Extracting Quality Relations from Categorical Data using Modified Qube Algorithm

Sayan, Nanda and Gopakumar, Rajesh and Singh, Sanjay (2017) Extracting Quality Relations from Categorical Data using Modified Qube Algorithm. In: Sixth International Conference on Advances in Computing, Communications and Informatics (ICACCI'17), 2017, Manipal University Manipal.

[img] PDF
876n.pdf - Published Version
Restricted to Registered users only

Download (152kB) | Request a copy

Abstract

Partial derivatives are used to describe the trend of a dependent categorical variable. This is used to extract quality relations from categorical data through the definition of a Probabilistic Discrete Qualitative Partial Derivative (PDQ PD). This has been covered in the Qube algorithm. However, on analysis of the current method, it is found that a large amount of the time is taken in the attribute selection phase. The objective of this paper is to improve the efficiency of this algorithm in particular by decreasing the time taken for attribute selection. In this paper we have modified the Qube algorithm, the modified algorithm is able to reduce the time taken by searching the data set for rows with the same variable values. The ordering is then replicated in each case. This has been found to improve the efficiency of the algorithm especially in data sets where there are multiple items with the same values.

Item Type: Conference or Workshop Item (Paper)
Subjects: Engineering > MIT Manipal > Computer Science and Engineering
Engineering > MIT Manipal > Information and Communication Technology
Depositing User: MIT Library
Date Deposited: 18 Nov 2017 05:05
Last Modified: 18 Nov 2017 05:05
URI: http://eprints.manipal.edu/id/eprint/149972

Actions (login required)

View Item View Item