Abstract
This research proposes a new model for constructing decision trees using interval-valued fuzzy membership values. Most existing fuzzy decision trees do not consider the uncertainty associated with their membership values, however, precise values of fuzzy membership values are not always possible. In this paper, we represent fuzzy membership values as intervals to model uncertainty and employ the look-ahead based fuzzy decision tree induction method to construct decision trees. We also investigate the significance of different neighbourhood values and define a new parameter insensitive to specific data sets using fuzzy sets. Some examples are provided to demonstrate the effectiveness of the approach.
Highlights
Decision tree is a powerful induction method in data mining
The interval values in a data mining problem does not need to be converted into an average to employ Fuzzy Decision Trees (FDT), instead, they can be directly mapped into an interval-valued fuzzy set and an interval-valued fuzzy decision tree can be established without any aggregation operation
In addition to the novel interval-valued fuzzy decision trees, we present a new way to determine the parameters of FDT in look-ahead based fuzzy decision trees (LAFDT)
Summary
Decision tree is a powerful induction method in data mining. realworld applications of decision trees exhibit uncertainty through imprecise data, vagueness, ambiguity etc [1,2,3,4, 25, 27]. It is well known that aggregation can lose information, and an interval-valued fuzzy decision tree will certainly convey more information than a traditional FDT, the ability to reveal more useful knowledge from the data than a FDT Such an interval-valued fuzzy decision tree is more powerful in dealing with data mining problems involving interval representation. In addition to the novel interval-valued fuzzy decision trees, we present a new way to determine the parameters of FDT in look-ahead based fuzzy decision trees (LAFDT). We call this the Look-Ahead Based Interval-Valued Fuzzy Decision Tree with Optimal Perimeter of the Neighbourhood (LAIVFDT-OPN) This new model simplifies the application of LAFDT by employing a parameter insensitive to data set changes on one hand, and improves the classification quality on the other hand by means of the employment of the full informtion in interval representation through interval-valued fuzzy sets.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
