Deriving human activity from geo-located data by ontological and statistical reasoning

TY - JOUR

T1 - Deriving human activity from geo-located data by ontological and statistical reasoning

AU - Dashdorj, Zolzaya

AU - Sobolevsky, Stanislav

AU - Lee, Sang-Geun

AU - Ratti, Carlo

N1 - Funding Information: The authors would like to special thank to Luciano Serafini at the Fondazione Bruno Kessler Data Knowledge Management Unit (FBK-DKM) for providing his intellectual advices for this research. The authors further thank the Telecom Italia Semantic Knowledge Innovation Lab (SKIL) and Banco Bilbao Vizcaya Argentaria (BBVA) for providing the datasets for this research, as well as Ericsson, the MIT SMART Program, the Center for Complex Engineering Systems (CCES) at KACST and MIT CCES program, the National Science Foundation, the MIT Portugal Program, the AT&T Foundation, Audi Volkswagen, BBVA, The Coca Cola Company, Expo 2015, Ferrovial, Liberty Mutual, The Regional Municipality of Wood Buffalo, UBER, all the members of the MIT SENSEable City Lab Consortium and Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT and Future Planning (Number 2015R1A2A1A10052665 ) for supporting the research. Publisher Copyright: © 2017 Elsevier B.V.

PY - 2018/3/1

Y1 - 2018/3/1

N2 - Every day, billions of geo-referenced data (e.g., mobile phone data records, geo-tagged social media, gps records, etc.) are generated by user activities. Such data provides inspiring insights about human activities and behaviors, the discovery of which is important in a variety of domains such as social and economic development, urban planning, and health prevention. The major challenge in those areas is that interpreting such a big stream of data requires a deep understanding of context where each activity occurs. In this study, we use a geographical information data, OpenStreetMap (OSM) to enrich such context with possible knowledge. We build a combined logical and statistical reasoning model for inferring human activities in qualitative terms in a given context. An extensive validation of the model is performed using separate data-sources in two different cities. The experimental study shows that the model is proven to be effective with a certain accuracy for predicting the context of human activity in mobile phone data records.

AB - Every day, billions of geo-referenced data (e.g., mobile phone data records, geo-tagged social media, gps records, etc.) are generated by user activities. Such data provides inspiring insights about human activities and behaviors, the discovery of which is important in a variety of domains such as social and economic development, urban planning, and health prevention. The major challenge in those areas is that interpreting such a big stream of data requires a deep understanding of context where each activity occurs. In this study, we use a geographical information data, OpenStreetMap (OSM) to enrich such context with possible knowledge. We build a combined logical and statistical reasoning model for inferring human activities in qualitative terms in a given context. An extensive validation of the model is performed using separate data-sources in two different cities. The experimental study shows that the model is proven to be effective with a certain accuracy for predicting the context of human activity in mobile phone data records.

KW - Human activity recognition

KW - Knowledge management

KW - Ontology

KW - Spatial data

UR - http://www.scopus.com/inward/record.url?scp=85037573451&partnerID=8YFLogxK

U2 - 10.1016/j.knosys.2017.11.038

DO - 10.1016/j.knosys.2017.11.038

M3 - Article

AN - SCOPUS:85037573451

SN - 0950-7051

VL - 143

SP - 225

EP - 235

JO - Knowledge-Based Systems

JF - Knowledge-Based Systems

ER -