Intelligent Traffic Monitoring with Hybrid AI
This work addresses traffic monitoring problems for urban planners and transportation systems, but appears incremental as it builds on existing neuro-symbolic and knowledge graph approaches.
The paper tackles challenges in Intelligent Traffic Monitoring (ITMo) by introducing HANS, a neuro-symbolic architecture for multi-modal context understanding, and shows through case studies how it addresses these challenges while integrating with various reasoning methods.
Challenges in Intelligent Traffic Monitoring (ITMo) are exacerbated by the large quantity and modalities of data and the need for the utilization of state-of-the-art (SOTA) reasoners. We formulate the problem of ITMo and introduce HANS, a neuro-symbolic architecture for multi-modal context understanding, and its application to ITMo. HANS utilizes knowledge graph technology to serve as a backbone for SOTA reasoning in the traffic domain. Through case studies, we show how HANS addresses the challenges associated with traffic monitoring while being able to integrate with a wide range of reasoning methods