Not checkedNot checked for notices yet.
ESA-ASO: An enhanced search ability based atom search optimization algorithm for epileptic seizure detection
Sumant Kumar Mohapatra, Srikanta Patnaik
Measurement: Sensors · 2022
doi:10.1016/j.measen.2022.100519 (opens in a new tab)
We email you when a new notice or a question about this paper appears.
Abstract
Epilepsy is a complex process and the prediction of seizure is uncertain. Currently, many researchers are exploring different optimization methods to detect the epileptic seizure. Atomic search optimization (ASO) shows a better search capability by using interaction force and the constraint force but it still some deficiency from a local optimum and a low search efficiency. To overcome these demerits, a new enhanced search ability based ASO named as ESAASO is proposed. In this study, inertia weight, levy flight and ranking strategies are integrated into ASO to improve the search performance. The proposed method has been studied on CHB-MIT scalp EEG database. There are 13 number of features are extracted by using TQWT and features are selected using genetic algorithm (GA). The proposed detection method has been computed using twelve well known optimization algorithms with LSSVM classifier. We have obtained average accuracy, sensitivity, selectivity, specificity, average detection rate, G-Mean and area under curve (AUC) values as 98.37%, 91.11%, 91.67%, 91.46%, 91.28%, 91.28% and 0.992 respectively using 10-fold cross-validation method. The proposed algorithm is found outperform as compared to conventional ASO for seizure and non-seizure detection. The proposed method can be experimented using short term EEG datasets in future.
Abstract licence: CC BY-NC
Reads
Read by people on this page
None yet.
Checked or read by AI through naulon
None yet.
A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.
Are you an author?
Is this your paper?
Claim it to add your note and be paid when agents cite it. Free.