Using entity identification and classification for automated integration of spatial-temporal data

Abstract

Big data, crucial to answering economic, social, and political questions facing our society, tend to be diverse and distributed through various sites across the Internet. The creation of tools to integrate and analyze such data is of paramount interest. Yet the automation of these processes continues to be a great challenge. Our work rests on the observation that a great number of public data sources in domains ranging from economic to demographic, although of complex structure, often share key similarities, namely the presence of the Time and Location. Our proposed Data Integration through Object Modeling framework or DIOM tackles the critical problem of automating data integration from a variety of public websites by abstracting key features of multi-dimensional tables and interpreting them in the context of knowledge-centered Unified Spatial Temporal Model. Our classification-driven extractors are trained to identify and classify entities from both structured and unstructured parts of spreadsheets. The unstructured part contained in titles, headers, and footers reveals critical information, so-called Implicit Knowledge, crucial to the correct interpretation of data. Our experimental results on real world datasets from heterogeneous public data sources show increased accuracy by 25% compared to state-of-the-art approaches.

Mathematical Modeling of Landslide Slope Dynamics and Sustainable Development of Territories of Asian Russia

“…One of the main goals of infrastructural organization of geospatial data is to provide users to be capable of acquiring complete, exact and updated dataset at the right time. With the advance of information technology, the capabilities of data storage, data mining, and data productivity have triggered a rise in the use of spatial information, especially in the area of regional social and economic development, management and safety (Ahsan et al 2016;Chan et al, 2018). Efficient decision making at the level of regional or interregional spatial development and management relies on the collected information (format, source, attributes etc.)…”

Integrated Virtual Modeling and Aggregation Framework for Optimized Management of Asphaltic Concrete Mixtures Data

“…Past studies adopted spreadsheets to gather and manage data for analysis based on previous designs [54]. However, a known obstacle in modeling is the need for automated tools for seamless data integration and management [55]. Since spreadsheet modeling needs creativity processes, this paper studied the adoption and use of various stages of designing, building, testing, and analysis from past studies [56].…”