A Moth–Flame Optimized Echo State Network and Triplet Feature Extractor for Epilepsy Electro-Encephalography Signals
The analysis of epilepsy electro-encephalography (EEG) signals is of great significance for the diagnosis of epilepsy, which is one of the common neurological diseases of all age groups. With the developments of machine learning, many data-driven models have achieved great performance in EEG signals...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/6/1438 |
| _version_ | 1797610268235137024 |
|---|---|
| author | Xue-song Tang Luchao Jiang Kuangrong Hao Tong Wang Xiaoyan Liu |
| author_facet | Xue-song Tang Luchao Jiang Kuangrong Hao Tong Wang Xiaoyan Liu |
| author_sort | Xue-song Tang |
| collection | DOAJ |
| description | The analysis of epilepsy electro-encephalography (EEG) signals is of great significance for the diagnosis of epilepsy, which is one of the common neurological diseases of all age groups. With the developments of machine learning, many data-driven models have achieved great performance in EEG signals classification. However, it is difficult to select appropriate hyperparameters for the models to file a specific task. In this paper, an evolutionary algorithm enhanced model is proposed, which optimizes the fixed weights of the reservoir layer of the echo state network (ESN) according to the specific task. As evaluating a feature extractor relies heavily on the classifiers, a new feature distribution evaluation function (FDEF) using the label information of EEG signals is defined as the fitness function, which is an objective way to evaluate the performance of a feature extractor that not only focuses on the degree of dispersion, but also considers the relation amongst triplets. The performance of the proposed method is verified on the Bonn University dataset with an accuracy of 98.16% and on the CHB-MIT dataset with the highest sensitivity of 96.14%. The proposed method outperforms the previous EEG methods, as it can automatically optimize the hyperparameters of ESN to adjust the structure and initial parameters for a specific classification task. Furthermore, the optimization direction by using FDEF as the fitness of MFO no longer relies on the performance of the classifier but on the relative separability amongst classes. |
| first_indexed | 2024-03-11T06:13:00Z |
| format | Article |
| id | doaj.art-0bf39ddd55dc421888daca4671ecb2cc |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-11T06:13:00Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-0bf39ddd55dc421888daca4671ecb2cc2023-11-17T12:28:37ZengMDPI AGMathematics2227-73902023-03-01116143810.3390/math11061438A Moth–Flame Optimized Echo State Network and Triplet Feature Extractor for Epilepsy Electro-Encephalography SignalsXue-song Tang0Luchao Jiang1Kuangrong Hao2Tong Wang3Xiaoyan Liu4Faculty of Information Science, Donghua University, Shanghai 201620, ChinaFaculty of Information Science, Donghua University, Shanghai 201620, ChinaFaculty of Information Science, Donghua University, Shanghai 201620, ChinaFaculty of Information Science, Donghua University, Shanghai 201620, ChinaFaculty of Information Science, Donghua University, Shanghai 201620, ChinaThe analysis of epilepsy electro-encephalography (EEG) signals is of great significance for the diagnosis of epilepsy, which is one of the common neurological diseases of all age groups. With the developments of machine learning, many data-driven models have achieved great performance in EEG signals classification. However, it is difficult to select appropriate hyperparameters for the models to file a specific task. In this paper, an evolutionary algorithm enhanced model is proposed, which optimizes the fixed weights of the reservoir layer of the echo state network (ESN) according to the specific task. As evaluating a feature extractor relies heavily on the classifiers, a new feature distribution evaluation function (FDEF) using the label information of EEG signals is defined as the fitness function, which is an objective way to evaluate the performance of a feature extractor that not only focuses on the degree of dispersion, but also considers the relation amongst triplets. The performance of the proposed method is verified on the Bonn University dataset with an accuracy of 98.16% and on the CHB-MIT dataset with the highest sensitivity of 96.14%. The proposed method outperforms the previous EEG methods, as it can automatically optimize the hyperparameters of ESN to adjust the structure and initial parameters for a specific classification task. Furthermore, the optimization direction by using FDEF as the fitness of MFO no longer relies on the performance of the classifier but on the relative separability amongst classes.https://www.mdpi.com/2227-7390/11/6/1438epilepsy detectionmoth–flame optimizationecho state networkfeature extractionEEG signals |
| spellingShingle | Xue-song Tang Luchao Jiang Kuangrong Hao Tong Wang Xiaoyan Liu A Moth–Flame Optimized Echo State Network and Triplet Feature Extractor for Epilepsy Electro-Encephalography Signals Mathematics epilepsy detection moth–flame optimization echo state network feature extraction EEG signals |
| title | A Moth–Flame Optimized Echo State Network and Triplet Feature Extractor for Epilepsy Electro-Encephalography Signals |
| title_full | A Moth–Flame Optimized Echo State Network and Triplet Feature Extractor for Epilepsy Electro-Encephalography Signals |
| title_fullStr | A Moth–Flame Optimized Echo State Network and Triplet Feature Extractor for Epilepsy Electro-Encephalography Signals |
| title_full_unstemmed | A Moth–Flame Optimized Echo State Network and Triplet Feature Extractor for Epilepsy Electro-Encephalography Signals |
| title_short | A Moth–Flame Optimized Echo State Network and Triplet Feature Extractor for Epilepsy Electro-Encephalography Signals |
| title_sort | moth flame optimized echo state network and triplet feature extractor for epilepsy electro encephalography signals |
| topic | epilepsy detection moth–flame optimization echo state network feature extraction EEG signals |
| url | https://www.mdpi.com/2227-7390/11/6/1438 |
| work_keys_str_mv | AT xuesongtang amothflameoptimizedechostatenetworkandtripletfeatureextractorforepilepsyelectroencephalographysignals AT luchaojiang amothflameoptimizedechostatenetworkandtripletfeatureextractorforepilepsyelectroencephalographysignals AT kuangronghao amothflameoptimizedechostatenetworkandtripletfeatureextractorforepilepsyelectroencephalographysignals AT tongwang amothflameoptimizedechostatenetworkandtripletfeatureextractorforepilepsyelectroencephalographysignals AT xiaoyanliu amothflameoptimizedechostatenetworkandtripletfeatureextractorforepilepsyelectroencephalographysignals AT xuesongtang mothflameoptimizedechostatenetworkandtripletfeatureextractorforepilepsyelectroencephalographysignals AT luchaojiang mothflameoptimizedechostatenetworkandtripletfeatureextractorforepilepsyelectroencephalographysignals AT kuangronghao mothflameoptimizedechostatenetworkandtripletfeatureextractorforepilepsyelectroencephalographysignals AT tongwang mothflameoptimizedechostatenetworkandtripletfeatureextractorforepilepsyelectroencephalographysignals AT xiaoyanliu mothflameoptimizedechostatenetworkandtripletfeatureextractorforepilepsyelectroencephalographysignals |