{"references": ["C. W. Anderson, S. V. Devulapalli, and E. A. Stolz. Determining\nmental state from EEG signals using parallel implementations of neural\nnetworks. Scientific Programming, 4(3):171-183, 1995.", "X. Bao, J. Wang, and J. Hu. Method of individual identification based\non electroencephalogram analysis. International Conference on New\nTrends in Information and Service Science, pages 390-393, 2009.", "I. Daubechies. Ten Lectures On Wavelets. Society for Industrial and\nApplied Mathematics Philadelphia, PA, 1992.", "C. Gope, N. Kehtarnavaz, and D. Nair. Neural network classification of\nEEG signals using time-frequency representation. In IEEE International\nJoint Conference on Neural Networks, volume 4, pages 2502 -2507,\nMontreal, Canada, 2005.", "C. Hema, M. Paulraj, and H. Kaur. Brain signatures: A modality for\nbiometric authentication. In International Conference on Electronic\nDesign, pages 1- 4, Penang, Malaysia, 2008.", "P. Jahankhani, V. Kodogiannis, and K. Revett. EEG signal classification\nusing wavelet feature extraction and neural networks. In IEEE John\nVincent Atanasoff 2006 International Symposium on Modern Computing,\npages 120 -124, Sofia, Bulgaria, 2006.", "H. Jian-Feng. Multifeature biometric system based on EEG signals.\nIn Proceedings of the 2nd International Conference on Interaction\nSciences, pages 1341-1345, Seoul, Korea, 2009.", "S. Marcel and J. Millan. Person authentication using brainwaves (EEG)\nand maximum a posteriori model adaptation. IEEE Transactions on\nPattern Analysis and Machine Intelligence, 29(4):743 -752, 2007.", "S. Minfen and S. Fenglin. The analysis of dynamic EEG signals by\nusing wavelet packets decomposition. pages 85 - 88, 1998.\n[10] R. Palaniappan and D. P. Mandic. Biometrics from brain electrical\nactivity: A machine learning approach. IEEE Transactions on Pattern\nAnalysis and Machine Intelligence, 29:738-742, 2007.\n[11] R. Palaniappan and D. P. Mandic. EEG based biometric framework\nfor automatic identity verification. Journal of VLSI Signal Processing\nSystems, 49(2):243-250, 2007.\n[12] R. Palaniappan and K. Ravi. Improving visual evoked potential feature\nclassification for person recognition using PCA and normalization.\nPattern Recognition Letters, 27(7):726 - 733, 2006.\n[13] R. Paranjape, J. Mahovsky, L. Benedicenti, and Z. Koles-. The electroencephalogram\nas a biometric. In Canadian Conference on Electrical\nand Computer Engineering, volume 2, pages 1363 -1366, 2001.\n[14] M. Poulos, M. Rangoussi, V. Chrissikopoulos, and A. Evangelou.\nParametric person identification from the EEG using computational\ngeometry. volume 2, pages 1005 -1008, Pafos, Cyprus, 1999.\n[15] M. Poulos, M. Rangoussi, V. Chrissikopoulos, and A. Evangelou. Person\nidentification based on parametric processing of the EEG. volume 1,\npages 283 -286, Pafos, Cyprus, 1999.\n[16] K. Ravi and R. Palaniappan. Leave-one-out authentication of persons\nusing 40Hz EEG oscillations. In The International Conference on\nComputer as a Tool, volume 2, pages 1386 -1389, Belgrade, Serbia\n& Montenegro, 2005.\n[17] A. Riera, A. Soria-Frisch, M. Caparrini, C. Grau, and G. Ruffini.\nUnobtrusive biometric system based on electroencephalogram analysis.\nEURASIP Journal on Advances in Signal Processing, 2008:18, 2008.\n[18] G. Singhal and P. RamKumar. Person identification using evoked\npotentials and peak matching. In Biometrics Symposium, pages 1- 6,\nBaltimore, MD, 2007.\n[19] V. Srinivasan, C. Eswaran, and N. Sriraam. Approximate entropybased\nepileptic EEG detection using artificial neural networks. IEEE\nTransactions on Information Technology in Biomedicine, 11(3):288-295,\n2007.\n[20] A. Subasi, A. Alkan, E. Koklukaya, and M. K. Kiymik. Wavelet neural\nnetwork classification of EEG signals by using AR model with MLE\npreprocessing. Neural Networks, 18(7):985-997, 2005.\n[21] L. Sun and M. Shen. Analysis of non-stationary electroencephalogram\nusing the wavelet transformation. In 6th International Conference on\nSignal Processing, volume 2, pages 1520 - 1523, Beijing, China, 2002.\n[22] S. Sun. Multitask learning for EEG-based biometrics. In International\nConference on Pattern Recognition, pages 1- 4, Tampa, FL, 2008.\n[23] P. Tangkraingkij, C. Lursinsap, S. Sanguansintukul, and T. Desudchit.\nSelecting relevant EEG signal locations for personal identification problem\nusing ICA and neural network. In 8th IEEE/ACIS International\nConference on Computer and Information Science, pages 616 - 621,\nShanghai, China, 2009.\n[24] W. Ting, Y. Guo-zheng, Y. Bang-hua, and S. Hong. EEG feature\nextraction based on wavelet packet decomposition for brain computer\ninterface. Measurement, 41(6):618 - 625, 2008.\n[25] A. Yazdani, A. Roodaki, S. Rezatofighi, K. Misaghian, and S. Setarehdan.\nFisher linear discriminant based person identification using visual\nevoked potentials. In 9th International Conference on Signal Processing,\npages 1677 -1680, Beijing, China, 2008."]}

This paper discusses the effectiveness of the EEG signal for human identification using four or less of channels of two different types of EEG recordings. Studies have shown that the EEG signal has biometric potential because signal varies from person to person and impossible to replicate and steal. Data were collected from 10 male subjects while resting with eyes open and eyes closed in 5 separate sessions conducted over a course of two weeks. Features were extracted using the wavelet packet decomposition and analyzed to obtain the feature vectors. Subsequently, the neural networks algorithm was used to classify the feature vectors. Results show that, whether or not the subjects- eyes were open are insignificant for a 4– channel biometrics system with a classification rate of 81%. However, for a 2–channel system, the P4 channel should not be included if data is acquired with the subjects- eyes open. It was observed that for 2– channel system using only the C3 and C4 channels, a classification rate of 71% was achieved.