EEG signal classification using LSTM and improved neural network algorithms

Neural network (NN) finds role in variety of applications due to combined effect of feature extraction and classification availability in deep learning algorithms. In this paper, we have chosen SVM, logistic regression machine learning algorithms and NN for EEG signal classification. Two-layer LSTM and four-layer improved NN deep learning algorithms are proposed to improve the performance in EEG classification. Novelty lies in one-dimensional gradient descent activation functions with radial basis operations used in the initial layers of improved NN which help in achieving better performance. Statistical features namely mean, standard deviation, kurtosis and skewness are extracted for input EEG collected from Bonn database and then applied for various classification techniques. Accuracy, precision, recall and F1 score are the performance metrics used for analyzing the algorithms. Improved NN and LSTM give better performance compared to all other architectures. The simulations are carried out with variety of activation functions, optimizers and loss models to analyze the performance using Python in keras.

[1]  M. L. Dewal,et al.  Epileptic seizures detection in EEG using DWT-based ApEn and artificial neural network , 2012, Signal, Image and Video Processing.

[2]  P. Aruna Priya,et al.  Artificial neural network based wavelet transform technique for image quality enhancement , 2019, Comput. Electr. Eng..

[3]  Ricardo Chavarriaga,et al.  Human EEG reveals distinct neural correlates of power and precision grasping types , 2018, NeuroImage.

[4]  U. Rajendra Acharya,et al.  Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals , 2019, Comput. Biol. Medicine.

[5]  Aboul Ella Hassanien,et al.  A hybrid automated detection of epileptic seizures in EEG based on wavelet and machine learning techniques , 2018 .

[6]  Satchidananda Dehuri,et al.  EEG signal classification using PSO trained RBF neural network for epilepsy identification , 2017 .

[7]  Rabab K. Ward,et al.  Optimized deep neural network architecture for robust detection of epileptic seizures using EEG signals , 2019, Clinical Neurophysiology.

[8]  Chin-Teng Lin,et al.  Brain Dynamics in Predicting Driving Fatigue Using a Recurrent Self-Evolving Fuzzy Neural Network , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Petr Klimes,et al.  Intracerebral EEG Artifact Identification Using Convolutional Neural Networks , 2018, Neuroinformatics.

[10]  D. M. Lazurenko,et al.  A Novel Neural Network Approach to Creating a Brain–Computer Interface Based on the EEG Patterns of Voluntary Muscle Movements , 2018, Neuroscience and Behavioral Physiology.

[11]  Li-zhen Cui,et al.  Automatic Sleep Stage Classification Based on Convolutional Neural Network and Fine-Grained Segments , 2018, Complex..

[12]  Xiaowei Li,et al.  EEG-based mild depression recognition using convolutional neural network , 2019, Medical & Biological Engineering & Computing.

[13]  Feng Duan,et al.  A Novel Deep Learning Approach With Data Augmentation to Classify Motor Imagery Signals , 2019, IEEE Access.

[14]  Ahmad Kamran Malik,et al.  A multi‐modal, multi‐atlas‐based approach for Alzheimer detection via machine learning , 2018, Int. J. Imaging Syst. Technol..

[15]  Chao Wu,et al.  DeepSleepNet: A Model for Automatic Sleep Stage Scoring Based on Raw Single-Channel EEG , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[16]  Hakan Isik,et al.  Employment and Comparison of Different Artificial Neural Networks for Epilepsy Diagnosis from EEG Signals , 2012, Journal of Medical Systems.

[17]  U. Rajendra Acharya,et al.  Automated EEG-based screening of depression using deep convolutional neural network , 2018, Comput. Methods Programs Biomed..

[18]  Laurent Vercueil,et al.  A convolutional neural network for sleep stage scoring from raw single-channel EEG , 2018, Biomed. Signal Process. Control..

[19]  Maryam Gholami Doborjeh,et al.  Attentional Bias Pattern Recognition in Spiking Neural Networks from Spatio-Temporal EEG Data , 2018, Cognitive Computation.

[20]  N. Arunkumar,et al.  Satellite cloud image classification for cyclone prediction using Dichotomous Logistic Regression Based Fuzzy Hypergraph model , 2019, Future Gener. Comput. Syst..

[21]  Alexander Bertrand,et al.  Distributed Signal Processing for Wireless EEG Sensor Networks , 2015, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[22]  J. Escudero,et al.  Analysis of EEG networks and their correlation with cognitive impairment in preschool children with epilepsy , 2019, Epilepsy & Behavior.

[23]  Klaus-Robert Müller,et al.  Interpretable deep neural networks for single-trial EEG classification , 2016, Journal of Neuroscience Methods.

[24]  N. Arunkumar,et al.  Fully automatic model‐based segmentation and classification approach for MRI brain tumor using artificial neural networks , 2018, Concurr. Comput. Pract. Exp..

[25]  N. Sivakumaran,et al.  Automated detection of the preseizure state in EEG signal using neural networks , 2019, Biocybernetics and Biomedical Engineering.

[26]  M. K. Hosain,et al.  Classification of malignant and benign tissue with logistic regression , 2019, Informatics in Medicine Unlocked.

[27]  E. Sokhadze,et al.  Neuroimaging Study of Alpha and Beta EEG Biofeedback Effects on Neural Networks , 2018, Applied Psychophysiology and Biofeedback.

[28]  Ying Wang,et al.  Classification of focal and non focal EEG signals using empirical mode decomposition (EMD), phase space reconstruction (PSR) and neural networks , 2019, Artificial Intelligence Review.

[29]  T. Fujita,et al.  Pathological tumor regression grade of metastatic tumors in lymph node predicts prognosis in esophageal cancer patients , 2018, Cancer science.

[30]  Javier Gomez-Pilar,et al.  Altered predictive capability of the brain network EEG model in schizophrenia during cognition , 2018, Schizophrenia Research.

[31]  Junfeng Chen,et al.  Learning Spatial–Spectral–Temporal EEG Features With Recurrent 3D Convolutional Neural Networks for Cross-Task Mental Workload Assessment , 2019, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[32]  Mohammad Reza Mosavi,et al.  Accurate Classification of EEG Signals Using Neural Networks Trained by Hybrid Population-physic-based Algorithm , 2018, International Journal of Automation and Computing.

[33]  Bo Zhou,et al.  A new segmented oversampling method for imbalanced data classification using quasi‐linear SVM , 2017 .

[34]  Gwanggil Jeon,et al.  Improving resolution of medical images with deep dense convolutional neural network , 2018, Concurr. Comput. Pract. Exp..

[35]  A. Ruhan Bevi,et al.  Design and investigation of a chaotic neural network architecture for cryptographic applications , 2018, Comput. Electr. Eng..

[36]  Francesco Carlo Morabito,et al.  On the Classification of EEG Signal by Using an SVM Based Algorithm , 2018, Multidisciplinary Approaches to Neural Computing.

[37]  Gao Bing,et al.  Classification of Hyperspectral Imagery based on spectral gradient, SVM and spatial random forest , 2018, Infrared Physics & Technology.

[38]  Tzyy-Ping Jung,et al.  EEG-based prediction of driver's cognitive performance by deep convolutional neural network , 2016, Signal Process. Image Commun..

[39]  Miad Faezipour,et al.  Sleep Stage Classification Using EEG Signal Analysis: A Comprehensive Survey and New Investigation , 2016, Entropy.

[40]  Rakesh Ranjan,et al.  A fuzzy neural network approach for automatic K-complex detection in sleep EEG signal , 2018, Pattern Recognit. Lett..

[41]  Hui Xiong,et al.  Unsupervised EEG feature extraction based on echo state network , 2019, Inf. Sci..

[42]  Yan Liang,et al.  Deep convolutional neural networks for diabetic retinopathy detection by image classification , 2018, Comput. Electr. Eng..

[43]  Edgar S. García-Treviño,et al.  A New Wavelet-Based Neural Network for Classification of Epileptic-Related States using EEG , 2019, Journal of Signal Processing Systems.

[44]  Li Yao,et al.  Euler Elastica Regularized Logistic Regression for Whole-Brain Decoding of fMRI Data , 2018, IEEE Transactions on Biomedical Engineering.

[45]  Qi Wang,et al.  Deep convolutional neural network for drowsy student state detection , 2018, Concurr. Comput. Pract. Exp..

[46]  Dynamics of Interaction of Neural Networks in the Course of EEG Alpha Biofeedback , 2017, Bulletin of Experimental Biology and Medicine.

[47]  Saeid Sanei,et al.  Detection of Interictal Discharges With Convolutional Neural Networks Using Discrete Ordered Multichannel Intracranial EEG , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[48]  Long Liu Recognition and Analysis of Motor Imagery EEG Signal Based on Improved BP Neural Network , 2019, IEEE Access.

[49]  R. Thornhill,et al.  Transition zone prostate cancer: Logistic regression and machine‐learning models of quantitative ADC, shape and texture features are highly accurate for diagnosis , 2019, Journal of magnetic resonance imaging : JMRI.

[50]  Francesco Carlo Morabito,et al.  A Convolutional Neural Network approach for classification of dementia stages based on 2D-spectral representation of EEG recordings , 2019, Neurocomputing.

[51]  Şaban Öztürk,et al.  HIC-net: A deep convolutional neural network model for classification of histopathological breast images , 2019, Comput. Electr. Eng..

[52]  Peter A. Robinson,et al.  Neural mechanisms of the EEG alpha-BOLD anticorrelation , 2018, NeuroImage.

[53]  Kai Keng Ang,et al.  ERNN: A Biologically Inspired Feedforward Neural Network to Discriminate Emotion From EEG Signal , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[54]  Yudong Zhang,et al.  Cerebral micro‐bleeding identification based on a nine‐layer convolutional neural network with stochastic pooling , 2019, Concurr. Comput. Pract. Exp..

[55]  Xinbo Gao,et al.  Deep Convolutional Neural Networks for mental load classification based on EEG data , 2018, Pattern Recognit..

[56]  Bengisu Tulu,et al.  Area Determination of Diabetic Foot Ulcer Images Using a Cascaded Two-Stage SVM-Based Classification , 2017, IEEE Transactions on Biomedical Engineering.

[57]  Shouqian Sun,et al.  Single-trial EEG classification of motor imagery using deep convolutional neural networks , 2017 .

[58]  Lei Cao,et al.  Short time Fourier transformation and deep neural networks for motor imagery brain computer interface recognition , 2018, Concurr. Comput. Pract. Exp..

[59]  U. Rajendra Acharya,et al.  Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals , 2017, Comput. Biol. Medicine.

[60]  Mehedi Masud,et al.  A forecasting tool for prediction of epileptic seizures using a machine learning approach , 2018, Concurr. Comput. Pract. Exp..

[61]  Farid Melgani,et al.  Spatial and Structured SVM for Multilabel Image Classification , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[62]  Karim Jerbi,et al.  Learning machines and sleeping brains: Automatic sleep stage classification using decision-tree multi-class support vector machines , 2015, Journal of Neuroscience Methods.

[63]  R Sundar,et al.  Performance enhanced Boosted SVM for Imbalanced datasets , 2019, Appl. Soft Comput..

[64]  Gokhan Ertas,et al.  Detection of high GS risk group prostate tumors by diffusion tensor imaging and logistic regression modelling. , 2018, Magnetic resonance imaging.