Key result
An empirical mode decomposition-based feature extraction method using EEG signals achieved a classification accuracy of 92.73% for detecting guilty and innocent subjects.
Why the study?
Does EMD-based feature extraction from multiple EEG channels improve the classification accuracy of guilty and innocent subjects in P300-based deception detection?
Does EMD-based feature extraction from multiple EEG channels improve the classification accuracy of guilty and innocent subjects in P300-based deception detection?
An EMD-based feature extraction method utilizing multiple EEG channels and a genetic algorithm achieves high accuracy (92.73%) in P300-based deception detection.
Answers are grounded in this paper and cite their sources.
Hypothesis-generating for EMD-enhanced P300 deception detection; prospective validation needed before forensic adoption.
Conventional polygraphy has several alternatives and one of them is P300-based guilty knowledge test. The purpose of this paper is to apply a new method called empirical mode decomposition (EMD) to extract features from electroencephalogram (EEG) signal. EMD is an appropriate tool to deal with the nonlinear and nonstationary nature of EEG. In the previous studies on the same data set, some morphological, frequency, and wavelet features were extracted only from Pz channel, and used for the detection of guilty and innocent subjects. In this paper, an EMD-based feature extraction was done on EEG recorded signal. Features were extracted from all three recorded channels (Pz, Cz, and Fz) for synergistic incorporation of channel information. Finally, a genetic algorithm was utilized as a tool for efficient feature selection and overcoming the challenge of input space dimension increase. The classification accuracy of guilty and innocent subjects was 92.73%, which was better than other previously used methods.
No takes yet. Share an insight, caveat, or question.
Arasteh et al. (2016) studied Deception detection. Empirical mode decomposition (EMD) based feature extraction with genetic algorithm vs. Previously used methods (morphological, frequency, and wavelet features) was evaluated on Classification accuracy of guilty and innocent subjects. An empirical mode decomposition-based feature extraction method using EEG signals achieved a classification accuracy of 92.73% for detecting guilty and innocent subjects.
Synapse has enriched 10 related papers. Consider them for comparative context: