Determination of Optimal Initial Weights of an Artificial Neural Network by Using the Harmony Search Algorithm: Application to Breakwater Armor Stones
In this study, an artificial neural network (ANN) model is developed to predict the stability number of breakwater armor stones based on the experimental data reported by Van der Meer in 1988. The harmony search (HS) algorithm is used to determine the near-global optimal initial weights in the train...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2076-3417/6/6/164 |
| _version_ | 1819091625549234176 |
|---|---|
| author | Anzy Lee Zong Woo Geem Kyung-Duck Suh |
| author_facet | Anzy Lee Zong Woo Geem Kyung-Duck Suh |
| author_sort | Anzy Lee |
| collection | DOAJ |
| description | In this study, an artificial neural network (ANN) model is developed to predict the stability number of breakwater armor stones based on the experimental data reported by Van der Meer in 1988. The harmony search (HS) algorithm is used to determine the near-global optimal initial weights in the training of the model. The stratified sampling is used to sample the training data. A total of 25 HS-ANN hybrid models are tested with different combinations of HS algorithm parameters. The HS-ANN models are compared with the conventional ANN model, which uses a Monte Carlo simulation to determine the initial weights. Each model is run 50 times and the statistical analyses are conducted for the model results. The present models using stratified sampling are shown to be more accurate than those of previous studies. The statistical analyses for the model results show that the HS-ANN model with proper values of HS algorithm parameters can give much better and more stable prediction than the conventional ANN model. |
| first_indexed | 2024-12-21T22:42:42Z |
| format | Article |
| id | doaj.art-c621f9156fae4ce184416495dd569b53 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-21T22:42:42Z |
| publishDate | 2016-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-c621f9156fae4ce184416495dd569b532022-12-21T18:47:48ZengMDPI AGApplied Sciences2076-34172016-05-016616410.3390/app6060164app6060164Determination of Optimal Initial Weights of an Artificial Neural Network by Using the Harmony Search Algorithm: Application to Breakwater Armor StonesAnzy Lee0Zong Woo Geem1Kyung-Duck Suh2Department of Civil and Environmental Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, KoreaDepartment of Energy and Information Technology, Gachon University, 1342 Seongnamdae-ro, Sujeong-gu, Seongnam-si, Gyeonggi-do 13120, KoreaDepartment of Civil and Environmental Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, KoreaIn this study, an artificial neural network (ANN) model is developed to predict the stability number of breakwater armor stones based on the experimental data reported by Van der Meer in 1988. The harmony search (HS) algorithm is used to determine the near-global optimal initial weights in the training of the model. The stratified sampling is used to sample the training data. A total of 25 HS-ANN hybrid models are tested with different combinations of HS algorithm parameters. The HS-ANN models are compared with the conventional ANN model, which uses a Monte Carlo simulation to determine the initial weights. Each model is run 50 times and the statistical analyses are conducted for the model results. The present models using stratified sampling are shown to be more accurate than those of previous studies. The statistical analyses for the model results show that the HS-ANN model with proper values of HS algorithm parameters can give much better and more stable prediction than the conventional ANN model.http://www.mdpi.com/2076-3417/6/6/164armor stonesartificial neural networkharmony search algorithmrubble mound structurestability number |
| spellingShingle | Anzy Lee Zong Woo Geem Kyung-Duck Suh Determination of Optimal Initial Weights of an Artificial Neural Network by Using the Harmony Search Algorithm: Application to Breakwater Armor Stones Applied Sciences armor stones artificial neural network harmony search algorithm rubble mound structure stability number |
| title | Determination of Optimal Initial Weights of an Artificial Neural Network by Using the Harmony Search Algorithm: Application to Breakwater Armor Stones |
| title_full | Determination of Optimal Initial Weights of an Artificial Neural Network by Using the Harmony Search Algorithm: Application to Breakwater Armor Stones |
| title_fullStr | Determination of Optimal Initial Weights of an Artificial Neural Network by Using the Harmony Search Algorithm: Application to Breakwater Armor Stones |
| title_full_unstemmed | Determination of Optimal Initial Weights of an Artificial Neural Network by Using the Harmony Search Algorithm: Application to Breakwater Armor Stones |
| title_short | Determination of Optimal Initial Weights of an Artificial Neural Network by Using the Harmony Search Algorithm: Application to Breakwater Armor Stones |
| title_sort | determination of optimal initial weights of an artificial neural network by using the harmony search algorithm application to breakwater armor stones |
| topic | armor stones artificial neural network harmony search algorithm rubble mound structure stability number |
| url | http://www.mdpi.com/2076-3417/6/6/164 |
| work_keys_str_mv | AT anzylee determinationofoptimalinitialweightsofanartificialneuralnetworkbyusingtheharmonysearchalgorithmapplicationtobreakwaterarmorstones AT zongwoogeem determinationofoptimalinitialweightsofanartificialneuralnetworkbyusingtheharmonysearchalgorithmapplicationtobreakwaterarmorstones AT kyungducksuh determinationofoptimalinitialweightsofanartificialneuralnetworkbyusingtheharmonysearchalgorithmapplicationtobreakwaterarmorstones |