Intelligent Epileptic Seizure Detection and Classification Model Using Optimal Deep Canonical Sparse Autoencoder

Abstract

Epileptic seizures are a chronic and persistent neurological illness that mainly affects the human brain. Electroencephalogram (EEG) is considered an effective tool among neurologists to detect various brain disorders, including epilepsy, owing to its advantages, such as its low cost, simplicity, and availability. In order to reduce the severity of epileptic seizures, it is necessary to design effective techniques to identify the disease at an earlier stage. Since the traditional way of diagnosing epileptic seizures is laborious and time-consuming, automated tools using machine learning (ML) and deep learning (DL) models may be useful. This paper presents an intelligent deep canonical sparse autoencoder-based epileptic seizure detection and classification (DCSAE-ESDC) model using EEG signals. The proposed DCSAE-ESDC technique involves two major processes, namely, feature selection and classification. The DCSAE-ESDC technique designs a novel coyote optimization algorithm (COA)-based feature selection technique for the optimal selection of feature subsets. Moreover, the DCSAE-based classifier is derived for the detection and classification of different kinds of epileptic seizures. Finally, the parameter tuning of the DSCAE model takes place via the krill herd algorithm (KHA). The design of the COA-based feature selection and KHA-based parameter tuning shows the novelty of the work. For examining the enhanced classification performance of the DCSAE-ESDC technique, a detailed experimental analysis was conducted using a benchmark epileptic seizure dataset. The comparative results analysis portrayed the better performance of the DCSAE-ESDC technique over existing techniques, with maximum accuracy of 98.67% and 98.73% under binary and multi-classification, respectively.

Guided deep embedded clustering regularization for multifeature medical signal classification

“…Second, if we compare our proposed models with other state-of-the-art models [5,11,13,14], we achieve state-of-the-art results on both the HITS and PTB datasets. On the HITS dataset, the best performing model is the proposed regularized multifeature model, outperforming the other models by a margin greater than 3.61% in terms of MCC.…”

“…Some works have tried to solve these tasks by using classic signal processing techniques and machine learning techniques [7,8,9]. However, few works have directly exploited the raw signal [10,5] as handcrafted features (or TFR) are often extracted to be fed to the different models [8,11,12,13,14]. Furthermore, inspired from natural language processing (NLP), several methods have been proposed to exploit the temporal context of time-dependent signals.…”

CAD system for epileptic seizure detection from EEG through image processing and SURF-BOF technique

“…There have also been some studies based on autoencoders. For example, one study [23] described an intelligent DCSAE-ESDC model. For the best choice of feature subsets, this approach develops a new feature selection method based on the COA.…”

Epileptic Patient Activity Recognition System Using Extreme Learning Machine Method

“…Binary classification involved labelling abnormal activity (that is, EEG signals showing seizure activity) as 0 based on 2300 instances to train the model and labelling normal activity (that is, EEG signals having no seizure activity as 1 based on 9200 instances to train the model. Multi-classification involved labelling normal classes from EEG signals showing seizure activity, tumor regions, a healthy brain, eyes closed, and eyes open as 0, 1, 2, 3, and 4, respectively, with each class having 200 instances to train the model [ 36 ].…”