Author(s):

Puneet Dheer, Purshottam and Vinod Singh

Abstract: Machine learning models viz., Logistic Regression, Linear Discriminant Analysis, K-Nearest Neighbor’s and Naïve-Bayes were studied for their accuracy, precision and recall accommodating 100 samples each of five most important metric traits namely, plant height, number of fertile tillers/plant, spike length, number of spikelets/spike and number of grains /spikes in seven diverse and promising wheat varieties (DBW 14, Halana, NW 1012, NW 2036, Raj. 3077, UP 2338 and WH 147) in order to use the best one model for classifying the varieties. The average accuracy of Logistic Regression, Linear Discriminant Analysis, K-Nearest Neighbor’s and Naïve-Bayes was 97.32%, 98.57%, 99.38% and 98.78%, respectively. The precision and recall of test data set of all 7 varieties were 100%. The K-NN model was thus found to be out performed over other models under studied and could therefore effectively be utilized for characterizing, classifying and or identifying the wheat varieties.

Pages: 47-49  |  1866 Views  483 Downloads

Download (632KB)