Hardware design of multiclass SVM classification for epilepsy and epileptic seizure detection

An automatic detection system for distinguishing healthy, ictal, and inter-ictal EEG signals plays an important role in medical practice. This paper presents a very large scale integration (VLSI) architecture of three-class classification for epilepsy and seizure detection. In order to find out the most efficient three-class classification scheme for hardware implementation, several multiclass non-linear support vector machine (NLSVM) classifiers are compared and validated using software implementation. Finally, the one-against-one (OAO) multiclass NLSVM is selected due to its highest accuracy. The designed system consists of a discrete wavelet transform (DWT)-based feature extraction module, a modified sequential minimal optimization (MSMO) training module, and an OAO multiclass classification module. A lifting structure of Daubechies order 4 wavelet is introduced in three-level DWT to save circuit area and speed up the computational time. The MSMO is used for on-chip training. The circuit of the largest absolute value decision is designed to avoid the unclassifiable problem in the OAO multiclass classification. The designed system is implemented on a field-programmable gate array (FPGA) platform and evaluated using the publicly available epilepsy dataset. The experimental results demonstrate that the designed system achieves high accuracy with low-dimensional feature vectors.

[1]  Ram Bilas Pachori,et al.  A novel approach for time-frequency localization of scaling functions and design of three-band biorthogonal linear phase wavelet filter banks , 2017, Digit. Signal Process..

[2]  U. Rajendra Acharya,et al.  A new approach to characterize epileptic seizures using analytic time-frequency flexible wavelet transform and fractal dimension , 2017, Pattern Recognit. Lett..

[3]  Guido Masera,et al.  Low-Complexity, Efficient 9/7 Wavelet Filters VLSI Implementation , 2006, IEEE Transactions on Circuits and Systems II: Express Briefs.

[4]  Yan Li,et al.  Improving the Separability of Motor Imagery EEG Signals Using a Cross Correlation-Based Least Square Support Vector Machine for Brain–Computer Interface , 2012, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[5]  Srinivasan Ramakrishnan,et al.  Hierarchical multi-class SVM with ELM kernel for epileptic EEG signal classification , 2015, Medical & Biological Engineering & Computing.

[6]  Jerald Yoo,et al.  A 1.83 µJ/Classification, 8-Channel, Patient-Specific Epileptic Seizure Classification SoC Using a Non-Linear Support Vector Machine , 2016, IEEE Trans. Biomed. Circuits Syst..

[7]  Giles M. Foody,et al.  Multiclass and Binary SVM Classification: Implications for Training and Classification Users , 2008, IEEE Geoscience and Remote Sensing Letters.

[8]  Amir Rastegarnia,et al.  A Wavelet-Based Artifact Reduction From Scalp EEG for Epileptic Seizure Detection , 2016, IEEE Journal of Biomedical and Health Informatics.

[9]  Deba Prasad Dash,et al.  A nonlinear feature based epileptic seizure detection using least square support vector machine classifier , 2015, TENCON 2015 - 2015 IEEE Region 10 Conference.

[10]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[11]  K Lehnertz,et al.  Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[12]  Andrea Petracca,et al.  A Classification Algorithm for Electroencephalography Signals by Self-Induced Emotional Stimuli , 2016, IEEE Transactions on Cybernetics.

[13]  Jerald Yoo,et al.  A 1.83µJ/classification nonlinear support-vector-machine-based patient-specific seizure classification SoC , 2013, 2013 IEEE International Solid-State Circuits Conference Digest of Technical Papers.

[14]  Kim Dremstrup,et al.  EMD-Based Temporal and Spectral Features for the Classification of EEG Signals Using Supervised Learning , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[15]  Elif Derya Übeyli,et al.  Multiclass Support Vector Machines for EEG-Signals Classification , 2007, IEEE Trans. Inf. Technol. Biomed..

[16]  Yanchun Zhang,et al.  Automatic epilepsy detection from EEG introducing a new edge weight method in the complex network , 2016 .

[17]  Tahir Ahmad,et al.  EEG signal of epiliptic patient by fast Fourier and wavelet transforms , 2013 .

[18]  T. Lindblad,et al.  Hardware Implementation of 1D Wavelet Transform on an FPGA for Infrasound Signal Classification , 2008, IEEE Transactions on Nuclear Science.

[19]  Naveen Verma,et al.  A Low-Power Processor With Configurable Embedded Machine-Learning Accelerators for High-Order and Adaptive Analysis of Medical-Sensor Signals , 2013, IEEE Journal of Solid-State Circuits.

[20]  Chih-Hsien Hsia,et al.  Memory-Efficient Hardware Architecture of 2-D Dual-Mode Lifting-Based Discrete Wavelet Transform , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

[21]  Ram Bilas Pachori,et al.  Discrimination between Ictal and Seizure-Free EEG Signals Using Empirical Mode Decomposition , 2008, J. Electr. Comput. Eng..

[22]  Irena Koprinska,et al.  Classification of Brain-Computer Interface Data , 2008, AusDM.

[23]  B. Fei,et al.  Binary tree of SVM: a new fast multiclass training and classification algorithm , 2006, IEEE Transactions on Neural Networks.

[24]  Hojjat Adeli,et al.  Principal Component Analysis-Enhanced Cosine Radial Basis Function Neural Network for Robust Epilepsy and Seizure Detection , 2008, IEEE Transactions on Biomedical Engineering.

[25]  Sang Yoon Park,et al.  CORDIC Designs for Fixed Angle of Rotation , 2013, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[26]  Sheng-Fu Liang,et al.  Combination of EEG Complexity and Spectral Analysis for Epilepsy Diagnosis and Seizure Detection , 2010, EURASIP J. Adv. Signal Process..

[27]  Rajeev Sharma,et al.  Classification of epileptic seizures in EEG signals based on phase space representation of intrinsic mode functions , 2015, Expert Syst. Appl..

[28]  Y. Tang,et al.  A tunable support vector machine assembly classifier for epileptic seizure detection , 2012, Expert Syst. Appl..

[29]  Ergun Erçelebi,et al.  ECG denoising on bivariate shrinkage function exploiting interscale dependency of wavelet coefficients , 2011 .

[30]  Elif Derya Übeyli,et al.  Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients , 2005, Journal of Neuroscience Methods.

[31]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[32]  Sheng-Fu Liang,et al.  A Fully Integrated 8-Channel Closed-Loop Neural-Prosthetic CMOS SoC for Real-Time Epileptic Seizure Control , 2013, IEEE Journal of Solid-State Circuits.

[33]  Yan Li,et al.  Clustering technique-based least square support vector machine for EEG signal classification , 2011, Comput. Methods Programs Biomed..

[34]  V. Srinivasan,et al.  Approximate Entropy-Based Epileptic EEG Detection Using Artificial Neural Networks , 2007, IEEE Transactions on Information Technology in Biomedicine.

[35]  Yan Li,et al.  Designing a robust feature extraction method based on optimum allocation and principal component analysis for epileptic EEG signal classification , 2015, Comput. Methods Programs Biomed..

[36]  Ta-Wen Kuan,et al.  VLSI Design of an SVM Learning Core on Sequential Minimal Optimization Algorithm , 2012, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[37]  Ram Bilas Pachori,et al.  Classification of Seizure and Nonseizure EEG Signals Using Empirical Mode Decomposition , 2012, IEEE Transactions on Information Technology in Biomedicine.

[38]  R. B. Pachori,et al.  Tunable-Q Wavelet Transform Based Multiscale Entropy Measure for Automated Classification of Epileptic EEG Signals , 2017 .

[39]  Bernhard Schölkopf,et al.  Training Invariant Support Vector Machines , 2002, Machine Learning.

[40]  Ram Bilas Pachori,et al.  Time-frequency localized three-band biorthogonal wavelet filter bank using semidefinite relaxation and nonlinear least squares with epileptic seizure EEG signal classification , 2017, Digit. Signal Process..

[41]  Dimitrios I. Fotiadis,et al.  Automatic Seizure Detection Based on Time-Frequency Analysis and Artificial Neural Networks , 2007, Comput. Intell. Neurosci..

[42]  K. Shanti Swarup,et al.  Classification and Assessment of Power System Security Using Multiclass SVM , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[43]  S. Sathiya Keerthi,et al.  Parallel sequential minimal optimization for the training of support vector machines , 2006, IEEE Trans. Neural Networks.

[44]  Weidong Zhou,et al.  Automatic Seizure Detection Using Wavelet Transform and SVM in Long-Term Intracranial EEG , 2012, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[45]  Ram Bilas Pachori,et al.  Epileptic seizure classification in EEG signals using second-order difference plot of intrinsic mode functions , 2014, Comput. Methods Programs Biomed..

[46]  H. Adeli,et al.  Analysis of EEG records in an epileptic patient using wavelet transform , 2003, Journal of Neuroscience Methods.

[47]  Christa Neuper,et al.  A Comparative Analysis of Multi-Class EEG Classification for Brain Computer Interface , 2005 .

[48]  Anantha Chandrakasan,et al.  An 8-Channel Scalable EEG Acquisition SoC With Patient-Specific Seizure Classification and Recording Processor , 2013, IEEE Journal of Solid-State Circuits.

[49]  Elif Derya Übeyli,et al.  Recurrent neural networks employing Lyapunov exponents for EEG signals classification , 2005, Expert Syst. Appl..

[50]  Ram Bilas Pachori,et al.  Classification of seizure and seizure-free EEG signals using local binary patterns , 2015, Biomed. Signal Process. Control..

[51]  Ram Bilas Pachori,et al.  Classification of ictal and seizure-free EEG signals using fractional linear prediction , 2014, Biomed. Signal Process. Control..

[52]  Mohammed Imamul Hassan Bhuiyan,et al.  Detection of Seizure and Epilepsy Using Higher Order Statistics in the EMD Domain , 2013, IEEE Journal of Biomedical and Health Informatics.

[53]  In-Cheol Park,et al.  Pipelined Discrete Wavelet Transform Architecture Scanning Dual Lines , 2009, IEEE Transactions on Circuits and Systems II: Express Briefs.

[54]  Sheau-Ling Hsieh,et al.  High-Performance Seizure Detection System Using a Wavelet-Approximate Entropy-fSVM Cascade With Clinical Validation , 2013, Clinical EEG and neuroscience.

[55]  Bijaya K. Panigrahi,et al.  Automated Diagnosis of Epilepsy Using Key-Point-Based Local Binary Pattern of EEG Signals , 2017, IEEE Journal of Biomedical and Health Informatics.

[56]  U. Rajendra Acharya,et al.  Automated EEG analysis of epilepsy: A review , 2013, Knowl. Based Syst..