A Novel Data Fusion Method for Multi-Dimensional Temporal Data Forecasting of Financial Homologous

Spatio temporal data clustering is challenge task. The result of clustering data are utilized to investigate the seismic parameters. Seismic parameters are used to describe the characteristics of earthquake behavior. One of the effective technique to study multidimensional spatio temporal data is visualization. But, visualization of multidimensional data is complicated problem. Because, this analysis consists of observed data cluster and seismic parameters. In this paper, we propose a visualization system, called as IES (Indonesia Earthquake System), for cluster analysis, spatio temporal analysis, and visualize the multidimensional data of seismic parameters. We analyze the cluster analysis by using automatic clustering, that consists of get optimal number of cluster and Hierarchical K-means clustering. We explore the visual cluster and multidimensional data in low dimensional space visualization. We made experiment with observed data, that consists of seismic data around Indonesian archipelago during 2004 to 2014.Keywords: Clustering, visualization, multidimensional data, seismic parameters.

In order to process data fusion, the author proposes a multidimensional sensor data fusion processing system based on big data. The author discusses the principle and basic steps of multidimensional sensor data fusion and analyzes the classification and common data fusion methods of data fusion. Then, the structure and training process of the DBN algorithm are emphatically expounded, experiments are carried out on the randomly collected multidimensional sensor datasets through the DBN algorithm, the validity of the algorithm is verified, and the algorithm is evaluated. The experimental results show that the number of hidden layers is 100, the number of nodes is 100, the weight matrix is a matrix of 784 × 100 , the learning rate is 2, the momentum is 0.5, the number of samples is 100, and the iteration is 1 time. The average reconstruction error obtained by the MATLAB Deep Learn Toolbox is 65.7798. Conclusion. The method proposed by the author can effectively process multidimensional sensor data fusion.

Association rule mining has shown great potential to extract knowledge from multidimensional data sets. However, existing methods in the literature are not effectively applicable to quantitative temporal data. This article extends the concepts of association rule mining from the literature. Based on the extended concepts is presented a method to mine rules from multidimensional temporal quantitative data sets using genetic algorithm, called GTARGA, in reference to Quantitative Temporal Association Rule Mining by Genetic Algorithm. Experiments with QTARGA in four real data sets show that it allows to mine several high-confidence rules in a single execution of the method.

The precipitation oxygen isotopic composition is a useful environmental tracer for climatic and hydrological studies. However, the observed precipitation oxygen is limited at both temporal and spatial scales. Isotope-equipped general circulation models (iGCMs) can compensate for the temporal and spatial discontinuity of observation networks, but they suffer from coarse spatial resolutions and systematic biases. The objective of this study is to build a high-resolution precipitation oxygen isoscape in China for a period of 148 years by integrating observed and iGCMs-simulated precipitation oxygen isotope composition (δ18Op) using data fusion and bias correction methods. The temporal and spatial resolutions are month and 50–60 km for the isoscape, respectively. Prior to building the oxygen isoscape, the performance of two bias correction methods (BCMs) and three data fusion methods (DFMs) is compared after post-processing of eight iGCM simulations. Results show that the outputs of the Convolutional Neural Networks (CNN) fusion method exhibit the strongest correlation with observations with correlation coefficient mostly larger than 0.8, and the smallest bias with root mean square error mostly smaller than 2 ‰. The other two DFMs also perform slightly better than the two BCMs, which show similar performance. Thus, precipitation oxygen isoscape is generated by using the CNN fusion method for the 1969–2007 period in which all iGCMs have output and by using the bias correction methods for the remaining years. Based on the precipitation oxygen isoscape, the spatiotemporal patterns of δ18Op across China are investigated. The generated isoscape shows similar spatial and temporal distribution characteristics to observations. In general, the distribution pattern of δ18Op is consistent with the temperature effect in northern China, and with the precipitation amount effect in southern China, and be more specific in the Qinghai-Tibet Plateau of China. The δ18Op time series mirrors a fluctuating upward trend of the temperature or precipitation in most regions of China. The temporal and spatial distribution characteristics of the generated isoscape are consistent with the characteristics of atmospheric circulation and climate change, indicating successful assimilation and extension of the observed precipitation oxygen isotopes in time and space. Overall, the built isoscape is reliable and useful for providing strong support for tracking atmospheric and hydrological processes. The dataset is available in Zenodo at https://doi.org/10.5281/zenodo.5703811 (Chen et al., 2021).

<strong class="journal-contentHeaderColor">Abstract.</strong> The precipitation oxygen isotopic composition is a useful environmental tracer for climatic and hydrological studies. However, the observed precipitation oxygen is limited at both temporal and spatial scales. Isotope-equipped general circulation models (iGCMs) can compensate for the temporal and spatial discontinuity of observation networks, but they suffer from coarse spatial resolutions and systematic biases. The objective of this study is to build a high-resolution precipitation oxygen isoscape in China for a period of 148 years by integrating observed and iGCMs-simulated precipitation oxygen isotope composition (&delta;¹⁸O_p) using data fusion and bias correction methods. The temporal and spatial resolutions are month and 50&ndash;60 km for the isoscape, respectively. Prior to building the oxygen isoscape, the performance of two bias correction methods (BCMs) and three data fusion methods (DFMs) is compared after post-processing of eight iGCM simulations. Results show that the outputs of the Convolutional Neural Networks (CNN) fusion method exhibit the strongest correlation with observations with correlation coefficient mostly larger than 0.8, and the smallest bias with root mean square error mostly smaller than 2 &permil;. The other two DFMs also perform slightly better than the two BCMs, which show similar performance. Thus, precipitation oxygen isoscape is generated by using the CNN fusion method for the 1969&ndash;2007 period in which all iGCMs have output and by using the bias correction methods for the remaining years. Based on the precipitation oxygen isoscape, the spatiotemporal patterns of &delta;¹⁸O_p across China are investigated. The generated isoscape shows similar spatial and temporal distribution characteristics to observations. In general, the distribution pattern of &delta;¹⁸O_p is consistent with the temperature effect in northern China, and with the precipitation amount effect in southern China, and be more specific in the Qinghai-Tibet Plateau of China. The &delta;¹⁸O_p time series mirrors a fluctuating upward trend of the temperature or precipitation in most regions of China. The temporal and spatial distribution characteristics of the generated isoscape are consistent with the characteristics of atmospheric circulation and climate change, indicating successful assimilation and extension of the observed precipitation oxygen isotopes in time and space. Overall, the built isoscape is reliable and useful for providing strong support for tracking atmospheric and hydrological processes. The dataset is available in Zenodo at <a href="https://doi.org/10.5281/zenodo.5703811" target="_blank" rel="noopener">https://doi.org/10.5281/zenodo.5703811</a> (Chen et al., 2021).

The precipitation oxygen isotopic composition is a useful environmental tracer for climatic and hydrological studies. However, the observed precipitation oxygen is limited at both temporal and spatial scales. Isotope-equipped general circulation models (iGCMs) can compensate for the temporal and spatial discontinuity of observation networks, but they suffer from coarse spatial resolutions and systematic biases. The objective of this study is to build a high-resolution precipitation oxygen isoscape in China for a period of 148 years by integrating observed and iGCMs-simulated precipitation oxygen isotope composition (δ18Op) using data fusion and bias correction methods. The temporal and spatial resolutions are month and 50–60 km for the isoscape, respectively. Prior to building the oxygen isoscape, the performance of two bias correction methods (BCMs) and three data fusion methods (DFMs) is compared after post-processing of eight iGCM simulations. Results show that the outputs of the Convolutional Neural Networks (CNN) fusion method exhibit the strongest correlation with observations with correlation coefficient mostly larger than 0.8, and the smallest bias with root mean square error mostly smaller than 2 ‰. The other two DFMs also perform slightly better than the two BCMs, which show similar performance. Thus, precipitation oxygen isoscape is generated by using the CNN fusion method for the 1969–2007 period in which all iGCMs have output and by using the bias correction methods for the remaining years. Based on the precipitation oxygen isoscape, the spatiotemporal patterns of δ18Op across China are investigated. The generated isoscape shows similar spatial and temporal distribution characteristics to observations. In general, the distribution pattern of δ18Op is consistent with the temperature effect in northern China, and with the precipitation amount effect in southern China, and be more specific in the Qinghai-Tibet Plateau of China. The δ18Op time series mirrors a fluctuating upward trend of the temperature or precipitation in most regions of China. The temporal and spatial distribution characteristics of the generated isoscape are consistent with the characteristics of atmospheric circulation and climate change, indicating successful assimilation and extension of the observed precipitation oxygen isotopes in time and space. Overall, the built isoscape is reliable and useful for providing strong support for tracking atmospheric and hydrological processes. The dataset is available in Zenodo at https://doi.org/10.5281/zenodo.5703811 (Chen et al., 2021).

The precipitation oxygen isotopic composition is a useful environmental tracer for climatic and hydrological studies. However, the observed precipitation oxygen is limited at both temporal and spatial scales. Isotope-equipped general circulation models (iGCMs) can compensate for the temporal and spatial discontinuity of observation networks, but they suffer from coarse spatial resolutions and systematic biases. The objective of this study is to build a high-resolution precipitation oxygen isoscape in China for a period of 148 years by integrating observed and iGCMs-simulated precipitation oxygen isotope composition (δ18Op) using data fusion and bias correction methods. The temporal and spatial resolutions are month and 50–60 km for the isoscape, respectively. Prior to building the oxygen isoscape, the performance of two bias correction methods (BCMs) and three data fusion methods (DFMs) is compared after post-processing of eight iGCM simulations. Results show that the outputs of the Convolutional Neural Networks (CNN) fusion method exhibit the strongest correlation with observations with correlation coefficient mostly larger than 0.8, and the smallest bias with root mean square error mostly smaller than 2 ‰. The other two DFMs also perform slightly better than the two BCMs, which show similar performance. Thus, precipitation oxygen isoscape is generated by using the CNN fusion method for the 1969–2007 period in which all iGCMs have output and by using the bias correction methods for the remaining years. Based on the precipitation oxygen isoscape, the spatiotemporal patterns of δ18Op across China are investigated. The generated isoscape shows similar spatial and temporal distribution characteristics to observations. In general, the distribution pattern of δ18Op is consistent with the temperature effect in northern China, and with the precipitation amount effect in southern China, and be more specific in the Qinghai-Tibet Plateau of China. The δ18Op time series mirrors a fluctuating upward trend of the temperature or precipitation in most regions of China. The temporal and spatial distribution characteristics of the generated isoscape are consistent with the characteristics of atmospheric circulation and climate change, indicating successful assimilation and extension of the observed precipitation oxygen isotopes in time and space. Overall, the built isoscape is reliable and useful for providing strong support for tracking atmospheric and hydrological processes. The dataset is available in Zenodo at https://doi.org/10.5281/zenodo.5703811 (Chen et al., 2021).

The precipitation oxygen isotopic composition is a useful environmental tracer for climatic and hydrological studies. However, the observed precipitation oxygen is limited at both temporal and spatial scales. Isotope-equipped general circulation models (iGCMs) can compensate for the temporal and spatial discontinuity of observation networks, but they suffer from coarse spatial resolutions and systematic biases. The objective of this study is to build a high-resolution precipitation oxygen isoscape in China for a period of 148 years by integrating observed and iGCMs-simulated precipitation oxygen isotope composition (δ18Op) using data fusion and bias correction methods. The temporal and spatial resolutions are month and 50–60 km for the isoscape, respectively. Prior to building the oxygen isoscape, the performance of two bias correction methods (BCMs) and three data fusion methods (DFMs) is compared after post-processing of eight iGCM simulations. Results show that the outputs of the Convolutional Neural Networks (CNN) fusion method exhibit the strongest correlation with observations with correlation coefficient mostly larger than 0.8, and the smallest bias with root mean square error mostly smaller than 2 ‰. The other two DFMs also perform slightly better than the two BCMs, which show similar performance. Thus, precipitation oxygen isoscape is generated by using the CNN fusion method for the 1969–2007 period in which all iGCMs have output and by using the bias correction methods for the remaining years. Based on the precipitation oxygen isoscape, the spatiotemporal patterns of δ18Op across China are investigated. The generated isoscape shows similar spatial and temporal distribution characteristics to observations. In general, the distribution pattern of δ18Op is consistent with the temperature effect in northern China, and with the precipitation amount effect in southern China, and be more specific in the Qinghai-Tibet Plateau of China. The δ18Op time series mirrors a fluctuating upward trend of the temperature or precipitation in most regions of China. The temporal and spatial distribution characteristics of the generated isoscape are consistent with the characteristics of atmospheric circulation and climate change, indicating successful assimilation and extension of the observed precipitation oxygen isotopes in time and space. Overall, the built isoscape is reliable and useful for providing strong support for tracking atmospheric and hydrological processes. The dataset is available in Zenodo at https://doi.org/10.5281/zenodo.5703811 (Chen et al., 2021).

The precipitation oxygen isotopic composition is a useful environmental tracer for climatic and hydrological studies. However, the observed precipitation oxygen is limited at both temporal and spatial scales. Isotope-equipped general circulation models (iGCMs) can compensate for the temporal and spatial discontinuity of observation networks, but they suffer from coarse spatial resolutions and systematic biases. The objective of this study is to build a high-resolution precipitation oxygen isoscape in China for a period of 148 years by integrating observed and iGCMs-simulated precipitation oxygen isotope composition (δ18Op) using data fusion and bias correction methods. The temporal and spatial resolutions are month and 50–60 km for the isoscape, respectively. Prior to building the oxygen isoscape, the performance of two bias correction methods (BCMs) and three data fusion methods (DFMs) is compared after post-processing of eight iGCM simulations. Results show that the outputs of the Convolutional Neural Networks (CNN) fusion method exhibit the strongest correlation with observations with correlation coefficient mostly larger than 0.8, and the smallest bias with root mean square error mostly smaller than 2 ‰. The other two DFMs also perform slightly better than the two BCMs, which show similar performance. Thus, precipitation oxygen isoscape is generated by using the CNN fusion method for the 1969–2007 period in which all iGCMs have output and by using the bias correction methods for the remaining years. Based on the precipitation oxygen isoscape, the spatiotemporal patterns of δ18Op across China are investigated. The generated isoscape shows similar spatial and temporal distribution characteristics to observations. In general, the distribution pattern of δ18Op is consistent with the temperature effect in northern China, and with the precipitation amount effect in southern China, and be more specific in the Qinghai-Tibet Plateau of China. The δ18Op time series mirrors a fluctuating upward trend of the temperature or precipitation in most regions of China. The temporal and spatial distribution characteristics of the generated isoscape are consistent with the characteristics of atmospheric circulation and climate change, indicating successful assimilation and extension of the observed precipitation oxygen isotopes in time and space. Overall, the built isoscape is reliable and useful for providing strong support for tracking atmospheric and hydrological processes. The dataset is available in Zenodo at https://doi.org/10.5281/zenodo.5703811 (Chen et al., 2021).

The precipitation oxygen isotopic composition is a useful environmental tracer for climatic and hydrological studies. However, the observed precipitation oxygen is limited at both temporal and spatial scales. Isotope-equipped general circulation models (iGCMs) can compensate for the temporal and spatial discontinuity of observation networks, but they suffer from coarse spatial resolutions and systematic biases. The objective of this study is to build a high-resolution precipitation oxygen isoscape in China for a period of 148 years by integrating observed and iGCMs-simulated precipitation oxygen isotope composition (δ18Op) using data fusion and bias correction methods. The temporal and spatial resolutions are month and 50–60 km for the isoscape, respectively. Prior to building the oxygen isoscape, the performance of two bias correction methods (BCMs) and three data fusion methods (DFMs) is compared after post-processing of eight iGCM simulations. Results show that the outputs of the Convolutional Neural Networks (CNN) fusion method exhibit the strongest correlation with observations with correlation coefficient mostly larger than 0.8, and the smallest bias with root mean square error mostly smaller than 2 ‰. The other two DFMs also perform slightly better than the two BCMs, which show similar performance. Thus, precipitation oxygen isoscape is generated by using the CNN fusion method for the 1969–2007 period in which all iGCMs have output and by using the bias correction methods for the remaining years. Based on the precipitation oxygen isoscape, the spatiotemporal patterns of δ18Op across China are investigated. The generated isoscape shows similar spatial and temporal distribution characteristics to observations. In general, the distribution pattern of δ18Op is consistent with the temperature effect in northern China, and with the precipitation amount effect in southern China, and be more specific in the Qinghai-Tibet Plateau of China. The δ18Op time series mirrors a fluctuating upward trend of the temperature or precipitation in most regions of China. The temporal and spatial distribution characteristics of the generated isoscape are consistent with the characteristics of atmospheric circulation and climate change, indicating successful assimilation and extension of the observed precipitation oxygen isotopes in time and space. Overall, the built isoscape is reliable and useful for providing strong support for tracking atmospheric and hydrological processes. The dataset is available in Zenodo at https://doi.org/10.5281/zenodo.5703811 (Chen et al., 2021).

The precipitation oxygen isotopic composition is a useful environmental tracer for climatic and hydrological studies. However, the observed precipitation oxygen is limited at both temporal and spatial scales. Isotope-equipped general circulation models (iGCMs) can compensate for the temporal and spatial discontinuity of observation networks, but they suffer from coarse spatial resolutions and systematic biases. The objective of this study is to build a high-resolution precipitation oxygen isoscape in China for a period of 148 years by integrating observed and iGCMs-simulated precipitation oxygen isotope composition (δ18Op) using data fusion and bias correction methods. The temporal and spatial resolutions are month and 50–60 km for the isoscape, respectively. Prior to building the oxygen isoscape, the performance of two bias correction methods (BCMs) and three data fusion methods (DFMs) is compared after post-processing of eight iGCM simulations. Results show that the outputs of the Convolutional Neural Networks (CNN) fusion method exhibit the strongest correlation with observations with correlation coefficient mostly larger than 0.8, and the smallest bias with root mean square error mostly smaller than 2 ‰. The other two DFMs also perform slightly better than the two BCMs, which show similar performance. Thus, precipitation oxygen isoscape is generated by using the CNN fusion method for the 1969–2007 period in which all iGCMs have output and by using the bias correction methods for the remaining years. Based on the precipitation oxygen isoscape, the spatiotemporal patterns of δ18Op across China are investigated. The generated isoscape shows similar spatial and temporal distribution characteristics to observations. In general, the distribution pattern of δ18Op is consistent with the temperature effect in northern China, and with the precipitation amount effect in southern China, and be more specific in the Qinghai-Tibet Plateau of China. The δ18Op time series mirrors a fluctuating upward trend of the temperature or precipitation in most regions of China. The temporal and spatial distribution characteristics of the generated isoscape are consistent with the characteristics of atmospheric circulation and climate change, indicating successful assimilation and extension of the observed precipitation oxygen isotopes in time and space. Overall, the built isoscape is reliable and useful for providing strong support for tracking atmospheric and hydrological processes. The dataset is available in Zenodo at https://doi.org/10.5281/zenodo.5703811 (Chen et al., 2021).

The precipitation oxygen isotopic composition is a useful environmental tracer for climatic and hydrological studies. However, the observed precipitation oxygen is limited at both temporal and spatial scales. Isotope-equipped general circulation models (iGCMs) can compensate for the temporal and spatial discontinuity of observation networks, but they suffer from coarse spatial resolutions and systematic biases. The objective of this study is to build a high-resolution precipitation oxygen isoscape in China for a period of 148 years by integrating observed and iGCMs-simulated precipitation oxygen isotope composition (δ18Op) using data fusion and bias correction methods. The temporal and spatial resolutions are month and 50–60 km for the isoscape, respectively. Prior to building the oxygen isoscape, the performance of two bias correction methods (BCMs) and three data fusion methods (DFMs) is compared after post-processing of eight iGCM simulations. Results show that the outputs of the Convolutional Neural Networks (CNN) fusion method exhibit the strongest correlation with observations with correlation coefficient mostly larger than 0.8, and the smallest bias with root mean square error mostly smaller than 2 ‰. The other two DFMs also perform slightly better than the two BCMs, which show similar performance. Thus, precipitation oxygen isoscape is generated by using the CNN fusion method for the 1969–2007 period in which all iGCMs have output and by using the bias correction methods for the remaining years. Based on the precipitation oxygen isoscape, the spatiotemporal patterns of δ18Op across China are investigated. The generated isoscape shows similar spatial and temporal distribution characteristics to observations. In general, the distribution pattern of δ18Op is consistent with the temperature effect in northern China, and with the precipitation amount effect in southern China, and be more specific in the Qinghai-Tibet Plateau of China. The δ18Op time series mirrors a fluctuating upward trend of the temperature or precipitation in most regions of China. The temporal and spatial distribution characteristics of the generated isoscape are consistent with the characteristics of atmospheric circulation and climate change, indicating successful assimilation and extension of the observed precipitation oxygen isotopes in time and space. Overall, the built isoscape is reliable and useful for providing strong support for tracking atmospheric and hydrological processes. The dataset is available in Zenodo at https://doi.org/10.5281/zenodo.5703811 (Chen et al., 2021).

The study of dynamic spatial and social phenomena in cities has evolved rapidly in the recent years, yielding new insights into urban dynamics. This evolution is strongly related to the emergence of new sources of data for cities (e.g. sensors, mobile phones, online social media etc.), which have potential to capture dimensions of social and geographic systems that are difficult to detect in traditional urban data (e.g. census data). However, as the available sources increase in number, the produced datasets increase in diversity. Besides heterogeneity, emerging social urban data are also characterized by multidimensionality. The latter means that the information they contain may simultaneously address spatial, social, temporal, and topical attributes of people and places. Therefore, integration and geospatial (statistical) analysis of multidimensional data remain a challenge. The question which, then, arises is how to integrate heterogeneous and multidimensional social urban data into the analysis of human activity dynamics in cities? To address the above challenge, this thesis proposes the design of a framework of novel methods and tools for the integration, visualization, and exploratory analysis of large-scale and heterogeneous social urban data to facilitate the understanding of urban dynamics. The research focuses particularly on the spatiotemporal dynamics of human activity in cities, as inferred from different sources of social urban data. The main objective is to provide new means to enable the incorporation of heterogeneous social urban data into city analytics, and to explore the influence of emerging data sources on the understanding of cities and their dynamics. In mitigating the various heterogeneities, a methodology for the transformation of heterogeneous data for cities into multidimensional linked urban data is, therefore, designed. The methodology follows an ontology-based data integration approach and accommodates a variety of semantic (web) and linked data technologies. A use case of data interlinkage is used as a demonstrator of the proposed methodology. The use case employs nine real-world large-scale spatiotemporal data sets from three public transportation organizations, covering the entire public transport network of the city of Athens, Greece. To further encourage the consumption of linked urban data by planners and policy-makers, a set of webbased tools for the visual representation of ontologies and linked data is designed and developed. The tools – comprising the OSMoSys framework – provide graphical user interfaces for the visual representation, browsing, and interactive exploration of both ontologies and linked urban data. After introducing methods and tools for data integration, visual exploration of linked urban data, and derivation of various attributes of people and places from different social urban data, it is examined how they can all be combined into a single platform. To achieve this, a novel web-based system (coined SocialGlass) for the visualization and exploratory analysis of human activity dynamics is designed. The system combines data from various geo-enabled social media (i.e. Twitter, Instagram, Sina Weibo) and LBSNs (i.e. Foursquare), sensor networks (i.e. GPS trackers, Wi-Fi cameras), and conventional socioeconomic urban records, but also has the potential to employ custom datasets from other sources. A real-world case study is used as a demonstrator of the capacities of the proposed web-based system in the study of urban dynamics. The case study explores the potential impact of a city-scale event (i.e. the Amsterdam Light festival 2015) on the activity and movement patterns of different social categories (i.e. residents, non-residents, foreign tourists), as compared to their daily and hourly routines in the periods before and after the event. The aim of the case study is twofold. First, to assess the potential and limitations of the proposed system and, second, to investigate how different sources of social urban data could influence the understanding of urban dynamics. The contribution of this doctoral thesis is the design and development of a framework of novel methods and tools that enables the fusion of heterogeneous multidimensional data for cities. The framework could foster planners, researchers, and policy makers to capitalize on the new possibilities given by emerging social urban data. Having a deep understanding of the spatiotemporal dynamics of cities and, especially of the activity and movement behavior of people, is expected to play a crucial role in addressing the challenges of rapid urbanization. Overall, the framework proposed by this research has potential to open avenues of quantitative explorations of urban dynamics, contributing to the development of a new science of cities.

The study of dynamic spatial and social phenomena in cities has evolved rapidly in the recent years, yielding new insights into urban dynamics. This evolution is strongly related to the emergence of new sources of data for cities (e.g. sensors, mobile phones, online social media etc.), which have potential to capture dimensions of social and geographic systems that are difficult to detect in traditional urban data (e.g. census data). However, as the available sources increase in number, the produced datasets increase in diversity. Besides heterogeneity, emerging social urban data are also characterized by multidimensionality. The latter means that the information they contain may simultaneously address spatial, social, temporal, and topical attributes of people and places. Therefore, integration and geospatial (statistical) analysis of multidimensional data remain a challenge. The question which, then, arises is how to integrate heterogeneous and multidimensional social urban data into the analysis of human activity dynamics in cities? To address the above challenge, this thesis proposes the design of a framework of novel methods and tools for the integration, visualization, and exploratory analysis of large-scale and heterogeneous social urban data to facilitate the understanding of urban dynamics. The research focuses particularly on the spatiotemporal dynamics of human activity in cities, as inferred from different sources of social urban data. The main objective is to provide new means to enable the incorporation of heterogeneous social urban data into city analytics, and to explore the influence of emerging data sources on the understanding of cities and their dynamics. In mitigating the various heterogeneities, a methodology for the transformation of heterogeneous data for cities into multidimensional linked urban data is, therefore, designed. The methodology follows an ontology-based data integration approach and accommodates a variety of semantic (web) and linked data technologies. A use case of data interlinkage is used as a demonstrator of the proposed methodology. The use case employs nine real-world large-scale spatiotemporal data sets from three public transportation organizations, covering the entire public transport network of the city of Athens, Greece. To further encourage the consumption of linked urban data by planners and policy-makers, a set of webbased tools for the visual representation of ontologies and linked data is designed and developed. The tools – comprising the OSMoSys framework – provide graphical user interfaces for the visual representation, browsing, and interactive exploration of both ontologies and linked urban data. After introducing methods and tools for data integration, visual exploration of linked urban data, and derivation of various attributes of people and places from different social urban data, it is examined how they can all be combined into a single platform. To achieve this, a novel web-based system (coined SocialGlass) for the visualization and exploratory analysis of human activity dynamics is designed. The system combines data from various geo-enabled social media (i.e. Twitter, Instagram, Sina Weibo) and LBSNs (i.e. Foursquare), sensor networks (i.e. GPS trackers, Wi-Fi cameras), and conventional socioeconomic urban records, but also has the potential to employ custom datasets from other sources. A real-world case study is used as a demonstrator of the capacities of the proposed web-based system in the study of urban dynamics. The case study explores the potential impact of a city-scale event (i.e. the Amsterdam Light festival 2015) on the activity and movement patterns of different social categories (i.e. residents, non-residents, foreign tourists), as compared to their daily and hourly routines in the periods before and after the event. The aim of the case study is twofold. First, to assess the potential and limitations of the proposed system and, second, to investigate how different sources of social urban data could influence the understanding of urban dynamics. The contribution of this doctoral thesis is the design and development of a framework of novel methods and tools that enables the fusion of heterogeneous multidimensional data for cities. The framework could foster planners, researchers, and policy makers to capitalize on the new possibilities given by emerging social urban data. Having a deep understanding of the spatiotemporal dynamics of cities and, especially of the activity and movement behavior of people, is expected to play a crucial role in addressing the challenges of rapid urbanization. Overall, the framework proposed by this research has potential to open avenues of quantitative explorations of urban dynamics, contributing to the development of a new science of cities.

The study of dynamic spatial and social phenomena in cities has evolved rapidly in the recent years, yielding new insights into urban dynamics. This evolution is strongly related to the emergence of new sources of data for cities (e.g. sensors, mobile phones, online social media etc.), which have potential to capture dimensions of social and geographic systems that are difficult to detect in traditional urban data (e.g. census data). However, as the available sources increase in number, the produced datasets increase in diversity. Besides heterogeneity, emerging social urban data are also characterized by multidimensionality. The latter means that the information they contain may simultaneously address spatial, social, temporal, and topical attributes of people and places. Therefore, integration and geospatial (statistical) analysis of multidimensional data remain a challenge. The question which, then, arises is how to integrate heterogeneous and multidimensional social urban data into the analysis of human activity dynamics in cities? To address the above challenge, this thesis proposes the design of a framework of novel methods and tools for the integration, visualization, and exploratory analysis of large-scale and heterogeneous social urban data to facilitate the understanding of urban dynamics. The research focuses particularly on the spatiotemporal dynamics of human activity in cities, as inferred from different sources of social urban data. The main objective is to provide new means to enable the incorporation of heterogeneous social urban data into city analytics, and to explore the influence of emerging data sources on the understanding of cities and their dynamics. In mitigating the various heterogeneities, a methodology for the transformation of heterogeneous data for cities into multidimensional linked urban data is, therefore, designed. The methodology follows an ontology-based data integration approach and accommodates a variety of semantic (web) and linked data technologies. A use case of data interlinkage is used as a demonstrator of the proposed methodology. The use case employs nine real-world large-scale spatiotemporal data sets from three public transportation organizations, covering the entire public transport network of the city of Athens, Greece. To further encourage the consumption of linked urban data by planners and policy-makers, a set of webbased tools for the visual representation of ontologies and linked data is designed and developed. The tools – comprising the OSMoSys framework – provide graphical user interfaces for the visual representation, browsing, and interactive exploration of both ontologies and linked urban data. After introducing methods and tools for data integration, visual exploration of linked urban data, and derivation of various attributes of people and places from different social urban data, it is examined how they can all be combined into a single platform. To achieve this, a novel web-based system (coined SocialGlass) for the visualization and exploratory analysis of human activity dynamics is designed. The system combines data from various geo-enabled social media (i.e. Twitter, Instagram, Sina Weibo) and LBSNs (i.e. Foursquare), sensor networks (i.e. GPS trackers, Wi-Fi cameras), and conventional socioeconomic urban records, but also has the potential to employ custom datasets from other sources. A real-world case study is used as a demonstrator of the capacities of the proposed web-based system in the study of urban dynamics. The case study explores the potential impact of a city-scale event (i.e. the Amsterdam Light festival 2015) on the activity and movement patterns of different social categories (i.e. residents, non-residents, foreign tourists), as compared to their daily and hourly routines in the periods before and after the event. The aim of the case study is twofold. First, to assess the potential and limitations of the proposed system and, second, to investigate how different sources of social urban data could influence the understanding of urban dynamics. The contribution of this doctoral thesis is the design and development of a framework of novel methods and tools that enables the fusion of heterogeneous multidimensional data for cities. The framework could foster planners, researchers, and policy makers to capitalize on the new possibilities given by emerging social urban data. Having a deep understanding of the spatiotemporal dynamics of cities and, especially of the activity and movement behavior of people, is expected to play a crucial role in addressing the challenges of rapid urbanization. Overall, the framework proposed by this research has potential to open avenues of quantitative explorations of urban dynamics, contributing to the development of a new science of cities.