Search

Community participation, as indicated by mobility and engagement in socially meaningful activities, is a central component of health based on the International Classification of Health, Functioning, and Disease (WHO, 2001). Global positioning systems (GPS) technology is emerging as a tool for tracking mobility and participation in health and disability-related research. This paper fills a gap in the literature and provides a thorough description of a method that can be used to generate a number of different variables related to the constructs of mobility and participation from GPS data. Here, these variables are generated with the help of ST-DBSCAN, a spatiotemporal data mining algorithm. The variables include the number of unique destinations, activity space area, distance traveled, time in transit, and time at destinations. Data obtained from five individuals with psychiatric disabilities who carried GPS-enabled cell phones for two weeks are presented. Within- and across- individual variability on these constructs was observed. Given the feasibility of gathering data with GPS, larger scale studies of mobility and participation employing this method are warranted., (Copyright © 2016 Elsevier Ltd. All rights reserved.)

Spatiotemporal data mining has many important applications in environmental modelling. This paper introduces a modified algorithm for spatiotemporal data mining based on density-based spatial clustering of applications with noise (DBSCAN). Based on the modified algorithm, a geographic information system (GIS) add-in was developed using ArcObjects and C#, and is freely available for download. Compared with some existing methods, the new method can perform automated detection of spatiotemporal clusters using limited user input parameters. The application of the add-in was demonstrated using summer temperature data collected from 104 weather stations in southwest China from 1961 to 2011. The results suggest that the modified algorithm can provide more detailed partition of temperature zones compared with some existing methods. [ABSTRACT FROM AUTHOR]

Spatiotemporal data mining studies the field of discovering interesting patterns from large spatiotemporal databases. Although these databases generate a huge volume of data daily from satellite images and mobile sensors like GPS, among these data we find first spatiotemporal and geographical data; secondly, the trajectories browsed by moving objects in some time intervals. Combination of these types of data leads to producing semantic trajectory data. Enriching trajectories with semantic geographical information leads to ease queries, analysis, and mining, in order to give more meaning to behaviors potentially extracted from trajectories. Therefore, applying mining techniques on semantic trajectories continue to prove to be a success story in discovering useful and nontrivial behavioral patterns of moving objects. The purpose of this paper is to make an overview of spatiotemporal knowledge discovery (STKD) and techniques recently used to extract knowledge from spatiotemporal data based on analysis of recent literature. Then leading towards a deeper analysis about semantic trajectory knowledge discovery as a specified field from STKD that integrates trajectory sample points with geographical data before applying mining techniques in order to extract behavioral knowledge from semantic trajectories which can be more useful and significant for the application users. [ABSTRACT FROM AUTHOR]

Spatial sciences are confronted with increasing amounts of high-dimensional data. These data commonly exhibit spatial and temporal dimensions. To explore, extract, and generalize inherent patterns in large spatiotemporal data sets, clustering algorithms are indispensable. These clustering algorithms must account for the distinct special properties of space and time to outline meaningful clusters in such data sets. Therefore, this research develops a hierarchical method based on self-organizing maps. The hierarchical architecture permits independent modeling of spatial and temporal dependence. To exemplify the utility of the method, this research uses an artificial data set and a socio-economic data set of the Ostregion, Austria, from the years 1961 to 2001. The results for the artificial data set demonstrate that the proposed method produces meaningful clusters that cannot be achieved when disregarding differences in spatial and temporal dependence. The results for the socio-economic data set show that the proposed method is an effective and powerful tool for analyzing spatiotemporal patterns in a regional context. [ABSTRACT FROM PUBLISHER]

Discovering traffic bottlenecks and taking action to alleviate congestion to enhance the performance of a traffic network are the most important tasks for the advanced traffic management system in the intelligent transportation system. However, traffic bottlenecks are affected by several factors and vary with spatial and temporal environments, which makes them difficult to define and discover. This paper proposes a three-phase spatiotemporal traffic bottleneck mining (STBM) model, including several spatiotemporal traffic patterns and STBM algorithms that use the raw data of location-based services to discover urban network spatiotemporal traffic bottlenecks. This paper implements an STBM prototype system based on a taxi dispatching system in a Taipei, Taiwan, urban network. The experimental results show that the congestion prediction capability of the proposed heuristic methods (congestion-propagation heuristic) is up to 79.6% during workdays and 72.1% on weekends, which outperforms other methods (e.g., the congestion-converge heuristic, the congestion-drop heuristic, and congested object item), and the discovered spatiotemporal bottlenecks match the travelers' experience. [ABSTRACT FROM PUBLISHER]