Abstract
A new machine learning method referred to as F-score_ELM was proposed to classify the lying and truth-telling using the electroencephalogram (EEG) signals from 28 guilty and innocent subjects. Thirty-one features were extracted from the probe responses from these subjects. Then, a recently-developed classifier called extreme learning machine (ELM) was combined with F-score, a simple but effective feature selection method, to jointly optimize the number of the hidden nodes of ELM and the feature subset by a grid-searching training procedure. The method was compared to two classification models combining principal component analysis with back-propagation network and support vector machine classifiers. We thoroughly assessed the performance of these classification models including the training and testing time, sensitivity and specificity from the training and testing sets, as well as network size. The experimental results showed that the number of the hidden nodes can be effectively optimized by the proposed method. Also, F-score_ELM obtained the best classification accuracy and required the shortest training and testing time.
Highlights
Deception is an important social and legal behavior
extreme learning machine (ELM) method was first introduced for the purpose of lie detection, and the optimization of the number of hidden nodes (NHN) of ELM was combined with the F-score feature selection method
As a popular feature selection method, principal component analysis (PCA) was combined with ELM, Figure 4
Summary
The traditional method for detecting deception is based on polygraph measurements. A number of studies have used neurophysiological signals, such as Functional Magnetic Resonance Imaging (fMRI) and Event Related Potential (ERP) [1,2,3], to investigate lie detection [4]. An endogenous ERP component, P300 (P3), has been extensively investigated and successfully used in the detection of deception and malingering [5,6,7]. The widely used P3-based lie-detection methods can be roughly divided into three categories: bootstrapped amplitude difference (BAD), bootstrapped correlation difference (BCD) [8] and pattern recognition (PR) methods [4,9,10]. The adoption of PR classifiers for lie detection has not yet been widely reported. Abootalebi et al [9] used linear discrimination analysis (LDA) to identify P3 responses and obtained a higher detection rate (86%) than that obtained using BAD- and BCD-
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.