Event-Based Analysis of People's Activities and Behavior Using Flickr and Panoramio Geotagged Photo Collections.
ABSTRACT Photo-sharing websites such as Flickr and Panoramio contain millions of geotagged images contributed by people from all over the world. Characteristics of these data pose new challenges in the domain of spatio-temporal analysis. In this paper, we define several different tasks related to analysis of attractive places, points of interest and comparison of behavioral patterns of different user communities on geotagged photo data. We perform analysis and comparison of temporal events, rankings of sightseeing places in a city, and study mobility of people using geotagged photos. We take a systematic approach to accomplish these tasks by applying scalable computational techniques, using statistical and data mining algorithms, combined with interactive geo-visualization. We provide exploratory visual analysis environment, which allows the analyst to detect spatial and temporal patterns and extract additional knowledge from large geotagged photo collections. We demonstrate our approach by applying the methods to several regions in the world.
- SourceAvailable from: utah.edu[show abstract] [hide abstract]
ABSTRACT: Technological advances in position-aware devices are leading to a wealth of data documenting motion. The integration of spatio-temporal data-mining techniques in GIScience is an important research field to overcome the limitations of static Geographic Information Systems with respect to the emerging volumes of data describing dynamics. This paper presents a generic geographic knowledge dis- covery approach for exploring the motion of moving point objects, the prime modelling construct to represent GPS tracked animals, people, or vehicles. The approach is based on the concept of geospatial lifelines and presents a formalism for describing different types of lifeline patterns that are generalizable for many application domains. Such lifeline patterns allow the identification and quantification of remarkable individual motion behaviour, events of distinct group motion behaviour, so as to relate the motion of individuals to groups. An application prototype featuring novel data-mining algorithms has been implemented and tested with two case studies: tracked soccer players and data points representing political entities moving in an abstract ideological space. In both case studies, a set of non-trivial and meaningful motion patterns could be identified, for instance highlighting the characteristic 'offside trap' behaviour in the first case and identifying trendsetting districts anticipating a political transformation in the latter case.International Journal of Geographical Information Science. 01/2005; 19:639-668.
- [show abstract] [hide abstract]
ABSTRACT: The study of human activities and movements in space and time has long been an important research area in social science. One of the earliest spatially integrated perspective for the analysis of human activities patterns and movement in space-time is time-geography. Despite the usefulness of time-geography, there are very few studies that actually implemented its constructs because of a lack of detailed individual-level data and analytical tools. With the increasing availability of georeferenced individual-level data and improvement in the representational and geocomputational capabilities of Geographical Information Systems (GIS), the operationalization of time-geographic constructs has become more feasible recently. This chapter illustrates the value of time-geographic methods in the description and analysis of human activity patterns using GIS-based three-dimensional (3D) geovisualization methods. These methods are used to study gender/ethnic differences in space-time activity patterns using an activity diary data set collected in the Portland (Oregon) metropolitan area. The study shows that geovisualization methods are not only effective in revealing the complex interaction between the spatial and temporal dimensions in structuring human spatial behavior. They are also effective tools for exploratory spatial data analysis that can help the formulation of more realistic computational or behavioral models.
- [show abstract] [hide abstract]
ABSTRACT: DBSCAN is a base algorithm for density based clustering.It can detect the clusters of different shapes and sizes fromthe large amount of data which contains noise and outliers.However, it is fail to handle the local density variation thatexists within the cluster. In this paper, we propose adensity varied DBSCAN algorithm which is capable tohandle local density variation within the cluster. Itcalculates the growing cluster density mean and then thecluster density variance for any core object, which issupposed to be expended further, by considering density ofits -neighborhood with respect to cluster density mean. Ifcluster density variance for a core object is less than orequal to a threshold value and also satisfying the clustersimilarity index, then it will allow the core object forexpansion. The experimental results show that theproposed clustering algorithm gives optimized results.International Journal of Computer Applications. 01/2010;