Amyotrophic Lateral Sclerosis EEG Classification Using Deep Neural Network And TLBO

Abstract

The prediction and detection of amyotrophic lateral sclerosis (ALS) diseases are a challenging task for the brain-computer interface. The discovery and classification of amyotrophic lateral sclerosis diseases used various neural network models. The limitation of the neural network deals with feature extraction and vector conversion of ALS data. The extraction of features of ALS diseases is very complex due to the recorded signal of the human brain. The recoded signal consists of the actual signal and other brain behaviours of a signal treat as noise. The noise recorded signal degraded the performance of the brain-computer interface. For the betterment of the brain-computer interface, I am using feature selection and reduction process with the neural network model. This paper proposed the deep learning-based classification algorithms for the prediction of ALS disease. The deep learning algorithm is a variant of a multilayer neural network for the extraction of features used discrete wavelet transform function. The discrete wavelet transform function decomposed the electroencephalogram signal in different sub-bands for the processing. The represent bands into varied frequency range. The proposed algorithms are simulated in MATLAB software and used the standard dataset of ALS diseases for the analysis of performance. The proposed algorithm compares with Bayesian-based neural network and ensemble-based machine learning classifiers for ALS disease detection. The performance of the proposed algorithms improved the efficiency of the brain-computer interface system.