Elsevier

Expert Systems with Applications

Volume 38, Issue 10, 15 September 2011, Pages 13475-13481
Expert Systems with Applications

Short Communication
EEG signals classification using the K-means clustering and a multilayer perceptron neural network model

https://doi.org/10.1016/j.eswa.2011.04.149Get rights and content

Abstract

We introduced a multilayer perceptron neural network (MLPNN) based classification model as a diagnostic decision support mechanism in the epilepsy treatment. EEG signals were decomposed into frequency sub-bands using discrete wavelet transform (DWT). The wavelet coefficients were clustered using the K-means algorithm for each frequency sub-band. The probability distributions were computed according to distribution of wavelet coefficients to the clusters, and then used as inputs to the MLPNN model. We conducted five different experiments to evaluate the performance of the proposed model in the classifications of different mixtures of healthy segments, epileptic seizure free segments and epileptic seizure segments. We showed that the proposed model resulted in satisfactory classification accuracy rates.

Highlights

► We consider a multilayer perceptron neural network model for the diagnosis of epilepsy. ► EEG signals are decomposed into frequency sub-bands using discrete wavelet transform. ► The wavelet coefficients are clustered using the K-means algorithm for each sub-band. ► The probability distributions are computed and then used as inputs to the model. ► The proposed model results in the satisfactory classification accuracies.

Introduction

Epilepsy is a critical neurological disease stemming from temporary abnormal discharges of the brain electrical activity, leading to uncontrollable movements and tremblings. About 1% of the world population suffers from epilepsy (Adeli, Zhou, & Dadmehr, 2003). Therefore, the diagnosis of epilepsy allows the choice of medicine or surgical treatment (Ogulata, Sahin, & Erol, 2009). Since the electroencephalogram (EEG) records show the brain electrical activities, they can provide valuable insight into disorders of the brain activity. In this context, the EEG recordings measured in seizure-free intervals from the epilepsy patients are considered as important components for the diagnosis or prediction process (Adeli et al., 2003, Subasi, 2005a, Subasi, 2007). Although the occurrence of epileptic seizures seems unpredictable (Subasi, 2007), more efforts are focused on the development of computational models for automatic detection of epileptic discharges, which then can be used to predict the onset of seizure (Adeli et al., 2003).

Artificial neural networks (ANNs) have been widely used in many biomedical signal analysis because they not only model the signal, but also make a decision to classify the signal (Subasi, 2007). Therefore, they provide an important support for the medical diagnostic decision. In a classification system with ANN, first step is related to the feature extraction from the raw data with minimal loss of important information by using numerous different methods such as frequency domain features, time-frequency features, wavelet transform (WT), leading to the extracted feature vectors (Hazarika et al., 1997, Ubeyli, 2009a, Ubeyli, 2009b). In the second step, some statistics over the vectors are used to reduce the dimensionality of these vectors. Final step is to apply the feature vectors as inputs to ANNs (Subasi, 2007, Ubeyli, 2009a, Ubeyli, 2009b). Both the architecture of the ANN and the training algorithm play key roles to obtain satisfactory results from ANNs (Ubeyli, 2009b).

In order to analyze the EEG signals, ANN models with different architectures have been used such as multilayer perceptron neural network (MLPNN) (Alkan et al., 2005, Subasi, 2005a, Subasi, 2005b, Subasi, 2007, Subasi and Ercelebi, 2005, Ubeyli, 2009a, Ubeyli, 2009b), adaptive neuro-fuzzy inference system (ANFIS) (Guler & Ubeyli, 2005), radial basis function neural network (RBFNN) (Aslan, Bozdemir, Sahin, Ogulata, & Erol, 2008), recurrent neural network (RNN) (Petrosian et al., 2000, Srinivasan et al., 2005), learning quantization vector (LVQ) (Pradhan, Sadasivan, & Arunodaya, 1996), support vector machine (SVM) (Ubeyli, 2008) and mixture of experts (ME) model (Subasi, 2007). We recently proposed the probability distribution approach based on equal frequency discretization for the epileptic seizure detection (Orhan, Hekim, & Ozer, 2011). Most of these studies focus on the epilepsy by using the statistical features obtained from the sub-bands of EEG signals to analyze the epileptic activities.

In order to extract associative features from EEG signals without any prior information, the signals can be grouped by a clustering algorithm. K-means is a well known clustering algorithm which requires no prior information about the associations of data points with clusters (Faraoun and Boukelif, 2007, Hekim and Orhan, 2007, Hekim and Orhan, 2011, Mwasiagi et al., 2009, Orhan and Hekim, 2007, Orhan et al., 2008, Ross, 2004). K-means algorithm groups the data points into K clusters according to the distance measure. But a literature survey leaves us with the impression that the K-means clustering algorithm has not been investigated in any detail related to the estimation of the MLPNN accuracy in the analysis of EEG signals. Therefore, our purpose in this paper is to investigate the impact of the K-means clustering algorithm on the MLPNN accuracy for the detection of epileptic events. For this aim, EEG signals are decomposed into sub-bands through the discrete wavelet transform (DWT). The wavelet coefficients are clustered by using K-means algorithm for each sub-band. The probability distributions are computed according to distribution of wavelet coefficients to the clusters, and then these distributions are used as inputs to MLPNN model (Fig. 1).

Section snippets

Data selection

We used the publicly available data in Andrzejak et al. (2001). The complete data consists of five sets (A, B, C, D, and E), each one containing 100 single-channel EEG segments of 23.6 s duration. The sets were selected from EEG records after purifying artifacts caused by eye and muscle movements. Sets A (eyes open) and B (eyes closed) were extracranially taken from five healthy subjects. Sets C, D, and E were intracranially taken from five epilepsy patients. While sets D and C contained the EEG

Results and discussion

EEG signals were decomposed into sub-bands by using the DWT with Daubechies wavelet of order 2 (db2) because it yields good results in classification of the EEG segments (Ubeyli, 2009a). Wavelet coefficients obtained from EEG segments with 4097 samples were clustered by K-means algorithm, and then the probability distributions of each sub-band for EEG segments were computed. These probability distributions were used as inputs to the MLPNN model. Five different experiments were implemented by

Conclusion

In this study, we used a MLPNN-based classification model to classify EEG signals. EEG signals were decomposed into sub-bands through the DWT. Instead of using basic statistics over the wavelet coefficients, we used the clustering approach for the wavelet coefficients in each sub-band by using K-means algorithm. The probability distributions were computed according to distribution of wavelet coefficients to the clusters, and then these distributions were used as inputs to MLPNN model. We

References (34)

Cited by (0)

View full text