Distributed Multi-class Rule Based Classification Using RIPPER

Govada, Aruna; Thomas, Varsha S.; Samal, Ipsita; Sahay, Sanjay K.

doi:10.1109/cit.2016.111

Cited by 7 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent times, there is a rise in research on parallel implementation strategies in both of the ACO and rulebased classification domains [81][82][83]. However, none of such strategies were adopted for AntMiner algorithms yet.…”

Section: Future Research Directionsmentioning

confidence: 99%

Rule-Based Classification Based on Ant Colony Optimization: A Comprehensive Review

Hossain

Ema

Sohn

2022

Applied Computational Intelligence and Soft Computing

View full text Add to dashboard Cite

The Ant Colony Optimization (ACO) algorithms have been well-studied by the Operations Research community for solving combinatorial optimization problems. A handful of researchers in the Data Science community have successfully implemented various ACO methodologies for rule-based classification. This family of ACO algorithms is referred to as AntMiner algorithms. Due to the flexibility of the framework, and the availability of alternative strategies at the modular level, a systematic review on the AntMiner algorithms can benefit the broader community of researchers and practitioners interested in highly interpretable classification techniques. In this paper, we provided a comprehensive review of each module of the AntMiner algorithms. Our motivation is to provide insight into the current practices and future research scope in the context of the rule-based classification. Our discussions address ACO methodologies, rule construction strategies, candidate selection metrics, rule quality evaluation functions, rule pruning strategies, methods to address continuous attributes, parameter selection, and experimental settings. This review also reports a summary of real-life implementations of the rule-based classifiers in diverse domains including medical, genetics, portfolio analysis, geographic information system (GIS), human-machine interaction (HMI), autonomous driving, ICT, quality, and reliability engineering. These implementations demonstrate the potential application domains that can be benefitted from the methodological contributions to the rule-based classification technique.

show abstract

Section: Future Research Directionsmentioning

confidence: 99%

Rule-Based Classification Based on Ant Colony Optimization: A Comprehensive Review

Hossain

Ema

Sohn

2022

Applied Computational Intelligence and Soft Computing

View full text Add to dashboard Cite

show abstract

“…In solving the problem of choosing the class [14] to which the innovation belongs, the problem arises of evaluating it according to several criteria [15] and correctly considering these estimates when generalizing them or considering them together at the stage of making the final decision. The solution to the problem is possible on the basis of a discrete approach to assessing the information content of heterogeneous characters and the analysis of statistical methods [16].…”

Section: B the Task Of Selecting An Innovation Classmentioning

confidence: 99%

Models and Methods of Classification of Innovation Market Information

Igorevna¹,

Aleksandrovna²,

Vladimirovich³

et al. 2020

Proceedings of the “New Silk Road: Business Cooperation and Prospective of Economic Development” (NSRBCPED 2019)

View full text Add to dashboard Cite

The importance of innovation as a product on the market field in the conditions of transformation of means of promotion, digitalization, and expansion of sales channels on the Internet is discussed in the article. The authors' vision of classifying innovations by the type based on a subjective approach has been developed: manufacturers who formulate supply on the market and buyers (customers) that determine real and potential demand. The informative characteristics of the types of innovations are based on nominal features that are of practical value to the main agents of the market. The selection of informative features of innovation is based on clustering methods. The Hamming metric is proposed as an effective way to determine the measure of distances. The search for the necessary information and data processing in the innovation market is carried out using modeling tools. Clustering algorithms are proposed as adequate models of intersecting. The clustering algorithm solves the problem of dividing the sample of signs of innovation into clusters that are similar by certain criteria (scientific novelty, patent protection, etc.), depending on the type of innovation as a product (patent, technology, etc.). The proposed classification of innovations will allow to position innovation on the market as an object of sale. Modeling tools accumulate, group, process, coordinate and manage innovation market information when making management decisions.

show abstract

“…In [13] Aruna Govada and others have proposed an algorithm for classification. Repeated Incremental Pruning to Produce Error Reduction (RIPPER) algorithm is use to handle noisy data sets.…”

Section: Related Workmentioning

confidence: 99%

“…The algorithms are used as defined in WEKA [2], [6], [7], [12]. Some researchers use a combination technique with classification algorithms [1], [4], [5], [13], [16]. Performances of these algorithms are also compared to find the best classifier.…”

Section: Experiments Setupmentioning

confidence: 99%