False Fire Alarm Detection Using Data Mining Techniques

False Fire Alarm Detection Using Data Mining Techniques

Raheel Zafar, Shah Zaib, Muhammad Asif
Copyright: © 2020 |Pages: 15
DOI: 10.4018/IJDSST.2020100102
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

In the era of smart home technology, early warning systems and emergency services are inevitable. To make smart homes safer, early fire alarm systems can play a significant role. Smart homes usually utilize communication, sensors, actuators, and other technologies to provide a safe and smart environment. This research work introduced a model for the fire alarm system and designed a fire alarm detection (FAD) simulator to produce a synthetic dataset. The designed simulator utilizes a variety of sensors (temperature, gas, and humidity) to simulate fire alarm scenarios based on real-world data. The produced data is investigated and analyzed to classify the possible fire behaviors based on key assumptions taken from real-world scenarios. Different classification models are used to determine an optimal classifier for fire detection. The proposed technique can identify the false alarms based on parameters like temperature, smoke, and gas values of different sensors embedded in a fire alarm detection simulator.
Article Preview
Top

Introduction

Smart homes consist of smart appliances, which are connected through a network to enables monitoring, control and to improve the quality of living. Modern systems typically consist of multiple sensors are being implemented leading to reduce the labor cost in developed countries. Many research groups including IBM, Microsoft and CISCO are already contributing their work in this domain. According to ABI research, 1.5 million smart home systems were installed in the USA by 2012 and about 130 million smart home devices have been shipped worldwide in the current year according to IHS Marki(technologies, 2012)Heterogeneous home automation systems with smart technologies are working to control the home appliances remotely (Harper, 2006). A recent study by (Sayavong, Rajmy, et al, 2020) has proposed a cost-effective system that can predict false fire alarms aiming to reduce the cost of false fire alarms.

For the safety of residents, the demands of intelligent home automation system have increased. As the security of the residents is a major concern in this smart environment, which enables the design of early warning systems in order to notify the emergency services on time. In order to prevent fire emergencies, fire detection techniques have got wide attention in smart homes. However, these techniques are facing a dilemma of triggering false fire alarms to identify the false fire alarms, fire detection techniques are categorized into two general types: one is the sensor-based technique and the other is vision based. (Wang, Shu, et al., 2019) suggested that most of the smoke sensors the intensity of scattering light as the indicator of fire smokes to trigger fire alarms, but sometimes a false fire alarm would be triggered by non-fire aerosols due to their similar concentration characteristics. Moreover, the study proposed a high-performance optical fire smoke detector with high sensitivity, low-cost and unique ability to resist the false alarms caused by non-fire aerosols.

Smart things with their sensing capabilities are used to control and automate the whole system through the Internet. There is no guarantee that appliances used in the smart home always generate accurate data to activate the emergency services. In modern automated homes, fire alarm systems are implemented to detect fires, to generate early warnings and to alert emergency services. The appliances can generate a false alarm which may lead to an extra cost for emergency service providers. In a study (Chan, Wen Shuo, et al., 2019) proposed laser-based smoke detectors for fire alarm system. The study proposed hardware-based solution to reduce the activation probability of false fire alarms.

Complete Article List

Search this Journal:
Reset
Volume 16: 1 Issue (2024)
Volume 15: 2 Issues (2023)
Volume 14: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 13: 4 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing