Discovery of Characteristic Sequential Patterns Based on Two Types of Constraints-Reference-Cited by-同舟云学术

Discovery of Characteristic Sequential Patterns Based on Two Types of Constraints

Published:2019-01 Issue:1 Volume:1 Page:40-54
ISSN:2577-4794
Container-title:International Journal of Extreme Automation and Connectivity in Healthcare
language:en
Short-container-title:

Author:

Sakurai Shigeaki¹

Affiliation:

1. Toshiba Digital Solutions, Kawasaki, Japan

Abstract

This article proposes a method for discovering characteristic sequential patterns from sequential data by using background knowledge. In the case of the tabular structured data, each item is composed of an attribute and an attribute value. This article focuses on two types of constraints describing background knowledge. The first one is time constraints. It can flexibly describe relationships related to the time between items. The second one is item constraints, it can select items included in sequential patterns. These constraints can represent the background knowledge representing the interests of analysts. Therefore, they can easily discover sequential patterns coinciding the interests as characteristic sequential patterns. Lastly, this article verifies the effect of the pattern discovery method based on both the evaluation criteria of sequential patterns and the background knowledge. The method can be applied to the analysis of the healthcare data.

Publisher

IGI Global

Subject

General Medicine

Reference37 articles.

1. Sakurai, S., Kyoko, M., & Matsumoto, S. (2014a). A prediction of attractive evaluation objects based on complex sequential data. World Academy of Science, Engineering and Technology, International Journal of Computer. Quantum and Information Engineering, 8(2), 88–96.

2. Sakurai, S., Kitahara, Y., & Orihara, R. (2008b). A Sequential Pattern Mining Method based on Sequential Interestingness. International Journal of Information and Mathematical Sciences, 4(4), 252–260.

3. Agrawal, R., & Srikant, R. (1994). Fast Algorithms for Mining Association Rules. In Proceedings of the 20th International Conference on Very Large Data Bases, Santiago de Chile, Chile (pp. 487-499).

4. Mining Sequential Patterns;R.Agrawal;Proceedings of the 11th International Conference on Data Engineering,1995

5. Sakurai, S., Makino, K., & Matsumoto, S. (2014b). An activation method of topic dictionary to expand training data for trend rule discovery. Applied Computational Intelligence and Soft Computing.