Abstract—In this study, a data mining method based on PCA-GA is presented to characterize agricultural crops. Specifically it draws improvements to classification problems by using Principal Components Analysis (PCA) as a preprocessing method and a modified Genetic Algorithm (GA) as the function optimizer. The GA performs the optimization process, selecting the most suited set of features that determines the class of a crop it belongs to. The fitness function in GA is studied and modified accordingly using efficient distance measures. The soybean dataset is used in the experiment and results are compared with several classifiers. The experimental results show improved classification rates. This lessens the time consumed of agricultural researchers in characterizing agricultural crops.

Index Terms—Classification, data mining, genetic algorithm, k-NN, principal component analysis.

G. B. Dela Cruz is with the Institute of Engineering, Tarlac College of Agriculture, Camiling, Tarlac, Philippines, he is also with the Technological Institute of Philippines, Cubao, Quezon City, Philippines (e-mail: geridelacruz2002@yahoo.com.hk, delacruz.geri@gmail.com).
B. D. Gerardo is with Administration and Finance at the Western Visayas Stare University, La Paz, Iloilo City, Philippines. He is also with the Department of Information Technology at WVSU. (e-mail: bgerardo@wvsu.edu.ph).
B. C. Tanguilig III is with the Academic Affairs and concurrent Dean of the College of Information end Information Technology Education at the Technological Institute of the Philippines, Quezon City, Philippines (e-mail: bttanguilig_3@yahoo.com).

Cite:Geraldin B. Dela Cruz, Bobby D. Gerardo, and Bartolome T. Tanguilig III, "An Improved Data Mining Mechanism Based on PCA-GA for Agricultural Crops Characterization," International Journal of Computer and Communication Engineering vol. 3, no. 3, pp. 221-225, 2014.