Optimizing epileptic seizure recognition performance with feature scaling and dropout layers

Abstract

Epilepsy is a widespread neurological disorder characterized by recurring seizures that have a significant impact on individuals' lives. Accurately recognizing epileptic seizures is crucial for proper diagnosis and treatment. Deep learning models have shown promise in improving seizure recognition accuracy. However, optimizing their performance for this task remains challenging. This study presents a new approach to optimize epileptic seizure recognition using deep learning models. The study employed a dataset of Electroencephalography (EEG) recordings from multiple subjects and trained nine deep learning architectures with different preprocessing techniques. By combining a 1D convolutional neural network (Conv1D) with a Long Short-Term Memory (LSTM) network, we developed the Conv1D + LSTM architecture. This architecture, augmented with dropout layers, achieved an effective test accuracy of 0.993. The LSTM architecture alone achieved a slightly lower accuracy of 0.986. Additionally, the Bidirectional LSTM (BiLSTM) and Gated Recurrent Unit (GRU) architectures performed exceptionally well, with accuracies of 0.983 and 0.984, respectively. Notably, standard scaling proved to be advantageous, significantly improving the accuracy of both BiLSTM and GRU compared to MinMax scaling. These models consistently achieved high test accuracies across different percentages of Principal Component Analysis (PCA), with the best results obtained when retaining 50% and 90% of the features. Chi-square feature selection also enhanced the classification performance of BiLSTM and GRU models. The study reveals that different deep learning architectures respond differently to feature scaling, PCA, and feature selection methods. Understanding these nuances can lead to optimized models for epileptic seizure recognition, ultimately improving patient outcomes and quality of life.

Hybrid Convolutional Recurrent Neural Network for Cyberbullying Detection on Textual Data

“…Cyberbullying detection on social media platforms has garnered significant attention in recent years, prompting the exploration of various machine learning and deep learning techniques to address this pervasive issue [9]. Previous studies have proposed diverse methodologies, including hybrid neural network architectures, to enhance the accuracy and efficiency of cyberbullying detection systems [10][11].…”

Lip-Reading Advancements: A 3D Convolutional Neural Network/Long Short-Term Memory Fusion for Precise Word Recognition

“…This approach attained an accuracy of 95.14%, surpassing ViT-B/16 and FABNet. Finally, Omar et al [10] focused on optimizing epileptic seizure recognition using deep learning models. Various architectures were explored, such as Conv1D, Long Short-Term Memory (LSTM), bidirectional LSTM (BiLSTM), and Gated Recurrent Units (GRUs).…”

A novel fusion of genetic grey wolf optimization and kernel extreme learning machines for precise diabetic eye disease classification

“…The latest advances in computer vision and artificial intelligence have profoundly impacted the development of diagnostic systems for face recognition [6], disease diagnosis [7][8][9][10], etc. Important image processing methods are the backbone of computer vision applications [11][12][13][14]. Imprecise diagnosis of Diabetic Retinopathy (DR), a more severe form of Diabetic Eye Disease (DED), may lead to significant blindness.…”