Detection of Epileptic Seizure Frequencies Using Wavelet Transform with Machine Learning Classifiers and Modified Particle Swarm Optimization Algorithm
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Epilepsy is a neurological disorder that affects approximately 1% of the global population. Early detection is crucial to protect and manage patients suffering from this condition. However, direct analysis of brain signals is highly complex, time-consuming, and prone to errors. In recent years, numerous mathematical tools have been developed for signal and image processing. Epileptic signals are time-frequency-varying EEG signals, and the Discrete Wavelet Transform (DWT) is a suitable method for extracting epileptic features from these signals. This research investigates the use of three types of Discrete Wavelet Transforms in combination with machine learning classifiers such as Linear regression, Non-linear regression, K-Nearest Neighbours (KNN) and Support Vector Machine (SVM). To enhance classification accuracy, feature selection methods such as modified Particle Swarm Optimization is employed. The EEG dataset utilized in this research was obtained from the Department of Epileptology at Bonn University, Germany. A fivelevel Discrete Wavelet Transform (DWT) decomposition was performed using a sampling rate of 2. From the resulting decomposed signals, key statistical features such as mean, median, standard deviation, kurtosis, and skewness were extracted. These features were then analysed using selected machine learning classifiers. The performance of the models was assessed through metrics like accuracy, sensitivity, and specificity, and the results were compared against current state-of-the-art techniques.
Fields of Study & Subjects
EEG and Brain-Computer Interfaces
Emotion and Mood Recognition
Machine Fault Diagnosis Techniques
Publication details
- Journal / source
- CRC Press eBooks
- Pages
- 219–227
- Publication date
- 26 March 2026
- Language
- EN
- Document type
- Book chapter