ON THE ROLE OF INTERPRETABILITY IN FUZZY DATA MINING

Data Mining, a central step in the broader overall process of Knowledge Discovery from Databases, concerns with discovering useful properties, called patterns, from data. Understandability is an essential — yet rarely tackled — feature that makes resulting patterns accessible by end users. In this paper we argue that the adoption of Fuzzy Logic for Data Mining can improve understandability of derived patterns. Indeed, Fuzzy Logic is able to represent concepts in a “human-centric” way. Hence, Data Mining methods based on Fuzzy Logic may potentially meet the so-called “Comprehensibility Postulate”, which characterizes the blurry notion of understandability. However, the mere adoption of Fuzzy Logic for Data Mining is not enough to achieve understandability. This paper describes and comments a number of issues that need to be addressed to provide for understandable patterns. A careful consideration of all such issues may end up in a systematic methodology to discover comprehensible knowledge from data.

Download Full-text

Augmented intelligence in educational data mining

Smart Learning Environments ◽

10.1186/s40561-019-0086-1 ◽

2019 ◽

Vol 6 (1) ◽

Cited By ~ 1

Author(s):

Tapani Toivonen ◽

Ilkka Jormanainen ◽

Markku Tukiainen

Keyword(s):

Data Mining ◽

Knowledge Discovery ◽

Predictive Model ◽

Iterative Process ◽

Educational Data Mining ◽

Parameter Tuning ◽

End Users ◽

Tree Models ◽

Level Of Knowledge ◽

Over Time

Abstract Educational data mining (EDM) processes have shifted towards open-ended processes with visualizations and parameter and predictive model adjusting. Data and models in hyperdimensions can be visualized for end-users with popular data mining platforms such as Weka and RapidMiner. Multiple studies have shown how the adjusting and even creating the decision tree classifiers help EDM end-users to better comprehend the dataset and the context where the data has been collected. To harness the power of such open-ended approach in EDM, we introduce a novel Augmented Intelligence method and a cluster analysis algorithm Neural N-Tree. These contributions allow EDM end-users to analyze educational data in an iterative process where the knowledge discovery and the accuracy of the predictive model generated by the algorithm increases over time through the interactions between the models and the end-users. In contrast to other similar approaches, the key in our method is in the model adjusting and not in parameter tuning. We report a study where the potential EDM end-users clustered data from an education setting and interacted with Neural N-Tree models by following Augmented Intelligence method. The findings of the study suggest that the accuracy of the models evolve over time and especially the end-users who have a adequate level of knowledge from data mining benefit from the method. Moreover, the study indicates that the knowledge discovery is possible through AUI.

Download Full-text

Formal Knowledge Engineering Methods for Knowledge Discovery

Journal of Information & Knowledge Management ◽

10.1142/s0219649202000455 ◽

2002 ◽

Vol 01 (02) ◽

pp. 141-154

Author(s):

Satheesh Ramachandran

Keyword(s):

Data Mining ◽

Knowledge Management ◽

Life Cycle ◽

Decision Support ◽

Knowledge Discovery ◽

Knowledge Engineering ◽

The Other ◽

Full Potential ◽

Formal Knowledge

This paper presents a framework for the integrated use of formal knowledge engineering methods and data mining based knowledge discovery methods. Knowledge is a key enterprise asset, and organizations are adopting both knowledge engineering and knowledge discovery paradigms for better knowledge management and enhanced decision support capability. Although there exists a useful interdependence between these endeavors, not much effort has been focused on using the full potential of one for the other. This paper presents a framework for the integrated use of established formal knowledge engineering methods and knowledge discovery processes with the ultimate intent of better managing the enterprise knowledge life cycle. It provides a brief overview of the knowledge discovery processes, and introduces a class of formal knowledge engineering methods and the perceived role of these methods in supporting the integration between the two worlds of knowledge discovery and knowledge engineering.

Download Full-text

Data mining methods for knowledge discovery in multi-objective optimization: Part A - Survey

Expert Systems with Applications ◽

10.1016/j.eswa.2016.10.015 ◽

2017 ◽

Vol 70 ◽

pp. 139-159 ◽

Cited By ~ 67

Author(s):

Sunith Bandaru ◽

Amos H.C. Ng ◽

Kalyanmoy Deb

Keyword(s):

Data Mining ◽

Knowledge Discovery ◽

Multi Objective Optimization ◽

Multi Objective ◽

Mining Methods

Download Full-text

Data Mining and Fuzzy Data Mining Using MapReduce Algorithms

Data Mining - Methods, Applications and Systems ◽

10.5772/intechopen.92232 ◽

2021 ◽

Author(s):

Poli Venkata Subba Reddy

Keyword(s):

Data Mining ◽

Fuzzy Logic ◽

Original Data ◽

Space Complexity ◽

Fuzzy Data ◽

Discovery Process ◽

Web Data ◽

Web Data Mining ◽

Inexact Information ◽

Time And Space Complexity

Data mining is knowledge discovery process. It has to deal with exact information and inexact information. Statistical methods deal with inexact information but it is based on likelihood. Zadeh fuzzy logic deals with inexact information but it is based on belief and it is simple to use. Fuzzy logic is used to deal with inexact information. Data mining consist methods and classifications. These methods and classifications are discussed for both exact and inexact information. Retrieval of information is important in data mining. The time and space complexity is high in big data. These are to be reduced. The time complexity is reduced through the consecutive retrieval (C-R) property and space complexity is reduced with blackboard systems. Data mining for web data based is discussed. In web data mining, the original data have to be disclosed. Fuzzy web data mining is discussed for security of data. Fuzzy web programming is discussed. Data mining, fuzzy data mining, and web data mining are discussed through MapReduce algorithms.

Download Full-text

Complex Biological Data Mining and Knowledge Discovery

Biotechnology ◽

10.4018/978-1-5225-8903-7.ch011 ◽

2019 ◽

pp. 305-321

Author(s):

Fatima Kabli

Keyword(s):

Data Mining ◽

Knowledge Discovery ◽

Dna Sequences ◽

Protein Structures ◽

Extraction Process ◽

Biological Data ◽

Knowledge Discovery In Databases ◽

Complex Data ◽

Mining Methods ◽

Scientific Challenge

The mass of data available on the Internet is rapidly increasing; the complexity of this data is discussed at the level of the multiplicity of information sources, formats, modals, and versions. Facing the complexity of biological data, such as the DNA sequences, protein sequences, and protein structures, the biologist cannot simply use the traditional techniques to analyze this type of data. The knowledge extraction process with data mining methods for the analysis and processing of biological complex data is considered a real scientific challenge in the search for systematically potential relationships without prior knowledge of the nature of these relationships. In this chapter, the authors discuss the Knowledge Discovery in Databases process (KDD) from the Biological Data. They specifically present a state of the art of the best known and most effective methods of data mining for analysis of the biological data and problems of bioinformatics related to data mining.

Download Full-text