Quadratic programming for class ordering in rule induction
Citation
Yıldız, O. T. (2015). Quadratic programming for class ordering in rule induction. Pattern Recognition Letters, 54, 63-68. doi:10.1016/j.patrec.2014.12.002Abstract
Separate-and-conquer type rule induction algorithms such as Ripper, solve a K>2 class problem by converting it into a sequence of K - 1 two-class problems. As a usual heuristic, the classes are fed into the algorithm in the order of increasing prior probabilities. Although the heuristic works well in practice, there is much room for improvement. In this paper, we propose a novel approach to improve this heuristic. The approach transforms the ordering search problem into a quadratic optimization problem and uses the solution of the optimization problem to extract the optimal ordering. We compared new Ripper (guided by the ordering found with our approach) with original Ripper (guided by the heuristic ordering) on 27 datasets. Simulation results show that our approach produces rulesets that are significantly better than those produced by the original Ripper.
Source
Pattern Recognition LettersVolume
54Related items
Showing items related by title, author, creator and subject.
-
Harmonic mappings related to close-to-convex functions of complex order b
Polatoğlu, Yaşar (Işık University Press, 2014)Let CC(b) be the class of functions close-to-convex functions of order b, and let SH be the class of harmonic mappings in the plane. In the present paper we investigate harmonic mappings related to close-to-convex functions ... -
Sufficient conditions for generalized Sakaguchi type functions of order β
Mathur, A. Trilok; Mathur, Ruchi; Sinha, C. Deepa (Işık University Press, 2014)In this paper, we obtain some sufficient conditions for generalized Sakaguchi type function of order β, defined on the open unit disk. Many interesting outcomes of our results are also calculated. -
Runs based on discrete order statistics
Stepanov, Alexei (Işık University Press, 2011-08-16)In the present paper, we study runs based on discrete order statistics. Limit results for the total number of such runs and the length of the longest run are derived.