A client-based visual analytics framework for large spatiotemporal data under architectural constraints

A primary aim of visual analytics is to provide end-users interactive and scalable environments to facilitate their decision making tasks. Researchers have often utilized several server-client solutions to support interactive data exploration (e.g., building the data cube, parallelizing data processing). However, these solutions can suffer from scalability issues especially in the absence of adequate computation functionality provided by servers. Organizational policies can also prohibit the transfer of data to external data servers because of security or budgetary concerns; thereby, severely limiting the capability of the visual analytic systems. Therefore, in this paper, we propose an interactive client-based visual analytics framework for large-scale spatiotemporal data. The proposed framework follows a sampling based incremental visual analysis approach to sustain the real-time responsiveness, meanwhile, with affordable computation resources in a client machine. General sampling methods [34] preprocess the entire dataset to build data indexing, which can bring the client unaffordable computation overhead. Instead, our framework proposes a novel data management model, using the spatiotemporal clustering pattern to predictively organize and sample data based on historical data acquisition activities. We demonstrate the capabilities and usefulness of our framework by applying it on crime data and Twitter data. We also conduct several experimental evaluations to determine the efficacy of our framework.