Internet of Thing and Machine Learning Approach for Agricultural Application: A Review
Pranita Kolhe, Kamlesh Kalbande, Atul Deshmukh
Abstract
Plants provide a significant portion of the global food supply. Plant infections are a factor in productivity loss, although they can be avoided with constant observation. Plant illness detection by hand is time-consuming and a mistake. Earlier diagnosis of fungal pathogens with computer vision and artificial intelligence (AI) can assist decrease illness severity and overcoming the limitations of continuous human observation. There have been significant advances in the creation of plant illness identification, and classifying systems based on “Machine Learning (ML) and Deep Learning (DL)” models, with a sample of assessment of several plant leaf illness classification techniques displayed with tables. In this article, we conduct a comprehensive literature review on the applications of state-of-the-art Machine, and Deep Learning techniques for plant disease categorization, including Support Vector Machine, Convolutional Neural Network, K-Nearest Neighbor, Naive Bayes, and other prevalent Machine learning algorithms, as well as AlexNet, GoogleNet, VGGNet, and other prevalent Deep learning techniques. Every algorithm can be defined by the processing techniques used, such as image segmentation and extraction and classification, as well as the standardized experimental-setup metrics used, such as the total number of training/testing datasets used, the number of diseases considered, the category of classification model used, and the classifier performance.