Machine Learning Algorithms for Early Detection of Legume Crop Disease

Abstract

Background: Legume crops are an essential component of global agriculture and are widely supplied for human consumption, livestock feed and soil improvement due to their vital nutritional nature. The economic and nutritional significance of legumes is threatened by a multitude of diseases that can cause substantial yield losses. Traditional methods for disease detection, relying on visual inspection, are often subjective and inefficient, leading to delayed intervention. Methods: This study investigates the utilization of machine learning algorithms for the early identification of diseases affecting legume crops. A comprehensive evaluation is conducted on machine learning algorithms, namely Support Vector Machines (SVM) and Convolutional Neural Networks (CNN) with respect to the domain of disease detection. Through a comparative analysis of their performance across different environmental conditions and phases of crop development, this study also explores their strengths and weaknesses. Result: The findings and comparative examination offered significant perspectives on the potential of machine learning algorithms in the realm of early legume crop disease detection. In addition to enhancing crop health and disease management, the research provides support for sustainable agricultural practices and possesses the capacity to augment environmental sustainability and food security through the application of machine learning techniques.

Dynamic Reconfiguration Using Signal Processing for Artificial Intelligence

“…Their three-LDPCcode decoder is built using their architecture and development methodology. Additionally, decoders may switch in milliseconds in real time while saving approximately half the hardware logic required [5]. Wu et al (2020) were of opinion that over the last several years, developers have seen a rising disparity between the complexity and efficiency of application development.…”

“…It's worth noting that plant and animal studies, particularly in the realm of agricultural and life sciences (AL), face analogous computational challenges. In AL research, tasks such as genomic analysis, phenotyping, and ecological modeling require substantial computational resources [5,6]. Additionally, machine learning algorithms are increasingly being employed for real-time fraud detection and risk assessment, leveraging the power of signal processing techniques to analyze vast amounts of financial data [7].…”

Development of Artificial Intelligence Education Programs Centered on Deep Learning Principles

“…Artificial intelligence makes machines think and act similarly to human and includes concepts such as big data and machine learning. Machine learning, which is the basis of artificial intelligence, is a concept defined by Arthur Samuel in 1959 as "the field of learning actions that are not commanded as code, but as data developed into algorithms for machines to execute (Christoph & Daniel, 2013;Park, 2020;Falah 2021;AlZubi, 2023;Cho, 2024).…”