Scientometric Analysis of Tomato Leaf Disease Classification using Artificial Intelligence

Timely detection of leaf issues is crucial for ad- vancing the national economy. This study intends to acquire the knowledge on detecting the leaf-related diseases. Nevertheless, it is essential to note that plant diseases can impact many parts of the plant. This study covers the articles published related to the multispectral or hyperspectral imaging from the year 2010 to 2024 to analyze the agricultural diseases. Leaf diseases are categorized using machine learning and deep learning models. This study has created a workflow system to assist researchers. Commonly employed leaf disease prediction models encompass Random Forest (RF), Support Vector Machine (SVM), and Multiple Twin Support Vector Machine (MTM). Various conventional deep-learning models are commonly employed for performing leaf disease identification. The models encompassed in this list are CNNs, DCNNs, BPNNs, DenseNet, LeafNet, and LeNet. The three most efficient deep- learning models for leaf disease identification are CNN, VGG, and ResNet. Typically, the effectiveness of an algorithm is assessed by measuring its F1 score, accuracy, precision, and other metrics. This research study aims to assist researchers in identifying suitable machine learning and deep learning-based classifiers for diagnosing the leaf diseases.