A layer-sensitivity based artificial neural network for characterization of oil palm fruitlets
This paper presents an intelligent means of addressing characterization and grading problems in the oil palm industry for the purpose of quality control. A Layer-Sensitivity Based Artificial Neural Network (LSB_ANN) which updates its layer weights based on sensitivity analysis was designed to predic...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Published: |
Chaoyang University of Technology
2021
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/95759/ |
| _version_ | 1848862215599292416 |
|---|---|
| author | Adedayo, Ojo O. Onibonoje, Moses Isa, Maryam |
| author_facet | Adedayo, Ojo O. Onibonoje, Moses Isa, Maryam |
| author_sort | Adedayo, Ojo O. |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | This paper presents an intelligent means of addressing characterization and grading problems in the oil palm industry for the purpose of quality control. A Layer-Sensitivity Based Artificial Neural Network (LSB_ANN) which updates its layer weights based on sensitivity analysis was designed to predict the oil content and dielectric constant of mature oil palm fruitlets. The LSB_ANN was designed, optimized and trained with 604 data points obtained from laboratory microwave coaxial sensor measurements within 2-
4 GHz. The performance evaluation of the model when tested with a separate set of data showed that the properties of the fruitlets were accurately modeled. To further investigate the generalization ability of the trained neural network, three other neural network training algorithms were deployed for the same dataset. A multi-criteria evaluation of the performances of the networks showed that the proposed LSB_ANN outperformed the other three in generalization accuracy, time and computing resources. The LSB_ANN therefore represents a handy tool for rapid and intelligent characterization of oil palm fruitlets for quality control and research purposes. |
| first_indexed | 2025-11-15T13:13:29Z |
| format | Article |
| id | upm-95759 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-15T13:13:29Z |
| publishDate | 2021 |
| publisher | Chaoyang University of Technology |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-957592023-04-04T06:40:18Z http://psasir.upm.edu.my/id/eprint/95759/ A layer-sensitivity based artificial neural network for characterization of oil palm fruitlets Adedayo, Ojo O. Onibonoje, Moses Isa, Maryam This paper presents an intelligent means of addressing characterization and grading problems in the oil palm industry for the purpose of quality control. A Layer-Sensitivity Based Artificial Neural Network (LSB_ANN) which updates its layer weights based on sensitivity analysis was designed to predict the oil content and dielectric constant of mature oil palm fruitlets. The LSB_ANN was designed, optimized and trained with 604 data points obtained from laboratory microwave coaxial sensor measurements within 2- 4 GHz. The performance evaluation of the model when tested with a separate set of data showed that the properties of the fruitlets were accurately modeled. To further investigate the generalization ability of the trained neural network, three other neural network training algorithms were deployed for the same dataset. A multi-criteria evaluation of the performances of the networks showed that the proposed LSB_ANN outperformed the other three in generalization accuracy, time and computing resources. The LSB_ANN therefore represents a handy tool for rapid and intelligent characterization of oil palm fruitlets for quality control and research purposes. Chaoyang University of Technology 2021 Article PeerReviewed Adedayo, Ojo O. and Onibonoje, Moses and Isa, Maryam (2021) A layer-sensitivity based artificial neural network for characterization of oil palm fruitlets. International Journal of Applied Science and Engineering, 18 (1). pp. 1-7. ISSN 1727-2394; ESSN: 1727-7841 https://gigvvy.com/journals/ijase/articles/18/1/ 10.6703/IJASE.202103_18(1).011 |
| spellingShingle | Adedayo, Ojo O. Onibonoje, Moses Isa, Maryam A layer-sensitivity based artificial neural network for characterization of oil palm fruitlets |
| title | A layer-sensitivity based artificial neural network for characterization of oil palm fruitlets |
| title_full | A layer-sensitivity based artificial neural network for characterization of oil palm fruitlets |
| title_fullStr | A layer-sensitivity based artificial neural network for characterization of oil palm fruitlets |
| title_full_unstemmed | A layer-sensitivity based artificial neural network for characterization of oil palm fruitlets |
| title_short | A layer-sensitivity based artificial neural network for characterization of oil palm fruitlets |
| title_sort | layer-sensitivity based artificial neural network for characterization of oil palm fruitlets |
| url | http://psasir.upm.edu.my/id/eprint/95759/ http://psasir.upm.edu.my/id/eprint/95759/ http://psasir.upm.edu.my/id/eprint/95759/ |