Agent-based personal monitoring system simulation using type-2 fuzzy

Towards being a developed country, Malaysia has started the new era where every industry adopting new technologies and innovations to improve their operations, services and profit margin. In the middle of this modernization, there is a part where each industry must obey to. It's the safety issue. In Malaysia, safety awareness still at low level and people seems doesn't care about safety which sometime may cause harm to themselves. Worse case if the incidents happen during work. In this paper, we propose an agent-based personal monitoring system using type-2 fuzzy to simulate the monitoring process for our worker at time of hazard operation. This simulation applies for dedicated person who works in hazard place such as oil and gas plant, sewerage main hole, fire rescue and underground electric generation plant in Malaysia. To design and develop this simulation system, we applied the agent-based approach as it ease the designing process by picturing the real entities of stakeholder to agents in the simulation system. Agents in this simulation help in decision making for personal monitoring using type-2 fuzzy. Type-2 fuzzy is the engine of monitoring, where it defines the relationship of input (sensors) and output (actuators) of this particular domain. Type-2 fuzzy basically make precise the uncertain inputs, so that the output will be TRUE and reliable. It's crucial to generate this type of output as we are dealing with human — expert workers life. The combination of agents and type-2 fuzzy is suitable for dynamic environment like this domain.

[1]  Witold Pedrycz,et al.  Type-2 Fuzzy Logic: Theory and Applications , 2007, 2007 IEEE International Conference on Granular Computing (GRC 2007).

[2]  Alexander Serenko,et al.  Intelligent agents as innovations , 2004, AI & SOCIETY.

[3]  D. M. Hutton,et al.  Agent‐Based Manufacturing and Control Systems. New Agile Manufacturing Solutions for Achieving Peak Performance , 2005 .

[4]  John R. Clymer.  Simulation-Based Engineering of Complex Systems , 2009 .

[5]  Michael Winikoff,et al.  Prometheus: a practical agent oriented methodology , 2002 .

[6]  Michael Winikoff,et al.  Prometheus: a methodology for developing intelligent agents , 2002, AAMAS '02.

[7]  Chee Peng Lim,et al.  A Multi-Agent Classifier System Based on the Trust-Negotiation-Communication Model , 2009, SOCO 2009.

[8]  Scott Moss,et al.  Multi-Agent-Based Simulation: Why Bother? , 2005, MABS.

[9]  Raymond S. T. Lee.  Fuzzy-neuro approach to agent applications : from the AI perspective to modern ontology , 2006 .

[10]  A. Smirnov,et al.  Multi-Agent Decision Support System for Disaster Response and Evacuation , 2004, MSRAS.

[11]  I. Burhan Türksen,et al.  Modeling Uncertainty with Fuzzy Logic - With Recent Theory and Applications , 2009, Studies in Fuzziness and Soft Computing.

[12]  Jafreezal Jaafar,et al.  A Fuzzy Action Selection Method for Virtual Agent Navigation in Unknown Virtual Environments , 2007, 2007 IEEE International Fuzzy Systems Conference.

[13]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[14]  Michael Winikoff,et al.  Tool support for agent development using the Prometheus methodology , 2005, Fifth International Conference on Quality Software (QSIC'05).

[15]  Massimo Paolucci,et al.  Agent-based manufacturing and control systems - new agile manufacturing solutions for achieving peak performance , 2004 .