AHW-BGOA-DNN: a novel deep learning model for epileptic seizure detection
- PDF / 2,963,965 Bytes
- 29 Pages / 595.276 x 790.866 pts Page_size
- 27 Downloads / 188 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
AHW-BGOA-DNN: a novel deep learning model for epileptic seizure detection H. Anila Glory1 • C. Vigneswaran1 • Sujeet S. Jagtap1 • R. Shruthi1 • G. Hariharan2 • V. S. Shankar Sriram1 Received: 28 March 2019 / Accepted: 24 September 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract ‘‘Brain–Computer Interface’’ (BCI)—a real-life support system provides a way for epileptic patients to improve their quality of life. In general, epileptic seizure detection using Electroencephalogram (EEG) signals provide a significant solution in preventing seizures through medication. Thus, the design of efficient machine learning-based seizure detection model is highly acclaimed by various academic and health professionals. In a motive to address the challenges posed by the state-of-the-art techniques in terms of noise, non-stationarity, and transient nature of EEG signals, this paper presents a novel Deep Learning model for epileptic seizure detection which hybridizes Adaptive Haar Wavelet-based Binary Grasshopper Optimization Algorithm and Deep Neural Network (AHW-BGOA-DNN). The experimental analysis was carried out using three benchmark EEG datasets obtained from the University of Bonn, the University of Bern and CHBMIT EEG database which confirm the proposed technique to be reliable and accurate over the existing state-of-the-art techniques in terms of stability analysis, classification accuracy, AUC–ROC Curve (Area Under Curve–Receiver Operating Characteristics), sensitivity, and specificity. Keywords Epileptic seizure detection Adaptive Haar wavelet Binary grasshopper optimization algorithm Deep learning
1 Introduction
& V. S. Shankar Sriram [email protected] H. Anila Glory [email protected] C. Vigneswaran [email protected] Sujeet S. Jagtap [email protected] R. Shruthi [email protected] G. Hariharan [email protected] 1
Centre for Information Super Highway (CISH), School of Computing, SASTRA Deemed University, Thanjavur, Tamil Nadu, India
2
Discrete Mathematics Research Laboratory (DMRL), Department of Mathematics, SASTRA Deemed University, Thanjavur, Tamil Nadu, India
Epilepsy a chronic neurological disorder, characterized by the unexpected occurrence of sensory inconvenience (seizures) or loss of consciousness that occurs due to the unusual electrical activity in the brain [1]. A report presented by WHO [2] states that globally about 50 million people suffer from a seizure disorder. About 75% of epileptic patients reside in economically backward countries. Out of 1000 people, 4–10 people are affected with active epilepsy at a given time, whereas in economically backward countries the proportion is much higher varying from 7 to 14 per 1000 people. Due to the massive prevalence of this disorder, there arises a need for proper detection and appropriate regimen. The most commonly preferred non-invasive test around the globe for the diagnosis of epilepsy is EEG (Electroencephalogram), which directly
Data Loading...
