Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

INVESTIGATION INTO GAME-BASED CRISIS SCENARIO MODELLING AND SIMULATION SYSTEM

Praiwattana, P (2018) INVESTIGATION INTO GAME-BASED CRISIS SCENARIO MODELLING AND SIMULATION SYSTEM. Doctoral thesis, Liverpool John Moores University.

[img]
Preview
Text
2018PisitPraiwattanaPhd.pdf - Published Version

Download (6MB) | Preview

Abstract

A crisis is an infrequent and unpredictable event. Training and preparation process requires tools for representation of crisis context. Particularly, crisis events consist of different situations, which can occur at the same time combining into complex situation and becoming a challenge in coordinating several crisis management departments. In this regards, disaster prevention, preparedness and relief can be conceptualized into a design of hypothetical crisis game. Many complex tasks during development of emergency circumstance provide an opportunity for practitioners to train their skills, which are situation analysis, decision-making, and coordination procedures. While the training in physical workouts give crisis personal a hand-on experience in the given situation, it often requires a long time to prepare with a considerable budget. Alternatively, computational framework which allows simulation of crisis models tailoring into crisis scenario can become a cost-effective substitution to this study and training. Although, there are several existing computational toolsets to simulate crisis, there is no system providing a generic functionality to define crisis scenario, simulation model, agent development, and artificial intelligence problem planning in the single unified framework. In addition, a development of genetic framework can become too complex due to a multi-disciplinary knowledge required in each component. Besides, they have not fully incorporated a game technology toolset to fasten the system development process and provide a rich set of features and functionalities to these mentioned components. To develop such crisis simulation system, there are several technologies that must be studied to derive a requirement for software engineering approach in system’s specification designs. With a current modern game technology available in the market, it enables fast prototyping of the framework integrating with cutting-edge graphic render engine, asset management, networking, and scripting library. Therefore, a serious game application for education in crisis management can be fundamentally developed early. Still, many features must be developed exclusively for the novel simulation framework on top of the selected game engine. In this thesis, we classified for essential core components to design a software specification of a serious game framework that eased crisis scenario generation, terrain design, and agent simulation in UML formats. From these diagrams, the framework was prototyped to demonstrate our proposed concepts. From the beginning, the crisis models for different disasters had been analysed for their design and environment representation techniques, thus provided a choice of based simulation technique of a cellular automata in our framework. Importantly, a study for suitability in selection of a game engine product was conducted since the state of the art game engines often ease integration with upcoming technologies. Moreover, the literatures for a procedural generation of crisis scenario context were studied for it provided a structure to the crisis parameters. Next, real-time map visualization in dynamic of resource representation in the area was developed. Then the simulation systems for a large-scale emergency response was discussed for their choice of framework design with their examples of test-case study. An agent-based modelling tool was also not provided from the game engine technology so its design and decision-making procedure had been developed. In addition, a procedural content generation (PCG) was integrated for automated map generation process, and it allowed configuration of scenario control parameters over terrain design during run-time. Likewise, the artificial planning architecture (AI planning) to solve a sequence of suitable action toward a specific goal was considered to be useful to investigate an emergency plan. However, AI planning most often requires an offline computation with a specific planning language. So the comparison study to select a fast and reliable planner was conducted. Then an integration pipeline between the planner and agent was developed over web-service architecture to separate a large computation from the client while provided ease of AI planning configuration using an editor interface from the web application. Finally, the final framework called CGSA-SIM (Crisis Game for Scenario design and Agent modelling simulation) was evaluated for run-time performance and scalability analysis. It shown an acceptable performance framerate for a real-time application in the worst 15 frame-per-seconds (FPS) with maximum visual objects. The normal gameplay performed capped 60 FPS. At same time, the simulation scenario for a wildfire situation had been tested with an agent intervention which generated a simulation data for personal or case evaluation. As a result, we have developed the CGSA-SIM framework to address the implementation challenge of incorporating an emergency simulation system with a modern game technology. The framework aims to be a generic application providing main functionality of crisis simulation game for a visualization, crisis model development and simulation, real-time interaction, and agent-based modelling with AI planning pipeline.

Item Type: Thesis (Doctoral)
Uncontrolled Keywords: Simulation System; Multi-agent framework; Serious Game; Crisis Management
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Computer Science
Date Deposited: 10 Sep 2018 10:17
Last Modified: 10 Sep 2018 10:21
DOI or Identification number: 10.24377/researchonline.ljmu.ac.uk.00009188
Supervisors: El Rhalibi, A
URI: http://researchonline.ljmu.ac.uk/id/eprint/9188

Actions (login required)

View Item View Item