Placemon Uses ML to Monitor Homes
This ESP32-based device uses sensor data along with machine learning to recognize different events that take place inside your house.
The IoT has allowed us to keep tabs on just about everything in our homes, from refrigerators to entertainment systems, and all things in between. While there are many home monitoring kits on the market, others prefer to design their own, which is what Hackaday user 'anfractuosity' did with Placemon – an open hardware platform that senses what’s happening in the home.
Instead of having separate platforms for everything, such as a smoke detector and burglar alarm, the Placemon combines everything under one roof as a generalized monitor, which is then analyzed by machine learning algorithms that notify the users when events happen. Anfractuosus built the Placemon using a series of sensors, including temperature, pressure, light, humidity, and PIR, and is also equipped with a microphone to pick up ambient sounds. Data is collected using an ESP32 microcontroller and sent via Wi-Fi to a box that utilizes TensorFlow that trains to recognize household events.
Training TensorFlow is done using easily repeatable events, like kitchen sounds and operating appliances. Once the specific actions can be identified, Placemon will send wireless notifications of the triggered occurrence. At least that what anfractuosity hopes it will do eventually, as the platform is still in development.
That said, anfractuosity is already in the process of recording specific sounds around his home using a microphone and a laptop, which he will then attempt to classify in TensorFlow. Those interested in his progress can follow anfractuosity's project page.