This paper aims to improve the response performance of min-max modular classifier by a module selection policy for two-class classification during recognition. We propose an efficient base classifier selection algorithm. We show that the quadratic complexity of original min-max modular classifier can fall onto the level of linear complexity in the number of base-classifier modules for each inpu...

In the last decades many classification methods and fusers have been developed. Considerable gains have been achieved in the classification performance by fusing and combining different classifiers. We experiment a new method for ship infrared imagery recognition based on the fusion of individual results in order to obtain a more reliable decision [1]. To optimize the results of every class of ...

We discussed the role of data complexity measures in the evaluation of classification algorithms performance. Knowing characteristics of benchmark data sets it is possible to check which algorithms perform well in the context of scarce data. To fully utilise this information, we present a graphical performance measure called generalisation curve. It is based on learning curve concept and allows...

In this paper we present a new type of binary classifier defined on the unit cube. This classifier combines some of the aspects of the standard methods that have been used in the logical analysis of data (LAD) and geometric classifiers, with a nearest-neighbor paradigm. We assess the predictive performance of the new classifier in learning from a sample, obtaining generalization error bounds th...

This paper analyzes the human performance of recognizing drunk speakers merely by voice and compares the results with the performance of an automatic statistical classifier. The study is carried out within the Interspeech 2011 Speaker State Challenge [1] employing the Alcohol Language Corpus (ALC) [2]. The 79 subjects yielded an average performance of 55.8% unweighted accuracy on a balanced int...

An approach to construct a new classifier called an intuitionistic fuzzy decision tree is presented. Well known benchmark data is used to analyze the performance of the classifier. The results are compared to some other popular classification algorithms. Finally, the classifier behavior is verified while solving a real-world classification problem.

We propose a winner-takes-all (WTA) classifier for structures represented by graphs. WTA classification follows the principle elimination of competition. The input structure is assigned to the class corresponding to the winner of the competition. In experiments we investigate the performance of the WTA classifier and compare it with the canonical maximum similarity (MS) classifier.