Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{179500,
        author = {P. Kalaivani and D. Pavithra and R. Bhuvaneswari and M. Nivetha and S. Pavithra},
        title = {Hazardous Gas Monitoring System Using AI and IoT Technology},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {7032-7037},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179500},
        abstract = {Over the past few years, the challenge has 
been the more extensive leakage of hazardous gases. 
Gas leakage can be easily predicted using the Internet 
of Things (IoT), but the accuracy of the prediction 
process is low. To address the problems associated with 
Convolutional Neural Networks (CNN), the early 
detection of gas leakage levels and hazardous gases 
offers more accurate performance. Furthermore, data 
preprocessing techniques aim to eliminate duplicate 
data, minimize unknown data, and maximize valuable 
data during preprocessing, which are crucial steps. 
Additionally, the Support Vector Machine (SVM) 
focuses on selected network connections within the 
processes, addressing each data type for a more 
accurate representation of performance. Moreover, the 
Decision Tree (DT) process involves selecting related 
features from the margin, which has a hierarchical tree 
structure, and analyzing the range levels in 
performance. Finally, the proposed method determines 
that early prevention in the gas leakage process is 
optimal for the weight rate, while long-term secure level 
testing is performed. Data transmission processes 
involve synchronous and asynchronous mechanisms, 
which measure the leak size, gas type, and surrounding 
conditions; these are evaluated for testing and 
validating the gas leakage prediction data. The process 
is more reliable, exhibiting a high level of performance, 
and the presented method maintains the standard 
scalability of the process. The proposed techniques 
reduce time complexity and low power consumption, 
with performance remaining within an accurate range 
of 92%.},
        keywords = {Convolutional Neural Networks (CNN),  Internet of Things (IoT), Decision Tree (DT), Support  Vector Machine (SVM), Data Preprocessing Technique.},
        month = {May},
        }