The Open Biomedical Engineering Journal




ISSN: 1874-1207 ― Volume 14, 2020
RESEARCH ARTICLE

Performance Analysis of Fuzzy Multilayer Support Vector Machine for Epileptic Seizure Disorder Classification using Auto Regression Features



T. Rajendran1, *, K.P. Sridhar1, S. Deepa2
1 Karpagam Academy of Higher Education, Coimbatore, India
2 Karpagam College of Engineering, Coimbatore, India

Abstract

Background:

Around 1% of the total population in the world suffers from epilepsy, a central nervous system disorder. Epilepsy is the neurological disorder of the human brain which can affect people of all ages. Classification techniques and Signal processing are basic methods in the advancement of an algorithm for seizure detection. The primary procedures of a typical biomedical evaluation and processing framework are data acquisition, feature extraction, preprocessing, and classification. Based on this, seizure detection is performed by using the following two methods.

Methods:

This paper proposes a technique for the classification of EEG signals to detect the epileptic seizures by using Cascade Forward Backpropagation Neural Network (CFBNN) and Fuzzy Multilayer Support Vector Machine (FMSVM) methods.

Results:

Finally, the results of developed classifiers are identified with seizure disorder activities. This research concentrated on Parametric Features such as AR (Autoregressive) Burg, AR YuleWalker, AR Covariance, AR Modified Covariance, and Levinson Durbin Recursion. Linear Prediction Coefficient was analyzed with the EEG dataset gathered from Karunya University. The sensitivity, specificity, and accuracy were calculated for the proposed classifiers.

Conclusion:

The results of the proposed classifiers were computed with minimum and maximum accuracy and these results were compared with the previous results of the classifiers like FFNN, and PNN as shown in the tables. Based on the obtained outputs and calculated parametric functions, the results validated that the FMSVM classifier performed better in the detection of epileptic seizure disorder in terms of accuracy, sensitivity and specificity.

Keywords: Cascade Forward Backpropagation Neural Network (CFBNN), Fuzzy Multilayer Support Vector Machine (FMSVM) methods, Autoregressive, Epilepsy, EEG, Epileptic Seizure Disorder.


Article Information


Identifiers and Pagination:

Year: 2019
Volume: 13
Issue: Suppl-1, M2
First Page: 103
Last Page: 113
Publisher Id: TOBEJ-13-103
DOI: 10.2174/1874120701913010103

Article History:

Received Date: 02/03/2019
Revision Received Date: 02/04/2019
Acceptance Date: 29/04/2019
Electronic publication date: 17/12/2019
Collection year: 2019

Article Metrics:

CrossRef Citations:
0

Total Statistics:

Full-Text HTML Views: 347
Abstract HTML Views: 263
PDF Downloads: 149
ePub Downloads: 151
Total Views/Downloads: 910

Unique Statistics:

Full-Text HTML Views: 187
Abstract HTML Views: 177
PDF Downloads: 101
ePub Downloads: 90
Total Views/Downloads: 555
Geographical View

© 2019 Rajendran et al

open-access license: This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.


* Address correspondence to this author at Karpagam Academy of Higher Education, Coimbatore, India; E-mail: rajendran.thavasimuthusamy@gmail.com





1. INTRODUCTION

Epilepsy, the second most critical neurological disorder in humans after stroke, is a perpetual state of the nervous system and it is distinguished by recurrent unprovoked seizures. Around one in every 100 people globally is affected by epilepsy. Electroencephalography (EEG) is a significant medical device for diagnosing, observing and directing neurological disorders incidental to epilepsy. In comparison with different strategies, for example, Electrocorticogram (ECOG), EEG is a safe and clean system for observing brain actions [1Y. Song, and P. Liò, "A new approach for epileptic seizure detection: sample entropy-based feature extraction and extreme learning machine", J. Biomed. Sci. Eng., vol. 3, no. 6, pp. 556-567.
[http://dx.doi.org/10.4236/jbise.2010.36078]
]. The side effects of epilepsy are distinguished by recurrent and impulsive seizures, called epileptic seizures, caused due to extreme neuronal activities in the brain.

Epileptic seizures adversely affect physical and mental conduct, causing critical social maladaptation and even death. The etiology of epilepsy is known to have lesions in the brain and genetic anomalies, resulting in hindered neuronal regulation. Though, epilepsy could likewise be induced by obscure factors that are hard to detect. The prognosis and diagnosis of epilepsy are reliant on the elucidation of neuronal actions in the cerebrum. Thus, the identification of epileptic signs integrated in neural action is more vital. Because of its simplicity and effectiveness, Electroencephalography (EEG) has been generally utilized in epilepsy research [2J-H. Kang, Y.G. Chung, and S-P. Kim, "An efficient detection of epileptic seizure by differentiation and spectral analysis of electroencephalograms", Comput. Biol. Med., vol. 66, no. 66, pp. 352-356.
[http://dx.doi.org/10.1016/j.compbiomed.2015.04.034] [PMID: 25982199]
]. The analysis of epilepsy can be subdivided into preprocessing, extraction of features, and classification. The reason behind seizure identification is to detect seizures with the most conceivable accuracy [3S.T. George, R. Balakrishnan, J.S. Johnson, and J. Jayakumar, "Application and evaluation of independent component analysis methods to generalized seizure disorder activities exhibited in the brain", Clin. EEG Neurosci., vol. 48, no. 4, pp. 295-300.
[http://dx.doi.org/10.1177/1550059416677915] [PMID: 27837050]
], Fig. (1).

Fig. (1)
EEG signal processing stages.


In EEG data recording, an EEG device is attached to the patient which gains the information over electrode terminals fixed on the scalp of the head. The signals acquired were in the range of low microvolt that is changed into processable range and digitized by A-to-D converter. The EEG functions non-intrusively, includes more data about various physiological conditions of the brain , as well as some undesirable signals known as artifacts. Despite the fact that EEG is an imperative medical device for diagnosing, observing and overseeing neurological disorders, particular challenges incidental to EEG analysis and interpretation, which impeded its far-reaching proficiency .

1.1. EEG Epileptic Seizure Database

The databases (EEG signal) for this research were collected from Karunya University. The performance results are compared with K-means, Navies Bayesian and Neural Network with respect to the parametric method. The features were extracted by applying feature extraction methods and the extracted features were classified by implementing the Elman Neural Network.

The EEG data utilized in this research was obtained utilizing 10-20 electrodes, specified by the standard international framework. The EEG data was downloaded from the database discovered in the link http://karunya.edu/ research/EEGdatabase/public/view_all.php. The data were recorded from 18 channels (2 periocular electrodes and 16 scalp electrodes, with reference to right and left mastoid) at a sampling rate of 256 Hz with analog passband of 0.01 to 100 Hz. Before setting the electrodes, the scalp was arranged in order to contact impedance below 5kΩ. EEG data generation had a 10-second term, involving 2560 data points, all having 4-ms duration. This database contains data on clinical status of the patients [3S.T. George, R. Balakrishnan, J.S. Johnson, and J. Jayakumar, "Application and evaluation of independent component analysis methods to generalized seizure disorder activities exhibited in the brain", Clin. EEG Neurosci., vol. 48, no. 4, pp. 295-300.
[http://dx.doi.org/10.1177/1550059416677915] [PMID: 27837050]
].

1.2. Selection of Leads

The recording of the EEG signal consisted of 32 channels that were acquired by placing metal electrodes on the scalp region. The position of the electrodes was indicated in the standard 10-20 electrode placement system. For this study, 8 channels were selected from Frontal Pole to Occipital region covering both the hemispheres of the cerebral cortex. During the onset of epileptic seizures, the cerebral functions of the human brain showed less randomness. This was captured by the EEG electrodes and transmitted to the detection system for processing. Fig (2) exhibits the 10-20 EEG lead placement system that is used for data acquisition [3S.T. George, R. Balakrishnan, J.S. Johnson, and J. Jayakumar, "Application and evaluation of independent component analysis methods to generalized seizure disorder activities exhibited in the brain", Clin. EEG Neurosci., vol. 48, no. 4, pp. 295-300.
[http://dx.doi.org/10.1177/1550059416677915] [PMID: 27837050]
-5Y.U. Khan, and O. Farooq, "Autoregressive features based classification for seizure detection using neural network in scalp Electroencephalogram", Int. J. Biomed. Eng. Technol., vol. 2, no. 4, pp. 370-381.
[http://dx.doi.org/10.1504/IJBET.2009.027800]
].

1.3. Pre-processing

The pre-processing stage separated the input EEG data into different multichannel signals. The 8 signals corresponding to FP1-F3, F3-C3, C3-P3, P3-O1, FP2-F4, F4-C4, C4-P4 and P4-O2 were used for the detection of epilepsy in this study . The selected lead locations are highlighted in Fig. (2). The channels were sampled at 256 Hz and are noise-free. The data sets used for training and testing the classifier had the same time duration of 60 sec [3S.T. George, R. Balakrishnan, J.S. Johnson, and J. Jayakumar, "Application and evaluation of independent component analysis methods to generalized seizure disorder activities exhibited in the brain", Clin. EEG Neurosci., vol. 48, no. 4, pp. 295-300.
[http://dx.doi.org/10.1177/1550059416677915] [PMID: 27837050]
-5Y.U. Khan, and O. Farooq, "Autoregressive features based classification for seizure detection using neural network in scalp Electroencephalogram", Int. J. Biomed. Eng. Technol., vol. 2, no. 4, pp. 370-381.
[http://dx.doi.org/10.1504/IJBET.2009.027800]
].

An extensive analysis of the brain signal could expose the decrease in the randomness of the EEG signal as the count of neurons comprising brain functions decreased during epileptic seizures. This characteristic nature of Epilepsy is used as an important classification rule in the system [3S.T. George, R. Balakrishnan, J.S. Johnson, and J. Jayakumar, "Application and evaluation of independent component analysis methods to generalized seizure disorder activities exhibited in the brain", Clin. EEG Neurosci., vol. 48, no. 4, pp. 295-300.
[http://dx.doi.org/10.1177/1550059416677915] [PMID: 27837050]
-5Y.U. Khan, and O. Farooq, "Autoregressive features based classification for seizure detection using neural network in scalp Electroencephalogram", Int. J. Biomed. Eng. Technol., vol. 2, no. 4, pp. 370-381.
[http://dx.doi.org/10.1504/IJBET.2009.027800]
].

Fig. (2)
EEG 10-20 Electrode Placement.


Fig. (3)
EEG Wave Signals corresponding to the Electrode Placement.


1.4. Feature Extraction

Generally, feature extraction is the process inspiring important features from a set of signals that inclines suitable classification and disease analysis. A measure which indicates the level to which the ups and downs of a wave vary on an average out of the mean voltage was said to be a SD. Since decomposing the signal, some important features could be extricated utilizing the SD. For dissecting the statistical feature of a signal, the signal's mean must be calculated. It can likewise be stated that the value of mean is the average estimation of a signal.

The feature extraction procedure is used to discover the average accuracy of the framework. The accompanying coefficients like Autoregression (AR) Burg, AR Covariance, AR Yule-Walker technique, AR Modified Covariance, Linear Prediction Coefficient, and Levinson Durbin Recursion were chosen for validation of the extraction procedure. It reduces the EEG structures and modules dependent on the training procedure.

2. RELATED WORKS

Rafiuddin et al., proposed Feature Extraction and Classification of EEG for Automated Seizure identification. One of the numerous difficulties in the automatic identification of epileptic seizures was to draw a line of division among non-seizure and seizure action. For performing this operation, detection of incidental features and their extrication out of the EEG play a key part. The research exhibited in this study is a segment of a general exertion proceeding to build up another technique for automatic identification of seizures. A wavelet-related feature extrication strategy has been discovered. Statistical features, Median Absolute Deviation (MAD), and Inter-Quartile Range (IQR) additionally frame some portion of the feature vector. The algorithm was assessed on 23 individuals with 195 seizures. The outcomes provided a normal detection precision of 96.5%. The database utilized was the CHB-MIT scalp EEG database [6N. Rafiuddin, Y.U. Khan, and O. Farooq, "Feature extraction and classification of EEG for automatic seizure detection", IEEE International Conference on Multimedia, Signal Processing and Communication Technologies, pp. 184-187.Aligarh, India
[http://dx.doi.org/10.1109/MSPCT.2011.6150470]
].

Nicoletta Nicolaou and Julius Georgiou, have proved a significant design in the review for the identification of epilepsy. This work examined the utilization of Permutation Entropy (PE) as the feature for automatic epileptic seizure identification. SVM was utilized to classify fragments of typical and epileptic EEG dependent on values of PE. The presented framework presented the way that the EEG epileptic seizures were described by less PE than ordinary EEG. It has produced average sensitivity of 94.38% and specificity of 93.23% was acquired by utilizing PE as the feature to describe epilepsy and EEG without seizure, while 100% specificity and sensitivity were additionally acquired in the classification of a single trial [7N. Nicolaou, and J. Georgiou, "Detection of epileptic electroencephalogram based on Permutation Entropy and Support Vector Machines", Expert Syst. Appl., vol. 39, no. 1, pp. 202-209.
[http://dx.doi.org/10.1016/j.eswa.2011.07.008]
].

B. AL-Bokhity et al., designed a smart diagnosis system for the classification of EEG which enhances the proficiency and precision of the diagnosis. Such a system required a solid learning capacity for managing the information. Diagnosing epilepsy was difficult as it required the perception of the individual and the EEG. Likewise, the collection of more medical data was required. The prescribed method included training the FIS classifier for detecting an epileptic seizure by means of utilizing the four types of EEG. These types of EEG were called as Information of the Healthy individuals, the Epileptic individuals all through without a seizure interval, the Epileptic individuals all through a seizure interval (focal), and the Epileptic individuals all through a seizure interval (Non-focal). Initially, it explained the usage of the Short-Time Fourier Transform (STFT) for denoising the signals through processing the STFT of the noise signals. they comprise of a threshold on the STFT and inverse STFT. Also, statistical features were extricated out of the wavelet sub-bands of the EEG signals. At that point, they were treated as the contributions of the FIS classifier. In this research, a huge dataset was utilized with a combination of two databases. The precision of detecting the FIS classifier was 96% throughout this application [8B. AL-Bokhity Dalia Nashat and T.M. Nazmy, "A Fuzzy Classifier based Detection for Epileptic Seizure Signals", IEEE International Computer Engineering Conference (ICENCO), pp. 100-105.Cairo, Egypt].

Dabye et al., proposed localization of epileptic seizure with a method dependent on the PSD with the autoregressive model. In this study, they presented a model dependent on the review of EEG signals through the mean of the conventional PSD in the target to restrict and identify the epileptic region of the brain. Initially, as the EEG signals were regularly non-stationary , they prepared the data with the method of separation so as to have the stationary which is advantageous to demonstrate with the autoregression model (AR). For this, they utilized numerous methods to decide the order which demonstrated better data in this work. Hence, they classified normal and abnormal action which compares epileptic release of the patient. This work contributes to the automatic recognition of epilepsy seizure with the PSD novel methodology by a fine resolution in the frequency domain as the examination of EEG signals is regularly completed with visual assessment of the rhythm (delta, theta, alpha, beta, and gamma) by neurologist experts. The precision of the recognition is evaluated at 70% with a sensitivity of 80.55% [9S. Ali, "Localization of epileptic seizure with an approach based on the PSD with an autoregressive model", https://arxiv.org/pdf/1506. 00947.pdf].

3. MATERIALS AND METHODS

This paper proposes a technique for the classification of EEG signals to detect epileptic seizures by using CFBNN and FMSVM methods Fig. (4).

3.1. Cascade Forward Backpropagation Neural Network (CFBNN)

CFBNN is similar to Backpropagation Artificial Neural Network (BPANN) which uses the Back Propagation algorithm for updating weights. CFBNN has a weight connection from the input to every layer and from every layer to the following layers. The network activation flow was one-way only, from the input to the output layer passing over the hidden layer. Fig. (3) presents a three-layer network that has links from layer 1 to layer 2, layer 2 to layer 3, and layer 1 to layer 3. More connections may enhance the speed at which the network recognizes the required relationship. Back propagation algorithm is used for updating weights. The errors propagate backward from the output nodes to the input nodes [10N. Mohana Sundaram, S.N. Sivanandam, and V. Renupriya, "Artificial neural network approach for dynamic modelling of heat exchanger for data prediction", Ind. J. Sci. Tech., vol. 9, no. S1, pp. 1-7.
[http://dx.doi.org/10.17485/ijst/2016/v9iS1/86189]
].

Fig (5) demonstrates the architecture of CFBNN. In this architecture, the neurons in each layer relate to the neurons in the past layer. The layers of the cascade neural networks are active in quality. With regard to cascade networks, with the support of one neuron, learning is initiated amid the training stage, the learning algorithm includes new neurons subsequently making a multilayer architecture. If the training error diminishes, it suggests that the aggregate number of hidden layer of neurons increments in a well-ordered manner. The development of the network is controlled by the learning algorithm. For the enhancement of the loads in the network, two training algorithm, Levenberg-Marquardt and Bayesian control back propagation algorithms are utilized. It can result in a quick learning rate when the availability is controlled inside the network [11S-F. Liang, H-C. Wang, and W-L. Chang, "Combination of EEG complexity and spectral analysis for epilepsy diagnosis and seizure detection", EURASIP. J. Adv. Sig. Pr, vol. 2010, no. 1, pp. 1-15.
[http://dx.doi.org/10.1155/2010/853434]
15T.G. Selvaraj, B. Ramasamy, S.J. Jeyaraj, and E.S. Suviseshamuthu, "EEG database of seizure disorders for experts and application developers", Clin. EEG Neurosci., vol. 45, no. 4, pp. 304-309.
[http://dx.doi.org/10.1177/1550059413500960] [PMID: 24357675]
].

Fig. (4)
Flow Diagram of the Proposed Methods.


Fig. (5)
The architecture of CFBNN model.


3.2. Fuzzy Multilayer Support Vector Machine Classification

Data classification is the way toward classifying and ordering the data into various types, classes, and different structures. To create a different objective, the classification and partitioning are facilitated by the classification of data according to the points of data. To separate whether the subject is epileptic or not, classification of data has been conducted . For accumulating data and various strategies, data classification is an important approach. To classify the epileptic seizure in this unit, FMSVM technique has been used. Fuzzy rule optimizes the MSVM parameters to improve the MSVM execution.

For performing different operations, feature extraction and pre-processing were conducted in the EEG signals. Uncontaminated non-cerebral artifacts are the significant issue obtained in clean information on brain activity. A hindrance was created during the task of decision-making , while occurrences of artifacts were detected in the EEG signals. Eyeblink and body movements or certain sources like electrical impedances were created by the subject during the process of data acquisition.

The proposed three-class classification of epileptic seizures is assigned a class label of yϵ(0,−1,+1), where 0, +1, and -1 represents seizure disorders for an input feature vector xϵRN. Consider an input-output training pair { (x1, y1), …, (in, yn) }, where vectors x1, x2, …, xn are input vectors and y1, y2, …, yn are the required output vectors. The issue is to identify a classifier f(x) which classifies the input samples.

These features were an input pattern and labeled as +1 for seizure presence and –1 for seizure absence. Collectively(x, y) forms an input-output pair, where x was the input feature and y was the output.

The fuzzy parameters utilized as a part of this work are necessary for a calculated relapse membership function. FMSVM implements a fuzzy membership capacity for every input data of SVM. SVM is receptive to exceptions and noises in the preparation of information that does not have a place with the three classes. Every data in the training dataset is doled out with membership and the total of the deviations weighted by its membership.

Fig. (6)
FMSVM Classifier Model.


By allocating a low membership value to an outlier, the error in the training method could be decreased. The use of FMSVM is beneficial as it has less membership value and would be allocated to data points that differ from the classes. The error in training is decreased by achieving better generalization capacity. The membership rate for the membership capacities was appointed a value in the interval of [0, 1]. In the FMSVM classifier, the regularization parameter was set as C = 10, σ2 = 1 for kernel. The trial outcomes show the solidity of the present method.

FMSVMM figures out how to evaluate the objective capacity utilizing the extricated vector as input. For registering the hidden layer portrayal f(x|θ) of input vector x, these works make utilization of:

Which is iteratively used by each SVM to compute the element f(x|θ)a. The target values for hidden-layer features were between -1 and 1, therefore if some target output is larger than 1 for a feature, the target value should be set at 1. To allow the hidden-layer SVMs to extract different features, breaking symmetry was necessary. For this, this study randomly initializes the trainable parameters in each hidden-layer SVM. However, a better way to initialize the hidden-layer SVM is to let them train on different perturbed versions of the target outputs. Therefore, a dataset should be constructed (xi, yi + γ a i), with γ a i random value ϵ [−γ, γ] for the hidden-layer SVM Sa, where γ is another meta parameter.

FMSVM have an excellent potential to be connected in programmed identification of variations from the seizures by lessening the misclassification rate. In the analysis of research, obtaining an accurate presumed area in seizure is a vital issue. The relating execution indicates that FMSVM is higher in terms of accuracy, specificity, sensitivity, and misclassification rate. The outcomes acquired from testing exhibited which fuzzy-based SVM classifier produced the best execution, dominating regular SVM [16V. Hariraj, "Fuzzy multi-layer SVM classification of breast cancer mammogram images", Int. J. Mech. Engg. Tech., vol. 9, no. 8, pp. 1281-1299.].

3.3. Autoregression Features

The autoregressive model was utilized to decrease the least square model and errors of prediction. This module is beneficial because it stays constant while processing the signal. The contribution to this module is in the structure of a column vector. Its parameters might be important as far as both various co-efficient and reflection coefficients are concerned. The AR module gives an elective method for examining the EEG spectral properties estimation [17T. Rajendran, and K.P. Sridhar, "Epileptic seizure classification using feed forward neural network based on parametric features", Int. J. Pharma. Res., vol. 10, no. 4, pp. 189-196.-20T. Rajendran, and K.P. Sridhar, "An overview of EEG seizure detection units and identifying their complexity- a review", Curr. Signal Transduct. Ther., .
[http://dx.doi.org/10.2174/1574362413666181030103616]
]. Related on the discrete linear stochastic procedure, it is stated as,

The errors are stated as, et = yt - µ - ψ1 et-1 - ψ2 et-2 - ··· .

Assume the stationarity model which holds for et should hold true for et-1, then et-1 = yt-1 - µ - ψ1 et-2 - ψ2 et-3 - ··· .

Finally, substitute the model for et-1 into the model for yt

(1)

Where, y1, y2, ···, yn are the observations with a joint density Pr(y1, y2, ···, yn). et are the errors with respect to time.

a) AR Covariance

The parameter γj was called as the autocovariance at lag j, combining all results together, it would be

(2)
(3)

The covariance matrices, V(y) were symmetric. If E(yt) does not base on t then it must not be a stationary series, so we can normally anticipate detecting the series in the neighborhood of µ.

(4)

If γj > 0, we could anticipate when a higher than normal observation could be followed by another higher than normal observation. We could normalize the covariance by describing the autocorrelation,

(5)

As usual, ρ0 = 1. The structure of the autocorrelations would significantly support us in knowing the conduct of the series, y [17T. Rajendran, and K.P. Sridhar, "Epileptic seizure classification using feed forward neural network based on parametric features", Int. J. Pharma. Res., vol. 10, no. 4, pp. 189-196.-20T. Rajendran, and K.P. Sridhar, "An overview of EEG seizure detection units and identifying their complexity- a review", Curr. Signal Transduct. Ther., .
[http://dx.doi.org/10.2174/1574362413666181030103616]
].

b) AR Yule-Walker

It calculates the AR parameters by shaping a biased measure of the signal's autocorrelation and comprehending the least square minimization of the forward prediction error. Here, the procedure linearly relies on the amplitude of a signal at the provided duration. The amplitude was acquired by adding various amplitudes of the past samples and error of estimation. The order for the filter linearly relies upon the count of AR coefficients. The modeling degree (p) consistently utilizes the Akaike Information Criteria (AIC) [17T. Rajendran, and K.P. Sridhar, "Epileptic seizure classification using feed forward neural network based on parametric features", Int. J. Pharma. Res., vol. 10, no. 4, pp. 189-196.-20T. Rajendran, and K.P. Sridhar, "An overview of EEG seizure detection units and identifying their complexity- a review", Curr. Signal Transduct. Ther., .
[http://dx.doi.org/10.2174/1574362413666181030103616]
].

Table 1
Subject-based classification of CFBNN using six PSD feature extraction methods.


Generally, an AR model of order p could be written as

(6)

The autocorrelations and the ϕi were incidental to each other, known as the Yule-Walker Equations:

(7)

Which could be utilized to measure values.

The Yule-Walker AR model is estimated by reducing the value of the prediction error power [17T. Rajendran, and K.P. Sridhar, "Epileptic seizure classification using feed forward neural network based on parametric features", Int. J. Pharma. Res., vol. 10, no. 4, pp. 189-196.-20T. Rajendran, and K.P. Sridhar, "An overview of EEG seizure detection units and identifying their complexity- a review", Curr. Signal Transduct. Ther., .
[http://dx.doi.org/10.2174/1574362413666181030103616]
].

c) AR Modified Covariance

The AR modified covariance was utilized to evaluate the PSD of an EEG input signal. The principal reason for this research is to reduce the forward and backward anticipation errors . At last, the evaluation order parameter should be not exactly, or equivalent to, 2:3 of the input vector length to settle the output. This procedure was completely characterized by a direct combination of past results and driving noise. It evaluates the P coefficients, where P is the model, by reducing the forward and backward prediction errors at all squares sense:

(8)
(9)

Where for the data length was N and was the AR coefficient of the kth term [17T. Rajendran, and K.P. Sridhar, "Epileptic seizure classification using feed forward neural network based on parametric features", Int. J. Pharma. Res., vol. 10, no. 4, pp. 189-196.-20T. Rajendran, and K.P. Sridhar, "An overview of EEG seizure detection units and identifying their complexity- a review", Curr. Signal Transduct. Ther., .
[http://dx.doi.org/10.2174/1574362413666181030103616]
].

d) Levinson Durbin Recursion

It is a normal algorithm that is simple to solve; here, the model for k =1 and k +1 coefficients estimated issues. The initial step completed in LDR is to reduce the error. At that point, the input vector and error vector are figured. The k values from o to m are evaluated [17T. Rajendran, and K.P. Sridhar, "Epileptic seizure classification using feed forward neural network based on parametric features", Int. J. Pharma. Res., vol. 10, no. 4, pp. 189-196.-20T. Rajendran, and K.P. Sridhar, "An overview of EEG seizure detection units and identifying their complexity- a review", Curr. Signal Transduct. Ther., .
[http://dx.doi.org/10.2174/1574362413666181030103616]
].

e) Linear Prediction Coefficient

In the linear prediction auto-correlation technique, the linear prediction coefficientsare calculated from the Bartlett-window-biased autocorrelation function [17T. Rajendran, and K.P. Sridhar, "Epileptic seizure classification using feed forward neural network based on parametric features", Int. J. Pharma. Res., vol. 10, no. 4, pp. 189-196.-20T. Rajendran, and K.P. Sridhar, "An overview of EEG seizure detection units and identifying their complexity- a review", Curr. Signal Transduct. Ther., .
[http://dx.doi.org/10.2174/1574362413666181030103616]
].

4. RESULTS

The performance for finding the epilepsy disorder based on feature extraction and classification is carried out by collecting EEG data of patients as epileptic seizure data and normal data. The feature extractions are performed on Auto-Regressive model. Training and testing the information have been done by cross-validation extract of the information, and the extracted features were forwarded to the neural network for detecting the epilepsy data. The result of the classification is based upon the CFBNN and FMSVM classifiers.

(10)
(11)
(12)

Where TP represents True Positive, TN represents True Negative, FP represents False Positive and FN represents False Negative [21F. Muthu, T.S. Aravinth, and T. Rajendran, "Design of CMOS 8-bit parallel adder energy efficient structure using SR-CPL logic style", Pak. J. Biotechnol. Iss, vol. II, no. Special Issue, pp. 257-260.-25T. Rajendran, "Recent innovations in soft computing applications", Curr. Signal Transduct. Ther., . (Article in Press).].

From the acquired dataset, the classification is initially done on subject-based and age-based patient’s data respectively. This classification is performed by using both CFBNN and FMSVM classifiers using six PSD feature extraction methods. The mean accuracy of selected data was computed and performed on proposed features as shown in the following tables.

The subject-based classification accuracy of CFBNN is represented in Table 1 and the graphical representation is plotted based on the computation as shown in Fig (6). Based on the features, the computations are calculated and presented. CFBNN achieved a classification accuracy of 92.34% as the best result on subject 10.

From the obtained classification results of both CFBNN and FMSVM classifiers, the minimum and maximum mean accuracy of the proposed classifiers are computerized, based on the six features as represented below in Tables 2, 3 and 4. The computed accuracy results are compared with previous results of the researches done using different classifiers like FFNN, and PNN Figs. (7, 8 and 9).

Fig. (7)
Graphical Plot of Subject-based Classification rates of CFBNN features.


Fig. (8)
Graphical Plot of Subject-based Classification rates of FMSVM features.


Table 2
Subject-based classification rate of FMSVM using six PSD feature extraction methods.


Table 3
Minimum mean accuracy comparison performance of four networks with six PSD feature extraction methods.


Table 4
Maximum mean accuracy comparison performance of four networks with six PSD feature extraction methods.


Fig. (9)
Graphical plot of minimum mean accuracy of proposed classifiers.


Table 5
Comparison of accuracy, sensitivity & specificity of different classifiers.


Fig. (10)
Graphical Plot of Maximum Mean Accuracy of proposed Classifiers.


Fig. (11)
Graphical Plot of comparison of Classifiers.


Based upon the above results it is clearly stated that FMSVM classifier has performed better and obtained better classification rates compared to the other proposed classifiers Table 5.

The comparison of the classifiers included the parametric estimations of sensitivity, specificity, and accuracy for each classifier in Fig. (10 and 11). The parameters are computed as per the equations 10, 11 and 12 . As seen from the computed estimations and graphical result, the FMSVM performed better than other classifiers in terms of sensitivity, specificity and accuracy.

CONCLUSION

In this research, CFBNN and FMSVM classifiers are proposed for classification and feature extraction of the EEG signal from the dataset, which was used to detect the epileptic seizures from the signal. The EEG dataset was collected from the database of Karunya University to conduct the proposed research. The Autoregressive methods for PSD such as AR Burg, AR Covariance, AR Yule-Walker, AR Modified Covariance, Linear Prediction Coefficient, and Levinson Durbin Recursion are used for feature extraction models. The results of the proposed classifiers were computed with minimum and maximum accuracy and these results were compared with the previous results of the classifiers like FFNN and PNN as shown in the above tables. The results validated that the FMSVM classifier performed better in the detection of epileptic seizure disorders.

LIST OF ABBREVIATIONS

EEG = Electroencephalography
AR = Autoregressive
PSD = Power Spectral Density
FFNN = Feed Forward Neural Network
PNN = Probabilistic Neural Network
LPC = Linear Prediction Coefficient

ETHICS APPROVAL AND CONSENT TO PARTICIPATE

Not applicable.

HUMAN AND ANIMAL RIGHTS

No animals/humans were used for studies that are the basis of this research.

CONSENT FOR PUBLICATION

Not applicable.

AVAILABILITY OF DATA AND MATERIALS

Not applicable.

FUNDING

Not applicable.

CONFLICT OF INTEREST

The authors declare no conflict of interest, financial or

otherwise.

ACKNOWLEDGEMENTS

Declared none.

REFERENCES

[1] Y. Song, and P. Liò, "A new approach for epileptic seizure detection: sample entropy-based feature extraction and extreme learning machine", J. Biomed. Sci. Eng., vol. 3, no. 6, pp. 556-567.
[http://dx.doi.org/10.4236/jbise.2010.36078]
[2] J-H. Kang, Y.G. Chung, and S-P. Kim, "An efficient detection of epileptic seizure by differentiation and spectral analysis of electroencephalograms", Comput. Biol. Med., vol. 66, no. 66, pp. 352-356.
[http://dx.doi.org/10.1016/j.compbiomed.2015.04.034] [PMID: 25982199]
[3] S.T. George, R. Balakrishnan, J.S. Johnson, and J. Jayakumar, "Application and evaluation of independent component analysis methods to generalized seizure disorder activities exhibited in the brain", Clin. EEG Neurosci., vol. 48, no. 4, pp. 295-300.
[http://dx.doi.org/10.1177/1550059416677915] [PMID: 27837050]
[4] L. Wang, W. Xue, Y. Li, M. Luo, J. Huang, W. Cui, and C. Huang, "Automatic epileptic seizure detection in EEG signals using multi-domain feature extraction and nonlinear analysis", Entropy (Basel), vol. 19, no. 6, pp. 222-239.
[http://dx.doi.org/10.3390/e19060222]
[5] Y.U. Khan, and O. Farooq, "Autoregressive features based classification for seizure detection using neural network in scalp Electroencephalogram", Int. J. Biomed. Eng. Technol., vol. 2, no. 4, pp. 370-381.
[http://dx.doi.org/10.1504/IJBET.2009.027800]
[6] N. Rafiuddin, Y.U. Khan, and O. Farooq, "Feature extraction and classification of EEG for automatic seizure detection", IEEE International Conference on Multimedia, Signal Processing and Communication Technologies, pp. 184-187.Aligarh, India
[http://dx.doi.org/10.1109/MSPCT.2011.6150470]
[7] N. Nicolaou, and J. Georgiou, "Detection of epileptic electroencephalogram based on Permutation Entropy and Support Vector Machines", Expert Syst. Appl., vol. 39, no. 1, pp. 202-209.
[http://dx.doi.org/10.1016/j.eswa.2011.07.008]
[8] B. AL-Bokhity Dalia Nashat and T.M. Nazmy, "A Fuzzy Classifier based Detection for Epileptic Seizure Signals", IEEE International Computer Engineering Conference (ICENCO), pp. 100-105.Cairo, Egypt
[9] S. Ali, "Localization of epileptic seizure with an approach based on the PSD with an autoregressive model", https://arxiv.org/pdf/1506. 00947.pdf
[10] N. Mohana Sundaram, S.N. Sivanandam, and V. Renupriya, "Artificial neural network approach for dynamic modelling of heat exchanger for data prediction", Ind. J. Sci. Tech., vol. 9, no. S1, pp. 1-7.
[http://dx.doi.org/10.17485/ijst/2016/v9iS1/86189]
[11] S-F. Liang, H-C. Wang, and W-L. Chang, "Combination of EEG complexity and spectral analysis for epilepsy diagnosis and seizure detection", EURASIP. J. Adv. Sig. Pr, vol. 2010, no. 1, pp. 1-15.
[http://dx.doi.org/10.1155/2010/853434]
[12] B. Karlik, and S.B. Hayta, "Comparison machine learning algorithms for recognition of epileptic seizures in EEG", Proceedings IWBBIO, pp. 1-12.Granada
[13] Nabeel Ahammad, Thasneem Fathima, and Paul Joseph, "Detection of Epileptic Seizure Event and Onset Using EEG", Biomed. Res. Int., vol. 2014, no. 1, pp. 1-7.
[http://dx.doi.org/10.1155/2014/450573]
[14] V. Sutha Jebakumari, D. Shanthi, and D. Devaraj, "Development of neural network classifier for classification of epileptic seizures in EEG signals", IEEE International Conference on Communication and Electronics Systems (ICCES), pp. 980-986.Coimbatore, India
[15] T.G. Selvaraj, B. Ramasamy, S.J. Jeyaraj, and E.S. Suviseshamuthu, "EEG database of seizure disorders for experts and application developers", Clin. EEG Neurosci., vol. 45, no. 4, pp. 304-309.
[http://dx.doi.org/10.1177/1550059413500960] [PMID: 24357675]
[16] V. Hariraj, "Fuzzy multi-layer SVM classification of breast cancer mammogram images", Int. J. Mech. Engg. Tech., vol. 9, no. 8, pp. 1281-1299.
[17] T. Rajendran, and K.P. Sridhar, "Epileptic seizure classification using feed forward neural network based on parametric features", Int. J. Pharma. Res., vol. 10, no. 4, pp. 189-196.
[18] T. Rajendran, and K.P. Sridhar, "Epileptic seizure-classification using probabilistic neural network based on parametric features", J. Int. Pharma. Res., vol. 46, no. 1, pp. 209-216.
[19] G. Emayavaramban, "Identifying user suitability in semg based hand prosthesis using neural networks", Curr. Signal. Transduct. Ther., .
[http://dx.doi.org/10.2174/1574362413666180604100542]
[20] T. Rajendran, and K.P. Sridhar, "An overview of EEG seizure detection units and identifying their complexity- a review", Curr. Signal Transduct. Ther., .
[http://dx.doi.org/10.2174/1574362413666181030103616]
[21] F. Muthu, T.S. Aravinth, and T. Rajendran, "Design of CMOS 8-bit parallel adder energy efficient structure using SR-CPL logic style", Pak. J. Biotechnol. Iss, vol. II, no. Special Issue, pp. 257-260.
[22] P. Yuvaraj, T. Rajendran, and K. Subramaniam, "Design of 4-bit multiplexer using Sub-Threshold Adiabatic Logic (STAL)", Pak J. Biotechnol. Iss, vol. II, no. Special Issue, pp. 261-264.
[23] S. Keerthivasan, G.R. Mahendrababu, and T. Rajendran, "“Design of low intricate 10-bit current steering digital to analog converter circuitry using full swing GDI”, ", Pak J Biotechnol.,, vol. 14. Iss II, no. Special Issue, pp. 204-208.
[24] P. Vijayakumar, T. Rajendran, and G.R. Mahendrababu, "“Efficient implementation of decoder using modified soft decoding algorithm in Golay (24, 12) code”,", Pak J Biotechnol.,, vol. Vol. 14. Iss II, no. Special Issue, pp. 200-203.
[25] T. Rajendran, "Recent innovations in soft computing applications", Curr. Signal Transduct. Ther., . (Article in Press).

Endorsements



"Open access will revolutionize 21st century knowledge work and accelerate the diffusion of ideas and evidence that support just in time learning and the evolution of thinking in a number of disciplines."


Daniel Pesut
(Indiana University School of Nursing, USA)

"It is important that students and researchers from all over the world can have easy access to relevant, high-standard and timely scientific information. This is exactly what Open Access Journals provide and this is the reason why I support this endeavor."


Jacques Descotes
(Centre Antipoison-Centre de Pharmacovigilance, France)

"Publishing research articles is the key for future scientific progress. Open Access publishing is therefore of utmost importance for wider dissemination of information, and will help serving the best interest of the scientific community."


Patrice Talaga
(UCB S.A., Belgium)

"Open access journals are a novel concept in the medical literature. They offer accessible information to a wide variety of individuals, including physicians, medical students, clinical investigators, and the general public. They are an outstanding source of medical and scientific information."


Jeffrey M. Weinberg
(St. Luke's-Roosevelt Hospital Center, USA)

"Open access journals are extremely useful for graduate students, investigators and all other interested persons to read important scientific articles and subscribe scientific journals. Indeed, the research articles span a wide range of area and of high quality. This is specially a must for researchers belonging to institutions with limited library facility and funding to subscribe scientific journals."


Debomoy K. Lahiri
(Indiana University School of Medicine, USA)

"Open access journals represent a major break-through in publishing. They provide easy access to the latest research on a wide variety of issues. Relevant and timely articles are made available in a fraction of the time taken by more conventional publishers. Articles are of uniformly high quality and written by the world's leading authorities."


Robert Looney
(Naval Postgraduate School, USA)

"Open access journals have transformed the way scientific data is published and disseminated: particularly, whilst ensuring a high quality standard and transparency in the editorial process, they have increased the access to the scientific literature by those researchers that have limited library support or that are working on small budgets."


Richard Reithinger
(Westat, USA)

"Not only do open access journals greatly improve the access to high quality information for scientists in the developing world, it also provides extra exposure for our papers."


J. Ferwerda
(University of Oxford, UK)

"Open Access 'Chemistry' Journals allow the dissemination of knowledge at your finger tips without paying for the scientific content."


Sean L. Kitson
(Almac Sciences, Northern Ireland)

"In principle, all scientific journals should have open access, as should be science itself. Open access journals are very helpful for students, researchers and the general public including people from institutions which do not have library or cannot afford to subscribe scientific journals. The articles are high standard and cover a wide area."


Hubert Wolterbeek
(Delft University of Technology, The Netherlands)

"The widest possible diffusion of information is critical for the advancement of science. In this perspective, open access journals are instrumental in fostering researches and achievements."


Alessandro Laviano
(Sapienza - University of Rome, Italy)

"Open access journals are very useful for all scientists as they can have quick information in the different fields of science."


Philippe Hernigou
(Paris University, France)

"There are many scientists who can not afford the rather expensive subscriptions to scientific journals. Open access journals offer a good alternative for free access to good quality scientific information."


Fidel Toldrá
(Instituto de Agroquimica y Tecnologia de Alimentos, Spain)

"Open access journals have become a fundamental tool for students, researchers, patients and the general public. Many people from institutions which do not have library or cannot afford to subscribe scientific journals benefit of them on a daily basis. The articles are among the best and cover most scientific areas."


M. Bendandi
(University Clinic of Navarre, Spain)

"These journals provide researchers with a platform for rapid, open access scientific communication. The articles are of high quality and broad scope."


Peter Chiba
(University of Vienna, Austria)

"Open access journals are probably one of the most important contributions to promote and diffuse science worldwide."


Jaime Sampaio
(University of Trás-os-Montes e Alto Douro, Portugal)

"Open access journals make up a new and rather revolutionary way to scientific publication. This option opens several quite interesting possibilities to disseminate openly and freely new knowledge and even to facilitate interpersonal communication among scientists."


Eduardo A. Castro
(INIFTA, Argentina)

"Open access journals are freely available online throughout the world, for you to read, download, copy, distribute, and use. The articles published in the open access journals are high quality and cover a wide range of fields."


Kenji Hashimoto
(Chiba University, Japan)

"Open Access journals offer an innovative and efficient way of publication for academics and professionals in a wide range of disciplines. The papers published are of high quality after rigorous peer review and they are Indexed in: major international databases. I read Open Access journals to keep abreast of the recent development in my field of study."


Daniel Shek
(Chinese University of Hong Kong, Hong Kong)

"It is a modern trend for publishers to establish open access journals. Researchers, faculty members, and students will be greatly benefited by the new journals of Bentham Science Publishers Ltd. in this category."


Jih Ru Hwu
(National Central University, Taiwan)


Browse Contents




Webmaster Contact: info@benthamopen.net
Copyright © 2020 Bentham Open