Degree

Master of Science in Computer Science

Faculty / School

Faculty of Computer Sciences (FCS)

Department

Department of Computer Science

Date of Submission

2020-06-30

Advisor

Dr. Tariq Mehmood, Professor, Faculty of Computer Science, Institute of Business Administration (IBA), Karachi

Project Type

MSCS Survey Report

Abstract

World is generating immeasurable amount of data every minute, that needs to be analyzed for better decision making. In order to fulfil this demand of faster analytics, businesses are adopting efficient stream processing and machine learning techniques. However, data streams are particularly challenging to handle. One of the prominent problems faced while dealing with streaming data is concept drift. Concept drift is described as, an unexpected change in the underlying distribution of the streaming data that can be observed as time passes. In this work, we have studied several methods that deal with the problem of concept drift. Most frequently used supervised and unsupervised techniques have been reviewed and we have also surveyed commonly used publicly available artificial and real-world datasets that are used to deal with concept drift issues.

Notes

This survey directly supports the researchers in understanding concept drift, it gives an overall view of the developments in concept drift learning. Most of the existing drift detection and adaptation techniques are proposed for labeled data streams. However, very few researches have been done to address the problem of concept drift in unsupervised or semi-supervised streams. In this survey we have tried to cover as many techniques as we can to address drift detection in unlabeled streaming data.

The full text of this document is only accessible to authorized users.

Share

COinS