Optimizing artificial neural network architectures for enhanced soil type classification
- Authors
- Aydin, Yaren; Bekdas, Gebrail; Isikdag, Uemit; Nigdeli, Sinan Melih; Geem, Zong Woo
- Issue Date
- May-2024
- Publisher
- TECHNO-PRESS
- Keywords
- artificial neural networks; bio-inspired methods; hyperparameter optimization; soil classification
- Citation
- GEOMECHANICS AND ENGINEERING, v.37, no.3, pp 263 - 277
- Pages
- 15
- Journal Title
- GEOMECHANICS AND ENGINEERING
- Volume
- 37
- Number
- 3
- Start Page
- 263
- End Page
- 277
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/92143
- DOI
- 10.12989/gae.2024.37.3.263
- ISSN
- 2005-307X
2092-6219
- Abstract
- Artificial Neural Networks (ANNs) are artificial learning algorithms that provide successful results in solving many machine learning problems such as classification, prediction, object detection, object segmentation, image and video classification. There is an increasing number of studies that use ANNs as a prediction tool in soil classification. The aim of this research was to understand the role of hyperparameter optimization in enhancing the accuracy of ANNs for soil type classification. The research results has shown that the hyperparameter optimization and hyperparamter optimized ANNs can be utilized as an efficient mechanism for increasing the estimation accuracy for this problem. It is observed that the developed hyperparameter tool (HyperNetExplorer) that is utilizing the Covariance Matrix Adaptation Evolution Strategy (CMAES), Genetic Algorithm (GA) and Jaya Algorithm (JA) optimization techniques can be successfully used for the discovery of hyperparameter optimized ANNs, which can accomplish soil classification with 100% accuracy.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/92143)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.