Context-Aware Fuzzy Logic Dispatcher for Real-Time IoT-Based Disaster Monitoring

Gavhane, Harsh Narayan (2025) Context-Aware Fuzzy Logic Dispatcher for Real-Time IoT-Based Disaster Monitoring. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration Manual) Download (9MB) | Preview

Abstract

Disaster-prone environments demand intelligent monitoring systems capable of making real-time decision to minimize harm and loss of life. Conventional threshold-based systems result a lack of flexibility and contextual awareness, which typically generating high rates of false alarms and delay in response. This paper proposes a contextual event prioritization solution using fuzzy logic and MQTT IoT communication along with a scalable serverless AWS disaster response architecture. It maps sensor events, for instance, gas, temperature and humidity to low, medium or high priority depending on sensor values as well as zone severity of the geographic zone. A fuzzy inference system is implemented using fuzzy algorithm simulating humanlike decision-making under uncertainty, where simulated IoT data is published over MQTT to a context-aware dispatcher that decides based on fuzzy rules and context weights. High-priority events trigger AWS Lambda for real-time response, medium-priority events are noted for fog-level computation, and low-priority data are persisted in DynamoDB to analyze later. Experimental validation with simulated data demonstrated event classification accuracy, with a reduction in false alarms compared to static threshold models, with less than one second real-time responsiveness. Such findings indicate that fuzzy-logic-based context-aware systems significantly improve prioritization accuracy and performance, with a cost-effective and scalable solution to disaster monitoring, and future development will focus on predictive analytics and integration of machine learning for further optimisation.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Kazmi, Aqeel UNSPECIFIED
Subjects:	T Technology > T Technology (General) > Information Technology > Cloud computing T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > Computer networks > Internet of things Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	26 Mar 2026 09:19
Last Modified:	26 Mar 2026 09:19
URI:	https://norma.ncirl.ie/id/eprint/9214

Actions (login required)

View Item