Detection of Ganoderma boninense diseases of palm oil trees using machine learning
About one-third of the world’s vegetable oil and fat supply is made up of palm oil, of which 75% is consumed as food. Palm oil is a vital economic resource for nations like Malaysia. The Basal Stem Rot disease of oil palm trees is one of many obstacles to the production of palm oil. The infection is...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
IEEE
2023
|
| _version_ | 1825949054438211584 |
|---|---|
| author | Yu, Hong Haw Zhao, Zhen Hum, Yan Chai Chuah, Joon Huang Voon, Wingates Bejo, Siti Khairunniza Husin, Nur Azuan Por, Lip Yee Lai, Khin Wee |
| author_facet | Yu, Hong Haw Zhao, Zhen Hum, Yan Chai Chuah, Joon Huang Voon, Wingates Bejo, Siti Khairunniza Husin, Nur Azuan Por, Lip Yee Lai, Khin Wee |
| author_sort | Yu, Hong Haw |
| collection | UPM |
| description | About one-third of the world’s vegetable oil and fat supply is made up of palm oil, of which 75% is consumed as food. Palm oil is a vital economic resource for nations like Malaysia. The Basal Stem Rot disease of oil palm trees is one of many obstacles to the production of palm oil. The infection is brought on by a fungus called Ganoderma Boninense, which colonizes trees. Early detection is difficult since the symptoms of infection are sometimes mild to non-existent. Terrestrial laser scanning was used to collect 88 photos of the oil palm tree’s grey-distribution canopy. The photos gathered were pre-processed to enhance the performance of the deep learning model. To train and verify the effectiveness of disease detection, a deep learning model called convolution neural network is used. The performance of disease detection is trained and tested using a convolutional neural network deep learning model, which divides the data into two classes: the healthy class and the non-healthy class. The improved DenseNet121 model reports a Macro F1-score of 0.7983. The model could only separate the images into two classes rather than categorizing the images into distinct infection levels, which is a limitation of our work. In order to investigate the feasibility of early oil palm disease diagnosis, it is advised for future research to undertake multi-class or multi-level classification using deep learning. |
| first_indexed | 2024-03-06T08:38:40Z |
| format | Conference or Workshop Item |
| id | upm.eprints-37542 |
| institution | Universiti Putra Malaysia |
| last_indexed | 2024-03-06T08:38:40Z |
| publishDate | 2023 |
| publisher | IEEE |
| record_format | dspace |
| spelling | upm.eprints-375422023-09-28T03:25:10Z http://psasir.upm.edu.my/id/eprint/37542/ Detection of Ganoderma boninense diseases of palm oil trees using machine learning Yu, Hong Haw Zhao, Zhen Hum, Yan Chai Chuah, Joon Huang Voon, Wingates Bejo, Siti Khairunniza Husin, Nur Azuan Por, Lip Yee Lai, Khin Wee About one-third of the world’s vegetable oil and fat supply is made up of palm oil, of which 75% is consumed as food. Palm oil is a vital economic resource for nations like Malaysia. The Basal Stem Rot disease of oil palm trees is one of many obstacles to the production of palm oil. The infection is brought on by a fungus called Ganoderma Boninense, which colonizes trees. Early detection is difficult since the symptoms of infection are sometimes mild to non-existent. Terrestrial laser scanning was used to collect 88 photos of the oil palm tree’s grey-distribution canopy. The photos gathered were pre-processed to enhance the performance of the deep learning model. To train and verify the effectiveness of disease detection, a deep learning model called convolution neural network is used. The performance of disease detection is trained and tested using a convolutional neural network deep learning model, which divides the data into two classes: the healthy class and the non-healthy class. The improved DenseNet121 model reports a Macro F1-score of 0.7983. The model could only separate the images into two classes rather than categorizing the images into distinct infection levels, which is a limitation of our work. In order to investigate the feasibility of early oil palm disease diagnosis, it is advised for future research to undertake multi-class or multi-level classification using deep learning. IEEE 2023 Conference or Workshop Item PeerReviewed Yu, Hong Haw and Zhao, Zhen and Hum, Yan Chai and Chuah, Joon Huang and Voon, Wingates and Bejo, Siti Khairunniza and Husin, Nur Azuan and Por, Lip Yee and Lai, Khin Wee (2023) Detection of Ganoderma boninense diseases of palm oil trees using machine learning. In: 13th IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE2023), 20-21 May 2023, Penang, Malaysia. (pp. 228-232). https://ieeexplore.ieee.org/document/10165368 10.1109/ISCAIE57739.2023.10165368 |
| spellingShingle | Yu, Hong Haw Zhao, Zhen Hum, Yan Chai Chuah, Joon Huang Voon, Wingates Bejo, Siti Khairunniza Husin, Nur Azuan Por, Lip Yee Lai, Khin Wee Detection of Ganoderma boninense diseases of palm oil trees using machine learning |
| title | Detection of Ganoderma boninense diseases of palm oil trees using machine learning |
| title_full | Detection of Ganoderma boninense diseases of palm oil trees using machine learning |
| title_fullStr | Detection of Ganoderma boninense diseases of palm oil trees using machine learning |
| title_full_unstemmed | Detection of Ganoderma boninense diseases of palm oil trees using machine learning |
| title_short | Detection of Ganoderma boninense diseases of palm oil trees using machine learning |
| title_sort | detection of ganoderma boninense diseases of palm oil trees using machine learning |
| work_keys_str_mv | AT yuhonghaw detectionofganodermaboninensediseasesofpalmoiltreesusingmachinelearning AT zhaozhen detectionofganodermaboninensediseasesofpalmoiltreesusingmachinelearning AT humyanchai detectionofganodermaboninensediseasesofpalmoiltreesusingmachinelearning AT chuahjoonhuang detectionofganodermaboninensediseasesofpalmoiltreesusingmachinelearning AT voonwingates detectionofganodermaboninensediseasesofpalmoiltreesusingmachinelearning AT bejositikhairunniza detectionofganodermaboninensediseasesofpalmoiltreesusingmachinelearning AT husinnurazuan detectionofganodermaboninensediseasesofpalmoiltreesusingmachinelearning AT porlipyee detectionofganodermaboninensediseasesofpalmoiltreesusingmachinelearning AT laikhinwee detectionofganodermaboninensediseasesofpalmoiltreesusingmachinelearning |