Research Article
Leveraging the Power of MRMR in Machine Learning Models for Multi Class Classification of Rice to Promote Sustainable and Efficient Smart Farming
@INPROCEEDINGS{10.1007/978-3-031-77075-3_8, author={N. Silpa and Sangram Keshari Swain and V. V. R. Maheswara Rao}, title={Leveraging the Power of MRMR in Machine Learning Models for Multi Class Classification of Rice to Promote Sustainable and Efficient Smart Farming}, proceedings={Cognitive Computing and Cyber Physical Systems. 5th EAI International Conference, IC4S 2024, Bhimavaram, India, April 5--7, 2024, Proceedings, Part-I}, proceedings_a={IC4S}, year={2025}, month={2}, keywords={Rice Variety Classification Machine Learning Models Maximum Relevance Minimum Redundancy Feature Engineering}, doi={10.1007/978-3-031-77075-3_8} }- N. Silpa
Sangram Keshari Swain
V. V. R. Maheswara Rao
Year: 2025
Leveraging the Power of MRMR in Machine Learning Models for Multi Class Classification of Rice to Promote Sustainable and Efficient Smart Farming
IC4S
Springer
DOI: 10.1007/978-3-031-77075-3_8
Abstract
Rice variety classification is of significant importance in the agricultural domain since it allows for effective crop management, quality evaluation, and yield optimization. This research paper presents an intelligent system for automatic rice variety identification into multiple classes using machine learning techniques. The Maximum Relevance Minimum Redundancy (MRMR) attribute selection technique is used in the framework to discover the most important attributes from a large dataset, ensuring accurate and reliable classification. Various machine learning based classification techniques, including Decision Trees, K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Ensemble methods, Neural Networks (NN), and Naive Bayes, are explored in their different variants.
Series of experiments were conducted on a real-time dataset featuring multiple rice varieties to evaluate the performance of each classifier based on metrics such as accuracy, precision, recall, and F1 score. The study explores the effectiveness of the proposed framework, revealing that Ensemble machine learning, SVM and Neural Networks emerge as the optimal classifiers, achieving an impressive accuracy rate of 99.8% in the multi-class classification of rice varieties. The proposed framework empowers farmers and researchers to make informed decisions in crop management, resource allocation, and ensuring food security in agricultural practices.
