AN ENHANCED ALGORITHM TO IMPROVE THE ACCURACY OF LIE DETECTION SYSTEM BASED ON EEG SIGNAL

Ayia A. S. A.  Jabar

doi:10.30572/2018/KJE/160404

Authors

Ayia A. S. A. Jabar Assisstant Lecturer, Al-Iraqia University, Baghdad, Iraq https://orcid.org/0009-0009-7214-5579

DOI:

https://doi.org/10.30572/2018/KJE/160404

Keywords:

Lie detection, Electroencephalogram, Event-related potential, independent component analysis

Abstract

In recent years, lie detection has been a prominent focus for many researchers due to its significant influence on criminology and society. A key challenge in numerous investigations has been the system's accuracy, which is heavily reliant on the type of algorithm employed in the classification process. Another critical factor affecting accuracy is the signal-to-noise ratio (SNR). In this paper, we explore a deep learning framework within the lie detection test paradigm. During the signal acquisition phase, EEG signals were recorded using the Natus device. Independent component analysis (ICA) was subsequently applied to remove noise during signal processing. Additionally, regression baseline correction was used to adjust the baseline, followed by averaging to generate event-related potentials (ERP), which resulted in a 23.2% improvement in SNR. Several algorithms were also employed, including support vector machines (SVM), deep belief networks (DBN), and linear discriminant analysis (LDA). Our proposed approach achieved an accuracy of 86% when using the same dataset from previous research, while new data collection from several participants yielded an accuracy of up to 78%

Downloads

Download data is not yet available.

References

Ali, S.M. and Hameed, H.A. (2020) 'Hand image verification method based on PCA eigenvectors', Journal of Kufa-Physics, 3(1).

Bablani, A., Edla, D., Kuppili, V. and Dharavath, R. (2021) 'Lie detection using fuzzy ensemble approach with novel defuzzification method for classification of EEG signals', IEEE Transactions on Instrumentation and Measurement, 70, 1–13.

Bablani, A., Edla, D.R., Kuppili, V. and Ramesh, D. (2020) 'A multistage EEG data classification using k-means and feed forward neural network', Clinical Epidemiology and Global Health, 8, 718–724.

Baghel, N., Singh, D., Dutta, M.K. et al. (2020) 'Truth identification from EEG signal by using convolution neural network: Lie detection', IEEE 43rd International Conference on Telecommunications and Signal Processing (TSP), 550–553.

Chao, H. and Liu, Y. (2020) 'Emotion recognition from multi-channel EEG signals by exploiting the deep belief-conditional random field framework', IEEE Access, 8, 33002–33012.

Gao, J., Gu, L., Min, X. et al. (2022) 'Brain fingerprinting and lie detection: A study of dynamic functional connectivity patterns of deception using EEG phase synchrony analysis', IEEE Journal of Biomedical and Health Informatics, 26(2), 600–613.

Gao, J., Min, X., Si, H. et al. (2022) 'Effective connectivity in cortical networks during deception: A lie detection study based on EEG', IEEE Journal of Biomedical and Health Informatics, 26(8), 3755–3766.

Gu, L., Jiang, J., Han, H. et al. (2023) 'Recognition of unilateral lower limb movement based on EEG signals with ERP-PCA analysis', Neuroscience Letters, 800.

Kappenman, E., Farrens, J., Zhang, W. et al. (2021) 'ERP CORE: An open resource for human event-related potential research', NeuroImage, 225.

Kokate, P., Pancholi, S. and Joshi, A. (2021) 'Classification of upper arm movements from EEG signals using machine learning with ICA analysis', arXiv preprint.

Lin, X., Sai, L. and Yuan, Z. (2018) 'Detecting concealed information with fused electroencephalography and functional near-infrared spectroscopy', Neuroscience, 386, 284–294.

Obais, Z. and Hasan, T. (2020) 'Classification of non-invasive recording of electroencephalography brain signals using Hoeffding tree', Journal of Kufa for Mathematics and Computer, 7(1).

Pooja, S., Pahuja, S. and Veer, K. (2022) 'Recent approaches on classification and feature extraction of EEG signal: A review', Robotica, 40(1), 77–101.

Rad, D., Paraschiv, N. and Kiss, C. (2023) 'Neural network applications in polygraph scoring—A scoping review', Information, 14(10).

Rahmani, M., Mohajelin, F., Khaleghi, N., Sheykhivand, S. and Danishvar, S. (2024) 'An automatic lie detection model using EEG signals based on the combination of type 2 fuzzy sets and deep graph convolutional networks', Sensors, 24(11).

Supriya, S., Siuly, S., Wang, H. et al. (2023) 'Epilepsy detection from EEG using complex network techniques: A review', IEEE Reviews in Biomedical Engineering, 16, 292–306.

Wei, S., Gao, J., Yang, Y. et al. (2023) 'Analysis of weight-directed functional brain networks in the deception state based on EEG signal', IEEE Journal of Biomedical and Health Informatics, 27(10), 4736–4747.

Xiong, Y., Gu, L. and Gao, J. (2020) 'Phase synchrony and its application to lie detection', IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS), 726–729.

Yue, Y., Plested, J. and Gedeon, T. (2020) 'Information-preserving feature filter for short-term EEG signals', Neurocomputing, 408, 91–99.

Zhou, J., Zhang, X. and Jiang, Z. (2021) 'Recognition of imbalanced epileptic EEG signals by a graph-based extreme learning machine', Wireless Communications and Mobile Computing.