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.     

Classification of EEG signals using neural network and logistic regression

Epileptic seizures are manifestations of epilepsy. Careful analyses of the electroencephalograph (EEG) records can provide valuable insight and improved understanding of the mechanisms causing epileptic disorders. The detection of epileptiform discharges in the EEG is an important component in the diagnosis of epilepsy. As EEG signals are non-stationary, the conventional method of frequency analysis is not highly successful in diagnostic classification. This paper deals with a novel method of analysis of EEG signals using wavelet transform and classification using artificial neural network (ANN) and logistic regression (LR). Wavelet transform is particularly effective for representing various aspects of non-stationary signals such as trends, discontinuities and repeated patterns where other signal processing approaches fail or are not as effective. Through wavelet decomposition of the EEG records, transient features are accurately captured and localized in both time and frequency context. In epileptic seizure classification we used lifting-based discrete wavelet transform (LBDWT) as a preprocessing method to increase the computational speed. The proposed algorithm reduces the computational load of those algorithms that were based on classical wavelet transform (CWT). In this study, we introduce two fundamentally different approaches for designing classification models (classifiers) the traditional statistical method based on logistic regression and the emerging computationally powerful techniques based on ANN. Logistic regression as well as multilayer perceptron neural network (MLPNN) based classifiers were developed and compared in relation to their accuracy in classification of EEG signals. In these methods we used LBDWT coefficients of EEG signals as an input to classification system with two discrete outputs: epileptic seizure or non-epileptic seizure. By identifying features in the signal we want to provide an automatic system that will support a physician in the diagnosing process. By applying LBDWT in connection with MLPNN, we obtained novel and reliable classifier architecture. The comparisons between the developed classifiers were primarily based on analysis of the receiver operating characteristic (ROC) curves as well as a number of scalar performance measures pertaining to the classification. The MLPNN based classifier outperformed the LR based counterpart. Within the same group, the MLPNN based classifier was more accurate than the LR based classifier.     

Presenting a new search strategy to select synchronization values for classifying bipolar mood disorders from schizophrenic patients

There is a growing interest to employ synchronization methods to reveal natural connections among the brain lobes by measuring co-activations among EEG channels. Regarding high number of EEG channels, lots of synchronization indexes are determined between two by two channels leading to construct a high dimensional feature vector for each time frame. The objective of this paper is to propose an effective feature selection method to find discriminative synchronization indexes in order to classify patients with schizophrenia from those with bipolar mood disorder (BMD). The state-of-art synchronization methods from various domains such as phase-locking value (PLV), robust synchronization (RS), and synchronization likelihood (SL), were implemented to provide a rich feature set in order to classify the two groups. To increase the classification accuracy, a capable feature selection scheme is proposed entitled greedy overall relevancy (GOR) to select discriminative synchronization indexes. The elicited synchronization vectors of 53 subjects imposed to support vector machine (SVM) classifier and the classification result with and without applying GOR, provided 92.45% and 88.68% accuracy, respectively. Across-group variance (AGV) is chosen as a rival method to GOR; the selected features by AGV entered to the classifier resulting in 91.34% accuracy. Using pair T-test exhibits the significant superiority of GOR to AGV such that P-value determined less than 0.05. To the best of authors' knowledge, this is the first attempt to utilize the selected synchronization indexes as informative features applying to a classifier for diagnosing the psychiatric patients.     

Improved particle swarm optimization algorithm and its application in text feature selection

Text feature selection is an importance step in text classification and directly affects the classification performance. Classic feature selection methods mainly include document frequency (DF), information gain (IG), mutual information (MI), chi-square test (CHI). Theoretically, these methods are difficult to get improvement due to the deficiency of their mathematical models. In order to further improve effect of feature selection, many researches try to add intelligent optimization algorithms into feature selection method, such as improved ant colony algorithm and genetic algorithms, etc. Compared to the ant colony algorithm and genetic algorithms, particle swarm optimization algorithm (PSO) is simpler to implement and can find the optimal point quickly. Thus, this paper attempt to improve the effect of text feature selection through PSO. By analyzing current achievements of improved PSO and characteristic of classic feature selection methods, we have done many explorations in this paper. Above all, we selected the common PSO model, the two improved PSO models based respectively on functional inertia weight and constant constriction factor to optimize feature selection methods. Afterwards, according to constant constriction factor, we constructed a new functional constriction factor and added it into traditional PSO model. Finally, we proposed two improved PSO models based on both functional constriction factor and functional inertia weight, they are respectively the synchronously improved PSO model and the asynchronously improved PSO model. In our experiments, CHI was selected as the basic feature selection method. We improved CHI through using the six PSO models mentioned above. The experiment results and significance tests show that the asynchronously improved PSO model is the best one among all models both in the effect of text classification and in the stability of different dimensions.     

A binary ABC algorithm based on advanced similarity scheme for feature selection

Feature selection is the basic pre-processing task of eliminating irrelevant or redundant features through investigating complicated interactions among features in a feature set. Due to its critical role in classification and computational time, it has attracted researchers’ attention for the last five decades. However, it still remains a challenge. This paper proposes a binary artificial bee colony (ABC) algorithm for the feature selection problems, which is developed by integrating evolutionary based similarity search mechanisms into an existing binary ABC variant. The performance analysis of the proposed algorithm is demonstrated by comparing it with some well-known variants of the particle swarm optimization (PSO) and ABC algorithms, including standard binary PSO, new velocity based binary PSO, quantum inspired binary PSO, discrete ABC, modification rate based ABC, angle modulated ABC, and genetic algorithms on 10 benchmark datasets. The results show that the proposed algorithm can obtain higher classification performance in both training and test sets, and can eliminate irrelevant and redundant features more effectively than the other approaches. Note that all the algorithms used in this paper except for standard binary PSO and GA are employed for the first time in feature selection.     

A new local search based hybrid genetic algorithm for feature selection

This paper presents a new hybrid genetic algorithm (HGA) for feature selection (FS), called as HGAFS. The vital aspect of this algorithm is the selection of salient feature subset within a reduced size. HGAFS incorporates a new local search operation that is devised and embedded in HGA to fine-tune the search in FS process. The local search technique works on basis of the distinct and informative nature of input features that is computed by their correlation information. The aim is to guide the search process so that the newly generated offsprings can be adjusted by the less correlated (distinct) features consisting of general and special characteristics of a given dataset. Thus, the proposed HGAFS receives the reduced redundancy of information among the selected features. On the other hand, HGAFS emphasizes on selecting a subset of salient features with reduced number using a subset size determination scheme. We have tested our HGAFS on 11 real-world classification datasets having dimensions varying from 8 to 7129. The performances of HGAFS have been compared with the results of other existing ten well-known FS algorithms. It is found that, HGAFS produces consistently better performances on selecting the subsets of salient features with resulting better classification accuracies.     

Time series classification for the prediction of dialysis in critically ill patients using echo statenetworks

Objective: Time series often appear in medical databases, but only few machine learning methods exist that process this kind of data properly. Most modeling techniques have been designed with a static data model in mind and are not suitable for coping with the dynamic nature of time series. Recurrent neural networks (RNNs) are often used to process time series, but only a few training algorithms exist for RNNs which are complex and often yield poor results. Therefore, researchers often turn to traditional machine learning approaches, such as support vector machines (SVMs), which can easily be set up and trained and combine them with feature extraction (FE) and selection (FS) to process the high-dimensional temporal data. Recently, a new approach, called echo state networks (ESNs), has been developed to simplify the training process of RNNs. This approach allows modeling the dynamics of a system based on time series data in a straightforwardway.The objective of this study is to explore the advantages of using ESN instead of other traditional classifiers combined with FE and FS in classification problems in the intensive care unit (ICU) when the input data consists of time series. While ESNs have mostly been used to predict the future course of a time series, we use the ESN model for classification instead. Although time series often appear in medical data, little medical applications of ESNs have been studiedyet.Methods and material: ESN is used to predict the need for dialysis between the fifth and tenth day after admission in the ICU. The input time series consist of measured diuresis and creatinine values during the first 3days after admission. Data about 830 patients was used for the study, of which 82 needed dialysis between the fifth and tenth day after admission. ESN is compared to traditional classifiers, a sophisticated and a simple one, namely support vector machines and the naive Bayes (NB) classifier. Prior to the use of the SVM and NB classifier, FE and FS is required to reduce the number of input features and thus alleviate the curse dimensionality. Extensive feature extraction was applied to capture both the overall properties of the time series and the correlation between the different measurements in the time series. The feature selection method consists of a greedy hybrid filter-wrapper method using a NB classifier, which selects in each iteration the feature that improves prediction the best and shows little multicollinearity with the already selected set. Least squares regression with noise was used to train the linear readout function of the ESN to mitigate sensitivity to noise and overfitting. Fisher labeling was used to deal with the unbalanced data set. Parameter sweeps were performed to determine the optimal parameter values for the different classifiers. The area under the curve (AUC) and maximum balanced accuracy are used as performance measures. The required execution time was also measured.Results: The classification performance of the ESN shows significant difference at the 5% level compared to the performance of the SVM or the NB classifier combined with FE and FS. The NB+FE+FS, with an average AUC of 0.874, has the best classification performance. This classifier is followed by the ESN, which has an average AUC of 0.849. The SVM+FE+FS has the worst performance with an average AUC of 0.838. The computation time needed to pre-process the data and to train and test the classifier is significantly less for the ESN compared to the SVM andNB.Conclusion: It can be concluded that the use of ESN has an added value in predicting the need for dialysis through the analysis of time series data. The ESN requires significantly less processing time, needs no domain knowledge, is easy to implement, and can be configured using rules ofthumb.     

Classification of sleep stages using class-dependent sequential feature selection and artificial neural network

Several studies have been conducted for automatic classification of sleep stages to ease time-consuming manual scoring process that can involve a high degree of experience and subjectivity. But none of them has found a practical usage in medical area so far because of their under acceptable success rates. In this study, a different classification scheme is proposed to increase the success rate in automatic sleep stage scoring in which sleep stages were classified as Awake, Non-REM1, Non-REM2, Non-REM3 and REM stages. Using EEG, EMG and EOG recordings of five healthy subjects, a modified version of sequential feature selection method was applied to the sleep epochs in class by class basis and different artificial neural network (ANN) architectures were trained for each class. That is to say, sleep stages were classified with five ANN architectures each of which uses different features and different network parameters for classification. The highest classification accuracy was obtained for REM sleep as 95.13 % in addition to the lowest classification accuracy of 86.42 % for Non-REM3 sleep. The overall accuracy, on the other hand, was recorded as 90.93 %, which is a comparatively good result when the other studies using all stages are taken into account.     

Supervised hybrid feature selection based on PSO and rough sets for medical diagnosis

Medical datasets are often classified by a large number of disease measurements and a relatively small number of patient records. All these measurements (features) are not important or irrelevant/noisy. These features may be especially harmful in the case of relatively small training sets, where this irrelevancy and redundancy is harder to evaluate. On the other hand, this extreme number of features carries the problem of memory usage in order to represent the dataset. Feature Selection (FS) is a solution that involves finding a subset of prominent features to improve predictive accuracy and to remove the redundant features. Thus, the learning model receives a concise structure without forfeiting the predictive accuracy built by using only the selected prominent features. Therefore, nowadays, FS is an essential part of knowledge discovery. In this study, new supervised feature selection methods based on hybridization of Particle Swarm Optimization (PSO), PSO based Relative Reduct (PSO-RR) and PSO based Quick Reduct (PSO-QR) are presented for the diseases diagnosis. The experimental result on several standard medical datasets proves the efficiency of the proposed technique as well as enhancements over the existing feature selection techniques.     

Epileptic EEG detection using neural networks and post-classification

Electroencephalogram (EEG) has established itself as an important means of identifying and analyzing epileptic seizure activity in humans. In most cases, identification of the epileptic EEG signal is done manually by skilled professionals, who are small in number. In this paper, we try to automate the detection process. We use wavelet transform for feature extraction and obtain statistical parameters from the decomposed wavelet coefficients. A feed-forward backpropagating artificial neural network (ANN) is used for the classification. We use genetic algorithm for choosing the training set and also implement a post-classification stage using harmonic weights to increase the accuracy. Average specificity of 99.19%, sensitivity of 91.29% and selectivity of 91.14% are obtained.     

A combination of Genetic Algorithm,Particle Swarm Optimization and Neural Network for palmprint recognition

In this study, a new approach to the palmprint recognition phase is presented. 2D Gabor filters are used for feature extraction of palmprints. After Gabor filtering, standard deviations are computed in order to generate the palmprint feature vector. Genetic Algorithm-based feature selection is used to select the best feature subset from the palmprint feature set. An Artificial Neural Network (ANN) based on hybrid algorithm combining Particle Swarm Optimization (PSO) algorithm with back-propagation algorithms has been applied to the selected feature vectors for recognition of the persons. Network architecture and connection weights of ANN are evolved by a PSO method, and then, the appropriate network architecture and connection weights are fed into ANN. Recognition rate equal to 96% is obtained by using conjugate gradient descent algorithm.

     

Particle swarm optimisation for feature selection in classification: Novel initialisation and updating mechanisms

In classification, feature selection is an important data pre-processing technique, but it is a difficult problem due mainly to the large search space. Particle swarm optimisation (PSO) is an efficient evolutionary computation technique. However, the traditional personal best and global best updating mechanism in PSO limits its performance for feature selection and the potential of PSO for feature selection has not been fully investigated. This paper proposes three new initialisation strategies and three new personal best and global best updating mechanisms in PSO to develop novel feature selection approaches with the goals of maximising the classification performance, minimising the number of features and reducing the computational time. The proposed initialisation strategies and updating mechanisms are compared with the traditional initialisation and the traditional updating mechanism. Meanwhile, the most promising initialisation strategy and updating mechanism are combined to form a new approach (PSO(4-2)) to address feature selection problems and it is compared with two traditional feature selection methods and two PSO based methods. Experiments on twenty benchmark datasets show that PSO with the new initialisation strategies and/or the new updating mechanisms can automatically evolve a feature subset with a smaller number of features and higher classification performance than using all features. PSO(4-2) outperforms the two traditional methods and two PSO based algorithm in terms of the computational time, the number of features and the classification performance. The superior performance of this algorithm is due mainly to both the proposed initialisation strategy, which aims to take the advantages of both the forward selection and backward selection to decrease the number of features and the computational time, and the new updating mechanism, which can overcome the limitations of traditional updating mechanisms by taking the number of features into account, which reduces the number of features and the computational time.     

Unsupervised probabilistic feature selection using ant colony optimization

Feature selection (FS) is one of the most important fields in pattern recognition, which aims to pick a subset of relevant and informative features from an original feature set. There are two kinds of FS algorithms depending on the presence of information about dataset class labels: supervised and unsupervised algorithms. Supervised approaches utilize class labels of dataset in the process of feature selection. On the other hand, unsupervised algorithms act in the absence of class labels, which makes their process more difficult. In this paper, we propose unsupervised probabilistic feature selection using ant colony optimization (UPFS). The algorithm looks for the optimal feature subset in an iterative process. In this algorithm, we utilize inter-feature information which shows the similarity between the features that leads the algorithm to decreased redundancy in the final set. In each step of the ACO algorithm, to select the next potential feature, we calculate the amount of redundancy between current feature and all those which have been selected thus far. In addition, we utilize a matrix to hold ant related pheromone which shows the rate of the co-presence of every pair of features in solutions. Afterwards, features are ranked based on a probability function extracted from the matrix; then, their m-top is returned as the final solution. We compare the performance of UPFS with 15 well-known supervised and unsupervised feature selection methods using different classifiers (support vector machine, naive Bayes, and k-nearest neighbor) on 10 well-known datasets. The experimental results show the efficiency of the proposed method compared to the previous related methods.     

基于GEPSO模型的面向对象遥感图像分类

针对演化算法的寻优能力,提出了基于GEPSO(GEP Optimized by PSO)模型的面向对象遥感图像分类方法.先对遥感图像进行分割,选择特征集,然后利用GEPSO算法为每类图像对象构造一个类中心.构造类中心的过程先利用GEP搜索一个次优解,再根据这个次优解利用PSO搜索最优解.实验结果表明,基于GEPSO模型的面向对象遥感图像分类方法具有较高的分类精度.     

An application of PSO technique for harmonic elimination in a PWM inverter

Harmonic elimination problem in PWM inverter is treated as an optimization problem and solved using particle swarm optimization (PSO) technique. The derived equation for computation of total harmonic distortion (THD) of the output voltage of PWM inverter is used as the objective function in the PSO algorithm. The objective function is minimized to contribute the minimum THD in the voltage waveform and the corresponding switching angles are computed. The method is applied to investigate the switching patterns of both unipolar and bipolar case. While minimizing the objective function, the individual selected harmonics like 5th, 7th, 11th and 13th can be controlled within the allowable limits by incorporating the constraints in the PSO algorithm. The results of the unipolar case using five switching angles are compared with that of a recently reported work and it is observed that the proposed method is effective in reducing the voltage THD in a wide range of modulation index. The simulated results are also validated through suitable experiments.     

Sleep spindle detection using artificial neural networks trained with filtered time-domain EEG: a feasibility study

An artificial neural network (ANN) based on the Multi-Layer Perceptron (MLP) architecture is used for detecting sleep spindles in band-pass filtered electroencephalograms (EEG), without feature extraction. Following optimum classification schemes, the sensitivity of the network ranges from 79.2% to 87.5%, while the false positive rate ranges from 3.8% to 15.5%. Furthermore, due to the operation of the ANN on time-domain EEG data, there is agreement with visual assessment concerning temporal resolution. Specifically, the total inter-spindle interval duration and the total duration of spindles are calculated with 99% and 92% accuracy, respectively. Therefore, the present method may be suitable for investigations of the dynamics among successive inter-spindle intervals, which could provide information on the role of spindles in the sleep process, and for studies of pharmacological effects on sleep structure, as revealed by the modification of total spindle duration.     

Exploiting multi-channels deep convolutional neural networks for multivariate time series classification

Time series classification is related to many different domains, such as health informatics, finance, and bioinformatics. Due to its broad applications, researchers have developed many algorithms for this kind of tasks, e.g., multivariate time series classification. Among the classification algorithms, k-nearest neighbor (k-NN) classification (particularly 1-NN) combined with dynamic time warping (DTW) achieves the state of the art performance. The deficiency is that when the data set grows large, the time consumption of 1-NN with DTWwill be very expensive. In contrast to 1-NN with DTW, it is more efficient but less effective for feature-based classification methods since their performance usually depends on the quality of hand-crafted features. In this paper, we aim to improve the performance of traditional feature-based approaches through the feature learning techniques. Specifically, we propose a novel deep learning framework, multi-channels deep convolutional neural networks (MC-DCNN), for multivariate time series classification. This model first learns features from individual univariate time series in each channel, and combines information from all channels as feature representation at the final layer. Then, the learnt features are applied into a multilayer perceptron (MLP) for classification. Finally, the extensive experiments on real-world data sets show that our model is not only more efficient than the state of the art but also competitive in accuracy. This study implies that feature learning is worth to be investigated for the problem of time series classification.     

New classification techniques for electroencephalogram (EEG) signals and a real-time EEG control of a robot

This paper studies the state-of-the-art classification techniques for electroencephalogram (EEG) signals. Fuzzy Functions Support Vector Classifier, Improved Fuzzy Functions Support Vector Classifier and a novel technique that has been designed by utilizing Particle Swarm Optimization and Radial Basis Function Networks (PSO-RBFN) have been studied. The classification performances of the techniques are compared on standard EEG datasets that are publicly available and used by brain–computer interface (BCI) researchers. In addition to the standard EEG datasets, the proposed classifier is also tested on non-EEG datasets for thorough comparison. Within the scope of this study, several data clustering algorithms such as Fuzzy C-means, K-means and PSO clustering algorithms are studied and their clustering performances on the same datasets are compared. The results show that PSO-RBFN might reach the classification performance of state-of-the art classifiers and might be a better alternative technique in the classification of EEG signals for real-time application. This has been demonstrated by implementing the proposed classifier in a real-time BCI application for a mobile robot control.     

Neural network classifier optimization using Differential Evolution with Global Information and Back Propagation algorithm for clinical datasets

A Computer-Aided Diagnostic (CAD) system that uses Artificial Neural Network (ANN) trained by drawing in the relative advantages of Differential Evolution (DE), Particle Swarm Optimization (PSO) and gradient descent based backpropagation (BP) for classifying clinical datasets is proposed. The DE algorithm with a modified best mutation operation is used to enhance the search exploration of PSO. The ANN is trained using PSO and the global best value obtained is used as a seed by the BP. Local search is performed using BP, in which the weights of the Neural Network (NN) are adjusted to obtain an optimal set of NN weights. Three benchmark clinical datasets namely, Pima Indian Diabetes, Wisconsin Breast Cancer and Cleveland Heart Disease, obtained from the University of California Irvine (UCI) machine learning repository have been used. The performance of the trained neural network classifier proposed in this work is compared with the existing gradient descent backpropagation, differential evolution with backpropagation and particle swarm optimization with gradient descent backpropagation algorithms. The experimental results show that DEGI-BP provides 85.71% accuracy for diabetes, 98.52% for breast cancer and 86.66% for heart disease datasets. This CAD system can be used by junior clinicians as an aid for medical decision support.