Ant-Based Clustering in Delta Episode Information Systems Based on Temporal Rough Set Flow Graphs

  • Authors:
  • Krzysztof Pancerz;Arkadiusz Lewicki;Ryszard Tadeusiewicz;Jan Warchoł

  • Affiliations:
  • University of Management and Administration, Akademicka Str. 4, 22-400 Zamość, Poland. kpancerz@wszia.edu.pl;University of Information Technology and Management, Sucharskiego Str. 2, 35-225 Rzeszów, Poland. alewicki@wsiz.rzeszow.pl;AGH University of Science and Technology, Mickiewicza Av. 30, 30-059 Kraków, Poland. rtad@agh.edu.pl;Medical University of Lublin, Jaczewskiego Str. 4, 20-090 Lublin, Poland. jan.warchol@umlub.pl

  • Venue:
  • Fundamenta Informaticae - Concurrency, Specification and Programming
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

In the paper, we focus on ant-based clustering time series data represented by means of the so-called delta episode information systems. A clustering process is made on the basis of delta representation of time series, i.e., we are interested in characters of changes between two consecutive data points in time series instead of original data points. Most algorithms use similarity measures to compare time series. In the paper, we propose to use a measure based on temporal rough set flow graphs. This measure has a probabilistic character and it is considered in terms of the Decision Theoretic Rough Set DTRS model. To perform ant-based clustering, the algorithm based on the versions proposed by J. Deneubourg, E. Lumer and B. Faieta as well as J. Handl et al. is used.