In this context, we would like to invite papers on advanced movement analysis, mining of trajectory and sensor data, detection of indoors and outdoors movement and activity patterns, and cutting-edge methods for analyzing and visualizing human mobility overs space and time. Relevant research topics include but are not limited to:
• Mining human mobility and/or sensor data, including predictive analytics (e.g., activity prediction)
• Indoor and outdoor positioning and tracking methods
• Estimation of individual exposures to environmental contexts (e.g., activity-space methods, buffer analysis, kernel density)
• Visualization of movement trajectories with or without objective measures collected from monitoring sensors
• Methodological issues (e.g., the uncertain geographic context problem, the modifiable temporal unit problem)
• Protection of geoprivacy in the collection and analysis of mobility data and in sharing research results
If you are interested in joining the sessions, please submit your abstract at the AAG webpage (http://annualmeeting.aag.org/call_for_submissions) and send the confirmation with your PIN to Kangjae Lee (firstname.lastname@example.org), Jue Wang (email@example.com), and Mei-Po Kwan (firstname.lastname@example.org). Please do not hesitate to contact us if you have any questions regarding the sessions.
Recent advances and widespread use of geospatial technologies (e.g., GPS and environmental sensing) have brought forth unprecedented opportunities for human mobility research in many disciplines, including geography, GIScience, public health, transportation, epidemiology, environmental science, sociology, and environmental health. In mobility research and movement analysis, data mining as an analytical tool provides a variety of ways to not only discover and explore meaningful patterns from trajectory and sensor data and investigate the associations between environmental contexts and health behaviors or outcome over space and time but also infer movement characteristics derived from tracking records. However, there are still daunting challenges in the analysis of huge amounts of trajectory and sensor data for discovering mobility patterns, estimation of individual exposures to environmental contexts, explaining or predicting behavioral outcomes, and visualization of dynamic movement in space and time.
Further, mobility research and movement analysis also face various methodological issues, such as the modifiable temporal unit problem and the uncertain geographic context problem. To address the spatial and temporal uncertainties associated with human mobility, it is imperative to accurately capture human interactions with various environmental contexts at specific places and times using appropriate tracking technologies and/or detailed activity records, such as daily activity diaries. In addition to using tracking techniques, diverse sensors for recording information about ambient environments (e.g., air monitoring sensors) or physical or physiological changes of body states (e.g., accelerometer, heart rate sensors) can also help collect useful data to enhance understanding of human behaviors associated with various health issues, such as health risks or physical and mental health issues.
|Presenter||Phoebe Tran*, , Lam Tran , University of Michigan , Liem Tran, University of Tennessee at Knoxville , Comparisons between 2015 US Asthma prevalence and two measures of asthma burden by racial/ethnic group||20||8:00 AM|
|Presenter||Jing Li*, University of Denver, Tong Zhang, Wuhan University, Xuantong Wang, University of Denver, A spatiotemporal sequence mining approach for ship trajectory data||20||8:20 AM|
|Presenter||Alexander Savelyev*, Texas State University, Exploratory Visualization of Massive Movement Datasets Derived from Social Media Data||20||8:40 AM|
|Presenter||Age Poom*, University of Tartu, Developing dynamic greenspace exposure assessment methodology from long-term GPS tracking dataset||20||9:00 AM|
|Presenter||Jay Christian*, University of Kentucky, Courtney Walker, University of Kentucky, Bin Huang, University of Kentucky, Using commercially available address data to investigate cancer and mountaintop removal coal mining||20||9:20 AM|
To access contact information login