Fuzzy Logic-Based Decision Support System for Disasters and Emergencies

Abstract

Summary Invention title: Fuzzy Logic-Based Decision Support System for Disasters and Emergencies. Invention Summary: This invention relates to a fuzzy logic-based computer and decision support system developed to ensure that search and rescue teams and logistical resources are dispatched to the most appropriate areas with optimal optimization during disasters and emergencies. The main purpose of the invention is to determine operational response priorities by processing uncertain data obtained from the field during crises, minimizing the margin of error. Technically, the system architecture involves weighting the parameters of debris severity (101), disaster victim density (102), transportation possibilities (103), and notification reliability (104) using Fuzzy Analytical Hierarchy Process algorithms in a fuzzy logic weighting module (300). The resulting defuzzified exact weights are integrated into a decision and ranking module (400) that works with the Fuzzy TOPSIS method, and vertex calculations are performed.The invention classifies the risk status via the output and routing interface (500) by generating a unique proximity coefficient as a result of this modeling and directs rescue resources to the most urgent points.

Description

1 TARIFF Fuzzy logic-based decision-making for managing uncertainty in disaster management. SUPPORT SYSTEM Technical Field This invention addresses the intense information uncertainty and missing information during the first 72 hours, the most critical phase of disaster management. Under pressure from data and time constraints, and with limited logistical resources and search and rescue teams, efforts were made to reach the most urgent areas. a hybrid decision-making system based on fuzzy logic and computer and hardware infrastructure that automates the dispatch process It is related to the support system. State of the Art: Existing disaster management systems provide a comprehensive data management platform. However, it is a mathematical decision that automates the management of limited resources in a chaotic environment. It lacks a mechanism. Traditional Multi-Criteria Decision Making (MCDM) methods, decision converting the verbal variables of the transmitters into precise quantitative values ​​consisting only of 0s or 1s because it requires fully acknowledging the inherent uncertainty and probabilistic distribution characteristics of the problem. It is unable to model it. These mathematical limitations in existing structures make the system impossible for human-computer interaction. In terms of interaction, it increases the cognitive load and reduces operational efficiency. 15 Purpose of the Invention The primary purpose of this invention is to create a fuzzy logic-based system capable of processing ambiguous and verbal data. The goal is to improve the decision-making capabilities of existing hardware systems by developing a hybrid algorithm. The invention replaces the binary structure of Classical Set Theory with an infinite range of membership degrees between 0 and 1; The triangle fuzzy logic uses the following criteria: severity of debris, density of disaster victims, transportation facilities, and reliability of reporting. Numbers and models. Thus, incomplete or complex data coming from the field to the servers is processed in a computer environment. 20 By processing the data, the speed of intervention is maximized. Explanation of Figures Figure 1: General overview of the disaster and emergency decision support system that is the subject of the invention. This is a basic block flowchart showing the architecture and hardware / software processing steps of the system. Figure 2: The system Triangular fuzzy number membership of the debris severity variable (101) transmitted to the input unit (100). It is a graph showing the functions. Figure 3: Triangular fuzzy number 25 for the disaster victim density variable (102). This is a graph showing membership functions. Figure 4: Triangular fuzzy graph of the transportation facilities variable (103). Figure 5: The triangle of the reporting reliability variable (104) This is a graph showing the fuzzy number membership functions. Figure 6: Decision and ranking module (400) triangular fuzzy number membership functions of the intervention priority output variable produced by Figure 7: Output and orientation showing the calculated Proximity Coefficient scores. This is a sample screenshot of the interface (500). Explanation of References in Figures 100: Data Collection and Input Unit 101: Debris Severity Data 102: Disaster Victim Density Data 103: Transportation Facilities Data 104: Report Reliability Data 200: Data 2 Processing and Normalization Module 300: Fuzzy Logic Weighting Module 400: Decision and Ranking Module 500: Output and Routing Interface Description of the Invention This invention enables the allocation of limited search and rescue resources to the most appropriate areas during a disaster. It is an integrated hardware and software decision support system that autonomously manages the dispatch of files. The system The study involves collecting field data and transmitting it to the input unit (100) via a communication network. This unit (100) starts with the following data: debris severity data (101), disaster victim density data (102), transportation The triangle in which the possibilities data (103) and the reporting reliability data (104) will be processed simultaneously in the system It accepts fuzzy numbers in a format. This raw data is primarily processed by the system processor. It is transferred to the processing and normalization module (200). In this module (200), fuzzy decision of alternatives The matrix is ​​normalized using linear scale transformation. 10 The weighting stage of the invention's decision-making mechanism is a fuzzy logic weighting module. (300) takes place within this module. This module (300) uses fuzzy variables based on expert opinions, Figure 2. Based on the triangular fuzzy number membership functions shown in Figures 3, 4, and 5, the system can be defined as follows: Fuzzy Analytic Hierarchy Process (FAHP) using Buckley's method while integrating It runs its algorithms. Thanks to the integration of the Buckley method, the refined exact 15 criteria are obtained. The importance weights are calculated. The resulting criterion weights and normalized field data are the main engine of the system. It is directed to the decision and ranking module (400). This module (400) uses Fuzzy TOPSIS algorithms. By running it, the algorithm creates a weighted normalized matrix for each alternative intervention point. Each alternative intervention point in the system has membership functions as shown in Figure 6. The vertex determines the proximity to the Fuzzy Positive Ideal Solution and the distance to the Fuzzy Negative Ideal Solution. It calculates mathematically using this method. In the final stage, a unique Proximity Coefficient is derived for each region as a result of the calculations. These coefficients are transferred to the output and routing interface (500) which runs on computer screens. The interface (500) arranges the obtained scores in descending order and, as shown in the example in Figure 7, 25 If the score generated by the system exceeds the critical threshold of 0.66, the relevant location will autonomously access the interface. It is labeled as having a critical risk level. How the Invention Can Be Applied to Industry: This invention can be used by AFAD (Disaster and Emergency Management Presidency), local governments, fire departments, and search and rescue organizations. to the existing computer and server infrastructures in the crisis management centers of rescue organizations 30 as an integrated decision support and logistics optimization tool in the disaster management industry It is ready for immediate use.

Claims

3 REQUESTS 1. Allocation of limited logistical resources and search and rescue teams in disaster and emergency situations. It is a computer-based decision support system that optimizes, and its feature is; • Severity of debris from the field and open databases (101), density of disaster victims (102), transportation facilities (103) and reporting reliability (104) data simultaneously 5 field hardware data collection and input unit (100), • Converts incoming data into standard mathematical values ​​using linear scale transformation. a data processing and normalization module (200), • Fuzzy Analytics by converting decision-makers' verbal variables into triangular fuzzy numbers. A fuzzy logic weighting module 10 that runs Hierarchy Process algorithms. (300), • Using the obtained criterion weights and normalized data, each alternative intervention was analyzed. A fuzzy TOPSIS-based decision that generates a weighted normalized matrix for the point, and Sorting module (400), • A system that displays calculated risk scores to decision-makers as visual and numerical alerts. It includes the output and routing interface (500).

2. It is a decision support system according to Claim 1, and its characteristic feature is the fuzzy logic in question. weighting module (300) using the Buckley method to preserve uncertainty structured to calculate the defuzzified precise weights of the criteria that is. 20 3. It is a decision support system according to Claim 1, and its characteristic feature is that the decision and ranking module in question... (400), the proximity of each alternative disaster area to the Fuzzy Positive Ideal Solution and By calculating the distance to the Fuzzy Negative Ideal Solution for each region using the vertex method. It is structured in such a way as to produce a singular Proximity Coefficient.

4. It is a decision support system according to claim 1, and its characteristic is that the output and guidance in question are 25. If the generated Proximity Coefficient value exceeds the critical threshold of 0.66, then the interface (500) It is the autonomous labeling of the relevant intervention location at a critical risk level.

Images