Simpl_eClass: Simplified potential-free evolving fuzzy rule-based classifiers

Abstract

This paper presents the sequel of evolving fuzzy rule-based classifier eClass, called here as simplified evolving classifier, simpl_eClass. Similarly to eClass, simpl_eClass comprises of two different classifiers, namely zero and first order (simpl_eClass0 and simpl_eClass1). The two classifiers differ from each other in terms of the consequent part of the fuzzy rules, and the classification strategy used. The design of simpl_eClass is based on the density increment principle introduced recently in so called simpl_eTS+ approach. The rule learning in simpl_eClass does not involve computation of potential values that allows it to attain computationally much less expensive model update phase compared to eClass. As compared to other FRB classifiers, it retains all the advantages of eClass, such as being on-line and evolving, having zero and first order. In comparison with other non-fuzzy classifiers it has the advantage of interpretability and transparency (especially zero order type). The goals of this paper are to demonstrate the applicability of simpl_eTS+ to classification task, and to empirically show that the simplification of eClass to simpl_eClass by using potential-free approach does not compromise the accuracy of the classifiers. In order to attain the goals, the classifiers are tested by performing several experiments using benchmark data sets. The simpl_eClass1 classifier is also applied to the real-life problem of on-line scene categorization for low-resource devices benefiting from its low computational cost. The results obtained from the experiments endorse that simpl_eClass achieves the accuracy of eClass while simplifying rule learning process.

Automatic scene recognition for low-resource devices using evolving classifiers

“…On the other hand, the determination of focal points in simpl_eClass1 requires only mean value calculation, and it can be calculated recursively as each sample arrives (same as in simpl_eTS+ [32]). Thus, in simpl_eClass1 the computational complexity is reduced from O(N) to O(1) -by a factor of N. A detailed description of simpl_eClass1 is presented in [30].…”

“…In this paper we use evolving fuzzy-rule based (FRB) classifiers of the eClass family [8], namely eClass1 [8] and a simplified version called simpl_eClass1 [30]. The evolving classifiers are characterized by self-learning of both structure and parameters and use evolving Takagi-Sugeno FRB models [31].…”

“…The consequent parameters of the rules are estimated using weighted recursive least squares (wRLS) approach [31]. Simpl_eClass1 differs from eClass1 mainly due to the learning mechanism which is potential/density free [30]. In order to determine whether an incoming sample is a new focal point, eClass1 requires calculation of a potential/density value [8], [31] for the incoming sample and update of potentials/densities of all the existing focal points.…”

Fault detection and identification methodology under an incremental learning framework applied to industrial electromechanical systems

“…based on eClass algorithms, in [78], based on simpleClass, or in [53], based on AutoClass. All of them provide an evolving and online solution for fault diagnosis under low-computational cost requirements.…”

Implementação e análise de algoritmos evolutivos de classificação em espaço de alta dimensão

“…Evoluir pode compreender a compressão ou a expansão da estrutura, sendo essa composta por regras em sistemas nebulosos, neurônios em redes neurais artiĄcias ou ambos em sistemas híbridos. ClassiĄcadores evolutivos que atendem essa deĄnição incluem: AnYa-Class (ANGELOV; YAGER, 2011), eClass (ANGELOV; ZHOU, 2008), FLEXFIS-Class (LUGHOFER et al, 2007) e Simpl_eClass (BARUAH et al, 2011). Lughofer (2011b) analisa o comportamento do classiĄcador evolutivo FLEXFIS-Class para processar dados com 17, 52 e 74 atributos.…”