A Low Power and High Performance Hardware Design for Automatic Epilepsy Seizure Detection

• Autorzy: Rafiammal S. Syed , Najumnissa D. , Anuradha G. , Mohideen S. Kaja , Jawahar P. K. , Mutalib Syed Abdul

Identyfikatory

DOI

10.24425/ijet.2019.130254

• Języki publikacji: EN

Abstrakty

EN

An application specific integrated design using Quadrature Linear Discriminant Analysis is proposed for automatic detection of normal and epilepsy seizure signals from EEG recordings in epilepsy patients. Five statistical parameters are extracted to form the feature vector for training of the classifier. The statistical parameters are Standardised Moment, Co-efficient of Variance, Range, Root Mean Square Value and Energy. The Intellectual Property Core performs the process of filtering, segmentation, extraction of statistical features and classification of epilepsy seizure and normal signals. The design is implemented in Zynq 7000 Zc706 SoC with average accuracy of 99%, Specificity of 100%, F1 score of 0.99, Sensitivity of 98% and Precision of 100 % with error rate of 0.0013/hr., which is approximately zero false detection.

Słowa kluczowe

EN

epilepsy detection; system on chip; implementation; quadrature linear discriminant analysis; hardware design; seizure detection

• Wydawca: Polish Academy of Sciences, Committee of Electronics and Telecommunication
• Czasopismo: International Journal of Electronics and Telecommunications
• Rocznik: 2019
• Tom: Vol. 65, No. 4
• Strony: 707--712
• Opis fizyczny: Bibliogr. 28 poz., rys., wykr., tab.

Twórcy

autor

Rafiammal S. Syed

• School of Electrical and Communication Sciences, B.S.A Crescent Institute of Science and Technology, Chennai, India

autor

Najumnissa D.

• School of Electrical and Communication Sciences, B.S.A Crescent Institute of Science and Technology, Chennai, India

autor

Anuradha G.

• School of Electrical and Communication Sciences, B.S.A Crescent Institute of Science and Technology, Chennai, India

autor

Mohideen S. Kaja

• School of Electrical and Communication Sciences, B.S.A Crescent Institute of Science and Technology, Chennai, India

autor

Jawahar P. K.

• School of Electrical and Communication Sciences, B.S.A Crescent Institute of Science and Technology, Chennai, India

autor

Mutalib Syed Abdul

• Faculty of Electrical Engineering, University Teknologi MARA, Malaysia

Bibliografia

• [1]. A. Isaksson, A. Wennberg, .H. Zetterberg, Computer analysis of EEG signals with parametric models, Proceedings of the IEEE 69 (1981).
• [2]. World Health Organisation–Epilepsy facts-http://www.who.int/news-room/fact-sheets/detail/epilepsy 8 February 2018. (accessed 26 November 2018).
• [3]. Alexandros T. Tzallas, Member, IEEE, Markos G. Tsipouras, and Dimitrios I. Fotiadis, Senior Member, IEEE Epileptic Seizure Detection in EEGs Using Time–Frequency Analysis, IEEE Transactions On Information Technology In Biomedicine, Vol. 13, No. 5, September 200, 703.
• [4]. U. R. Acharya, S. V. Sree and J. S. Suri, “Automatic detection of epileptic EEG signals using higher order cumulant features,” International Journal of Neural Systems 21: 403-414, 2011.
• [5]. J. L. Semmlow, Biosignal and biomedical image processing, New York: Marcel Dekker, 2004.
• [6]. A. Subasi, “Automatic detection of epileptic seizure using dynamic fuzzy neural networks,” Expert Syst. Appl., 31: 320-328, 2006.
• [7]. Y. U. Khan, O. Farooq and P. Sharma, “Automatic detection of seizure onset in pediatric EEG,” Int. J. Emb. Syst. Appl., 2: 81-89, 2012.
• [8]. Md Mursalina , Yuan Zhanga, , Yuan Zhanga, Yuehui Chena, Nitesh V Chawla “ Automated epileptic seizure detection using improved correlation-based feature selection with random forest classifier” Neurocomputing 241 (2017) 204–214.
• [9]. Guangyi Chen, Wenfang Xie, Tien D. Bui, Adam Krzyżak ”Automatic Epileptic Seizure Detection in EEG Using Nonsubsampled Wavelet–Fourier Features” Journal of Medical and Biological Engineering - 2017 - 37 - 1 - 123-131.
• [10]. Manish Sharmaa Abhinav, Dhereb Ram, Bilas Pachoria U. Rajendra Acharyacde “An automatic detection of focal EEG signals using new class of time–frequency localized orthogonal wavelet filter banks “ Knowledge-Based System Volume 118, 15 February 2017, Pages 217-227.
• [11]. Vahabi Z, Amirfattahi R, Shayegh F, Ghassemi F. Online epileptic seizure prediction using wavelet-based bi-phase correlation of electrical signals tomography. Int J Neural Syst. 2015;25:1550028.
• [12]. Tzallas AT, Tsipouras MG, Fotiadis DI. Feature extraction and recognition of ictal EEG using EMD and SVM. Comput Biol Med. 43 (2013); 43: pp 807-816.
• [13]. Epileptic seizure detection in EEGs using time-frequency analysis. IEEE Trans Inf Technol Biomed.;13 (2009) 703-710.
• [14]. A.J. Gabor, R.R. Leach and F.U. Dowla, Automated seizure detection using a self-organizing neural network, Electroencephalogr, Clin. Neurophysiol, 99 (1996) 257-266.
• [15]. J. L. Semmlow, Biosignal and biomedical image processing, New York: Marcel Dekker, (2004). ISBN: 0–8247-4803–4
• [16]. Jerald Yoo, Long Yan, Dina El-Damak, An 8-Channel Scalable EEG Acquisition SoC with Patient-Specific Seizure, IEEE Journal Of Solid-State Circuits, 48 (1) (2013).
• [17]. Lichen Feng , Zunchao Li , and Yuanfa Wang. VLSI Design of SVM-Based Seizure Detection System With On-Chip Learning Capability. IEEE Transactions On Biomedical Circuits And Systems, 12,( 1), (2018).
• [18]. Muhammad Awais Bin Altaf A , 1.83 J/Classification, 8-Channel, Patient-Specific Epileptic Seizure Classification SoC Using a Non-Linear Support Vector Machine, IEEE Transactions On Biomedical Circuits And Systems,. 10,1, (2016).
• [19]. Ta-Wen Kuan, Jhing-Fa, Jia-Ching Wang, Po-Chuan Lin, and Gaung-Hui Gu “VLSI Design of an SVM Learning Core on Sequential Minimal Optimization Algorithm” IEEE Transactions On Very Large Scale Integration Systems, 20, (4), 2012.
• [20]. Mushfiq U. Saleheen, Homa Alemzadeh, Ajay M. Cheriyan, Zbigniew Kalbarczyk, Ravishankar K. Iyer An Efficient Embedded Hardware for High Accuracy Detection of Epileptic Seizures 2010 3rd International Conference on Biomedical Engineering and Informatics (2010).
• [21]. Yuanfa Wang,Zunchao Li, Lichen Feng, Chuang Wang, Wen Jing and Yefei Zhang, ” Hardware Design of Seizure Detection Based on Wavelet Transform and Sample Entropy” Journal of Circuits, Systems, and Computers Vol. 25, No. 9 (2016).
• [22]. Maria Hugle, Simon Heller† , Manuel Watter, Manuel Blum, Farrokh Manzouri , Matthias Dumpelmann Andreas Schulze-Bonhage, Peter Woias, Joschka Boedecker, Early Seizure Detection with an Energy-Efficient Convolutional Neural Network on an Implantable Microcontroller. cornell university library, june 2018.
• [23]. S. TamilarasiEmail author ,J. Sundararajan “FPGA based seizure detection and control for brain computer interface” Springer cluster computing (2018) pp 1-8. https://doi.org/10.1007/s10586-017-1501-4.
• [24]. Matthias Ring, Ulf Jensen, Patrick Kugler and Bjoern Eskofier, Software-based Performance and Complexity Analysis for the Design of Embedded Classification Systems, 21st International Conference on Pattern Recognition (ICPR 2012).
• [25]. Lehnertz K, Elger CE. Spatio-temporal dynamics of the primary epileptogenic area in temporal lobe epilepsy characterized by neuronal complexity loss. Electroencephalography and Clinical Neurophysiology. 1995; 95:108–117. Doi: 10.1016/0013-4694(95)00071-6.
• [26]. Marcin Blachnik . Time Complexity of SVM Model by LVQ Data Compression-International Conference on Artificial Intelligence and Soft Computing( 2015): Artificial Intelligence and Soft Computing pp 687-695.
• [27]. M.E. Saab, J. Gotman, A system to detect the onset of epileptic seizures in scalp EEG. clinical Neuro physiology. Volume 116, Issue 2, (2005) Pages 427–442 DOI:10.1016/j.clinph.2004.08.004.
• [28]. Deng Cai, Student Member, IEEE, Xiaofei He, and Jiawei Han, Senior Member, IEEE, SRDA: An Efficient Algorithm for Large-Scale Discriminant Analysis, IEEE Transactions On Knowledge And Data Engineering, (20), 1,(2008).DOI: 10.1109/TKDE.2007.190669