Robust Epileptic Seizure Detection Using Long Short-Term Memory and Feature Fusion of Compressed Time–Frequency EEG Images

Abstract

Epilepsy is a prevalent neurological disorder with considerable risks, including physical impairment and irreversible brain damage from seizures. Given these challenges, the urgency for prompt and accurate seizure detection cannot be overstated. Traditionally, experts have relied on manual EEG signal analyses for seizure detection, which is labor-intensive and prone to human error. Recognizing this limitation, the rise in deep learning methods has been heralded as a promising avenue, offering more refined diagnostic precision. On the other hand, the prevailing challenge in many models is their constrained emphasis on specific domains, potentially diminishing their robustness and precision in complex real-world environments. This paper presents a novel model that seamlessly integrates the salient features from the time–frequency domain along with pivotal statistical attributes derived from EEG signals. This fusion process involves the integration of essential statistics, including the mean, median, and variance, combined with the rich data from compressed time–frequency (CWT) images processed using autoencoders. This multidimensional feature set provides a robust foundation for subsequent analytic steps. A long short-term memory (LSTM) network, meticulously optimized for the renowned Bonn Epilepsy dataset, was used to enhance the capability of the proposed model. Preliminary evaluations underscore the prowess of the proposed model: a remarkable 100% accuracy in most of the binary classifications, exceeding 95% accuracy in three-class and four-class challenges, and a commendable rate, exceeding 93.5% for the five-class classification.

Fault Diagnosis in Centrifugal Pumps: A Dual-Scalogram Approach with Convolution Autoencoder and Artificial Neural Network

“…Consequently, time-frequency analysis emerges as a potent tool, adeptly unveiling the concealed fault information within centrifugal pump signals, presenting them visually as images [33]. The time-frequency domain methodology dissects signals across varied time and frequency scales, subsequently presenting them as a two-dimensional visual representation [34]. This image encompasses both the local (pertaining to specific segments of the image) and global (encompassing the entire image) traits of the signal.…”

Auscultation-Based Pulmonary Disease Detection through Parallel Transformation and Deep Learning

“…This approach offers a dual-modality method that enhances diagnostic capabilities by simultaneously analyzing cardiac and respiratory data. In [ 28 ], the authors classified electroencephalogram (EEG) signals using CWT and a long short-term memory (LSTM) model, similar to the study in [ 29 ], in which a dual scalogram comprising the Stockwell transform and a CWT scalogram was employed for fault diagnosis in centrifugal pumps. Furthermore, recent studies have explored different ML and DL techniques for binary-class (normal vs. abnormal) classification and multi-class classification of respiratory diseases [ 30 ].…”