Downloads: 132
M.Tech / M.E / PhD Thesis | Computer Science & Engineering | India | Volume 4 Issue 11, November 2015
Implementation of Very Fast Decision Rules for Classification in Data Streams
Vaddadi R V S Prasad
Abstract: In this work huge amount of continuous and rapid data records are considered to solve the stream mining problems such as extracting knowledge structures by using several algorithms. One of the most interpretable and flexible model for predictive data mining are decision rules. Few algorithms are proposed in our work to have a clear idea on the decision rules. One of it is the VFDR algorithm and its proposed versions. These versions are one pass and any time algorithms. It works online and produces ordered or unordered rule sets. An adaptive extension is enabled to detect changes and quickly adapt the decision model. In this extension we monitor the evolution performance metric to detect concept drift. This explicit change detection mechanism provides useful information about the dynamics of process generating data.
Keywords: Stream mining, decision rules, extracting knowledge, vfdr algorithm
Edition: Volume 4 Issue 11, November 2015,
Pages: 264 - 267
Similar Articles with Keyword 'extracting knowledge'
Downloads: 99 | Weekly Hits: ⮙1 | Monthly Hits: ⮙1
Survey Paper, Computer Science & Engineering, India, Volume 3 Issue 12, December 2014
Pages: 528 - 532Knowledge Fusion Technique Using Classifier Ensemble by Combining the Sets of Classification Rules
Jaydeep B. Patil | Vaishali Nandedkar [3]
Downloads: 120
Research Paper, Computer Science & Engineering, India, Volume 2 Issue 5, May 2013
Pages: 199 - 202Improved approach to predict user future sessions using classification and clustering
Akshay Kansara | Swati Patel