Evaluating the Window Size’s Role in Automatic EEG Epilepsy Detection

Abstract

Electroencephalography is one of the most commonly used methods for extracting information about the brain’s condition and can be used for diagnosing epilepsy. The EEG signal’s wave shape contains vital information about the brain’s state, which can be challenging to analyse and interpret by a human observer. Moreover, the characteristic waveforms of epilepsy (sharp waves, spikes) can occur randomly through time. Considering all the above reasons, automatic EEG signal extraction and analysis using computers can significantly impact the successful diagnosis of epilepsy. This research explores the impact of different window sizes on EEG signals’ classification accuracy using four machine learning classifiers. The machine learning methods included a neural network with ten hidden nodes trained using three different training algorithms and the k-nearest neighbours classifier. The neural network training methods included the Broyden–Fletcher–Goldfarb–Shanno algorithm, the multistart method for global optimization problems, and a genetic algorithm. The current research utilized the University of Bonn dataset containing EEG data, divided into epochs having 50% overlap and window lengths ranging from 1 to 24 s. Then, statistical and spectral features were extracted and used to train the above four classifiers. The outcome from the above experiments showed that large window sizes with a length of about 21 s could positively impact the classification accuracy between the compared methods.

Integrating EEG and Ensemble Learning for Accurate Grading and Quantification of Generalized Anxiety Disorder: A Novel Diagnostic Approach

“…This study reveals that the appropriate time window length is essential for evaluating the stability and performance of the model. Further analysis indicates that selecting an appropriate time window length can yield the best classification accuracy, while too-short time windows may not fully extract EEG signal features, and too-long time windows may lead to masking variability in features, adversely affecting the performance of the classification model [ 37 ]. He et al analyzed that the length of the time window has a significant impact on the dynamic brain network analysis under different emotional conditions [ 38 ].…”

A Dataset of Scalp EEG Recordings of Alzheimer’s Disease, Frontotemporal Dementia and Healthy Subjects from Routine EEG

“…Electroencephalography (EEG) has become a potential method for the identification and monitoring of Alzheimer's disease and frontotemporal dementia, in addition to clinical evaluation and imaging testing [8]. EEG measures brain electrical activity and can identify anomalies in brain waves linked to certain disorders [9][10][11][12]. Then, using machine learning techniques, these signals can be automatically analyzed to find patterns that might point to sickness.…”

“…Each folder is associated to one participant-id of the participant table. Additionally, each folder contains three files: (A) A sub-0XX-task_eyesclosed_eeg.json file, which contains all the necessary EEG recording information, such as the placement scheme (10)(11)(12)(13)(14)(15)(16)(17)(18)(19)(20), the reference (A1 and A2), the model of the device and amplifier used, the channel count, the sampling frequency, the recording duration, and more. (B) A sub-0XX_task-eyesclosed_channels.tsv file, which provides information about electrode location.…”

Utilizing Constructed Neural Networks for Autism Screening

“…BFGS is an iterative optimization technique primarily used in various domains [74], including machine learning [75], mainly aimed at estimating the inverse of the Hessian matrix (matrix of second-order partial derivatives). With the help of an estimate, we can determine the search direction to minimize the objective function.…”