Guilty Knowledge Test by Chaotic Processing of Electroencephalogram Signals Based on Fuzzy Recurrence Plot

Document Type : Original Article

Authors

1 Master's student, Faculty of Modern Sciences and Technologies, Semnan University, Semnan, Iran

2 Assistant Professor, Faculty of Modern Sciences and Technologies, Semnan University, Semnan, Iran

3 Assistant Professor, Faculty of Medical Engineering, Hamedan University of Technology, Hamedan, Iran

Abstract

The EEG-based guilty knowledge test (GKT) is one of the most frequent lie detection methods. Recurrence plot analysis is a conventional chaotic signal processing method applied in different lie detection studies. One of the most important challenges of this method is selecting the appropriate threshold as the criterion of state recurrence in the phase space. Inappropriate selection of this threshold significantly affects the performance of this method. So in this study, the fuzzy recurrence plot is applied to overcome this challenge. This method is applied to transform EEG trials into grayscale texture images. Then, the gray-level co-occurrence matrix (GLCM) is used to extract the texture features from these images. Finally, The extracted features are classified using the K-NN classifier. The classification results of the 4-D feature vectors with 90% accuracy indicate the superiority of this method compared to the classic RQA method with 13-D feature vectors. This reduction in feature vector dimension improves the train and test speed and generalization of the KNN as a lazy learner. Moreover, the subject-based EEG-trial processing approach of this research eliminates the need for data set from various subjects and the only data set required to determine the sincerity of each subject is solely its own data set.

Keywords


Smiley face

[1]   N. R. Council and T. Polygraph, The Polygraph and Lie Detection. Washington, DC: The National Academies Press, 2003.
[2]   L. A. Farwell and E. Donchin, “The Truth Will Out: Interrogative Polygraphy (‘Lie Detection’) with Event‐related Brain Potentials,” Psychophysiology, vol. 28, no. 5. pp. 531–547, 1991.
[3]   J. P. Rosenfeld, J. Ellwanger, and J. Sweet, “Detecting Simulated Amnesia with Event-related Brain Potentials,” Int. J. Psychophysiol., vol. 19, no. 1, pp. 1–11, 1995.
[4]    Z. amini,  V. Abootalebi, and  M. T. Sadeghi, “Evaluation and Comparision of Common Spatial Patterns (CSP) and Intelligent Segmentation in P300 Detection,” Comput. Intell. Electr. Eng., vol. 2, no. 2, pp. 37–54, 2011.
[5]   J. P. Rosenfeld, “Event-Related Potentials in the Detection of Deception, Malingering, and False Memories,” In Handbook of Polygraph Testing, 2002, pp. 265–286. Accessed: Jul. 02, 2020. 
[6]   J. P. Rosenfeld, M. Soskins, G. Bosh, and A. Ryan, “Simple, Effective Countermeasures to P300-based Tests of Detection of Concealed Information,” Psychophysiology, vol. 41, no. 2, pp. 205–219, 2004.
[7]   A. H. Mehrnam, A. M. Nasrabadi, M. Ghodousi, A. Mohammadian, and S. Torabi, “Reprint of ‘A new Approach to Analyze Data from EEG-based Concealed Face Recognition System,” Int. J. Psychophysiol., vol. 122, no. January 2016, pp. 17–23, 2017.
[8]   J. Gao, H. Tian, Y. Yang, X. Yu, C. Li, and N. Rao, “A Novel Algorithm to Enhance P300 in Single Trials: Application to Lie Detection Using F-score and SVM,” PLoS One, vol. 9, no. 11, pp. 1-15, 2014.
[9]   V. Abootalebi, M. H. Moradi, and M. A. Khalilzadeh, “A New Approach for EEG Feature Extraction in P300-based Lie Detection,” Comput. Methods Programs Biomed., vol. 94, no. 1, pp. 48–57, 2009.
[10] M. A. Mubeen and K. H. Knuth, “Evidence-Based Filters for Signal Detection: Application to Evoked Brain Responses, ” arXiv preprint arXiv: 1107.1257, 2011, Accessed: Jul. 08, 2020.
[11] V. Abootalebi, M. H. Moradi, and M. A. Khalilzadeh, “A Comparison of Methods for ERP Assessment in a P300-based GKT,” Int. J. Psychophysiol., vol. 62, no. 2, pp. 309–320, 2006.
[12] L. A. Farwell and E. Donchin, “The Truth Will Out: Interrogative Polygraphy (‘Lie Detection’) With Event‐Related Brain Potentials,” Psychophysiology, vol. 28, no. 5, pp. 531–547, 1991.
[13] A. Arasteh, M. H. Moradi, and A. Janghorbani, “A Novel Method Based on Empirical Mode Decomposition for P300-Based Detection of Deception,” IEEE Trans. Inf. Forensics Secur., vol. 11, no. 11, pp. 2584–2593, 2016.
[14] N. Saini, S. Bhardwaj, and R. Agarwal, “Classification of EEGSignals Using Hybrid Combination of Features for Lie Detection,” Neural Comput. Appl., vol. 32, no. 8, pp. 3777–3787, 2020.
[15] V. Abootalebi, “Computer Brain Communication (BCI) Using ERP Cognitive Components,” 11th Iran. Conf. Biomed. Eng. ICBME 2004, no. Icbm, pp. 193-201, 2004. 
[16] A. Akhavan and M. H. Moradi, “Detection of Concealed Information Using Multichannel Discriminative Dictionary and Spatial Filter Learning,” IEEE Trans. Inf. Forensics Secur., vol. 13, no. 10, pp. 2616–2627, 2018.
[17] A. Turnip, M. F. Amri, H. Fakrurroja, A. I. Simbolon, M. A. Suhendra, and D. E. Kusumandari, “Deception Detection of EEG-P300 Component Classified by SVM Method,” ACM Int. Conf. Proceeding Ser., pp. 299–303, 2017.
[18] M. R. Bhutta, M. J. Hong, Y. H. Kim, and K. S. Hong, “Single-trial Lie Detection Using a Combined fNIRS-polygraph System,” Front. Psychol., vol. 6, no. JUN, pp. 1–9, 2015.
[19] J. F. Gao et al., “Exploring Time-and Frequency-dependent Functional Connectivity and Brain Networks During Deception with Single-trial Event-related Potentials,” Sci. Rep., vol. 6, pp. 1–13, 2016.
[20] C. Saavedra, R. Salas, and L. Bougrain, “Wavelet-based Semblance Methods to Enhance the Single-trial Detection of Event-related Potentials for a BCI Spelling System,” Comput. Intell. Neurosci., vol. 2019, 2019.
[21] L. Hu, A. Mouraux, Y. Hu, and G. D. Iannetti, “A Novel Approach for Enhancing the Signal-to-Noise Ratio and Detecting Automatically Event-Related Potentials (ERPs) in Single Trials,” Neuroimage, vol. 50, no. 1, pp. 99–111, 2010.
[22] N. Marwan, N. Wessel, U. Meyerfeldt, A. Schirdewan, and J. Kurths, “Recurrence-plot-based Measures of Complexity and their Application to Heart-rate-variability Data,” Phys. Rev. E - Stat. Physics, Plasmas, Fluids, Relat. Interdiscip. Top., vol. 66, no. 2, pp. 1–16, 2002.
[23] J. P. Eckmann, O. Oliffson Kamphorst, and D. Ruelle, “Recurrence Plots of Dynamical Systems,” Epl, vol. 4, no. 9, pp. 973–977, 1987.
[24] N. Marwan, N. Wessel, U. Meyerfeldt, A. Schirdewan, and J. Kurths, “Recurrence-plot-based Measures of Complexity and their Application to  Heart-rate-variability Data,” Phys. Rev. E. Stat. Nonlin. Soft Matter Phys., vol. 66, no. 2 Pt 2, p. 26702, 2002,
[25] N. Talebi and A. M. Nasrabadi, “Recurrence Plots for Identifying Memory Components in Single-trial EEGs,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 6334 LNAI, pp. 124–132, 2010,
[26] S. Schinkel, N. Marwan, and J. Kurths, “Brain Signal Analysis Based on Recurrences,” J. Physiol. Paris, vol. 103, no. 6, pp. 315–323, 2009,
[27] F. Bahari and A. Janghorbani, “EEG-based Emotion Recognition Using Recurrence Plot Analysis and K Nearest Neighbor Classifier,” 2013 20th Iran. Conf. Biomed. Eng. ICBME 2013, no. Icbme, pp. 228–233, 2013,
[28] M. B. Khodabakhshi and V. Saba, “A Nonlinear Dynamical Approach to Analysis of Emotions Using EEG Signals Based on the Poincare Map Function and Recurrence Plots,” Biomed. Eng. Tech., vol. 65, no. 5, pp. 507–520, 2020.
[29] I. Gruszczyńska, R. Mosdorf, P. Sobaniec, M. Żochowska-Sobaniec, and M. Borowska, “Epilepsy Identification Based on EEG Signal Using RQA Method,” Adv. Med. Sci., vol. 64, no. 1, pp. 58–64, 2019,
[30] A. H. Mehrnam, A. M. Nasrabadi, A. Mohammadian, and S. Torabi, “Concealed Face Recognition Analysis Based on Recurrence Plots,” 18th Iran. Conf. Biomed. Eng. ICBME 2011, no. December, pp. 1–4, 2011.
[31] N. Marwan, M. Carmen Romano, M. Thiel, and J. Kurths, “Recurrence Plots for the Analysis of Complex Systems,” Physics Reports, vol. 438, no. 5–6. pp. 237–329, 2007.
[32] M. Thiel, M. C. Romano, J. Kurths, R. Meucci, E. Allaria, and F. T. Arecchi, “Influence of Observational Noise on the Recurrence Quantification Analysis,” Phys. D Nonlinear Phenom., vol. 171, no. 3, pp. 138–152, 2002.
[33] J. P. Zbilut, J. M. Zaldivar-Comenges, and F. Strozzi, “Recurrence Quantification Based Liapunov Exponents for Monitoring Divergence in Experimental Data,” Phys. Lett. Sect. A Gen. At. Solid State Phys., vol. 297, no. 3–4, pp. 173–181, 2002.
[34] G. P. King and I. Stewart, “Phase Space Reconstruction for Symmetric Dynamical Systems,” Phys. D Nonlinear Phenom., vol. 58, no. 1–4, pp. 216–228, 1992.
[35] F. Takens, “Detecting Strange Attractors in Turbulence,” In Springer, 1981, pp. 366–381.
[36] S. Wallot and D. Mønster, “Calculation of Average Mutual Information (AMI) and False-Nearest Neighbors (FNN) for the Estimation of Embedding Parameters of Multidimensional Time Series in Matlab,” Front. Psychol., vol. 9, no. SEP, pp. 1–10, 2018.
[37] N. Marwan, A. Groth, and J. Kurths, “Quantification of Order Patterns Recurrence Plots of Event Related Potentials,” Chaos Complex. Lett., vol. 2, pp. 301–314, 2007.
[38] N. Marwan, “How to Avoid Potential Pitfalls in Recurrence Plot Based Data Analysis,” Int. J. Bifurc. Chaos, vol. 21, no. 4, pp. 1003–1017, 2011.
[39] N. Marwan, J. F. Donges, Y. Zou, R. V. Donner, and J. Kurths, “Complex Network Approach for Recurrence Analysis of Time Series,” Phys. Lett. Sect. A Gen. At. Solid State Phys., vol. 373, no. 46, pp. 4246–4254, 2009,
[40] S. Martín-González, J. L. Navarro-Mesa, G. Juliá-Serdá, G. M. Ramírez-Ávila, and A. G. Ravelo-García, “Improving the Understanding of Sleep Apnea Characterization Using Recurrence Quantification Analysis by Defining Overall Acceptable Values for the Dimensionality of the System, the Delay, and the Distance Threshold,” PLoS One, vol. 13, no. 4, pp. 1-35, 2018.
[41] M. Javorka, Z. Trunkvalterova, I. Tonhajzerova, Z. Lazarova, J. Javorkova, and K. Javorka, “Recurrences in Heart Rate Dynamics are Changed in Patients with Diabetes Mellitus,” Clin. Physiol. Funct. Imaging, vol. 28, no. 5, pp. 326–331, 2008.
[42] T. D. Pham, Fuzzy Recurrence Plots and Networks with Applications in Biomedicine. Cham, Switzerland: Springer, 2020.
[43] İ. Cantürk, “Fuzzy Recurrence Plot-based Analysis of Dynamic and Static Spiral Tests of Parkinson’s Disease Patients,” Neural Comput. Appl., vol. 33, no. 1, pp. 349–360, 2021.
[44] T. D. Pham, “From Fuzzy Recurrence Plots to Scalable Recurrence Networks of Time Series,” Epl, vol. 118, no. 2, pp. 1-170, 2017.
[45] E. Ghanbari Maman and M. Ebrahimi Moghaddam, “Offline text-Independent Persian Handwriting Forgery Detection Using Texture Analysis,” Electron. Cyber Def., vol. 7, no. 3, pp. 37–52, 2019.
[46] O. Rajadell, P. García-Sevilla, and F. Pla, “Textural Features for Hyperspectral Pixel Classification BT  - Image and Signal Processing,” Image and Signal Processing, vol. 5524, no. Chapter 28. pp. 208–216, 2009. 
[47] T. D. Pham, “Texture Classification and Visualization of Time Series of Gait Dynamics in Patients with Neuro-Degenerative Diseases,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 26, no. 1, pp. 188–196, 2018.
[48] P. D. Mryka Hall-Beyer, “GLCM Texture: A Tutorial,” 17th Int. Symp. Ballist., vol. 2, no. March, pp. 18–19, 2017.
[49] A. Janghorbani and M. H. Moradi, “Fuzzy Evidential Network and Its Application as Medical Prognosis and Diagnosis Models,” J. Biomed. Inform., vol. 72, no. 1, pp. 96–107, 2017.
[50] M. Pelikan, “Hierarchical Bayesian Optimization Algorithm: Toward a New Generation of Evolutionary algorithms,” SICE 2003 Annu. Conf. Fukui, pp. 547–552, 2003. 
[51] M. Injadat, F. Salo, A. B. Nassif, A. Essex, and A. Shami, “Bayesian Optimization with Machine Learning Algorithms Towards Anomaly Detection,” IEEE Glob. Commun. Conf. GLOBECOM 2018 - Proc., 2018.
[52]   N. Saini, S. Bhardwaj, and R. Agarwal, “Classification of EEG Signals Using Hybrid Combination of Features for Lie Detection,” Neural Comput. Appl., vol. 32, no. 8, pp. 3777–3787, 2020.
  • Receive Date: 05 July 2021
  • Revise Date: 09 May 2022
  • Accept Date: 09 August 2022
  • Publish Date: 23 September 2022