Hemp Disease Detection and Classification Using Machine Learning
2020 International Conferences on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics)
In smart agriculture, disease detection and classification for diverse plants in farm fields is very important and critical in agriculture quality production. According to industry reports in the United States, the HEMP market is growing an annual rate of 34 percent, from 4.6 billion in 2019 to 26.6 billion in 2025. In hemp production, diseases and bugs may easily cause farmers to lose their profits up to 11% of hemp production value. This paper reports our recent machine learning research results in hemp disease detection and classification using a data-driven machine learning approach. This paper presents our pioneer research project on hemp disease detect and classification results. Unlike other existing research in plan disease detection using machine learning in agriculture production, we have applied transfer learning approaches based on three existing deep learning models (CNN, VGG16, and AlexNet), and present comparative research results. In addition, a detailed hemp data collection, preparation, and training process is presented and the detailed validation results are reported.
CNN, Hemp disease detection and classification, Inception V3, machine learning, Smart agriculture, Transfer Learning, VGG-16
Jing Zhu, Tianhao Yu, Sen Zheng, Chenguang Niu, Jerry Gao, and Jerome Tang. "Hemp Disease Detection and Classification Using Machine Learning" 2020 International Conferences on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics) (2020): 878-887. https://doi.org/10.1109/iThings-GreenCom-CPSCom-SmartData-Cybermatics50389.2020.00151