Scribd
Upload
35 views

Model-Based Automatic Fire Extinguisher System Using SVM in Matlab

This project proposal aims to develop a model-based automatic fire extinguisher system using support vector machines for early fire detection and mitigation. The system will integrate SVM algorithms into the fire detection mechanism to accurately identify potential fire hazards and trigger immediate extinguishing actions. This will help prevent the escalation of fires and reduce risks. The proposal describes developing an SVM-based model for detection using multi-sensor data fusion. An automated extinguishing mechanism will be integrated with the SVM output. The system will be validated under simulated fire scenarios and a user interface created for monitoring detection and extinguishing.

Uploaded by

Chimaroke Umunna
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
35 views

Model-Based Automatic Fire Extinguisher System Using SVM in Matlab

This project proposal aims to develop a model-based automatic fire extinguisher system using support vector machines for early fire detection and mitigation. The system will integrate SVM algorithms into the fire detection mechanism to accurately identify potential fire hazards and trigger immediate extinguishing actions. This will help prevent the escalation of fires and reduce risks. The proposal describes developing an SVM-based model for detection using multi-sensor data fusion. An automated extinguishing mechanism will be integrated with the SVM output. The system will be validated under simulated fire scenarios and a user interface created for monitoring detection and extinguishing.

Uploaded by

Chimaroke Umunna
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

PROJECT PROPOSAL

Model-based Automatic fire Extinguisher system using


support vector Machines(SVM) for early fire detection
and mitigation

BY

UMUNNA CHIMAROKE DAVID


19CK025927

Submitted to

THE DEPARTMENT OF ELECTRICAL AND


INFORMATION ENGINERING,
COLLEGE OF ENGINEERING, COVENANT
UNIVERSITY

Supervised By:

Dr . Isaac Samuel
Background of study
Fire poses a significant threat to life and property, necessitating the development of advanced
fire detection and extinguishing systems. Even though fire is widely used in many processes,
including cooking, manufacturing, and other activities, and has historically been beneficial
for the advancement of human society, when fire gets out of control—that is, when it
becomes a fire hazard or outbreak—it can seriously affect both human life and property. A
fire can cause significant harm to the natural surroundings as well. The process of detecting
one or more fire-related phenomena, such as smoke, heat, infrared light radiation, or gas, is
known as "fire outbreak detection." The typical method of manually detecting fire outbreaks
is visual observation, but this is a dangerous task that could endanger human life [1]. By
leveraging the capabilities of support vector machines and the computational power of
MATLAB. Support vector machines are nonlinear, data-driven methods that do not take into
account domain expertise when solving pattern classification problems [2] [3]. Support vector
machines is a supervised learning technique which is a whole new class of learning
machines[4]. Moreover, an SVM is well-suited to the utilisation of a small trained data set
and efficiently learns complex relationships without the need for heuristic feature parameters.
Using kernel functions to map the training data into a high-dimensional feature space is the
primary objective of SVM theory. Next, in this feature space, a hyperplane that maximises
the margin between categories is located. Then, vectors of unknown classification with the
largest margin between classes can be classified using the created hyper plane as a basis. This
proposed system aims to enhance fire safety measures through timely detection and
automated extinguishing, minimizing potential damages and casualties.

Significance of Motivation
The proposed model-based automatic fire extinguisher system holds immense potential in
revolutionizing fire safety protocols, particularly in high-risk environments such as industrial
facilities, residential buildings and public spaces. By integrating SVM algorithms into the fire
detection mechanism, the system can accurately identify potential fire hazards and trigger
immediate extinguishing actions, thereby preventing the escalation of fires and reducing the
associated risk.

Problem Statement
Conventional fire detection systems often rely on human intervention or basic sensor
technologies, leading to delayed fire detection and response times. The absence of an
automated and intelligent fire extinguisher system further exacerbates the potential dangers,
resulting in severe property damage and life-threatening situations during fire incidents.
Aim and objectives
 Develop a robust SVM-based model for early fire detection using multi-sensor data
fusion and pattern recognition techniques.
 Implement an automated fire extinguishing mechanism triggered by the SVM models
fire detection outputs to enable swift and effective fire suppression.
 Validate the systems performance through rigorous testing under various simulated
fire scenarios to ensure its reliability and efficiency in real-world applications.
 Design a user-friendly interface for monitoring the fire detection and extinguishing
process, providing real-time alerts and system status updates to users or emergency
responders

Methodology
 Data Acquisition: Collect multi-sensor data, including temperature, smoke density,
and gas emission levels, from integrated fire sensors and environmental monitoring
devices.
 Feature Extraction: Extract relevant features from the acquired data and preprocess
the inputs for the SVM model training and validation.
 SVM Model Development: implement the SVM algorithm to build a robust
classification model capable of accurately detecting fire events based on the extracted
features.
 Extinguishing Mechanism Integration: Integrate the SVM model outputs with an
automated fire extinguishing agent and detection mechanisms.
 Interface Development: Create an intuitive graphical interface using MATLAB for
real-time monitoring of the fire detection and extinguisher process.

References
[1] Umoh, U., Udo, E., & Emmanuel, N. (2019). SUPPORT VECTOR MACHINE-BASED
FIRE OUTBREAK DETECTION SYSTEM. International Journal on Soft Computing,
Artificial Intelligence and Applications, 08(02), 01–18.
https://doi.org/10.5121/ijscai.2019.8201
[2] Wang L., and X. Fu X. (2005). Data Mining with Computational Intelligence. Springer.
Sloin A., Burshtein D. (2008). Support vector machine training for improved hidden Markov
modeling. IEEE Transactions on Signal Processing, Volume 56, 172–188.

[3] Khandoker A. H., Palaniswami M., Karmakar C., K. (2009). Support vector machines for
automatedrecognition of obstructive sleep apnea syndrome from ECG recordings. IEEE
Transactions on
Information Technology in Biomedicine, volume. 13, no. 1, pp. 37–48.
[4] Byoungchul k., Kwang-Ho C., Jae-Yeal N. (2009). Fire detection based on vision sensor
and support
vector machines. Fire Safety Journal. Volume 44, 322-32.

You might also like