We present a methodology to analyze Multiple Classifiers Systems (MCS) performance, using the disagreement concept. The goal is to define an alternative approach to the conventional recognition rate criterion, which usually requires an exhaustive combination search. This approach defines a Distance-based Disagreement (DbD) measure using an Euclidean distance computed between confusion matrices and a soft-correlation rule to indicate the most likely candidates to the best classifiers ensemble. As case study, we apply this strategy to two different handwritten recognition systems. Experimental results indicate that the method proposed can be used as a low-cost alternative to conventional approaches.

No abstract

No abstract

The purpose of this work was to study the influence of soybean biodiesel addition in ultra-low sulfur diesel (ULSD) on its tribological behavior under low-amplitude reciprocating conditions, simulating the operation of a fuel injector system. The methodology was divided into three parts: the first was the fuel preparation and its physicochemical characterization, where were studied four fuels (diesel, soybean biodiesel, and mixtures of them).The following step was the evaluation of the fuel tribological properties, using the high-frequency reciprocating rig (HFRR) test. These tests were carried out by steel ball-on-disk lubricated contact, on which the friction coefficient of friction (COF), the film percentage, and the wear scar diameter (WSD) were measured, according to ASTM D6079-11. In the end, the analysis of the damages presented on the worn disk surfaces was characterized by scanning electronic microscopy (SEM) and atomic force microscopy (AFM) techniques. Results showed that the addition of biodiesel to ULSD is an excellent option to restore the lubricating ability of this fuel. The biodiesel incorporation reduces the friction coefficient and improves the film formation. Besides, the evaluation of worn disk surfaces using SEM and AFM techniques showed that biodiesel avoids damages to surface through protective film formation and reduces the superficial roughness.

We present a methodology to analyze Multiple Classifiers Systems (MCS) performance, using the diversity concept. The goal is to define an alternative approach to the conventional recognition rate criterion, which usually requires an exhaustive combination search. This approach defines a Distance-based Disagreement (DbD) measure using an Euclidean distance computed between confusion matrices and a soft-correlation rule to indicate the most likely candidates to the best classifiers ensemble. As case study, we apply this strategy to two different handwritten recognition systems. Experimental results indicate that the method proposed can be used as a low-cost alternative to conventional approaches.