Optimization the Initial Weights of Artificial Neural Networks via Genetic Algorithm Applied to Hip Bone Fracture Prediction
This paper aims to find the optimal set of initial weights to enhance the accuracy of artificial neural networks (ANNs) by using genetic algorithms (GA). The sample in this study included 228 patients with first low-trauma hip fracture and 215 patients without hip fracture, both of them were intervi...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2012-01-01
|
| Series: | Advances in Fuzzy Systems |
| Online Access: | http://dx.doi.org/10.1155/2012/951247 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832550207611469824 |
|---|---|
| author | Yu-Tzu Chang Jinn Lin Jiann-Shing Shieh Maysam F. Abbod |
| author_facet | Yu-Tzu Chang Jinn Lin Jiann-Shing Shieh Maysam F. Abbod |
| author_sort | Yu-Tzu Chang |
| collection | DOAJ |
| description | This paper aims to find the optimal set of initial weights to enhance the accuracy of artificial neural networks (ANNs) by using genetic algorithms (GA). The sample in this study included 228 patients with first low-trauma hip fracture and 215 patients without hip fracture, both of them were interviewed with 78 questions. We used logistic regression to select 5 important factors (i.e., bone mineral density, experience of fracture, average hand grip strength, intake of coffee, and peak expiratory flow rate) for building artificial neural networks to predict the probabilities of hip fractures. Three-layer (one hidden layer) ANNs models with back-propagation training algorithms were adopted. The purpose in this paper is to find the optimal initial weights of neural networks via genetic algorithm to improve the predictability. Area under the ROC curve (AUC) was used to assess the performance of neural networks. The study results showed the genetic algorithm obtained an AUC of 0.858±0.00493 on modeling data and 0.802 ± 0.03318 on testing data. They were slightly better than the results of our previous study (0.868±0.00387 and 0.796±0.02559, resp.). Thus, the preliminary study for only using simple GA has been proved to be effective for improving the accuracy of artificial neural networks. |
| format | Article |
| id | doaj-art-3f7c85c58d0b496eaa55e228a0ea1c8f |
| institution | Kabale University |
| issn | 1687-7101 1687-711X |
| language | English |
| publishDate | 2012-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Fuzzy Systems |
| spelling | doaj-art-3f7c85c58d0b496eaa55e228a0ea1c8f2025-02-03T06:07:28ZengWileyAdvances in Fuzzy Systems1687-71011687-711X2012-01-01201210.1155/2012/951247951247Optimization the Initial Weights of Artificial Neural Networks via Genetic Algorithm Applied to Hip Bone Fracture PredictionYu-Tzu Chang0Jinn Lin1Jiann-Shing Shieh2Maysam F. Abbod3Department of Mechanical Engineering, Yuan Ze University, 32003 Chungli, TaiwanDepartment of Orthopaedic Surgery, National Taiwan University Hospital, Taipei, TaiwanDepartment of Mechanical Engineering, Yuan Ze University, 32003 Chungli, TaiwanSchool of Engineering and Design, Brunel University, London, UKThis paper aims to find the optimal set of initial weights to enhance the accuracy of artificial neural networks (ANNs) by using genetic algorithms (GA). The sample in this study included 228 patients with first low-trauma hip fracture and 215 patients without hip fracture, both of them were interviewed with 78 questions. We used logistic regression to select 5 important factors (i.e., bone mineral density, experience of fracture, average hand grip strength, intake of coffee, and peak expiratory flow rate) for building artificial neural networks to predict the probabilities of hip fractures. Three-layer (one hidden layer) ANNs models with back-propagation training algorithms were adopted. The purpose in this paper is to find the optimal initial weights of neural networks via genetic algorithm to improve the predictability. Area under the ROC curve (AUC) was used to assess the performance of neural networks. The study results showed the genetic algorithm obtained an AUC of 0.858±0.00493 on modeling data and 0.802 ± 0.03318 on testing data. They were slightly better than the results of our previous study (0.868±0.00387 and 0.796±0.02559, resp.). Thus, the preliminary study for only using simple GA has been proved to be effective for improving the accuracy of artificial neural networks.http://dx.doi.org/10.1155/2012/951247 |
| spellingShingle | Yu-Tzu Chang Jinn Lin Jiann-Shing Shieh Maysam F. Abbod Optimization the Initial Weights of Artificial Neural Networks via Genetic Algorithm Applied to Hip Bone Fracture Prediction Advances in Fuzzy Systems |
| title | Optimization the Initial Weights of Artificial Neural Networks via Genetic Algorithm Applied to Hip Bone Fracture Prediction |
| title_full | Optimization the Initial Weights of Artificial Neural Networks via Genetic Algorithm Applied to Hip Bone Fracture Prediction |
| title_fullStr | Optimization the Initial Weights of Artificial Neural Networks via Genetic Algorithm Applied to Hip Bone Fracture Prediction |
| title_full_unstemmed | Optimization the Initial Weights of Artificial Neural Networks via Genetic Algorithm Applied to Hip Bone Fracture Prediction |
| title_short | Optimization the Initial Weights of Artificial Neural Networks via Genetic Algorithm Applied to Hip Bone Fracture Prediction |
| title_sort | optimization the initial weights of artificial neural networks via genetic algorithm applied to hip bone fracture prediction |
| url | http://dx.doi.org/10.1155/2012/951247 |
| work_keys_str_mv | AT yutzuchang optimizationtheinitialweightsofartificialneuralnetworksviageneticalgorithmappliedtohipbonefractureprediction AT jinnlin optimizationtheinitialweightsofartificialneuralnetworksviageneticalgorithmappliedtohipbonefractureprediction AT jiannshingshieh optimizationtheinitialweightsofartificialneuralnetworksviageneticalgorithmappliedtohipbonefractureprediction AT maysamfabbod optimizationtheinitialweightsofartificialneuralnetworksviageneticalgorithmappliedtohipbonefractureprediction |