Abstract This paper presents a new gender and age classification system based on Electroencephalography (EEG) brain signals. First, Continuous Wavelet Transform (CWT) technique is used to get the time-frequency information of only one EEG electrode for eight distinct emotional states instead of the ordinary neutral or relax states. Then, sequential steps are implemented to extract the improved grayscale image feature. For system evaluation, a three-fold-cross validation strategy is applied to construct four different classifiers. The experimental test shows that the proposed extracted feature with Convolutional Neural Network (CNN) classifier improves the performance of both gender and age classification, and achieves an average accuracy of 96.3% and 89% for gender and age classification, respectively. Moreover, the ability to predict human gender and age during the mood of different emotional states is practically approved.

References

[1] Al-Wajih E. and Ahmed M., “A New Application for Gabor Filters in Face-Based Gender Classification,” The International Arab Journal of Information Technology, vol. 17, no. 2, pp. 178-187, 2020.

[2] Chaudhary U., Birbaumer N., and Ramos- Murguialday A., “Brain-Computer Interfaces For Communication and Rehabilitation,” Nature Reviews Neurology, vol. 12, no. 9, pp. 513-525, 2016.

[3] Fisher J., Huang S., Ye M., Nabili M., Wilent A Novel Method for Gender and Age Detection Based on EEG Brain Signals 709 W., Krauthamer V., Myers M., and Welle C., “Real-Time Detection and Monitoring of Acute Brain Injury Utilizing Evoked Electroencephalographic Potentials,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 24, no. 9, pp. 1003-1012, 2016.

[4] Gunes H. and Pantic M., “Automatic, Dimensional and Continuous Emotion Recognition,” International Journal of Synthetic Emotions, vol. 1, no. 1, pp. 68-99, 2010.

[5] Issa S., Peng Q., You X., and Ali W., “Emotion Assessment Using EEG Brain Signals and Stacked Sparse Autoencoder,” Journal of Information Assurance and Security, vol. 14, no. 1, pp. 20-29, 2019.

[6] Issa S., Peng Q., and You X., “Emotion Classification Using EEG Brain Signals and the Broad Learning System,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, pp. 1- 10, 2020.

[7] Jatupaiboon N., Pan-ngum S., and Israsena P., “Real-Time Eeg-Based Happiness Detection System,” The Scientific World Journal, pp. 618- 649, 2013.

[8] Joysly L. and Tamilselvi R., “Abnormality Recognition During Drowsy State from ECG and EEG,” in Proceedings of International Conference on Innovations in Information Embedded and Communication Systems, Coimbatore, 2015.

[9] Kaur B., Singh D., and Roy P., “Age and Gender Classification Using Brain-Computer Interface,” Neural Computing and Applications, vol. 31, pp. 5887-5900, 2019.

[10] Kaushik P., Gupta A., Roy P., and Dogra D., “EEG-based Age and Gender Prediction Using Deep BLSTM-LSTM Network Model,” IEEE Sensors Journal, vol. 19, no. 7, pp. 2634-2641, 2019.

[11] Koelstra S., Muhl C., Soleymani M., Lee J., Yazdani A., Ebrahimi T., Pun T., Nijholt A., and Patras I., “Deap: A Database for Emotion Analysis Using Physiological Signals,” IEEE Transactions on Affective Computing, vol. 3, no. 1, pp. 18-31, 2012.

[12] Kübler A., “The History of bci: from a Vision for the Future to Real Support for Personhood In People with Locked-in Syndom,” Neuroethics, vol. 13, pp. 163-180, 2019.

[13] Kumar J. and Bhuvaneswari P., “Analysis of Electroencephalography (EEG) Signals and its Categorization- A Study,” Procedia Engineering, vol. 38, pp. 2525-2536, 2012.

[14] Kumara N., Khaunda K., and Hazarikaa S., “Bispectral Analysis of EEG for Emotion Recognition,” in Proceedings of The 7th International Conference on Intelligent Human Computer Interaction, India, pp. 31-35, 2015.

[15] Liu H., He L., Shang S., Lu J., Wan M., and Liu S., “Convolutional Neural Network For Resting State EEG Signal Analysis,” in Proceedings of IEEE 16th International Conference on Networking, Sensing and Control, Banff, pp.138- 143, 2019.

[16] Meena K., Subramaniam K., and Gomathy M., “Gender Classification in Speech Recognition using Fuzzy Logic and Neural Network,” The International Arab Journal of Information Technology, vol. 10, no. 5, pp. 477-485, 2013.

[17] Nguyen P., Tran D., Huang X., Ma W., “Age and Gender Classification Using EEG Paralinguistic Features,” in Proceedings of Annual International IEEE EMBS Conference on Neural Engineering, San Diego, pp. 1295-1298, 2013.

[18] Nguyen P., Tran D., Vo T., Huang X., Ma W., and Phung D., “EEG-Based Age and Gender Recognition Using Tensor Decomposition and Speech Features,” in Proceedings of International Conference on Neural Information Processing, Daegu, pp. 632-639, 2013.

[19] Oral E., Ozbek I., and Codur M., “Gender Classification Based on Single Channel EEG Signal,” in Proceedings of International Artificial Intelligence and Data Processing Symposium, Malatya, pp.1-4, 2017.

[20] Peng M., Wang C., Chen T., and Liu G., “Nirfacenet: A Convolutional Neural Network for Near Infrared Face Identification,” Information, vol. 7, no. 4, pp. 1-14, 2016.

[21] Poza J., Caminal P., Vallverdu M., Hornero R., Romero S., and Barbanoj M., “Study of the EEG Changes During the Combined Ingestion of Alcohol and H1-Antihistamines by Using the Wavelet Transform,” in Proceedings of 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Lyon, pp. 23-26, 2007.

[22] Polikar R., The Wavelet Tutorial, Rowan University, Glassboro, Camden, Stratford, New Jersey, 1999.

[23] Sharma R., Varshney P., Pachori R., and Vishvakarma S., “Automated System for Epileptic Eeg Detection Using Iterative Filtering,” IEEE Sensors Letters, vol. 2, no. 4, pp. 2472-2475, 2018.

[24] Simonyan K. and Zisserman A., “Very Deep Convolutional Networks for Large-Scale Image Recognition,” CoRR, vol. abs/1409.1556, 2014.

[25] “The Bci-brain computer interfaces,” Brain Vision UK, Zeal House, 8 Deer Park Road, London, 2014.

[26] “The Calculation of F1 Score”, at: https://towardsdatascience.com/accuracy- precision-recall-or-f1-331fb37c5cb9, Last Visited, 2021. 710 The International Arab Journal of Information Technology, Vol. 18, No. 5, September 2021

[27] “The Calculation of P value,” at: https://stats.stackexchange.com/questions/240453 /statistical-significance-of-multiple-classifiers- by-using-p-value, Last Visited, 2021.

[28] “The Eeg signals”, at: http://www.hopkinsmedicine.org, Last Visited, 2019.

[29] “The Electroencephalography (EEG),” Mayo Clinic, at: https://www.mayoclinic.org/tests- procedures/eeg/about/pac-20393875, Last Visited, 2021.

[30] Trans Cranial Technologies, at :https://www.transcranial.com, Last Visited 2019.

[31] Ueno S., Iramina K., Harada K., and Matsuoka S., “MEG and EEG Topography and A Source Model of Slow Wave Types of Abnormality,” IEEE Translation Journal on Magnetics in Japan, vol. 3, no. 3, pp. 281-287, 1988.

[32] Yılmaz A. and Nabiyev V., “A Novel Age Classification Method Using Morph Based Models,” The International Arab Journal of Information Technology, vol. 16, no. 4, pp. 677- 685, 2019.

[33] Yuan Y., Xun G., Jia K., and Zhang A., “A multi-View Deep Learning Framework for Eeg Seizure Detection,” IEEE Journal of Biomedical and Health Informatics, vol. 23, no. 1, pp. 83-94, 2013. Haitham Issa received his Ph.D. in Communications and Information systems from Zhejiang University, Hangzhou, China, in 2002. He is currently teaching in the Department of Electrical Engineering in Zarqa University, Zarqa, Jordan. His current research interests include image processing, signal Processing, pattern recognition, machine learning, communication, and renewable energy. Sali Issa received her Ph.D. in Electrical Information and Communication Engineering from Huazhong University of Science and Technology, Wuhan, China, in 2020. Her main research interests include artificial intelligence, signal processing, pattern recognition, and brain computer interface. Wahab Shah received his Ph.D. in Electrical and Electronic Engineering from Huazhong University of Science and Technology, Wuhan, China, in 2019. His main research interests include the artificial neural networks, insulation design of power systems and long air-gap discharge.