Integration of a secure type-2 fuzzy ontology with a multi-agent platform: A proposal to automate the personalized flight ticket booking domain

  • Authors:

  • Ahmad C. Bukhari;Yong-Gi Kim

  • Affiliations:

  • Artificial Intelligence Lab, Department of Computer Science, Gyeongsang National University, Jinju, Kyungnam 660-701, Republic of Korea;Artificial Intelligence Lab, Department of Computer Science, Gyeongsang National University, Jinju, Kyungnam 660-701, Republic of Korea

  • Venue:
  • Information Sciences: an International Journal
  • Year:
  • 2012

Quantified Score

Hi-index 0.07

Visualization

Abstract

Recently, several fuzzy ontology-based solutions have been proposed in the domain of web-based applications to reduce the manual work load of daily activities. However, because of the explosive heterogeneity in the current internet structure, the performance of the available solutions has been decreasing drastically. We propose an integrated secure type-2 fuzzy ontology multi-agent platform (ST2FO-MAS) to completely automate the laborious process of manual air ticket booking. The air ticket booking domain is rife with uncertainties, and most of the information is based on complex linguistic terminologies. The available fuzzy ontology schemes cannot extract intensively blurred information from the internet to provide personalized solutions. Meanwhile, information security attacks have been growing significantly, which is a discouraging indicator for e-commerce applications. The proposed ST2FO-MAS can provide an end-to-end solution that can ideally address the ongoing information security challenges. The accommodation of a multi-agent system in a secure type-2 fuzzy ontology boosts the performance of the system because of its robust autonomous working scheme. To completely judge the performance of the proposed solution, we developed an intelligent prototype system that was based on JAVA, JADE and XML security recommendations. We conducted several experiments under the supervision of domain experts, and we evaluated the performance of the system. The experimental results are quite satisfactory and support the efficacy of the proposed model.