Abstract:
Purpose: The most often published international journal articles are shown to discover the study fields that are most interested in ML in agriculture. In all, 129 journals were pertinent to the topic of the course. Remote sensing, as a general point, was important because satellite data, for example, provides significant input data for ML systems. Agricultural sustainability, smart farming, and the environment were also major concerns. There was also a high frequency of journals related to computational approaches. Methods that combine various stimuli to make a choice are referred to as EL in this context. One kind of inducer receives labelled samples and builds a model capable of generalizing these examples. As a result, more unlabelled cases may be predicted. Weed identification methods relied heavily on images as input data. Photos derived from in-situ measurements and multispectral images from the aforementioned sources were used to create these images. Regression-based multivariate statistical approaches are the most efficient for indirect selection. Artificial neural networks (ANN) may be used in plant tissue culture research to perform pattern recognition, nonlinear regression, and classification due to their ability to process binary information, continuous information, categorical information, and fuzzy information. A target function is used to establish a starting population and an evaluation of an individual's fitness at the beginning of the process. Accuracy necessitates the acquisition of a big dataset. Each picture in each category has its own set of characteristics that we've extracted. GLCM texture extraction and edge detection are used to extract the features, and the degree of moisture content is measured using these two techniques. Using pixel values, these characteristics define the plant's current state. As an analytical tool, moisture content is one of the most important factors.....

Cite:
Adlin Jebakumari S, Dr. A. Jayanthiladevi,"Using Machine Learning tools and Techniques, Genetic Disease Analysis Prediction on agriculture crops using AI & ML", IARJSET International Advanced Research Journal in Science, Engineering and Technology, vol. 10, no. 12, pp. 178-192, 2023, Crossref https://doi.org/10.17148/IARJSET.2023.101224.

| DOI: 10.17148/IARJSET.2023.101224