Artificial Bee Colony Algorithm Based on Dimensional Memory Mechanism and Adaptive Elite Population for Training Artificial Neural Networks
Based on dimensional memory mechanism and adaptive elite population, this paper proposes a satisfactory and efficient artificial bee colony algorithm (DMABC_elite) to solve optimization problems and train artificial neural networks (ANN). DMABC_elite proposes the concept of ada...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10268445/ |
| _version_ | 1797357888689143808 |
|---|---|
| author | Yiyang Zhang Bao Pang Yong Song Qingyang Xu Xianfeng Yuan |
| author_facet | Yiyang Zhang Bao Pang Yong Song Qingyang Xu Xianfeng Yuan |
| author_sort | Yiyang Zhang |
| collection | DOAJ |
| description | Based on dimensional memory mechanism and adaptive elite population, this paper proposes a satisfactory and efficient artificial bee colony algorithm (DMABC_elite) to solve optimization problems and train artificial neural networks (ANN). DMABC_elite proposes the concept of adaptive elite population that changes dynamically with the search process, and modifies the search equations for employed and onlooker bee phases on this basis. In addition, a dimensional memory mechanism has been introduced that allows multi-dimensional updates, which improves exploitation and speeds up convergence. Next, a new selection strategy and a Lévy flight-based solution-generating method are introduced in the scout bee phase to enhance the global search ability. Finally, the performance of DMABC_elite on two different problem groups is analyzed experimentally. On the one hand, DMABC_elite is evaluated using 22 classical benchmark functions with different dimensions and CEC 2013 test functions. Compared with basic ABC and nine state-of-the-art ABC variants, DMABC_elite achieved better results, ranking first in all 10-, 30- and 100-dimensional tests across 22 classical benchmark functions and 30-dimensional tests across CEC 2013 test functions. On the other hand, DMABC_elite is compared with traditional backpropagation-based algorithms and other ABC variants when training seven different ANNs. The results show that DMABC_elite is efficient and competitive in training ANNs. |
| first_indexed | 2024-03-08T14:51:55Z |
| format | Article |
| id | doaj.art-04d57ef2d7554172bec205e6eee6b9c8 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T14:51:55Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-04d57ef2d7554172bec205e6eee6b9c82024-01-11T00:01:56ZengIEEEIEEE Access2169-35362023-01-011110761610763710.1109/ACCESS.2023.332102310268445Artificial Bee Colony Algorithm Based on Dimensional Memory Mechanism and Adaptive Elite Population for Training Artificial Neural NetworksYiyang Zhang0https://orcid.org/0000-0002-6348-0430Bao Pang1https://orcid.org/0000-0002-1172-1036Yong Song2https://orcid.org/0000-0003-2505-2766Qingyang Xu3https://orcid.org/0000-0003-3870-5551Xianfeng Yuan4https://orcid.org/0000-0002-6217-6429School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, ChinaSchool of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, ChinaSchool of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, ChinaSchool of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, ChinaSchool of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, ChinaBased on dimensional memory mechanism and adaptive elite population, this paper proposes a satisfactory and efficient artificial bee colony algorithm (DMABC_elite) to solve optimization problems and train artificial neural networks (ANN). DMABC_elite proposes the concept of adaptive elite population that changes dynamically with the search process, and modifies the search equations for employed and onlooker bee phases on this basis. In addition, a dimensional memory mechanism has been introduced that allows multi-dimensional updates, which improves exploitation and speeds up convergence. Next, a new selection strategy and a Lévy flight-based solution-generating method are introduced in the scout bee phase to enhance the global search ability. Finally, the performance of DMABC_elite on two different problem groups is analyzed experimentally. On the one hand, DMABC_elite is evaluated using 22 classical benchmark functions with different dimensions and CEC 2013 test functions. Compared with basic ABC and nine state-of-the-art ABC variants, DMABC_elite achieved better results, ranking first in all 10-, 30- and 100-dimensional tests across 22 classical benchmark functions and 30-dimensional tests across CEC 2013 test functions. On the other hand, DMABC_elite is compared with traditional backpropagation-based algorithms and other ABC variants when training seven different ANNs. The results show that DMABC_elite is efficient and competitive in training ANNs.https://ieeexplore.ieee.org/document/10268445/Artificial bee colony algorithmadaptive elite populationdimensional memory mechanismsearch equationartificial neural network |
| spellingShingle | Yiyang Zhang Bao Pang Yong Song Qingyang Xu Xianfeng Yuan Artificial Bee Colony Algorithm Based on Dimensional Memory Mechanism and Adaptive Elite Population for Training Artificial Neural Networks IEEE Access Artificial bee colony algorithm adaptive elite population dimensional memory mechanism search equation artificial neural network |
| title | Artificial Bee Colony Algorithm Based on Dimensional Memory Mechanism and Adaptive Elite Population for Training Artificial Neural Networks |
| title_full | Artificial Bee Colony Algorithm Based on Dimensional Memory Mechanism and Adaptive Elite Population for Training Artificial Neural Networks |
| title_fullStr | Artificial Bee Colony Algorithm Based on Dimensional Memory Mechanism and Adaptive Elite Population for Training Artificial Neural Networks |
| title_full_unstemmed | Artificial Bee Colony Algorithm Based on Dimensional Memory Mechanism and Adaptive Elite Population for Training Artificial Neural Networks |
| title_short | Artificial Bee Colony Algorithm Based on Dimensional Memory Mechanism and Adaptive Elite Population for Training Artificial Neural Networks |
| title_sort | artificial bee colony algorithm based on dimensional memory mechanism and adaptive elite population for training artificial neural networks |
| topic | Artificial bee colony algorithm adaptive elite population dimensional memory mechanism search equation artificial neural network |
| url | https://ieeexplore.ieee.org/document/10268445/ |
| work_keys_str_mv | AT yiyangzhang artificialbeecolonyalgorithmbasedondimensionalmemorymechanismandadaptiveelitepopulationfortrainingartificialneuralnetworks AT baopang artificialbeecolonyalgorithmbasedondimensionalmemorymechanismandadaptiveelitepopulationfortrainingartificialneuralnetworks AT yongsong artificialbeecolonyalgorithmbasedondimensionalmemorymechanismandadaptiveelitepopulationfortrainingartificialneuralnetworks AT qingyangxu artificialbeecolonyalgorithmbasedondimensionalmemorymechanismandadaptiveelitepopulationfortrainingartificialneuralnetworks AT xianfengyuan artificialbeecolonyalgorithmbasedondimensionalmemorymechanismandadaptiveelitepopulationfortrainingartificialneuralnetworks |