Optimizing Partition Granularity, Membership Function Parameters, and Rule Bases of Fuzzy Classifiers for Big Data by a Multi-objective Evolutionary Approach

Abstract

Background/Introduction -Classical data mining algorithms are considered inadequate to manage the volume, variety, velocity, and veracity aspects of Big Data. The advent of a number of open source cluster computing frameworks has opened new interesting perspectives for handling the volume and velocity features. In this context, thanks to their capability of coping with vague and imprecise information, distributed fuzzy models appear to be particularly suitable for handling the variety and veracity features of big data. Moreover, the interpretability of fuzzy models may assume a particular relevance in the context of big data mining.Methods -In this work, we propose a novel approach for generating, out of big data, a set of fuzzy rule-based classifiers characterized by different optimal trade-offs between accuracy and interpretability. We extend a state-of-theart distributed multi-objective evolutionary learning scheme, implemented under the Apache Spark environment. In particular, we exploit a recently proposed distributed fuzzy decision tree learning approach for generating an initial rule base that serves as input to the evolutionary process. Furthermore, we integrate the evolutionary learning scheme with an ad-hoc strategy for the granularity learning of the fuzzy partitions, along with the optimization of both the rule base and the fuzzy set parameters.Results and Conclusions -Experimental investigations show that the proposed approach is able to generate fuzzy rule-based classifiers that are significantly less complex than the ones generated by the original multi-objective evolutionary learning scheme, while keeping the same accuracy levels.

An overview of recent distributed algorithms for learning fuzzy models in Big Data classification

“…al algorithm achieve the worst results. On Sus dataset, the accuracies achieved [22,23,70] Global distributed Chi for Big Data CHI_BD [24] Distributed Fuzzy Associative Classifier based on Fuzzy Frequent Pattern DFAC-FFP [26] Distributed PAES with Rule and Condition Selection DPAES-RCS [27] Distributed PAES with Fuzzy Decision Tree and Granularity Learning DPAES-FDT-GL [29] Multi-way Fuzzy Decison Tree Multi-way FDT [25] Multi-way Fuzzy Decison Tree with Improved Fuzzy Partitioning FMDT l [30] by the remaining algorithms are similar. On HIG dataset, DFAC-FFP and DPAESs achieve accuracies up to 5% lower than the ones achieved by FDTs.…”

“…The parameters of the fuzzy sets are learnt concurrently with the RB. Recently, a novel version of DPAES-RCS, called DPAES-FDT-GL has been presented by Barsacchi et al in [29]. Here, the initial rule set is generated adopting the distributed FDT discussed in "Distributed Fuzzy Decision Trees" section and introduced by Segatori et al in [26].…”

“…More details regarding the chromosome coding, the mating operators and the PAES-RCS learning scheme can be found in the contributions of Ferranti et al in [27] and of Barsacchi et al in [29].…”

“…Since 2014, a number of contributions on fuzzy models for Big Data have been proposed in the literature, focusing on different application fields. Most of them regard the design, implementation and experimentation of fuzzy models for classification [21][22][23][24][25][26][27][28][29][30]. There also exist some contributions regarding regression tasks [31][32][33] and descriptive models, such as fuzzy clustering [34][35][36], subgroup discovery [37] and the generation of fuzzy association rules [38].…”

A Hybrid Systematic Review Approach on Complexity Issues in Data-Driven Fuzzy Inference Systems Development

“…GaneshKumar et al, 2014), and comparison of fuzzy numbers (Matarazzo and Munda, 2001). As the selected papers' analysis shows, this issue is analysed in tandem with complexity issue of fuzzy rules, like in Rajeswari and Deisy (2019), Ravi and Khare (2018), Barsacchi et al (2019).…”