Poster
Feasibility on Detecting Door Slamming towards Monitoring Early Signs of Domestic Violence
IEEE/ACM IoTDI 2022.
Project Overview
Examines whether microcontrollers and TinyML can detect aggressive door slamming as an early warning signal for domestic violence.
By using low-cost microcontrollers and TinyML, this project investigates the feasibility of detecting potential early warning signs of domestic violence and other anti-social behaviors within the home.
The prototype trains a TinyML model to classify door closing events using audio and accelerometer data on an Arduino Nano 33 BLE Sense. The machine learning model achieved 88.89% accuracy under controlled conditions, declining to 87.50% when assorted background noises were mixed in. Results show promising accuracy under varied background noise, highlighting potential for supporting social workers and law enforcement in social housing contexts.
Team
Osian Morgan
Hakan Kayan
Charith Perera