Hemp disease detection and classification using machine learning and deep learning

Publication Date

12-1-2020

Document Type

Conference Proceeding

Publication Title

2020 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom)

DOI

10.1109/ISPA-BDCloud-SocialCom-SustainCom51426.2020.00121

First Page

762

Last Page

769

Abstract

Hemp is a multipurpose plant that has industrial as well as medicinal value. The plant is easy to grow, maintain, and suitable under any climate. However, just like other plants, Hemp diseases affect plant growth and cause a significant economic loss in hemp production. With the rapid advancement of artificial intelligence and machine learning technology, researchers have started using data-driven machine learning approaches in smart agriculture and farming. Plant disease detection and classification is an application of the smart agriculture technique. This paper focuses on hemp disease detection and classification by proposing one SVM-based machine learning model and three deep learning ensemble models. The focused hemp diseases include Hemp Powdery Mildew, Hemp Leaf Spot, Hemp Bud Rot, and Hemp Nutrient Deficiency. The paper uses pre-trained deep learning ensemble models with transfer learning. It reports comparative evaluation results of the three deep learning ensemble models with an SVM-based model with manual feature extraction. The evaluation results from different models show as high as 98% accuracy with strong application potential.

Keywords

Deep learning, Feature extraction, Hemp disease detection and classification, Machine learning, Model training, Smart agriculture, Transfer learning

Department

Computer Engineering

Link to Full Text

Share

COinS