Automatic feature extraction using genetic programming: An application to epileptic EEG classification
TL;DR: Genetic programming is applied to perform automatic feature extraction from original feature database with the aim of improving the discriminatory performance of a classifier and reducing the input feature dimensionality at the same time.
Abstract: This paper applies genetic programming (GP) to perform automatic feature extraction from original feature database with the aim of improving the discriminatory performance of a classifier and reducing the input feature dimensionality at the same time. The tree structure of GP naturally represents the features, and a new function generated in this work automatically decides the number of the features extracted. In experiments on two common epileptic EEG detection problems, the classification accuracy on the GP-based features is significant higher than on the original features. Simultaneously, the dimension of the input features for the classifier is much smaller than that of the original features.
Citations
More filters
TL;DR: In this work, a 13-layer deep convolutional neural network (CNN) algorithm is implemented to detect normal, preictal, and seizure classes and achieved an accuracy, specificity, and sensitivity of 88.67%, 90.00% and 95.00%, respectively.
1,117 citations
TL;DR: This review discusses various feature extraction methods and the results of different automated epilepsy stage detection techniques in detail, and briefly presents the various open ended challenges that need to be addressed before a CAD based epilepsy detection system can be set-up in a clinical setting.
Abstract: Epilepsy is an electrophysiological disorder of the brain, characterized by recurrent seizures. Electroencephalogram (EEG) is a test that measures and records the electrical activity of the brain, and is widely used in the detection and analysis of epileptic seizures. However, it is often difficult to identify subtle but critical changes in the EEG waveform by visual inspection, thus opening up a vast research area for biomedical engineers to develop and implement several intelligent algorithms for the identification of such subtle changes. Moreover, the EEG signals are nonlinear and non-stationary in nature, which contribute to further complexities related to their manual interpretation and detection of normal and abnormal (interictal and ictal) activities. Hence, it is necessary to develop a Computer Aided Diagnostic (CAD) system to automatically identify the normal and abnormal activities using minimum number of highly discriminating features in classifiers. It has been found that nonlinear features are able to capture the complex physiological phenomena such as abrupt transitions and chaotic behavior in the EEG signals. In this review, we discuss various feature extraction methods and the results of different automated epilepsy stage detection techniques in detail. We also briefly present the various open ended challenges that need to be addressed before a CAD based epilepsy detection system can be set-up in a clinical setting.
601 citations
Cites methods from "Automatic feature extraction using ..."
...60% using wavelet transform and line length feature [42], and an accuracy of 99% using genetic programming based features in a K-Nearest Neighbor (KNN) classifier [43]....
[...]
TL;DR: A multiparadigm approach based on the integration of wavelets, nonlinear dynamics and chaos theory, and neural networks advanced by Adeli and associates is the most effective method for automated EEG-based diagnosis of epilepsy.
Abstract: Electroencephalography (EEG) is an important tool for studying the human brain activity and epileptic processes in particular. EEG signals provide important information about epileptogenic networks that must be analyzed and understood before the initiation of therapeutic procedures. Very small variations in EEG signals depict a definite type of brain abnormality. The challenge is to design and develop signal processing algorithms which extract this subtle information and use it for diagnosis, monitoring and treatment of patients with epilepsy. This paper presents a review of wavelet techniques for computer-aided seizure detection and epilepsy diagnosis with an emphasis on research reported during the past decade. A multiparadigm approach based on the integration of wavelets, nonlinear dynamics and chaos theory, and neural networks advanced by Adeli and associates is the most effective method for automated EEG-based diagnosis of epilepsy.
449 citations
Cites methods from "Automatic feature extraction using ..."
...Examples of classification algorithms used for seizure detection and epilepsy diagnosis are: k-Nearest Neighbor algorithm (k-NN) [31], Probabilistic Neural Network (PNN) [32], Fisher’s linear discriminant (FLD) [33], Support Vector Machine (SVM) [34], Optimum Path Forest (OPF) [35], Principal Component Analysis (PCA) [36], and Enhanced Probabilistic Neural Network (EPNN) [37]....
[...]
...Employing nonlinear dynamics and chaos theory researchers have extracted various nonlinear features such as entropies [24], energy [25], correlation dimension [47], fractal dimension [47,27], Lyapunov exponent [47], Higher Order Spectra (HOS) [28,25] from both detailed and approximate coefficients of the WT and used them for signal classification and seizure detection and epilepsy diagnosis [29,30,31]....
[...]
TL;DR: It is observed that the quantitative value of fuzzy approximate entropy drops during the ictal period which proves that the epileptic EEG signal is more ordered than the EEG signal of a normal subject.
261 citations
TL;DR: The detection of an epileptic seizure based on DWT statistical features using naïve Bayes (NB) and k-nearest neighbor (k-NN) classifiers is more suitable in real time for a reliable, automatic epilepsy detection system to enhance the patient's care and the quality of life.
Abstract: Electroencephalogram (EEG) comprises valuable details related to the different physiological state of the brain. In this paper, a framework is offered for detecting the epileptic seizures from EEG data recorded from normal subjects and epileptic patients. This framework is based on a discrete wavelet transform (DWT) analysis of EEG signals using linear and nonlinear classifiers. The performance of the 14 different combinations of two-class epilepsy detection is studied using naive Bayes (NB) and k-nearest neighbor (k-NN) classifiers for the derived statistical features from DWT. It has been found that the NB classifier performs better and shows an accuracy of 100% for the individual and combined statistical features derived from the DWT values of normal eyes open and epileptic EEG data provided by the University of Bonn, Germany. It has been found that the computation time of NB classifier is lesser than k-NN to provide better accuracy. So, the detection of an epileptic seizure based on DWT statistical features using NB classifiers is more suitable in real time for a reliable, automatic epileptic seizure detection system to enhance the patient’s care and the quality of life.
239 citations
Cites background from "Automatic feature extraction using ..."
...Researchers have attempted various classifiers namely artificial neural network [16]–[19], support vector machines [8], [20]–[23], k-nearest neighbor (k-NN) [24], [25], quadratic analysis [26], logistic regression [6], [13], naïve Bayes (NB) [13], decision tree [13], [27], Gaussian mixture model [2], [25], adaptive neuro-fuzzy inference systems [20], [31], mixture of expert model [28]–[30], surrogate data analysis [12], [32], learning vector quantization [33], Markov modeling [34] to classify the epileptic seizure abnormality from the EEG data....
[...]
References
More filters
TL;DR: In this paper, it is shown that the difference of information between the approximation of a signal at the resolutions 2/sup j+1/ and 2 /sup j/ (where j is an integer) can be extracted by decomposing this signal on a wavelet orthonormal basis of L/sup 2/(R/sup n/), the vector space of measurable, square-integrable n-dimensional functions.
Abstract: Multiresolution representations are effective for analyzing the information content of images. The properties of the operator which approximates a signal at a given resolution were studied. It is shown that the difference of information between the approximation of a signal at the resolutions 2/sup j+1/ and 2/sup j/ (where j is an integer) can be extracted by decomposing this signal on a wavelet orthonormal basis of L/sup 2/(R/sup n/), the vector space of measurable, square-integrable n-dimensional functions. In L/sup 2/(R), a wavelet orthonormal basis is a family of functions which is built by dilating and translating a unique function psi (x). This decomposition defines an orthogonal multiresolution representation called a wavelet representation. It is computed with a pyramidal algorithm based on convolutions with quadrature mirror filters. Wavelet representation lies between the spatial and Fourier domains. For images, the wavelet representation differentiates several spatial orientations. The application of this representation to data compression in image coding, texture discrimination and fractal analysis is discussed. >
20,028 citations
Book•
01 Jan 1992TL;DR: This book discusses the evolution of architecture, primitive functions, terminals, sufficiency, and closure, and the role of representation and the lens effect in genetic programming.
Abstract: Background on genetic algorithms, LISP, and genetic programming hierarchical problem-solving introduction to automatically-defined functions - the two-boxes problem problems that straddle the breakeven point for computational effort Boolean parity functions determining the architecture of the program the lawnmower problem the bumblebee problem the increasing benefits of ADFs as problems are scaled up finding an impulse response function artificial ant on the San Mateo trail obstacle-avoiding robot the minesweeper problem automatic discovery of detectors for letter recognition flushes and four-of-a-kinds in a pinochle deck introduction to biochemistry and molecular biology prediction of transmembrane domains in proteins prediction of omega loops in proteins lookahead version of the transmembrane problem evolutionary selection of the architecture of the program evolution of primitives and sufficiency evolutionary selection of terminals evolution of closure simultaneous evolution of architecture, primitive functions, terminals, sufficiency, and closure the role of representation and the lens effect Appendices: list of special symbols list of special functions list of type fonts default parameters computer implementation annotated bibliography of genetic programming electronic mailing list and public repository
13,487 citations
TL;DR: The nearest neighbor decision rule assigns to an unclassified sample point the classification of the nearest of a set of previously classified points, so it may be said that half the classification information in an infinite sample set is contained in the nearest neighbor.
Abstract: The nearest neighbor decision rule assigns to an unclassified sample point the classification of the nearest of a set of previously classified points. This rule is independent of the underlying joint distribution on the sample points and their classifications, and hence the probability of error R of such a rule must be at least as great as the Bayes probability of error R^{\ast} --the minimum probability of error over all decision rules taking underlying probability structure into account. However, in a large sample analysis, we will show in the M -category case that R^{\ast} \leq R \leq R^{\ast}(2 --MR^{\ast}/(M-1)) , where these bounds are the tightest possible, for all suitably smooth underlying distributions. Thus for any number of categories, the probability of error of the nearest neighbor rule is bounded above by twice the Bayes probability of error. In this sense, it may be said that half the classification information in an infinite sample set is contained in the nearest neighbor.
12,243 citations
Book•
01 Jan 1972
TL;DR: This completely revised second edition presents an introduction to statistical pattern recognition, which is appropriate as a text for introductory courses in pattern recognition and as a reference book for workers in the field.
Abstract: This completely revised second edition presents an introduction to statistical pattern recognition Pattern recognition in general covers a wide range of problems: it is applied to engineering problems, such as character readers and wave form analysis as well as to brain modeling in biology and psychology Statistical decision and estimation, which are the main subjects of this book, are regarded as fundamental to the study of pattern recognition This book is appropriate as a text for introductory courses in pattern recognition and as a reference book for workers in the field Each chapter contains computer projects as well as exercises
10,526 citations