Detection of Basal Stem Rot Disease Using Deep Learning

被引:4
|
作者
Haw, Yu Hong [1 ]
Hum, Yan Chai [2 ]
Chuah, Joon Huang [3 ]
Voon, Wingates [2 ]
Khairunniza-Bejo, Siti [4 ]
Husin, Nur Azuan [4 ]
Yee, Por Lip [5 ]
Lai, Khin Wee [1 ]
机构
[1] Univ Malaya, Dept Biomed Engn, Kuala Lumpur 50603, Malaysia
[2] Univ Tunku Abdul Rahman, Lee Kong Chian Fac Engn & Sci, Dept Mechatron & Biomed Engn, Kajang 43000, Selangor, Malaysia
[3] Univ Malaya, Fac Engn, Dept Elect Engn, Kuala Lumpur 50603, Malaysia
[4] Univ Putra Malaysia, Fac Engn, Dept Biol & Agr Engn, Serdang 43400, Selangor, Malaysia
[5] Univ Malaya, Fac Comp Sci & Informat Technol, Dept Comp Syst & Technol, Kuala Lumpur 50603, Malaysia
关键词
Crops; Vegetable oils; Biological system modeling; Diseases; Economics; Testing; Laser modes; Basal stem rot; convolutional neural network; deep learning; Ganoderma boninense; oil palm; terrestrial laser scanning; CLASSIFICATION;
D O I
10.1109/ACCESS.2023.3276763
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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 the feature extractor models and some of the fine-tuned models. However, fine-tuned models suffered from model overfitting due to dataset limitations. For future work, it is recommended to increase the sample size and utilize other CNN architectures 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.
引用
收藏
页码:49846 / 49862
页数:17
相关论文
共 50 条
  • [21] Plant Disease Detection Using Deep Learning
    Hirani, Ebrahim
    Magotra, Varun
    Jain, Jainam
    Bide, Pramod
    2021 6TH INTERNATIONAL CONFERENCE FOR CONVERGENCE IN TECHNOLOGY (I2CT), 2021,
  • [22] Detection of Leaf Disease Using Deep Learning A Deep Learning Based for Automated Detection.
    Agusthiyar, R.
    Devi, Shyamala J.
    Saravanabhavan, N. M.
    BIOSCIENCE BIOTECHNOLOGY RESEARCH COMMUNICATIONS, 2020, 13 (06): : 34 - 38
  • [23] Classifying the severity of basal stem rot disease in oil palm plantations using WorldView-3 imagery and machine learning algorithms
    Santoso, Heri
    Tani, Hiroshi
    Wang, Xuifeng
    Prasetyo, Agus Eko
    Sonobe, Rei
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 2019, 40 (19) : 7624 - 7646
  • [24] Optimization of machine learning classifier using multispectral data in assessment of Ganoderma basal stem rot (BSR) disease in oil palm plantation
    Baharim M.S.A.
    Adnan N.A.
    Mohd F.A.
    Seman I.A.
    Anuar M.I.
    Latif Z.A.
    Aziz N.A.
    Shahabuddin N.A.
    Nor S.M.
    International Journal of Information Technology, 2023, 15 (8) : 4259 - 4273
  • [25] Early Detection of Basal Stem Rot Disease in Oil Palm Tree Using Unmanned Aerial Vehicle-Based Hyperspectral Imaging
    Kurihara, Junichi
    Koo, Voon-Chet
    Guey, Cheaw Wen
    Lee, Yang Ping
    Abidin, Haryati
    REMOTE SENSING, 2022, 14 (03)
  • [26] Early detection of basal stem rot disease (Ganoderma) in oil palms based on hyperspectral reflectance data using pattern recognition algorithms
    Liaghat, Shohreh
    Ehsani, Reza
    Mansor, Shattri
    Shafri, Helmi Z. M.
    Meon, Sariah
    Sankaran, Sindhuja
    Azam, Siti H. M. N.
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 2014, 35 (10) : 3427 - 3439
  • [27] Molecular approaches to the elucidation of basal stem rot disease of oil palm
    Darmono, TW
    PROCEEDINGS OF THE BTIG WORKSHOP ON OIL PALM IMPROVEMENT THROUGH BIOTECHNOLOGY, 1998, : 83 - 94
  • [28] Detection of Basal Stem Rot (BSR) Infected Oil Palm Tree Using Laser Scanning Data
    Khairunniza-Bejo, Siti
    Vong, Chin Nee
    2ND INTERNATIONAL CONFERENCE ON AGRICULTURAL AND FOOD ENGINEERING (CAFE 2014) - NEW TRENDS FORWARD, 2014, 2 : 156 - 164
  • [29] DETECTING GANODERMA BASAL STEM ROT DISEASE ON OIL PALM USING ARTIFICIAL NEURAL NETWORK METHOD
    Hermantoro
    Kurniawan, Muhammad A.
    Trinugroho, Joko P.
    Suparyanto, Teddy
    Isnan, Mahmud
    Sudigyo, Digdo
    Pardamean, Bens
    COMMUNICATIONS IN MATHEMATICAL BIOLOGY AND NEUROSCIENCE, 2023,
  • [30] Development of classification models for basal stem rot (BSR) disease in oil palm using dielectric spectroscopy
    Khaled, Alfadhl Yahya
    Abd Aziz, Samsuzana
    Bejo, Siti Khairunniza
    Nawi, Nazmi Mat
    Abu Seman, Idris
    Izzuddin, Mohamad Anuar
    INDUSTRIAL CROPS AND PRODUCTS, 2018, 124 : 99 - 107