Epileptic seizure classification in EEG signals using second-order difference plot of intrinsic mode functions

Epilepsy is a neurological disorder which is characterized by transient and unexpected electrical disturbance of the brain. The electroencephalogram (EEG) is a commonly used signal for detection of epileptic seizures. This paper presents a new method for classification of ictal and seizure-free EEG signals. The proposed method is based on the empirical mode decomposition (EMD) and the second-order difference plot (SODP). The EMD method decomposes an EEG signal into a set of symmetric and band-limited signals termed as intrinsic mode functions (IMFs). The SODP of IMFs provides elliptical structure. The 95% confidence ellipse area measured from the SODP of IMFs has been used as a feature in order to discriminate seizure-free EEG signals from the epileptic seizure EEG signals. The feature space obtained from the ellipse area parameters of two IMFs has been used for classification of ictal and seizure-free EEG signals using the artificial neural network (ANN) classifier. It has been shown that the feature space formed using ellipse area parameters of first and second IMFs has given good classification performance. Experimental results on EEG database available by the University of Bonn, Germany, are included to illustrate the effectiveness of the proposed method.     

Examination of scale-invariant characteristics of epileptic electroencephalograms using wavelet-based analysis

There is evidence that biological and physiological systems including the brain exhibit can exhibit fractal characteristics that can be used to identify the state of the system. In this study, wavelet-based fractal analysis is used to examine self-similar or scale-invariant characteristics of intracranial EEG data in terms of the spectral exponent. The intracranial EEG data were recorded from subjects with epilepsy during non-seizure period and during epileptic seizure activity. From the computational results, it is observed that the self-similar or scale-invariant characteristics of the intracranial EEG data obtained during these two periods are significantly different. The actual value of the estimated spectral exponent depends on the wavelet bases used for the computations.     

引入迁移学习的癫痫EEG信号自适应识别

在脑电图( EEG)信号识别中,EEG信号的采样环境、病人状态的多样性导致分类器训练所用的源域与分类器测试所用的目标域不匹配,分类器在目标域上表现不佳。为此,引入邻域适应策略,提出一种基于子空间相似度的改进主成分分析特征提取方法( SSM-PCA),在选择主成分时,考虑源域和目标域数据的几何和统计特性,并结合迁移学习分类器大间隔投射迁移支持向量机( LMPROJ),给出以SSM-PCA为基础的LMPROJ分类识别方法。实验结果表明,与结合PCA特征抽取技术和K近邻分类器实现的识别方法相比,该方法在识别正确率方面得到较大提升。     

Classifying mental tasks based on features of higher-order statistics from EEG signals in brain-computer interface

In order to characterize the non-Gaussian information contained within the EEG signals, a new feature extraction method based on bispectrum is proposed and applied to the classification of right and left motor imagery for developing EEG-based brain-computer interface systems. The experimental results on the Graz BCI data set have shown that based on the proposed features, a LDA classifier, SVM classifier and NN classifier outperform the winner of the BCI 2003 competition on the same data set in terms of either the mutual information, the competition criterion, or misclassification rate.     

Classification of Electroencephalogram Signals Using LSTM and SVM Based on Fast Walsh-Hadamard Transform

Classification of electroencephalogram (EEG) signals for humans can be achieved via artificial intelligence (AI) techniques. Especially, the EEG signals associated with seizure epilepsy can be detected to distinguish between epileptic and non-epileptic regions. From this perspective, an automated AI technique with a digital processing method can be used to improve these signals. This paper proposes two classifiers: long short-term memory (LSTM) and support vector machine (SVM) for the classification of seizure and non-seizure EEG signals. These classifiers are applied to a public dataset, namely the University of Bonn, which consists of 2 classes –seizure and non-seizure. In addition, a fast Walsh-Hadamard Transform (FWHT) technique is implemented to analyze the EEG signals within the recurrence space of the brain. Thus, Hadamard coefficients of the EEG signals are obtained via the FWHT. Moreover, the FWHT is contributed to generate an efficient derivation of seizure EEG recordings from non-seizure EEG recordings. Also, a k-fold cross-validation technique is applied to validate the performance of the proposed classifiers. The LSTM classifier provides the best performance, with a testing accuracy of 99.00%. The training and testing loss rates for the LSTM are 0.0029 and 0.0602, respectively, while the weighted average precision, recall, and F1-score for the LSTM are 99.00%. The results of the SVM classifier in terms of accuracy, sensitivity, and specificity reached 91%, 93.52%, and 91.3%, respectively. The computational time consumed for the training of the LSTM and SVM is 2000 and 2500 s, respectively. The results show that the LSTM classifier provides better performance than SVM in the classification of EEG signals. Eventually, the proposed classifiers provide high classification accuracy compared to previously published classifiers.     

Detection of epileptic electroencephalogram based on Permutation Entropy and Support Vector Machines

The electroencephalogram (EEG) has proven a valuable tool in the study and detection of epilepsy. This paper investigates for the first time the use of Permutation Entropy (PE) as a feature for automated epileptic seizure detection. A Support Vector Machine (SVM) is used to classify segments of normal and epileptic EEG based on PE values. The proposed system utilizes the fact that the EEG during epileptic seizures is characterized by lower PE than normal EEG. It is shown that average sensitivity of 94.38% and average specificity of 93.23% is obtained by using PE as a feature to characterize epileptic and seizure-free EEG, while 100% sensitivity and specificity were also obtained in single-trial classifications.     

An integrated alcoholic index using tunable-Q wavelet transform based features extracted from EEG signals for diagnosis of alcoholism

Alcoholism affects the structure and functioning of brain. Electroencephalogram (EEG) signals can depict the state of brain. The EEG signals are ensemble of various neuronal activity recorded from different scalp regions having different characteristics and very low magnitude in microvolts. These factors make human interpretation difficult and time consuming to analyze these signals. Moreover, these highly varying EEG signals are susceptible to inter/intra variability errors. So, a Computer-Aided Diagnosis (CAD) can be used to identify the alcoholic and normal subjects accurately. However, these EEG signals exhibit nonlinear and non-stationary properties. Therefore, it needs much effort in deciphering the diagnostic evidence from them using linear time and frequency-domain methods. The nonlinear parameters together with time-frequency/scale domain methods can help to detect tiny changes in these signals. The correntropy is nonlinear indicator which characterizes the dynamic behavior of EEG signals in time-scale domain. In this paper, we present a new way for diagnosis of alcoholism using Tunable-Q Wavelet Transform (TQWT) based features derived from EEG signals. The feature extraction is performed using TQWT based decomposition and extracted Centered Correntropy (CC) from the forth decomposed detail sub-band. The Principal Component Analysis (PCA) is used for feature reduction followed by Least Squares-Support Vector Machine (LS-SVM) for classifying normal and alcoholic EEG signals. In order to make sure reliable classification performance, 10-fold cross-validation scheme is adopted. Our proposed system is able to diagnose the alcoholic and normal EEG signals, with an average accuracy of 97.02%, sensitivity of 96.53%, specificity of 97.50% and Matthews correlation coefficient of 0.9494 for Q-factor (Q) varying between 3 and 8 using Radial Basis Function (RBF) kernel function. Also, we have established a novel Alcoholism Risk Index (ARI) using three clinically significant features to discriminate the given classes by means of a single number. This system can be used for automated diagnosis and monitoring of alcoholic subjects to evaluate the effect of treatment.     

Biogeography based hybrid scheme for automatic detection of epileptic seizures from EEG signatures

Biogeography Based Optimization (BBO) algorithm is one of the nature-inspired optimization methods, based on the study of geographical distribution of species on earth. The present research work is based upon decomposition of human electroencephalograms (EEG) signal by Wavelet Packet Transform, computation of a complete feature set using statistical and non-statistical properties followed by optimal selection of features by BBO; the optimality criterion being classification rate. The stopping criterion for BBO is set to 100% correct classification rate. The proposed algorithm is novel in terms of TWSVM computing the Habitat Suitability Index (HSI) values for BBO, perfect classification rate, low computation time, and feature selection mechanism. The proposed scheme outperforms several previous results reported in literature in that it gives a feature subset which gives 100% classification accuracy for different classification instances.     

A Noise-Aware Real-Time Processing Approach for Electroencephalogram Signal Classification

Electroencephalogram (EEG) signal processing has emerged as a critical problem for biometric applications due to its real-time requirement. While compressive sensing is an efficient method for signal compression, its application in EEG signal processing is limited due to its noise unawareness during transmission and time-consuming reconstruction procedure. In this paper, we propose a noise-aware sparse Bayesian learning approach with block structure (NA-BSBL) to achieve higher efficiency on data compression, reconstruction and classification. By applying novel structure for parameter and introducing the Mahalanobis Distance, our approach achieves an almost 20% reconstruction performance lift and 10% accuracy lift under noise condition. For further application of reconstructed EEG signal, we extract both the spatial and frequency domain features for classification. Experimental results show that the proposed approach can achieve 94% classification accuracy with 16% speed up compared with the conventional approach.     

Learning polynomial networks for classification of clinical electroencephalograms

We describe a polynomial network technique developed for learning to classify clinical electroencephalograms (EEGs) presented by noisy features. Using an evolutionary strategy implemented within group method of data handling, we learn classification models which are comprehensively described by sets of short-term polynomials. The polynomial models were learnt to classify the EEGs recorded from Alzheimer and healthy patients and recognize the EEG artifacts. Comparing the performances of our technique and some machine learning methods we conclude that our technique can learn well-suited polynomial models which experts can find easy-to-understand.