Support Vector Machine-Based Fire Outbreak Detection System

Umoh, Uduak; Udo, Edward N.; Emmanuel, Nyoho

doi:10.5121/ijscai.2019.8201

Cited by 9 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fire outbreak data capture device was developed by Umoh et al 12 using sensors like DHT11 for sensing temperature, MQ‐2 Sensor for smelling smoke, and LM393 for sensing flame. Support vector machine algorithm was employed for the classification and prediction of fire outbreak.…”

Section: Related Workmentioning

confidence: 99%

A multimodel fire detection and alarm system for automobiles using internet of things and machine learning

Uma

Eswari

2022

Concurrency and Computation

View full text Add to dashboard Cite

Fire accidents in vehicles lead to the loss of human lives. The fire detection and alarm systems are often error-prone and respond to nonactual indications of fire presence, known as false alarms. The proposed model detects the fire at the smoldering stage and buzzes an alarm if an actual fire or smoke is detected. This system can achieve this real alarm using multiple internet of things-based sensors, namely smoke/gas, flame, temperature, and a visualization camera. The visualization camera continuously captures images of the vehicle to check the existence of fire. Machine learning algorithms are executed on the sensor and image dataset to reduce false alarms and achieve high accuracy of results by using various performance metrics. K E Y W O R D Sfire detection and alarm system, flame sensor, gas sensor, internet of things, temperature sensor, visualization camera INTRODUCTIONLoss of human lives and economic losses are observed every year due to fire accidents. Many types of research were carried out to study the cause and explosion of fire and the efficient ways to control or prevent the fire outbreak in automobiles. Research findings state that most of the fire accident takes place during summer due to overheating of engine and other components. Use of old vehicle and low-maintenance vehicles is highly prone to get fire. Identified reasons for fire outbreaks are gas Leakage, electrical short circuit, electric car battery, AC problems, etc. The leakage of toxic gases due to car burning is hazardous.In recent days, the probability of fire accidents in vehicles has been higher, and it could be even more in electric cars. In fire detection, sensors are used to detect the fire; a single sensor cannot sense the fire effectively. It is high time to detect fire beforehand. Smoke is a significant sign for detecting early fire conditions. A number of fire detection systems were proposed in the past few years. Most approaches use different visual elements, including flame colors, motion, and geometrical contour. Integrated sensors work efficiently in Fire environments.These Integrated alarm systems allow fast identification, alarm alerts, and even fire extinguishing. This can be achieved by using integrated sensors.In this article, a fire detection and alarm system is proposed to detect fire in earlier stages. The proposed model uses integratedsensors and a camera for fire detection. Therefore, the proposed model avoids the rising of false alarm. The data is collected from the sensors such as smoke, temperature, and flame and are used to train the machine using the machine learning algorithms. Similarly, the image patterns of smoke and flame are also collected and used to train the machine. Therefore, when the fire is detected, the alarm will be buzzed.The remainder of the article is organized as follows: Section 2 discusses the related work. Section 3 presents the proposed system. Section 4 elucidates the components of the proposed architecture. Section 6 confers the efficiency of the proposed system and discusses the ...

show abstract

Section: Related Workmentioning

confidence: 99%

A multimodel fire detection and alarm system for automobiles using internet of things and machine learning

Uma

Eswari

2022

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…In this experiment, we used a dataset collected by Umoh at al. [ 69 ]. The authors graciously provided their dataset with 2100 records from three sensors: DHT11 used as temperature sensor, MQ-2 smoke sensor, and LM393 flame sensor.…”

Section: Experimental Evaluationmentioning

confidence: 99%

“…The authors graciously provided their dataset with 2100 records from three sensors: DHT11 used as temperature sensor, MQ-2 smoke sensor, and LM393 flame sensor. The experiment conducted in [ 69 ] reproduced fire and environment conditions. Therefore, the dataset comprises three features (temperature, smoke, and flame), TS is the timestamp, and a real situation with an output label called “fire outbreak detection” (i.e., the ground truth).…”

Section: Experimental Evaluationmentioning

confidence: 99%

Dempster–Shafer Theory for Modeling and Treating Uncertainty in IoT Applications Based on Complex Event Processing

Bezerra

Teles

Coutinho

et al. 2021

Sensors

View full text Add to dashboard Cite

The Internet of Things (IoT) has emerged from the proliferation of mobile devices and objects connected, resulting in the acquisition of periodic event flows from different devices and sensors. However, such sensors and devices can be faulty or affected by failures, have poor calibration, and produce inaccurate data and uncertain event flows in IoT applications. A prominent technique for analyzing event flows is Complex Event Processing (CEP). Uncertainty in CEP is usually observed in primitive events (i.e., sensor readings) and rules that derive complex events (i.e., high-level situations). In this paper, we investigate the identification and treatment of uncertainty in CEP-based IoT applications. We propose the DST-CEP, an approach that uses the Dempster–Shafer Theory to treat uncertainties. By using this theory, our solution can combine unreliable sensor data in conflicting situations and detect correct results. DST-CEP has an architectural model for treating uncertainty in events and its propagation to processing rules. We describe a case study using the proposed approach in a multi-sensor fire outbreak detection system. We submit our solution to experiments with a real sensor dataset, and evaluate it using well-known performance metrics. The solution achieves promising results regarding Accuracy, Precision, Recall, F-measure, and ROC Curve, even when combining conflicting sensor readings. DST-CEP demonstrated to be suitable and flexible to deal with uncertainty.

show abstract

Fire Hazard Detection and Prediction by Machine Learning Techniques in Smart Buildings (SBs) Using Sensors and Unmanned Aerial Vehicles (UAVs)

Tarar

Bhasin²

2021

Digital Cities Roadmap

View full text Add to dashboard Cite

Support Vector Machine-Based Fire Outbreak Detection System

Cited by 9 publications

References 7 publications

A multimodel fire detection and alarm system for automobiles using internet of things and machine learning

A multimodel fire detection and alarm system for automobiles using internet of things and machine learning

Dempster–Shafer Theory for Modeling and Treating Uncertainty in IoT Applications Based on Complex Event Processing

Fire Hazard Detection and Prediction by Machine Learning Techniques in Smart Buildings (SBs) Using Sensors and Unmanned Aerial Vehicles (UAVs)

Contact Info

Product

Resources

About