Download or read book Analysis and Modeling Techniques for Geo-spatial and Spatio-temporal Datasets written by Kulsawasd Jitkajornwanich and published by . This book was released on 2017 with total page 144 pages. Available in PDF, EPUB and Kindle. Book excerpt: In recent years, spatio-temporal data has received a lot of attention and increasingly plays an important role in our everyday lives as we can witness from the fast-growing mobile technologies and its location-based application development. By spatio-temporal data, we mean data that is associated with specific spatial locations that change over time. For example, a cellphone or car with GPS will generate the object location at regular time intervals. Another example would be the track of a storm center as it moves. Spatio-temporal data could be thought of as a huge data warehouse, which contains hidden and meaningful information. However, to analyze the available spatiotemporal data directly from its original formats and locations is not easy because the data is often in a format that is difficult to analyze and is usually 'big'. Our research goals focus on spatio-temporal datasets and how to summarize, model, and conceptualize them for analysis and mining. Five main parts of this dissertation include: 1) spatio-temporal knowledge representation, 2) identifying meaningful concepts from raw data, 3) converting raw data to conceptual data, 4) analysis and mining of conceptual data, and 5) a general framework for big data analysis and mining. In the first part of the dissertation, we look at the spatio-temporal datasets in general by considering spatio-temporal data semantics using techniques similar to those utilized in the “Semantic Web”. We work towards creating a spatio-temporal ontology framework, which can be used to represent and reason about spatio-temporal data. In the next three parts, we focus on the spatio-temporal datasets in a specific domain, which is rainfall precipitation data in the hydrology domain. However, the techniques and methodology that we use can be adapted to different types of hydrological data such as soil moisture, water level, etc., as well as other types of big spatio-temporal data. Therefore, in the final part, we propose a generalized framework for analyzing and mining big data in any given domain. The framework allows big data in a particular domain to be conceptually analyzed and mined by using ontologies and EER.