Detection of basal stem rot disease using deep learning
Palm oil industry is an important economic resource for Malaysia. However, an oil palm tree disease called Basal Stem Rot has impeded the production of palm oil , which caused significant economic loss at the same time. The oil palm tree disease is caused by a fungus known as Ganoderma Boninense. In...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Published: |
Institute of Electrical and Electronics Engineers
2023
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/107250/ |
| _version_ | 1848864869009326080 |
|---|---|
| author | Haw, Yu Hong Hum, Yan Chai Chuah, Joon Huang Voon, Wingates Bejo, Siti Khairunniza Husin, Nur Azuan Yee, Por Lip Lai, Khin Wee |
| author_facet | Haw, Yu Hong Hum, Yan Chai Chuah, Joon Huang Voon, Wingates Bejo, Siti Khairunniza Husin, Nur Azuan Yee, Por Lip Lai, Khin Wee |
| author_sort | Haw, Yu Hong |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Palm oil industry is an important economic resource for Malaysia. However, an oil palm tree disease called Basal Stem Rot has impeded the production of palm oil , which caused significant economic loss at the same time. The oil palm tree disease is caused by a fungus known as Ganoderma Boninense. Infected trees often have little to no symptoms during early stage of infection, which made early detection difficult. Early disease detection is necessary to allow early sanitization and disease control efforts. Using Terrestrial Laser Scanning technology, 88 grey-distribution canopy images of oil palm tree were obtained. The images were pre-processed and augmented before being used for training and testing of the deep learning models. The capabilities of the Convolution Neural Network deep learning models in the classification of dataset into healthy and non-healthy class were tested and the best performing model was identified based on the Macro-F1 score. Fine-tuned DenseNet121 model was the best performing model, recorded a Macro F1- score of 0.798. It was also noted that Baseline model showed a relatively remarkable macro-F1 score of 0.747, which was better than all feature extractor model and some fine-tuned models. However, fine-tuned models suffered from model overfitting due to the limitation on dataset. For future work, it is recommended to increase the sample size, utilize other CNN architectures and incorporate data augmentation for testing dataset to improve the model performance and progress towards detecting Basal Stem Rot at the early stage of infection by classifying sample images into multiple classes. |
| first_indexed | 2025-11-15T13:55:40Z |
| format | Article |
| id | upm-107250 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-15T13:55:40Z |
| publishDate | 2023 |
| publisher | Institute of Electrical and Electronics Engineers |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1072502024-10-17T01:56:33Z http://psasir.upm.edu.my/id/eprint/107250/ Detection of basal stem rot disease using deep learning Haw, Yu Hong Hum, Yan Chai Chuah, Joon Huang Voon, Wingates Bejo, Siti Khairunniza Husin, Nur Azuan Yee, Por Lip Lai, Khin Wee Palm oil industry is an important economic resource for Malaysia. However, an oil palm tree disease called Basal Stem Rot has impeded the production of palm oil , which caused significant economic loss at the same time. The oil palm tree disease is caused by a fungus known as Ganoderma Boninense. Infected trees often have little to no symptoms during early stage of infection, which made early detection difficult. Early disease detection is necessary to allow early sanitization and disease control efforts. Using Terrestrial Laser Scanning technology, 88 grey-distribution canopy images of oil palm tree were obtained. The images were pre-processed and augmented before being used for training and testing of the deep learning models. The capabilities of the Convolution Neural Network deep learning models in the classification of dataset into healthy and non-healthy class were tested and the best performing model was identified based on the Macro-F1 score. Fine-tuned DenseNet121 model was the best performing model, recorded a Macro F1- score of 0.798. It was also noted that Baseline model showed a relatively remarkable macro-F1 score of 0.747, which was better than all feature extractor model and some fine-tuned models. However, fine-tuned models suffered from model overfitting due to the limitation on dataset. For future work, it is recommended to increase the sample size, utilize other CNN architectures and incorporate data augmentation for testing dataset to improve the model performance and progress towards detecting Basal Stem Rot at the early stage of infection by classifying sample images into multiple classes. Institute of Electrical and Electronics Engineers 2023 Article PeerReviewed Haw, Yu Hong and Hum, Yan Chai and Chuah, Joon Huang and Voon, Wingates and Bejo, Siti Khairunniza and Husin, Nur Azuan and Yee, Por Lip and Lai, Khin Wee (2023) Detection of basal stem rot disease using deep learning. IEEE Access, 11. pp. 49846-49862. ISSN 2169-3536 https://ieeexplore.ieee.org/document/10124970 10.1109/ACCESS.2023.3276763 |
| spellingShingle | Haw, Yu Hong Hum, Yan Chai Chuah, Joon Huang Voon, Wingates Bejo, Siti Khairunniza Husin, Nur Azuan Yee, Por Lip Lai, Khin Wee Detection of basal stem rot disease using deep learning |
| title | Detection of basal stem rot disease using deep learning |
| title_full | Detection of basal stem rot disease using deep learning |
| title_fullStr | Detection of basal stem rot disease using deep learning |
| title_full_unstemmed | Detection of basal stem rot disease using deep learning |
| title_short | Detection of basal stem rot disease using deep learning |
| title_sort | detection of basal stem rot disease using deep learning |
| url | http://psasir.upm.edu.my/id/eprint/107250/ http://psasir.upm.edu.my/id/eprint/107250/ http://psasir.upm.edu.my/id/eprint/107250/ |