EEG based alcoholism detection by oscillatory modes decomposition second order difference plots and machine learning

• Autorzy: Salankar Nilima , Qaisar Saeed Mian , Pławiak Paweł , Tadeusiewicz Ryszard , Hammad Mohamed

Identyfikatory

DOI

10.1016/j.bbe.2021.12.009

• Języki publikacji: EN

Abstrakty

EN

The excessive drinking of alcohol can disrupt the neural system. This can be observed by properly analysing the Electroencephalogram (EEG) signals. However, the EEG is a signal of complex nature. Therefore, an accurate categorization between alcoholic (A) and nonalcoholic (NA) subjects, while using a short time EEG recording, is a challenging task. In this paper a novel hybridization of the oscillatory modes decomposition, features mining based on the Second Order Difference Plots (SODPs) of oscillatory modes, and machine learning algorithms is devised for an effective identification of alcoholism. The Empirical Mode Decomposition (EMD) and Variational Mode Decomposition (VMD) are used to respectively decompose the considered EEG signals in Intrinsic Mode Functions (IMFs) and Modes. Onward, the SODPs, derived from first six IMFs and Modes, are considered. Features of SODPs are mined. To reduce the dimension of features set and computational complexity of the classification model, the pertinent features selection is made on the basis of Wilcoxon statistical test. Three features with p-values (p) of < 0.05 are selected from each intended SODP and these are the Central Tendency Measure (CTM), area and mean. These features are used for the discrimination between A and NA classes. In order to determine a suitable EEG signal segment length for the intended application, experiments are performed by considering features extracted from three different length time windows. The classification is carried out by using the Least Square Support Vector Machine (LS-SVM), Multilayer perceptron neural network (MLPNN), K-Nearest Neighbour (KNN) and Random Forest (RF) algorithms. The applicability is tested by using the UCI-KDD EEG dataset. The results are noteworthy for MLPNN with 99.89% and 99.45% accuracies for EMD and VMD respectively for 8-second window.

Słowa kluczowe

EN

alcoholism detection; electroencephalogram; empirical mode decomposition; features extraction; machine learning; second order difference plot; variational mode decomposition

PL

wykrywanie alkoholizmu; elektroencefalogram; dekompozycja empiryczna; ekstrakcja cech; uczenie maszynowe

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2022
• Tom: Vol. 42, no. 1
• Strony: 173--186
• Opis fizyczny: Bibliogr. 40 poz., rys., tab., wykr.

Twórcy

autor

Salankar Nilima

• School of Computer Science, University of Petroleum & Energy Studies: UPES, Dehradun, India

autor

Qaisar Saeed Mian

• Electrical and Computer Engineering Department, Effat University, Jeddah 22332, Saudi Arabia; Communication and Signal Processing Lab, Energy and Technology Research Centre, Effat University, Jeddah, Saudi Arabia

autor

Pławiak Paweł

• Department of Computer Science, Faculty of Computer Science and Telecommunications, Cracow University of Technology, Warszawska 24, 31-155 Krakow, Poland; Institute of Theoretical and Applied Informatics, Polish Academy of Sciences, Gliwice, Poland

autor

Tadeusiewicz Ryszard

• AGH University of Science and Technology, Department of Biocybernetics and Biomedical Engineering, Krakow, Poland

autor

Hammad Mohamed

• Department of Information Technology, Faculty of Computers and Information, Menoufia University, Menoufia, Egypt

Bibliografia

• [1] Rieg T, Frick J, Hitzler M, Buettner R, High-performance detection of alcoholism by unfolding the amalgamated EEG spectra using the Random Forests method, 2019. doi: 10.24251/hicss.2019.455.
• [2] Callinan S, Smit K, Mojica-Perez Y, D’Aquino S, Moore D, Kuntsche E. Shifts in alcohol consumption during the COVID19 pandemic: early indications from Australia. Addiction 2021;116(6):1381–8. https://doi.org/10.1111/add.15275.
• [3] Bade R, Simpson BS, Ghetia M, Nguyen L, White JM, Gerber C. Changes in alcohol consumption associated with social distancing and self-isolation policies triggered by COVID-19 in South Australia: a wastewater analysis study. Addiction 2021;116(6):1600–5. https://doi.org/10.1111/add.15256.
• [4] Calina D, Hartung T, Mardare I, Mitroi M, Poulas K, Tsatsakis A, et al. COVID-19 pandemic and alcohol consumption: Impacts and interconnections. Toxicol Rep 2021;8:529–35. https://doi.org/10.1016/j.toxrep.2021.03.005.
• [5] Grossman ER, Benjamin-Neelon SE, Sonnenschein S. Alcohol consumption during the covid-19 pandemic: A crosssectional survey of us adults. Int J Environ Res Public Health 2020;17(24):9189. https://doi.org/10.3390/ijerph17249189.
• [6] Wang Y, Lu H, Hu M, Wu S, Chen J, Wang L, et al. Alcohol consumption in china before and during COVID-19: preliminary results from an online retrospective survey. Front Psychiatry 2020;11. https://doi.org/10.3389/ fpsyt.2020.597826.
• [7] Weerakoon SM, Jetelina KK, Knell G. Longer time spent at home during COVID-19 pandemic is associated with binge drinking among US adults. Am J Drug Alcohol Abuse 2021;47 (1):98–106. https://doi.org/10.1080/00952990.2020.1832508.
• [8] Bavkar S, Iyer B, Deosarkar S. Optimal EEG channels selection for alcoholism screening using EMD domain statistical features and harmony search algorithm. Biocybernetics and Biomedical Engineering 2021;41(1):83–96.
• [9] Hernandez JE, Cretu E. A wireless, real-time respiratory effort and body position monitoring system for sleep. Biomed Signal Process Control 2020;61:102023. https://doi.org/ 10.1016/j.bspc.2020.102023.
• [10] Salankar N, Mishra P, Garg L. Emotion recognition from EEG signals using empirical mode decomposition and secondorder difference plot. Biomed Signal Process Control 2021;65:102389. https://doi.org/10.1016/j.bspc.2020.102389.
• [11] Pachori RB, Patidar S. Epileptic seizure classification in EEG signals using second-order difference plot of intrinsic mode functions. Comput Methods Programs Biomed 2014;113 (2):494–502. https://doi.org/10.1016/j.cmpb.2013.11.014.
• [12] Anuragi A, Sisodia DS, Pachori RB. Automated alcoholism detection using Fourier-Bessel series expansion based empirical wavelet transform. IEEE Sens J 2020;20(9):4914–24. https://doi.org/10.1109/JSEN.2020.2966766.
• [13] Anuragi A, Sisodia DS. Empirical wavelet transform based automated alcoholism detecting using EEG signal features. Biomed Signal Process Control 2020;57:101777. https://doi. org/10.1016/j.bspc.2019.101777.
• [14] Shah S, Sharma M, Deb D, Pachori RB, An automated alcoholism detection using orthogonal wavelet filter bank, 2019. doi: 10.1007/978-981-13-0923-6_41.
• [15] Popescu AB et al., Privacy preserving classification of eeg data using machine learning and homomorphic encryption, Appl Sci Switz, 2021;11(16), doi: 10.3390/app11167360.
• [16] Mukhtar H, Qaisar SM, Zaguia A, Deep convolutional neural network regularization for alcoholism detection using EEG signals, Sensors, 2021;21(16), doi: 10.3390/s21165456.
• [17] Bavkar S, Iyer B, Deosarkar S, Detection of alcoholism: An EEG hybrid features and ensemble subspace K-NN based approach, 2019. doi: 10.1007/978-3-030-05366-6_13.
• [18] Siuly S, Li Y, Zhang Y, EEG signal analysis and classification techniques and applications. 2016.
• [19] Farsi L, Siuly S, Kabir E, Wang H. Classification of alcoholic EEG signals using a deep learning method. IEEE Sensors J 2021;21(3):3552–60.
• [20] Saddam M, Tjandrasa H, Navastara DA, Classification of alcoholic EEG using wavelet packet decomposition, principal component analysis, and combination of genetic algorithm and neural network, 2018. doi: 10.1109/ICTS.2017.8265600.
• [21] UKEssays, A review on alcoholic detection from EEG signals, UK Essays, 2013.
• [22] Upadhyay R, Padhy PK, Kankar PK, Alcoholism diagnosis from EEG signals using continuous wavelet transform, 2015. doi: 10.1109/INDICON.2014.7030476.
• [23] Patidar S, Pachori RB, Upadhyay A, Rajendra Acharya U. An integrated alcoholic index using tunable-Q wavelet transform based features extracted from EEG signals for diagnosis of alcoholism. Appl Soft Comput J 2017;50:71–8. https://doi.org/10.1016/j.asoc.2016.11.002.
• [24] Sharma M, Sharma P, Pachori RB, Acharya UR. Dual-tree complex wavelet transform-based features for automated alcoholism identification. Int J Fuzzy Syst 2018;20 (4):1297–308. https://doi.org/10.1007/s40815-018-0455-x.
• [25] Salankar N, B. Nemade S, P. Gaikwad V. Classification of seizure and seizure free EEG signals using optimal mother wavelet and relative power. Indones J Electr Eng Comput Sci 2020;20(1):197. https://doi.org/10.11591/ijeecs.v20.i1.pp197- 205.
• [26] Sinha SR, Sullivan L, Sabau D, San-Juan D, Dombrowski KE, Halford JJ, et al. American Clinical Neurophysiology Society Guideline 1: Minimum technical requirements for performing clinical electroencephalography. J Clin Neurophysiol 2016;33(4):303–7. https://doi.org/10.1097/ WNP.0000000000000308.
• [27] Zhang XL, Begleiter H, Porjesz B, Wang W, Litke A. Event related potentials during object recognition tasks. Brain Res Bull 1995;38(6):531–8.
• [28] Anuragi A, Singh Sisodia D. Alcohol use disorder detection using EEG Signal features and flexible analytical wavelet transform. Biomed Signal Process Control 2019;52:384–93.
• [29] Sood S, Kumar M, Pachori RB, Acharya UR. Application of empirical mode decomposition-based features for analysis of normal and CAD heart rate signals. J Mech Med Biol 2016;16 (1):1640002. https://doi.org/10.1142/S0219519416400029.
• [30] Rehman Nu, Aftab H. Multivariate Variational Mode Decomposition. IEEE Trans Signal Process 2019;67 (23):6039–52. https://doi.org/10.1109/TSP.2019.2951223.
• [31] Pachori RB, Bajaj V. Analysis of normal and epileptic seizure EEG signals using empirical mode decomposition. Comput Methods Programs Biomed 2011;104:373–81. https://doi.org/ 10.1016/j.cmpb.2011.03.009.
• [32] Thuraisingham RA. A classification system to detect congestive heart failure using second-order difference plot of RR intervals. Cardiol Res Pract 2009:1–7. https://doi.org/ 10.4061/2009/807379.
• [33] Cortes C, Vapnik V. Support-vector networks. Mach Learn 1995. https://doi.org/10.1023/A:1022627411411.
• [34] De Brabanter K et al. LS-SVMlab toolbox user’s guide. Pattern Recognit Lett 2003.
• [35] Md Isa NE, Amir A, Ilyas MZ, Razalli MS. Motor imagery classification in brain computer interface (BCI) based on EEG signal by using machine learning technique. Bull Electr Eng Inform 2019;8(1):269–75. https://doi.org/10.11591/eei. V8i1.1402.
• [36] Breiman L, Cutler A. Breiman and Cutler’s random forests for classification and regression. Package RandomForest 2012.
• [37] Boloukian B, Safi-Esfahani F. Recognition of words from brain-generated signals of speech-impaired people: Application of autoencoders as a neural Turing machine controller in deep neural networks. Neural Netw 2020;121:186–207. https://doi.org/10.1016/j. Neunet.2019.07.012.
• [38] Mehla VK, Singhal A, Singh P. A novel approach for automated alcoholism detection using Fourier decomposition method. J Neurosci Methods 2020;346:108945. https://doi.org/10.1016/j.jneumeth.2020.108945.
• [39] Mian Qaisar S. Event-driven coulomb counting for effective online approximation of Li-ion battery state of charge. Energies 2020;13(21):5600.
• [40] Mian Qaisar S, Gadekallu TR. Signal-piloted processing and machine learning based efficient power quality disturbances recognition. PLoS ONE 2021;16(5):e0252104.