ACOGARE: Acoustic-Based Litter Garbage Recognition Utilizing Smartwatch

Litter has become a social problem. To prevent litter, we consider urban planning, the efficient placement of garbage bins, and interventions with litterers. In order to carry out these actions, need comprehensively grasp types locations litter in advance. However, existing methods, collecting is very costly low privacy. this research, have proposed conceptual design estimate using only sensor data from smartwatch worn by user. This system can record when user raps on picks it up. Also, constructed sound recognition model data, carried experiments. We confirmed that built other people’s enabled F-measure 80.2% noisy environment through experiment 12 participants.