Comparing the Performance of Classification Algorithms in the Conservation of Plant Genetic Resources for Agriculture and Food Security

Plant germplasm for agriculture and eatable safety are essential for ensuring food security and sustainable agriculture. It is crucial to conserve these resources for future generations. Conservationists often classify plant genetic resources into long-term, medium-term, and short-term conservation categories, which helps them prioritize their efforts and allocate resources effectively. Data mining has become increasingly helpful in identifying beneficial genetic traits and optimizing conservation strategies. Leveraging the power of data mining, conservationists can make informed decisions that will help safeguard our planet's plant genetic resources for generations to come. The performance of the decision tree, support vector machine, Naive Bayes, and K-Nearest Neighbor are measured and compared. The comparison involves measuring accuracy as well as the error values. The Decision Tree algorithm achieved the highest accuracy value of 95 %, while the SVM algorithm achieved the lowest with 77.50 %. This prediction can help conservationists in taking necessary measures for the future.