Event-triggered Natural Hazard Monitoring with Convolutional Neural Networks on the Edge
This work addresses the challenge of energy-efficient, real-time hazard monitoring for edge-based sensor networks, though it appears incremental by combining existing techniques like quantization and pipelining with a new co-detection method.
The authors tackled the problem of fast decision-making in natural hazard warning systems by developing a wireless sensor network with event-triggered micro-seismic sensors and a novel co-detection technique, resulting in improved response time and memory efficiency for running convolutional neural networks on low-power embedded devices, as demonstrated in a field study on the Matterhorn since 2018.
In natural hazard warning systems fast decision making is vital to avoid catastrophes. Decision making at the edge of a wireless sensor network promises fast response times but is limited by the availability of energy, data transfer speed, processing and memory constraints. In this work we present a realization of a wireless sensor network for hazard monitoring based on an array of event-triggered single-channel micro-seismic sensors with advanced signal processing and characterization capabilities based on a novel co-detection technique. On the one hand we leverage an ultra-low power, threshold-triggering circuit paired with on-demand digital signal acquisition capable of extracting relevant information exactly and efficiently at times when it matters most and consequentially not wasting precious resources when nothing can be observed. On the other hand we utilize machine-learning-based classification implemented on low-power, off-the-shelf microcontrollers to avoid false positive warnings and to actively identify humans in hazard zones. The sensors' response time and memory requirement is substantially improved by quantizing and pipelining the inference of a convolutional neural network. In this way, convolutional neural networks that would not run unmodified on a memory constrained device can be executed in real-time and at scale on low-power embedded devices. A field study with our system is running on the rockfall scarp of the Matterhorn Hörnligrat at 3500 m a.s.l. since 08/2018.