Principal component analysis-based neural network with fuzzy membership function for epileptic seizure detection

Abstract

A hybrid principal component analysis (PCA)-based neural network with fuzzy membership function (NEWFM) is proposed for epileptic seizure detection. By combining PCA and NEWFM, the proposed method improves the accuracy in epileptic seizure detection. The PCA is used for wavelet feature enhancement needed to eliminate the sensitivity of noise, electrode artifacts, or redundancy. NEWFM, a model of neural networks, is integrated to improve prediction results by updating weights of fuzzy membership functions. A dataset made up of 5 sets, each consisting 100 single EEGs segments, is employed to evaluate the proposed system's performance. Based on the experiments, the prediction results show an accuracy rate of 98.29% for epileptic seizure classification while in the best cases the accuracy reaches 99.5% for the 'normal' (Z-S) seizure classification task.

A Combined AdaBoost and NEWFM Technique for Medical Data Classification

“…Forecasting KOSPI based on NEWFM was also presented in [14]. A hybrid Principle Component Analysis based NEWFM using EEG signals was recently proposed in [6] for epileptic seizure detection. To further improve the performance of classification methods, some hybrid approaches combining different optimization algorithms with other classification methods have also been proposed [15,16].…”

“…Such uses in [2][3][4][5][6] focus on epileptic seizure detection, schizophrenia detection and Alzheimer based on EEG signals. While the work in [8][9][10][11] focus on medical data classification tasks for ailments such as diabetes, heart disease, hepatitis, Parkinson, liver, and cancer.…”

“…Most of the available literature utilise Neural Network methods as the common classifiers to classify medical data [2,3,4,6], which together with fuzzy theory have been proven as classification methods that can effectively predict patterns required to generate predictive rules. One of such approaches, the neural network with fuzzy membership functions (NEWFM), maintains important information without decreasing the classification capability by updating weighted fuzzy membership functions, and it has been applied in [12] in feature selection, and the antibody deficiency syndrome prediction, with high accuracy.…”

Evidence Accumulation Clustering with Possibilitic Fuzzy C-Means base clustering approach to disease diagnosis

“…Some of the available literature [1][2][3][4][5][6] focus on medical data classification tasks for ailments such as diabetes, heart disease, hepatitis, Parkinson, liver, and cancer. Similarly, EEG and ECG signals are usually used in diagnosing other diseases such as epileptic seizure, schizophrenia, Alzheimer, asthma, and arrhythmia [7][8][9][10][11].…”

“…Medical data classification tasks are executed using different varieties of data types including text, signal, image, DNA, voice, etc. [1][2][3][4][5][6][7][8][9][10]. Some of the available literature [1][2][3][4][5][6] focus on medical data classification tasks for ailments such as diabetes, heart disease, hepatitis, Parkinson, liver, and cancer.…”