Discovering Periodic Patterns in Time Series from Twitter Data Set
Elavarasi D
Elavarasi D., HOD, Department of Computer Science & Engineering, Mount Zion College of Engineering and Technology, Pudukkottai (Tamil Nadu), India.
Manuscript received on October 06, 2020. | Revised Manuscript received on October 25, 2020. | Manuscript published on November 30, 2020. | PP: 92-102 | Volume-9 Issue-4, November 2020. | Retrieval Number: 100.1/ijrte.A2014059120 | DOI: 10.35940/ijrte.A2014.119420
Open Access | Ethics and Policies | Cite | Mendeley
© 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: The important class of regularities that exist in a time series is nothing but the Partial periodic patterns. These patterns have key properties such as starting, stopping, and restartinganywhere− within a series. Partial periodic patterns areclassifiedinto two types: (i) regular patterns− exhibiting periodic behavior throughout a series with some exceptions and( ii) periodic patterns exhibiting periodic behavior only for particular time intervals within a series. We have focused primarily on finding regular patterns during past studies on partial periodic search. The knowledge pertaining to periodic patterns cannot be ignored. This is because useful information pertaining to seasonal or time-based associations between events is provided bythem. Because of the foll o wi n g two main reasons, finding periodic patterns is a non-trivial task. (i) Each periodic pattern is associated with time-based information pertaining to its durations of periodic appearances in a series. Since the information can vary within and across patterns, obtaining this information ischallenging. (ii) As they do not satisfy the anti-monotonic property, finding all periodic patterns is a computationally expensive process. In this paper, periodic pattern model is proposed by addressing the above issues. Periodic Pattern growth algorithm along with an efficient pruning technique is also proposed to discover these patterns. The results through Experimentation have shown that Periodic patterns canbe really useful and it has also proven that our algorithm isnoteworthy.
Keywords: Categories and Subject Descriptors H.2.8 [Database Management]: Database Applications – Data Mining. General Terms Algorithms.