行動化即時防災與通報系統之設計與探討－應用在土石流災害

A Real-time Mobile Communication System Applied on the Assessment of Debris Flow Disaster Prevention and Alert

龔旭陽(Hsu-Yang Kung) ； 顧浩翔(Hao-Hsiang Ku) ； 蔡光榮(Kuang-Jung Tasi) ； 黃崇明(Chung-Ming Huang)

《資訊管理學報》 11卷4期 (2004/10) Pp. 29-50

https://doi.org/10.6382/JIM.200410.0029

摘要

台灣自歷經921地震後，山區常發生大規模土石量崩塌，每當颱風季節或豪雨來臨，便引發土石流災害的發生，造成人民生命財產的重大損失，為此政府投入大量經費建置救災防災系統，並設立防災國家計劃，期許相關領域學者專家建立防災與救災研究與系統。其中針對土石流防災通報系統而言，由於土石流發生時，一般有線通訊往往是中斷，因此原有的災情通報系統往往無法發揮其功能。此外災區現場之即時資訊，尤其是災區即時照片與影片，對於災情之通報與搶救有關鍵之幫助。有鑑於此，本論文提出並建置出一“行動化土石流災情預防與通報系統(A Real-time Mobile Debris-flow Disaster Prevention and Alter system，RMD^2PA)”。RMD^2PA系統為三層次(3-tier)架構由行動式使用者端(Mobile Users)、應用伺服器端(Application Server)與專家決策伺服器端(Decision Support Server，DSS)所組成。行動式使用者利用手持設備(Handheld Devices)，例如PDA與手機，可以經由GSM/GPRS個人行動通訊網路，進行災區雙向多媒體土石流資訊傳收。此外為預防行動網路斷訊或收訊不良，在手持設備上設計了條例式推理(Rule-Based Reasoning，RBR)與案例式推理(Case-Based Reasoning，CBR)引擎，以加強災區現場之災情分析與預測。應用伺服器提供多媒體資訊，擁有七個智慧型代理人(Intelligent Agents)進行資料處理與過濾(Filtering)，以節省保貴的無線網路頻寬並達成客制化(Customized)與個人化(Personalized)需求。應用伺服器端亦提供虛擬實境(Virtual Reality)相關地形模擬以及WEB與WAP服務，讓網際網路的使用者連結RMD^2PA系統存取土石流相關資訊。位於網際網路後端的專家決策伺服器利用數值回歸分析法則進行土石流推論，所採用之推論資料庫為南投縣境內181條土石流潛勢溪流資料，並結合全球衛星定位系統(GPS)、地理資訊系統(GIS)與遙感探測(RS)資訊技術找出土石流災害因子，再利用本論文所提出之倒傳式類神經網路統計分析法進行數值回歸分析與比較，進而建立精確與客觀的土石流災害發生預測模式。

關鍵字

決策支援機制 ； 嵌入式多媒體通訊系統 ； 推理引擎 ； 土石流 ； 無線與行動通訊

並列摘要

Effective information transmitted via robust communications is very important and critical on the prevention and alert of the debris flow disaster. However, the wired communication environment is always destroyed on the occurrence of a debris-flow. Furthermore, the effective disaster prediction is based on the accurate debris-flow decision model, which can be achieved via the real-time information communications between the disaster area and the rescue-control center. In this paper, we proposed and designed a Real-time Mobile Debris-flow Disaster Prevention and Alert system (RMD^2PA), which is the three-tier architecture composed of the mobile clients, the application servers, and the decision support server based on the wireless/mobile and Internet communications. Mobile clients use handheld devices, e.g., PDA combining a cellular phone, to transmit and receive multimedia debris-flow information via the GSM/GPRS network. The case-based and rule-based reasoning mechanism is embedded in the handheld device to achieve the simple debris-flow prevention and decision when the mobile communication fails. The application server is composed of a Virtual-Reality manager and seven intelligent agents to provide the debris-flow VR emulation and the customized information for mobile users and effectively reduce the bandwidth consumption of the mobile network. Based on the database of the pre- analyzed 181 potential debris-flows in Taiwan, we build the accurate prediction models to achieve the effective debris-flow prevention by adopting the back-propagation network scheme in the decision support server.

並列關鍵字

Decision and Support Mechanisms ； Embedded Multimedia Communication System ； Reasoning Engines ； Debris-flow ； Wireless and Mobile Communications

參考文獻

Aamodt, A.,Plaza, E.(1991).Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches.AT Communications.7(1),39-59.

Andrew, R.G.,Paul S.R.(1995).Improving accuracy by combining rule-based and case-based reasoning.(MERL-TR-94-19a).

David, W.A.,Leonard, A.B.,Tucker, M.(1998).Supporting Conversational Case-Based Reasoning in an Integrated Reasoning Framework.Navy Center for Applied Research in Artificial Intelligence.

Efraim, T.,Jay, E.A.P.(1998).(Decision Support System and Intelligent System).

George, F.L.,William, A.S.A.(1999).(Artificial Intelligence-Structures and Strategies for Complex Problem Solving).