Smoke Detectors Using ANN

International Journal of Academic Engineering Research (IJAER) 7 (10):1-9 (2023)
  Copy   BIBTEX

Abstract

Abstract: Smoke detectors are critical devices for early fire detection and life-saving interventions. This research paper explores the application of Artificial Neural Networks (ANNs) in smoke detection systems. The study aims to develop a robust and accurate smoke detection model using ANNs. Surprisingly, the results indicate a 100% accuracy rate, suggesting promising potential for ANNs in enhancing smoke detection technology. However, this paper acknowledges the need for a comprehensive evaluation beyond accuracy. It discusses potential challenges, such as overfitting, dataset size, and class imbalance, and presents strategies employed to address these issues. Additionally, the paper emphasizes the importance of alternative evaluation metrics, including precision, recall, and F1-score, to assess the model's performance comprehensively. Detailed information regarding the model architecture, data preprocessing, and hyperparameter tuning is provided to enhance the reproducibility of the research. The study also discusses ethical considerations and the implications of false positives and false negatives in smoke detection applications. While achieving 100% accuracy is a notable accomplishment, this paper calls for cautious interpretation and further validation in real-world settings. It concludes by highlighting areas for future research and improvement in smoke detection technology, emphasizing the need for practical deployment and the reduction of false alarms.

Author's Profile

Samy S. Abu-Naser
North Dakota State University (PhD)

Analytics

Added to PP
2023-11-11

Downloads
911 (#14,926)

6 months
882 (#1,256)

Historical graph of downloads since first upload
This graph includes both downloads from PhilArchive and clicks on external links on PhilPapers.
How can I increase my downloads?