Detecting earthquakes in seismological time series is a core task in observational seismology, supporting a range of applications from early warning systems to tectonic research. Typically, seismic sensors passively record data and send it to the cloud or edge for integration, storage, and analysis. While this cloud-based approach is effective in urban or well-connected areas, it is impractical in remote, underwater, or underground environments where network infrastructure is unreliable. In such settings, the sensors must operate independently for extended periods while coping with strict constraints on power, memory, and connectivity. To address these challenges, we present LightEQ, a system that combines an efficient data processing pipeline and a lightweight deep-learning model specifically designed for seismic event detection in such environments. LightEQ runs on ultra-low-power microcontrollers with just 100 kB of RAM, enabling real-time, on-device earthquake detection without the need for continuous streaming of raw data to a central location. We evaluate LightEQ against a traditional STA/LTA approach and state-of-the-art (SOTA) machine learning models, using the Stanford Earthquake Dataset. Unlike existing neural network (NN) models, which are too large for microcontrollers, LightEQ is over ten times smaller than most of the SOTA models. Our results demonstrate that communication is the most energy-intensive task in this setting, and that traditional model-driven filters like STA/LTA are inefficient due to their high false positive rate. In contrast, LightEQ improves detection accuracy with NN, providing a more energy-efficient solution by reducing the number of false positives before transmission. Compared to the STA/LTA method alone, LightEQ extends battery life by at least 3-fold by minimizing energy consumption associated with transmitting false positives to the cloud.
Wireless communication is an essential element within Intelligent Transportation Systems and motivates new approaches to intersection management, allowing safer and more efficient road usage. With lives at stake, wireless protocols should be readily available and guarantee safe coordination for all involved traffic participants, even in the presence of radio failures. This work introduces STARC, a coordination primitive for safe, decentralized resource coordination. Using STARC, traffic participants can safely coordinate at intersections despite unreliable radio environments and without a central entity or infrastructure. Unlike other methods that require costly and energy-consuming platforms, STARC utilizes affordable and efficient Internet of Things devices that connect cars, bicycles, electric scooters, pedestrians, and cyclists. For communication, STARC utilizes low-power IEEE 802.15.4 radios and Synchronous Transmissions for multi-hop communication. In addition, the protocol provides distributed transaction, election, and handover mechanisms for decentralized, thus cost-efficient, deployments. While STARC’s coordination remains resource-agnostic, this work presents and evaluates STARC in a roadside scenario. Our simulations have shown that using STARC at intersections leads to safer and more efficient vehicle coordination. We found that average waiting times can be reduced by up to 50% compared to using a fixed traffic light schedule in situations with fewer than 1000 vehicles per hour. Additionally, we design platooning on top of STARC, improving scalability and outperforming static traffic lights even at traffic loads exceeding 1000 vehicles per hour.
Two-Way Ranging enables the distance estimation between two active parties and allows time of flight measurements despite relative clock offset and drift. Limited by the number of messages, scalable solutions build on Time Difference of Arrival to infer timing information at passive listeners. However, the demand for accurate distance estimates dictates a tight bound on the time synchronization, thus limiting scalability to the localization of passive tags relative to static, synchronized anchors. This work describes the extraction of Time Difference of Arrival information from a Two-Way Ranging process, enabling the extraction of distance information on passive listeners and further allowing scalable tag localization without the need for static or synchronized anchors. The expected error is formally deducted. The extension allows the extraction of the timing difference despite relative clock offset and drift for the Double-Sided Two-Way Ranging and Single-Sided Two-Way Ranging with additional carrier frequency offset estimation.