Performance Optimization and Scalability of Cloud-Based Data Processing Pipelines for Fire Emergency Response Systems

Olawuyi, Olajide Ahmed (2024) Performance Optimization and Scalability of Cloud-Based Data Processing Pipelines for Fire Emergency Response Systems. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (697kB) | Preview

Abstract

Historically, communities have faced devastating fire hazards, underscoring the need for early detection and alert systems to ensure effective evacuation planning. This study integrates wireless sensor networks (WSNs), cloud computing, and machine learning to develop a robust fire emergency management system. The system employs DHT11 and MQ2 sensors to monitor temperature, humidity, gas, and smoke levels, transmitting data through MQTT brokers to a cloud-based platform. Machine learning models, including Logistic Regression, Support Vector Machine, Random Forest, and Decision Tree classifiers, are trained and evaluated using real sensor data. Metrics such as specificity, sensitivity, accuracy, F1-score, and area under curve assess the models’ effectiveness, while system performance is measured in terms of throughput, latency, and resource utilization. A web-based monitor application visualizes real-time data and alerts users to fire incidents. Experimental results demonstrate the efficiency of integrating WSNs with cloud computing for real-time fire detection and response, which significantly enhances fire management strategies.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Arun, Shreyas Setlur UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing H Social Sciences > HD Industries. Land use. Labor > Issues of Labour and Work > Health and Safety at Work. 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:	16 Jul 2025 09:10
Last Modified:	16 Jul 2025 09:11
URI:	https://norma.ncirl.ie/id/eprint/8130

Actions (login required)

View Item