Ontology-aided feature correlation for multi-modal urban sensing

• Main Authors: MISRA, Archan, LANTRA, Zaman, JAYARAJAH, Kasthuri
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2016
• Subjects: Event Detection; Information Fusion; Multi-Modal Sensing; Asian Studies; Environmental Sciences; Numerical Analysis and Scientific Computing; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/3582; https://ink.library.smu.edu.sg/context/sis_research/article/4583/viewcontent/Ontology_aided_SPIE2016_av.pdf
• Institution: Singapore Management University

The paper explores the use of correlation across features extracted from different sensing channels to help in urban situational understanding. We use real-world datasets to show how such correlation can improve the accuracy of detection of city-wide events by combining metadata analysis with image analysis of Instagram content. We demonstrate this through a case study on the Singapore Haze. We show that simple ontological relationships and reasoning can significantly help in automating such correlation-based understanding of transient urban events.