Browsing by Subject "Feature projections"

Now showing 1 - 3 of 3

Open Access
Learning feature-projection based classifiers
(Pergamon Press, 2012-03) Dayanik, A.
This paper aims at designing better performing feature-projection based classification algorithms and presents two new such algorithms. These algorithms are batch supervised learning algorithms and represent induced classification knowledge as feature intervals. In both algorithms, each feature participates in the classification by giving real-valued votes to classes. The prediction for an unseen example is the class receiving the highest vote. The first algorithm, OFP.MC, learns on each feature pairwise disjoint intervals which minimize feature classification error. The second algorithm. GFP.MC, constructs feature intervals by greedily improving the feature classification error. The new algorithms are empirically evaluated on twenty datasets from the UCI repository and are compared with the existing feature-projection based classification algorithms (FILIF, VFI5, CFP, k-NNFP, and NBC). The experiments demonstrate that the OFP.MC algorithm outperforms other feature-projection based classification algorithms. The GFP.MC algorithm is slightly inferior to the OFP.MC algorithm, but, if it is used for datasets with large number of instances, then it reduces the space requirement of the OFP.MC algorithm. The new algorithms are insensitive to boundary noise unlike the other feature-projection based classification algorithms considered here. (C) 2011 Elsevier Ltd. All rights reserved.
Open Access
Regression by selecting best feature(s)
(2000) Aydın, Tolga
Two new machine learning methods, Regression by Selecting Best Feature Projections (RSBFP) and Regression by Selecting Best Features (RSBF), are presented for regression problems. These methods heavily make use of least squares regression to induce eager, parametric and context-sensitive models. Famous regression approaches of machine learning and statistics literature such as DART, MARS, RULE and kNN can not construct models that are both predictive and have reasonable training and/or querying time durations. We developed RSBFP and RSBF to fill the gap in the literature for a regression method having higher predictive accuracy and faster training and querying time durations. RSBFP constructs a decision list consisting of simple linear regression lines belonging to linear features and/or categorical feature segments. RSBF is the extended version of RSBFP such that the decision list consists of both simple, belonging to categorical feature segments, and/or multiple, belonging to linear features, linear regression lines. A relevancy heuristic has been developed to determine the features involved in the multiple regression lines. It is shown that the proposed methods are robust to irrelevant features, missing feature values and target feature noise, which make them suitable prediction tools for real-world databases. In terms of robustness, RSBFP and RSBF give better results when compared to other famous regression methods.
Open Access
Voting features based classifier with feature construction and its application to predicting financial distress
(Pergamon Press, 2010) Güvenir, H. A.; Çakır, M.
Voting features based classifiers, shortly VFC, have been shown to perform well on most real-world data sets. They are robust to irrelevant features and missing feature values. In this paper, we introduce an extension to VFC, called voting features based classifier with feature construction, VFCC for short, and show its application to the problem of predicting if a bank will encounter financial distress, by analyzing current financial statements. The previously developed VFC learn a set of rules that contain a single condition based on a single feature in their antecedent. The VFCC algorithm proposed in this work, on the other hand, constructs rules whose antecedents may contain conjuncts based on several features. Experimental results on recent financial ratios of banks in Turkey show that the VFCC algorithm achieves better accuracy than other well-known rule learning classification algorithms. © 2009 Elsevier Ltd. All rights reserved.