International Journal of Science, Engineering and TechnologyAuthors: Swapnil Wagh, Ruchi Sharma, Ankit Temurnikar
Abstract: In the field of contemporary agriculture, the challenge of early recognition of plant diseases is one of the most vital occurrence since the possibility of consequential factors directly influences the harvest, food security, and economical continueance. Although data mining method has demonstrated much promise in identifying useful patterns in agricultural data sets, given its tendency to enumerate complicated interaction of attributes and the ability to notice patterns that are not observed or visible, it frequently has difficulty distinguishing the core. To handle the shortcomings, this research paper suggests an Optimization-Enhanced Data Mining Framework which combines modern data optimization algorithms with conventional methods of data mining in detection of the plant diseases. The systematically preprocesses the agriculture data, includes attribute and symptom variations, and makes use of optimization that is used to find out non-linear and combinatorial impacts that are not usually apparent to the conventional mining strategies. The comparison of all the parametric conditions (a change of the attributes, the effects of a combination of several methods, or the effects of a combination of several modulations) through the means of an experiment proved that optimization integration may contribute significantly to an increase in the disease detection accuracy, device strength, and prolonged computations. Findings have also shown a significant change in false detection trends and improvement in identifying indicators of subtle diseases, thus making the structure applicable in practice and as a component of agricultural decision-making systems. This study also bridges the gap between pattern mining and optimization-based learning in making the study feel scalable and versatile to vulnerable applications by the intelligent detection of plant disease. The results emphasize impact of preciseness data mining that is optimization-enhanced to enhance agricultural tools in managing the disease as well as disease diagnosis activities and sustainable farming in serving purpose of precision agriculture.
DOI: https://doi.org/10.5281/zenodo.19448564
