An Improved Equilibrium Optimizer Algorithm and Its Application in LSTM Neural Network
An improved equilibrium optimizer (EO) algorithm is proposed in this paper to address premature and slow convergence. Firstly, a highly stochastic chaotic mechanism is adopted to initialize the population for range expansion. Secondly, the capability to conduct global search to jump out of local opt...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/13/9/1706 |
| _version_ | 1797517164590137344 |
|---|---|
| author | Pu Lan Kewen Xia Yongke Pan Shurui Fan |
| author_facet | Pu Lan Kewen Xia Yongke Pan Shurui Fan |
| author_sort | Pu Lan |
| collection | DOAJ |
| description | An improved equilibrium optimizer (EO) algorithm is proposed in this paper to address premature and slow convergence. Firstly, a highly stochastic chaotic mechanism is adopted to initialize the population for range expansion. Secondly, the capability to conduct global search to jump out of local optima is enhanced by assigning adaptive weights and setting adaptive convergence factors. In addition 25 classical benchmark functions are used to validate the algorithm. As revealed by the analysis of the accuracy, speed, and stability of convergence, the IEO algorithm proposed in this paper significantly outperforms other meta-heuristic algorithms. In practice, the distribution is asymmetric because most logging data are unlabeled. Traditional classification models have difficulty in accurately predicting the location of oil layer. In this paper, the oil layers related to oil exploration are predicted using long short-term memory (LSTM) networks. Due to the large amount of data used, however, it is difficult to adjust the parameters. For this reason, an improved equilibrium optimizer algorithm (IEO) is applied to optimize the parameters of LSTM for improved performance, while the effective IEO-LSTM is applied for oil layer prediction. As indicated by the results, the proposed model outperforms the current popular optimization algorithms including particle swarm algorithm PSO and genetic algorithm GA in terms of accuracy, absolute error, root mean square error and mean absolute error. |
| first_indexed | 2024-03-10T07:11:00Z |
| format | Article |
| id | doaj.art-dc2dd570bb2448028e17567e06e1f3da |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-10T07:11:00Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-dc2dd570bb2448028e17567e06e1f3da2023-11-22T15:28:47ZengMDPI AGSymmetry2073-89942021-09-01139170610.3390/sym13091706An Improved Equilibrium Optimizer Algorithm and Its Application in LSTM Neural NetworkPu Lan0Kewen Xia1Yongke Pan2Shurui Fan3School of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, ChinaSchool of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, ChinaSchool of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, ChinaSchool of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, ChinaAn improved equilibrium optimizer (EO) algorithm is proposed in this paper to address premature and slow convergence. Firstly, a highly stochastic chaotic mechanism is adopted to initialize the population for range expansion. Secondly, the capability to conduct global search to jump out of local optima is enhanced by assigning adaptive weights and setting adaptive convergence factors. In addition 25 classical benchmark functions are used to validate the algorithm. As revealed by the analysis of the accuracy, speed, and stability of convergence, the IEO algorithm proposed in this paper significantly outperforms other meta-heuristic algorithms. In practice, the distribution is asymmetric because most logging data are unlabeled. Traditional classification models have difficulty in accurately predicting the location of oil layer. In this paper, the oil layers related to oil exploration are predicted using long short-term memory (LSTM) networks. Due to the large amount of data used, however, it is difficult to adjust the parameters. For this reason, an improved equilibrium optimizer algorithm (IEO) is applied to optimize the parameters of LSTM for improved performance, while the effective IEO-LSTM is applied for oil layer prediction. As indicated by the results, the proposed model outperforms the current popular optimization algorithms including particle swarm algorithm PSO and genetic algorithm GA in terms of accuracy, absolute error, root mean square error and mean absolute error.https://www.mdpi.com/2073-8994/13/9/1706equilibrium optimizer algorithmadaptive inertia weightsIEO-LSTMoil layer prediction |
| spellingShingle | Pu Lan Kewen Xia Yongke Pan Shurui Fan An Improved Equilibrium Optimizer Algorithm and Its Application in LSTM Neural Network Symmetry equilibrium optimizer algorithm adaptive inertia weights IEO-LSTM oil layer prediction |
| title | An Improved Equilibrium Optimizer Algorithm and Its Application in LSTM Neural Network |
| title_full | An Improved Equilibrium Optimizer Algorithm and Its Application in LSTM Neural Network |
| title_fullStr | An Improved Equilibrium Optimizer Algorithm and Its Application in LSTM Neural Network |
| title_full_unstemmed | An Improved Equilibrium Optimizer Algorithm and Its Application in LSTM Neural Network |
| title_short | An Improved Equilibrium Optimizer Algorithm and Its Application in LSTM Neural Network |
| title_sort | improved equilibrium optimizer algorithm and its application in lstm neural network |
| topic | equilibrium optimizer algorithm adaptive inertia weights IEO-LSTM oil layer prediction |
| url | https://www.mdpi.com/2073-8994/13/9/1706 |
| work_keys_str_mv | AT pulan animprovedequilibriumoptimizeralgorithmanditsapplicationinlstmneuralnetwork AT kewenxia animprovedequilibriumoptimizeralgorithmanditsapplicationinlstmneuralnetwork AT yongkepan animprovedequilibriumoptimizeralgorithmanditsapplicationinlstmneuralnetwork AT shuruifan animprovedequilibriumoptimizeralgorithmanditsapplicationinlstmneuralnetwork AT pulan improvedequilibriumoptimizeralgorithmanditsapplicationinlstmneuralnetwork AT kewenxia improvedequilibriumoptimizeralgorithmanditsapplicationinlstmneuralnetwork AT yongkepan improvedequilibriumoptimizeralgorithmanditsapplicationinlstmneuralnetwork AT shuruifan improvedequilibriumoptimizeralgorithmanditsapplicationinlstmneuralnetwork |