Performance comparison of bio-inspired and learning-based clustering analysis with machine learning techniques for classification of EEG signals
A comprehensive analysis of an automated system for epileptic seizure detection is explained in this work. When a seizure occurs, it is quite difficult to differentiate the non-stationary patterns from the discharges occurring in a rhythmic manner. The proposed approach deals with it efficiently by...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2023.1156269/full |
| _version_ | 1827919952992010240 |
|---|---|
| author | Sunil Kumar Prabhakar Dong-Ok Won |
| author_facet | Sunil Kumar Prabhakar Dong-Ok Won |
| author_sort | Sunil Kumar Prabhakar |
| collection | DOAJ |
| description | A comprehensive analysis of an automated system for epileptic seizure detection is explained in this work. When a seizure occurs, it is quite difficult to differentiate the non-stationary patterns from the discharges occurring in a rhythmic manner. The proposed approach deals with it efficiently by clustering it initially for the sake of feature extraction by using six different techniques categorized under two different methods, e.g., bio-inspired clustering and learning-based clustering. Learning-based clustering includes K-means clusters and Fuzzy C-means (FCM) clusters, while bio-inspired clusters include Cuckoo search clusters, Dragonfly clusters, Firefly clusters, and Modified Firefly clusters. Clustered values were then classified with 10 suitable classifiers, and after the performance comparison analysis of the EEG time series, the results proved that this methodology flow achieved a good performance index and a high classification accuracy. A comparatively higher classification accuracy of 99.48% was achieved when Cuckoo search clusters were utilized with linear support vector machines (SVM) for epilepsy detection. A high classification accuracy of 98.96% was obtained when K-means clusters were classified with a naive Bayesian classifier (NBC) and Linear SVM, and similar results were obtained when FCM clusters were classified with Decision Trees yielding the same values. The comparatively lowest classification accuracy, at 75.5%, was obtained when Dragonfly clusters were classified with the K-nearest neighbor (KNN) classifier, and the second lowest classification accuracy of 75.75% was obtained when Firefly clusters were classified with NBC. |
| first_indexed | 2024-03-13T04:04:48Z |
| format | Article |
| id | doaj.art-faa0accd75f144ebaa4f1c3f9af497db |
| institution | Directory Open Access Journal |
| issn | 2624-8212 |
| language | English |
| last_indexed | 2024-03-13T04:04:48Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Artificial Intelligence |
| spelling | doaj.art-faa0accd75f144ebaa4f1c3f9af497db2023-06-21T09:20:31ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122023-06-01610.3389/frai.2023.11562691156269Performance comparison of bio-inspired and learning-based clustering analysis with machine learning techniques for classification of EEG signalsSunil Kumar PrabhakarDong-Ok WonA comprehensive analysis of an automated system for epileptic seizure detection is explained in this work. When a seizure occurs, it is quite difficult to differentiate the non-stationary patterns from the discharges occurring in a rhythmic manner. The proposed approach deals with it efficiently by clustering it initially for the sake of feature extraction by using six different techniques categorized under two different methods, e.g., bio-inspired clustering and learning-based clustering. Learning-based clustering includes K-means clusters and Fuzzy C-means (FCM) clusters, while bio-inspired clusters include Cuckoo search clusters, Dragonfly clusters, Firefly clusters, and Modified Firefly clusters. Clustered values were then classified with 10 suitable classifiers, and after the performance comparison analysis of the EEG time series, the results proved that this methodology flow achieved a good performance index and a high classification accuracy. A comparatively higher classification accuracy of 99.48% was achieved when Cuckoo search clusters were utilized with linear support vector machines (SVM) for epilepsy detection. A high classification accuracy of 98.96% was obtained when K-means clusters were classified with a naive Bayesian classifier (NBC) and Linear SVM, and similar results were obtained when FCM clusters were classified with Decision Trees yielding the same values. The comparatively lowest classification accuracy, at 75.5%, was obtained when Dragonfly clusters were classified with the K-nearest neighbor (KNN) classifier, and the second lowest classification accuracy of 75.75% was obtained when Firefly clusters were classified with NBC.https://www.frontiersin.org/articles/10.3389/frai.2023.1156269/fullepilepsyEEGK-means clustersfuzzy C-means clustersCuckoo search clustersFirefly clusters |
| spellingShingle | Sunil Kumar Prabhakar Dong-Ok Won Performance comparison of bio-inspired and learning-based clustering analysis with machine learning techniques for classification of EEG signals Frontiers in Artificial Intelligence epilepsy EEG K-means clusters fuzzy C-means clusters Cuckoo search clusters Firefly clusters |
| title | Performance comparison of bio-inspired and learning-based clustering analysis with machine learning techniques for classification of EEG signals |
| title_full | Performance comparison of bio-inspired and learning-based clustering analysis with machine learning techniques for classification of EEG signals |
| title_fullStr | Performance comparison of bio-inspired and learning-based clustering analysis with machine learning techniques for classification of EEG signals |
| title_full_unstemmed | Performance comparison of bio-inspired and learning-based clustering analysis with machine learning techniques for classification of EEG signals |
| title_short | Performance comparison of bio-inspired and learning-based clustering analysis with machine learning techniques for classification of EEG signals |
| title_sort | performance comparison of bio inspired and learning based clustering analysis with machine learning techniques for classification of eeg signals |
| topic | epilepsy EEG K-means clusters fuzzy C-means clusters Cuckoo search clusters Firefly clusters |
| url | https://www.frontiersin.org/articles/10.3389/frai.2023.1156269/full |
| work_keys_str_mv | AT sunilkumarprabhakar performancecomparisonofbioinspiredandlearningbasedclusteringanalysiswithmachinelearningtechniquesforclassificationofeegsignals AT dongokwon performancecomparisonofbioinspiredandlearningbasedclusteringanalysiswithmachinelearningtechniquesforclassificationofeegsignals |