Analysis of Various Time Series Change Detection Techniques: An Empirical Review
Sony Kanhaiyalal Ahuja
Sony Kanhaiyalal Ahuja, Shri Ramdeobaba College of Engineering and Management, Ramdeo Tekdi, Gittikhadan, Katol Road, Nagpur (Maharashtra), India.
Manuscript received on 24 March 2019 | Revised Manuscript received on 05 April 2019 | Manuscript Published on 18 April 2019 | PP: 559-561 | Volume-7 Issue-6S March 2019 | Retrieval Number: F03080376S19/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Time series change detection techniques have various uses, ranging from data classification, prediction, clustering and application based inference. These data mining techniques on time series change detection are usually application specific but the concepts are equally applicable to any other application area of research. In this paper, we have performed an empirical analysis of some standard algorithms on time series analysis, and evaluated their performance. This analysis has enabled us to identify some algorithmic traits which are specific to a given area of research, and thus would help researchers in selecting base algorithms for their own research purposes. Although, the techniques reviewed in this paper are targeted towards forest cover datasets, but are applicable to any other dataset as per application requirements.
Keywords: Time Series, Mining, Classification, Clustering, Prediction, Forest Cover Change.
Scope of the Article: Predictive Analysis