ShelterSense is an edge AI system for predicting developing environmental and infrastructure failures in emergency shelters through a network of environmental, air-quality, and occupancy sensors.
Emergency shelters will use an Arduino UNO Q Edge AI device to interpret streaming real-time data from CO₂, particulate matter, temperature, humidity, gas, and ventilation sensors. The detection algorithms will identify multimodal patterns associated with degrading ventilation and worsening shelter conditions, allowing the system to recognize developing failures before conventional single-sensor thresholds indicate a critical condition.
Detected conditions will be reported locally through an audible warning system and will continue to operate without an Internet connection. The prototype will use a fan to simulate developing ventilation failures and evaluate whether the Edge AI model can provide earlier and more reliable warnings than conventional threshold-based monitoring.
Gusty is a mesh network for reporting of thunderstorm gust fronts through a cooperating network of automated weather stations, Edge AI, and a LoRa based MeshCore sensor network
Edge wildfire detection and evidence fusion: a detector on any camera, as small as an ESP32, one integrator to weigh their reports. Kernwerk.