A distributed approach to multi-objective evolutionary generation of fuzzy rule-based classifiers from big data

Ferranti, Andrea; Marcelloni, Francesco; Segatori, Armando; Antonelli, Michela; Ducange, Pietro

doi:10.1016/j.ins.2017.06.039

Cited by 36 publications

(33 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different strategies have been applied to obtain humanreadable fuzzy models in Big Data classification problems, including fuzzy versions of decision trees (FDTs) [17], [22], subgroup discovery (SD) [20], associative classifiers (FACs) [13], [21], emerging patterns mining (EPM) [18], and rule-based classifiers (FRBCs) [14]- [17], [19]. In [17], a distributed version of C4.5 is used to extract a candidate rule base that is optimized by an evolutionary algorithm. Segatori et al proposed a distributed FDT that exploits the classical Decision Tree implementation in Spark MLlib 9 , extending the learning scheme by employing fuzzy information gain based on fuzzy entropy [22].…”

Section: Related Workmentioning

confidence: 99%

CFM-BD: A Distributed Rule Induction Algorithm for Building Compact Fuzzy Models in Big Data Classification Problems

Elkano

Sanz

Barrenechea

et al. 2020

IEEE Trans. Fuzzy Syst.

View full text Add to dashboard Cite

Interpretability has always been a major concern for fuzzy rule-based classifiers. The usage of human-readable models allows them to explain the reasoning behind their predictions and decisions. However, when it comes to Big Data classification problems, fuzzy rule-based classifiers have not been able to maintain the good trade-off between accuracy and interpretability that has characterized these techniques in non-Big Data environments. The most accurate methods build too complex models composed of a large number of rules and fuzzy sets, while those approaches focusing on interpretability do not provide state-of-the-art discrimination capabilities. In this paper, we propose a new distributed learning algorithm named CFM-BD to construct accurate and compact fuzzy rulebased classification systems for Big Data. This method has been specifically designed from scratch for Big Data problems and does not adapt or extend any existing algorithm. The proposed learning process consists of three stages: 1) pre-processing based on the probability integral transform theorem; 2) rule induction inspired by CHI-BD and Apriori algorithms; 3) rule selection by means of a global evolutionary optimization. We conducted a complete empirical study to test the performance of our approach in terms of accuracy, complexity, and runtime. The results obtained were compared and contrasted with four state-ofthe-art fuzzy classifiers for Big Data (FBDT, FMDT, Chi-Spark-RS, and CHI-BD). According to this study, CFM-BD is able to provide competitive discrimination capabilities using significantly simpler models composed of a few rules of less than 3 antecedents, employing 5 linguistic labels for all variables.

show abstract

Section: Related Workmentioning

confidence: 99%

CFM-BD: A Distributed Rule Induction Algorithm for Building Compact Fuzzy Models in Big Data Classification Problems

Elkano

Sanz

Barrenechea

et al. 2020

IEEE Trans. Fuzzy Syst.

View full text Add to dashboard Cite

show abstract

“…This is a very interesting topic to be analyzed in depth, as it comprises several perspectives. On the one hand, whether to carry out an a apriori learning of the DB via strong fuzzy partitions that are properly adapted to the density related to each attribute of the dataset 21,22 . On the other hand, to carry out a post-processing stage for the tuning of the membership functions 23,24 .…”

Section: Lessons Learned and Discussionmentioning

confidence: 99%

Why Linguistic Fuzzy Rule Based Classification Systems perform well in Big Data Applications?

Fernández¹,

Altalhi²,

Alshomrani³

et al. 2017

IJCIS

View full text Add to dashboard Cite

The significance of addressing Big Data applications is beyond all doubt. The current ability of extracting interesting knowledge from large volumes of information provides great advantages to both corporations and academia. Therefore, researchers and practitioners must deal with the problem of scalability so that Machine Learning and Data Mining algorithms can address Big Data properly. With this end, the MapReduce programming framework is by far the most widely used mechanism to implement fault-tolerant distributed applications. This novel framework implies the design of a divide-and-conquer mechanism in which local models are learned separately in one stage (Map tasks) whereas a second stage (Reduce) is devoted to aggregate all sub-models into a single solution. In this paper, we focus on the analysis of the behavior of Linguistic Fuzzy Rule Based Classification Systems when embedded into a MapReduce working procedure. By retrieving different information regarding the rules learned throughout the MapReduce process, we will be able to identify some of the capabilities of this particular paradigm that allowed them to provide a good performance when addressing Big Data problems. In summary, we will show that linguistic fuzzy classifiers are a robust approach in case of scalability requirements.

show abstract

“…Then, many researchers worked in this area and built various types of fuzzy sets and membership functions to illustrate fuzzy decision tree. 17 A combination of decision trees with random vectors of samples is named as random forest in the work of Breiman. This fuzzy partition is easy to understand and useful in diagnosing for potential transformers.…”

Section: Related Workmentioning

confidence: 99%

“…11 Big data is also one of the research branches in the fuzzy decision tree, and lots of novel methods are proposed such as big data-driven smart energy management, 12 indexing techniques, 13 semiautomagical fuzzy partition method, 14 modified Gini index fuzzy SLIQ decision tree algorithm, 15 Chi-FRBCS-BigData algorithm, 16 and multiobjective evolutionary algorithms. 17 A combination of decision trees with random vectors of samples is named as random forest in the work of Breiman. 18 This paper employs fuzzy logic on to the random forest and its error rates yielded by randomly selecting features.…”

Section: Related Workmentioning

confidence: 99%

A general model for fuzzy decision tree and fuzzy random forest

Zheng

Zhang

et al. 2018

Computational Intelligence

View full text Add to dashboard Cite

The problem of risk classification and prediction, an essential research direction, aiming to identify and predict risks for various applications, has been researched in this paper.To identify and predict risks, numerous researchers build models on discovering hidden information of a label (positive credit or negative credit). Fuzzy logic is robust in dealing with ambiguous data and, thus, benefits the problem of classification and prediction. However, the way to apply fuzzy logic optimally depends on the characteristics of the data and the objectives, and it is extraordinarily tricky to find such a way. This paper, therefore, proposes a general membership function model for fuzzy sets (GMFMFS) in the fuzzy decision tree and extend it to the fuzzy random forest method. The proposed methods can be applied to identify and predict the credit risks with almost optimal fuzzy sets. In addition, we analyze the feasibility of our GMFMFS and prove our GMFMFS-based linear membership function can be extended to a nonlinear membership function without a significant increase in computing complex. Our GMFMFS-based fuzzy decision tree is tested with a real dataset of US credit, Susy dataset of UCI, and synthetic datasets of big data. The results of experiments further demonstrate the effectiveness and potential of our GMFMFS-based fuzzy decision tree with linear membership function and nonlinear membership function. KEYWORDSfuzzy decision tree, fuzzy random forest, membership function, risk classification and prediction 310

show abstract

A distributed approach to multi-objective evolutionary generation of fuzzy rule-based classifiers from big data

Cited by 36 publications

References 41 publications

CFM-BD: A Distributed Rule Induction Algorithm for Building Compact Fuzzy Models in Big Data Classification Problems

CFM-BD: A Distributed Rule Induction Algorithm for Building Compact Fuzzy Models in Big Data Classification Problems

Why Linguistic Fuzzy Rule Based Classification Systems perform well in Big Data Applications?

A general model for fuzzy decision tree and fuzzy random forest

Contact Info

Product

Resources

About