Improving Residential Safety by Multiple Sensors on Multiple Nodes for Joint Emergency Detection

TL;DR

This work tackles residential safety by moving from single-device alerts to a decentralized multi-sensor, multi-node DSN capable of detecting five emergencies. It introduces a two-level voting mechanism that combines intra-node sensor fusion for specificity with inter-node consensus for sensitivity, using node weights to tailor performance. The authors implement ESP32-based nodes with seven sensors per node, ESP-NOW communication, and a two-core voting process, showing robustness to node failures and efficient power usage suitable for long-term operation. Experimental results demonstrate high detection accuracy across fires, gas and water leaks, earthquakes, and intrusions, along with reliable indoor communication and favorable energy characteristics, indicating practical viability for smart homes.

Abstract

Recent advances in low-cost microcontrollers have enabled innovative smart home applications. However, existing systems typically consist of single-purpose devices that only report sensed data to a controller. Given the potential for residential emergencies, we propose to integrate emergency detection systems into smart home environments. We present an ad-hoc distributed sensor network (DSN) designed to detect five common residential emergencies: fires, gas and water leakages, earthquakes, and intrusions. Our novel approach combines diverse sensors with a voting-based consensus algorithm among multiple nodes, improving accuracy and reliability over traditional alert systems. The consensus algorithm employs a majority rule with weighted votes, allowing adjustments for various scenarios. An experimental evaluation confirms our approach's effectiveness in accurately detecting emergencies while demonstrating reliability in mitigating node failures, ensuring system longevity, and maintaining robust communication. Additionally, our approach significantly reduces power consumption compared to alternatives.

Figures (5)

• Figure 1: Odorized gas and CO measurements of a smoldering fire
• Figure 2: Acceleration measurement of a 1 kg mass dropped from a fixed height of 40 cm
• Figure 3: Power consumption of one node for different deep sleep intervals
• Figure 4: Comparison of successful received messages for scenarios (i), (ii), (iii) and (iv)
• Figure 5: successful received messages for scenario (v)