Abstract

This paper presents SmartStove Guardian, a cloud-integrated Internet of Things (IoT) system designed to detect unsafe gas stove conditions in households occupied by elderly individuals with memory impairment, and to automatically dispatch emergency services when intervention thresholds are exceeded. The system combines edge-based sensor fusion—incorporating gas concentration, infrared thermal sensing, and carbon monoxide detection—with a serverless cloud pipeline built on Microsoft Azure. Azure Functions orchestrate real-time ingestion and anomaly scoring using a weighted composite risk model; Azure SignalR Service delivers sub-second caregiver alerts across web and mobile clients; and an emergency dispatch module can interface with public-safety dispatch infrastructure (e.g., CAD/PSAP integrations where available) when the computed risk score exceeds a configurable critical threshold. In simulation across 500 generated scenarios, the system achieves a detection accuracy of 97.3%, a mean end-to-end alert latency of 1.2 seconds, and an estimated false-positive dispatch rate of 0.4%. The proposed architecture eliminates dependency on caregiver availability and provides an autonomous, always-on safety layer for a vulnerable population currently underserved by existing smart-home technology. System cost is projected at approximately $120 USD per deployed unit. This work contributes a complete reference architecture, a formal risk-scoring formulation, and a discussion of deployment considerations including regulatory compliance and data privacy.

References

• National Fire Protection Association, “Home Fires Involving Cooking Equipment,” NFPA Research, Quincy, MA, USA, Tech. Rep., 2023. [Online]. Available: https://www.nfpa.org/education-and-research/research/nfpa-research/fire-statistical-reports/home-fires-involving-cooking-equipment
• M. Chan, D. Esteve, C. Escriba, and E. Campo, “A review of smart homes—Present state and future challenges,” Comput. Methods Programs Biomed., vol. 91, no. 1, pp. 55–81, Jul. 2008, doi: 10.1016/j.cmpb.2008.02.001.
• P. Rashidi and A. Mihailidis, “A survey on ambient-assisted living tools for older adults,” IEEE J. Biomed. Health Inform., vol. 17, no. 3, pp. 579–590, May 2013, doi: 10.1109/TITB.2012.2234129.
• J. Kim and S. Lee, “CookSafe: Non-intrusive load monitoring for kitchen appliance safety,” in Proc. IEEE Int. Conf. Consumer Electron. (ICCE), Las Vegas, NV, USA, 2019, pp. 1–4, doi: 10.1109/ICCE.2019.8661974.
• Y. Wang, H. Li, and Q. Zhang, “iStove: Vision-based flame and hazard detection for smart kitchens,” IEEE Sensors J., vol. 21, no. 8, pp. 10112–10121, Apr. 2021, doi: 10.1109/JSEN.2021.3056893.
• F. Bonomi, R. Milito, J. Zhu, and S. Addepalli, “Fog computing and its role in the Internet of Things,” in Proc. 1st Edition MCC Workshop Mobile Cloud Comput. (MCC), Helsinki, Finland, 2012, pp. 13–16, doi: 10.1145/2342509.2342513.
• Microsoft Corporation, “Azure IoT Reference Architecture,” Microsoft Docs, 2022. [Online]. Available: https://learn.microsoft.com/en-us/azure/architecture/reference-architectures/iot
• European Parliament and Council, “Regulation (EU) 2015/758 Concerning Type-Approval Requirements for the Deployment of the eCall In-Vehicle System,” Official Journal of the European Union, 2015.
• Occupational Safety and Health Administration, “Carbon Monoxide Poisoning,” U.S. Department of Labor, 2023. [Online]. Available: https://www.osha.gov/carbon-monoxide-poisoning