VibrosSense tracks home appliance using deep learning

For many years, researchers in eldercare have sought ways to detect how elders are faring in their living environments by placing sensors on appliances, cabinets, and lights, alone with monitors for falls.  In this piece, Cornell electrical engineers have developed a single sensor that does all these things by sensing vibrations.  “Researchers created the sensor device to detect usage in two ways: First, to detect tiny vibrations using a laser Doppler vibrometer; and second to differentiate similar vibrations created by multiple devices by identifying the paths traveled by the vibrations from room to room. The device was trained to distinguish between different activities and learning path signatures as well as distinct noises. VibroSense showed nearly 96% accuracy in identifying 17 different activities across five houses including dripping faucets, an exhaust fan, an electric kettle, a refrigerator and a range hood.”  MORE

Image Credit: Cornell and NewsAtlas