CommuniWave: ML model quantifies informal behavior in urban communities

This study introduces CommuniWave, a machine learning model designed to detect and quantify the Degree of Informal Behavior (DIB) in urban communities.

• The model integrates a Behavior Capture Net (BCN) based on mmaction2.
• It utilizes a self-developed YOLOv10 model named YLX for detection.
• A Behavior Eval Model (BEM) using random forest processes the data.
• The system generates DIB fluctuation charts from street videos to facilitate dynamic monitoring.

The model supports urban managers in making refined decisions to enhance the overall resilience of communities.