extracting features from EEG signals and provides a new solution of detecting lying.

关键词

主成分分析网络 / 脑电 / 测谎 / 深度学习 / 支持向量机

Key words

principal components analysis network (PCANet) / EEG / deception detection / deep learning / support vector machine

引用本文

导出引用
顾凌云, 吕文志, 杨勇, 高军峰, 官金安, 周到. 基于PCANet和SVM的谎言测试研究[J]. 电子学报, 2016, 44(8): 1969-1973. https://doi.org/10.3969/j.issn.0372-2112.2016.08.028
GU Ling-yun, LV Wen-zhi, YANG Yong, GAO Jun-feng, GUAN Jin-an, ZHOU Dao. Deception Detection Study Based on PCANet and Support Vector Machine[J]. Acta Electronica Sinica, 2016, 44(8): 1969-1973. https://doi.org/10.3969/j.issn.0372-2112.2016.08.028
中图分类号: R318   

参考文献

[1] BARRY R J,DE BALSIO F M.EEG-ERP phase dynamics children in the auditory Go/NoGo task[J].International Journal of Psychophysiology,2012,86(3):251-261.
[2] GAO J F,TIAN H J,YANG Y,et al.A novel algorithm to enhance P300 in single trials:application to lie detection using F-score and SVM[J].Plos One,2014,9(11):1-15.
[3] LABKOVSKY E,PETER ROSENFELD J.A novel dual probe complex trial protocol for detection of concealed information[J].Psychophysiology,2014,1(11):1122-1130.
[4] HINTON G E,SALAKHUTDINOVR R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[5] VINCENT P,LAROCHELLE H,BENGIO Y.Extracting and composing robust features with denoising auto-encoders[J].ICML,2008,25(592):1096-1103.
[6] YU D,HINTON G,MORGAN N,et al.Introduction to the special section on deep learning for speech and language processing[J].Audio Speech&Language Processing IEEE Transactions on,2012,20(1):4-6.
[7] CHAN T H,JIA K,GAO S,et al.PCANet:A simple deep learning baseline for image classification?[J].IEEE Transactions on Image Processing,2015,24(12):5017-5032.
[8] ZENG R,WU J,SHAO Z,et al.Multilinear principal component analysis network for tensor object classification[J].ArXiv Preprint ArXiv:1411.1171,2014.
[9] ZENG R,WU J,et al.Tensor object classification via multilinear discriminant analysis network[A].ICASSP,2015[C].South Brisbane,QLD:IEEE,2015.1971-1975.
[10] 庞存锁,刘磊,单涛.基于短时分数阶傅里叶变换的时频分析方法[J].电子学报,2014,(2):347-352.PANG Cun-suo,LIU Lei,DAN Tao.Time frequency analysis is method based on short-time fractional fourier transform[J].Acta Electronica Sinica,2014,(2):347-352.(in Chinese)
[11] GAO W,GUAN J A,Gao J F.Multi-ganglion ANN based feature learning with application to P300-BCI signal classification[J].Biomedical Signal Processing and Control,2015,18:127-137.
[12] DELORMEA,MAKEIG S.EEGLAB:an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis[J].Journal of Neuroscience Methods,2004,134(1):9-21.
[13] LIU C,WECHSLER H.Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition[J].Image Processing,2002,11(4):467-476.
[14] Rosenfeld J P,Hu X,Pederson K.Deception awareness improves P300-based deception detection in concealed information tests[J].International Journal of Psychophysiology,2012,86(1):114-121.
[15] 高军峰,张文佳,杨勇,胡佳,陶春毅,官金安.基于P300和极限学习机的脑电测谎研究[J].电子科技大学学报,2014,43(2):301-305.GAO Jun-Feng,ZHANG Wen-Jia,YANG Yong et al.Lie detection study based on P300 and extreme learning machine[J].Journal of University of Electronic Science&Technology of China,2014,43(2):301-305.(in Chinese)

基金

国家自然科学基金 (No.81271659,No.61262034,No.61462031,No.91120017); 江西省自然科学基金 (No.20151BAB207033); 中国博士后科学基金 (No.2014M552346)
PDF(722 KB)

1849

Accesses

0

Citation

Detail

段落导航
相关文章

/