Mining of Sequential Patterns using Directed Graphs
Sabeen S1, R. Arunadevi2, Kanisha3, R. Kesavan4

1Dr. Sabeen S, Department of Computer Science, SRM Institute of Sceince and Technology, Kattankulathur, Tamilnadu, India.
2Dr. R. Arunadevi, Department of Computer Science, Vidhya Sagar Women’s College, Chengalpettu, Tamilnadu, India.
3Dr. B. Kanisha, Department of Information Technology, Veltech Multitech Dr.RR & Dr.SR Engineering College, Chennai, India.
4Dr. R. Kesavan, Department of Information Technology, Jaya Engineering College, Thiruninravur, Chennai, Tamilnadu, India.
Manuscript received on 26 August 2019. | Revised Manuscript received on 06 September 2019. | Manuscript published on 30 September 2019. | PP: 4002-4007 | Volume-8 Issue-11, September 2019. | Retrieval Number: K22420981119/2019©BEIESP | DOI: 10.35940/ijitee.K2242.0981119
Open Access | Ethics and 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 (

Abstract: Sequential pattern mining is one of the important functionalities of data mining. It is used for analyzing sequential database and discovers sequential patterns. It is focused for extracting interesting subsequences from a set of sequences. Various factors such as rate of occurrence, length, and profit are used to define the interestingness of subsequence derived from the sequence database. Sequential pattern mining has abundant real-life applications since sequential data is logically programmed as sequences of cipher in many fields such as bioinformatics, e-learning, market basket analysis, texts, and webpage click-stream analysis. A large diversity of competent algorithms such as Prefixspan, GSP and Freespan have been proposed during the past few years. In this paper we propose a data model for organizing the sequential database, which consists of a directed graph DGS (cycles and several edges are allowed) and an organization of directed paths in DGS to represent a sequential data for discovering sequential pattern3 from a sequence database. Competent algorithms for constructing the digraph model (DGS) for extracting all sequential patterns and mining association rules are proposed. A number of theoretical parameters of digraph model are also introduced, which lead to more understanding of the problem.
Keywords: Sequential pattern, Data mining, Directed graph, Directed path, Frequent item, Association rule, Minimum support
Scope of the Article: Cryptography and Applied Mathematics.