A DEEP LEARNING TRANSFER-BASED MODEL FOR PANAMA DISEASE DETECTION
DOI:
https://doi.org/10.56238/revgeov16n4-073Keywords:
Deep Learning, Detection, Panama DiseaseAbstract
Deep learning approaches are applicable to the banana (Musa spp.) production process. The Panama disease phytopathology can cause losses of up to 100% in the crop. As a detection mechanism, image feature extraction techniques can be applied through Deep Transfer Learning (DTL). This work aims to apply and evaluate a DTL algorithm capable of classifying this disease using 102 images of diseased banana leaves and 264 healthy ones. Six pre-trained state-of-the-art neural models were tested and evaluated based on: accuracy (ACC), f1-score (F1), area under the curve (AUC), and mean squared error (MSE). All models achieved accuracy above 98%. The agile detection should assist banana farmers in making timely decisions.
Downloads
References
ALMEYDA, Estefani; IPANAQUÉ, William. Recent developments of artificial intelligence for banana: Application areas, learning algorithms, and future challenges. Engenharia Agrícola, v. 42, p. e20210144, 2022.
ATHIRAJA, A.; VIJAYAKUMAR, P. Retracted article: Banana disease diagnosis using computer vision and machine learning methods. Journal of Ambient Intelligence and Humanized Computing, v. 12, n. 6, p. 6537-6556, 2021.
AZIMI, Sepideh Alsadat et al. Classification of radioxenon spectra with deep learning algorithm. Journal of Environmental Radioactivity, v. 237, p. 106718, 2021.
ABOU BAKER, Nermeen; ZENGELER, Nico; HANDMANN, Uwe. A transfer learning evaluation of deep neural networks for image classification. Machine Learning and Knowledge Extraction, v. 4, n. 1, p. 22-41, 2022.
BEGUM, A. Sumaiya et al. Diagnosis of leaf disease using enhanced convolutional neural network. Int. J. Innov. Res. Appl. Sci. Eng, v. 3, n. 12, p. 579-586, 2020.
CARNEIRO, Tiago et al. Performance analysis of google colaboratory as a tool for accelerating deep learning applications. Ieee Access, v. 6, p. 61677-61685, 2018.
CODEVASF. Formoso A/H. 2022. Disponível em: <https://www.codevasf.gov.br/linhasde-negocio/irrigacao/projetos-publicos-de irrigacao/elenco-de-projetos/emproducao/formoso-a-h>.
DHAKA, Vijaypal Singh et al. A survey of deep convolutional neural networks applied for prediction of plant leaf diseases. Sensors, v. 21, n. 14, p. 4749, 2021.
EMBRAPA. Banana. 2022. Disponível em: <https://www.embrapa.br/agencia-de-informacaotecnologica/cultivos/banana>.
EUNICE, Jennifer et al. Deep learning-based leaf disease detection in crops using images for agricultural applications. Agronomy, v. 12, n. 10, p. 2395, 2022.
GAURAPPAWAR, P. et al. Banana leaf and stem disease detection by using classification technique. IJFMR-International Journal For Multidisciplinary Research, IJFMR, v. 2, n. 1, p. 1-4, 2020.
GAUTAM, Vinay et al. A transfer learning-based artificial intelligence model for leaf disease assessment. Sustainability, v. 14, n. 20, p. 13610, 2022.
HAILU, Y. Banana leaf disease images. Mendeley Data, v. 1, 2021. 7
KAWATRA, Mihir; AGARWAL, Shreyas; KAPUR, Raghu. Leaf disease detection using neural network hybrid models. In: 2020 IEEE 5th international conference on computing communication and automation (ICCCA). IEEE, 2020. p. 225-230.
KHAMPARIA, Aditya et al. Seasonal crops disease prediction and classification using deep convolutional encoder network. Circuits, Systems, and Signal Processing, v. 39, n. 2, p. 818-836, 2020.
KRISHNAN, V. Gokula et al. An automated segmentation and classification model for banana leaf disease detection. Journal of Applied Biology and Biotechnology, v. 10, n. 1, p. 213-220, 2022.
LI, Lili; ZHANG, Shujuan; WANG, Bin. Plant disease detection and classification by deep learning—a review. IEEE access, v. 9, p. 56683-56698, 2021.
MAHENDRAN, T.; SEETHARAMAN, K. Banana Leaf Disease Detection Using Glcm Based Feature Extraction And Classification Using Deep Convoluted Neural Networks (Dcnn). Journal of Positive School Psychology, v. 6, n. 10, 2022.
MEDHI, Epsita; DEB, Nabamita. PSFD-Musa: A dataset of banana plant, stem, fruit, leaf, and disease. Data in brief, v. 43, p. 108427, 2022.
MUHAMMAD, Marinah; ZAWAWI, Muhammad Akmal Mohd; JEMALI, N. Incorporating the Plant Disease Triangle Framework for Analyzing the Effect of FWB Incidence on Soil Attributes. Israa University Journal of Applied Science, 2023.
MUTASA, Simukayi; SUN, Shawn; HA, Richard. Understanding artificial intelligence based radiology studies: What is overfitting?. Clinical imaging, v. 65, p. 96-99, 2020.
NANDHINI, M. et al. Applicability of deep learning techniques for crop protection in plantain tree cultivation. Indian Journal of Computer Science and Engineering, v. 12, n. 1, p. 1-9, 2021.
RAGHAVENDRA, S. et al. Deep learning based dual channel banana grading system using convolution neural network. Journal of Food Quality, v. 2022, 2022.
RIDHOVAN, Andreanov et al. Disease detection in banana leaf plants using densenet and inception method. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), v. 6, n. 5, p. 710-718, 2022.
SANGEETHA, Ramachandran et al. An improved agro deep learning model for detection of Panama wilts disease in banana leaves. AgriEngineering, v. 5, n. 2, p. 660-679, 2023.
STRASHKO, Artem; STOUDENMIRE, E. Miles. Generalization and overfitting in matrix product state machine learning architectures. arXiv preprint arXiv:2208.04372, 2022.
TEJASWINI, Pallapothala et al. Rice leaf disease classification using CNN. In: IOP Conference Series: Earth and Environmental Science. IOP Publishing, 2022. p. 012017.
TSAI, Cheng-Fa; CHEN, Yu-Chieh; TSAI, Chia-En. Real life image recognition of Panama disease by an effective deep learning approach. In: 2019 International Conference on Machine Learning and Cybernetics (ICMLC). IEEE, 2019. p. 1-5.
TUGRUL, Bulent; ELFATIMI, Elhoucine; ERYIGIT, Recep. Convolutional neural networks in detection of plant leaf diseases: A review. Agriculture, v. 12, n. 8, p. 1192, 2022.
YADHAV, S. Yegneshwar et al. Plant disease detection and classification using cnn model with optimized activation function. In: 2020 international conference on electronics and sustainable communication systems (ICESC). IEEE, 2020. p. 564-569.
