The information of public security event contained in text can be the data source of the evaluation and the relief if it can be structured into a relational database. Although previous research can extract the information of events into different attributes, the determination on the attribution of the attribute information to specific event remains unsolved. To solve the problem, this paper proposes a theoretical frame of public security event themed web text structuring, which is composed of three parts. First, an event semantic model is used to construct the seismic event semantic framework which defines abstract elements of event and their semantic relationships. Taking seismicity as an example, spatial element, time element, attribute element, source element are defined as basic elements. Spatial element includes earthquake latitude, longitude, depth and location. Attribute element is further subdivided into four sub-elements: Cause, result, behavior and influence element. Next, an annotation system is applied to typical event materials to label semantic elements, e.g. the place name where an earthquake took place, that is, instantiation of the abstract elements. The key to this step is labeling the relations between elements and specific event. Finally, the event text is structured into event type, event name, event time, event location and other attributes by using the text information extraction algorithm. The algorithm used the labeled materials in the last step as training data to optimize parameters, which can incorporate linked information. The extracted event text (e.g. words, phrases) finally is normalized to structured information for further analysis. An event information mining platform following the whole frame is developed, which includes the modules of webpage searching, text cleaning, event information extraction, visualization and analyzing. The platform processed the whole Chinese webpages of 2014 and found 85 506 seismicity reports. Taking Yunnanludian earthquake as an example, we display the structuring process and result of related web text, which can be the important reference for the relief of the disaster and the analysis of public concern. With the platform, we can demonstrate the seismic text structuring result and its social concern across China, which can be a new tool of event information mining and analyzing.
The international relations are intricate and ever-changing since the 21st century, and have brought profound changes to the world's economy, security, and diplomacy. These changes have had a major impact on China's internal and external policies. A comprehensive and timely analysis of international relations and its changing characteristics has important reference value for China's economic and diplomatic development planning. The analysis of international relations has spatio-temporal characteristics, and it needs real-time processing. Thus, it needs to introduce the methods of spatio-temporal big data analysis to analyze international relations. Traditional mass media such as news, radio, etc. record all kinds of events happening in the world. It contains a wealth of information. Compared with social media data recording personal activities, it is more suitable for large-scale and long-term analysis of human society. The Global Database of Events Language, and Tone (GDELT) is a free and open news database which monitors news from print, broadcast, and online media in the world, analyzes the texts and extracts the key information such as people, place, organization, and event. This paper researches the network characteristics of GDELT based on theory of complex network and further analyze the relations between countries. Firstly, this paper constructs national interaction networks using GDELT, then analyze the interaction relationship between countries through network characteristic statistics, and finally detect the time series changes of the national conflict event interaction network. The results show that: (1)The National interaction network has scale-free characteristics, the interaction between countries is unevenly distributed from a global and local perspective. Very few countries have lots of interactions while most countries have very few interactions, and one country has lots of interactions with a few countries while a few interactions with most countries. (2) Sudden changes in the national interaction network of conflict events often indicates some significant national conflict events. This paper can provide a new perspective for the exploration of international relations and a reference for the analysis of news media in the era of big data.
Given the importance of environment-friendly cities, the development of public bicycle systems (PBSs) has become more popular in recent years around the world. The purpose of this study was to explore the usage patterns of PBSs in small and medium-sized cities in Guangdong province, China, and to infer the driving mechanisms of system attributes and the built environment. The research applied time series analysis of global activity patterns, hierarchical clustering algorithm using Dynamic Time Warping distances as features and spatial data visualization on station-based data, and then compared different systems by employing a random forest algorithm to evaluate the influencing factors. The study objective was to better understand the relationship between public bicycle usage activity and underlying built environment characteristics. In Huicheng District of Huizhou City and Shaoguan City, the public bicycle usage patterns are regular, and bicycle stations are grouped into several clusters based on usage patterns of "morning destination, night origin" "morning origin, night destination" and "steady throughout the day". The PBS in Huicheng District plays various roles by helping users commute to and from jobs and schools, and to make short distance trips. The PBS also is a complementary tool for bus transit facilities. The PBS in Shaoguan City mostly serves as a mode for commuting. The PBS is inefficiently used in Huiyang District of Huizhou City owing to the poor road conditions. This research provides a study framework that can be reproduced in other areas, and offers a way of optimizing PBSs, thereby assisting urban transportation planning and urban land use allocation.
Indoor position data records the Spatiotemporal trajectory of users' activities in indoor space and is an important source of information for studying individual behavior. The similarity with the outdoor positioning data is that the space and time of the data is coupled and distributed, and the visual analysis can better reveal its regularity. However, unlike outdoor positioning data, indoor data has characteristics such as fine granularity in space and time, high positioning accuracy, and a clearer spatial relationship with POI (Point of Interest). Its trajectory is constrained by indoor facilities and space, resulting in high dimensional and irregular characteristics. The visual analysis of these data provides a basis for indoor behavior research, but also brings certain challenges. The existing visualization methods are mainly applied to outdoor positioning data, focusing on the trajectory analysis of spatiotemporal behavior itself, and often neglecting the expression of the POI semantic information with trajectory. To solve this problem, this paper first analyzed the characteristics of indoor location data, in comparison with the particularity of outdoor spatial visualization analysis. On this basis, facing spatial-temporal behavior analysis requirements for the indoor population spatial and temporal distribution, the movement mode and the correlation between related POIs of indoor population, detailed visual analysis contents, cleared the objects for visualize analysis and presentation, and design data structures . And then, this paper constructs a spatiotemporal behavior visualization analysis model from data structure, visualization method, display map and user interaction. Based on the above methods, a passenger flow visualization analysis system was designed for shopping mall with users' Wifi positioning data and implemented by use of the technology of WebGIS (Web based Geographic Information System ) and WebGL (Web Graphics Library). The system realized passenger flow analysis and display in different shops, floors and entire shopping malls in the form of two-dimensional and three-dimensional integration. Finally, correctness and effectiveness of the research results were verified through a practical example.
Urban environmental assessment research has traditionally adopted a method based on field survey, which is difficult to evaluate on a large scale and refined scale. Street view image has a wide coverage, can provide street-level landscape and intuitively reflect the city facade information, and have the advantage of lower cost than on-site data collection, so it provides a large sample data source and new research ideas for urban environmental assessment. Different from the sky view of remote sensing image and the user interaction data of geo-tagged social media, street view image is more focused on recording stereoscopic sectional view of the city street level from the perspective of people, which can represent scenes seen or felt from the ground on a fine scale, so it is more suitable to replace on-site observation of urban environmental assessment. The continuous breakthrough of artificial intelligence technology and its application in various fields make it possible to conduct urban environmental assessment research based on street view image on a wide range of spatial scales. In this paper, we first described and compared three categories of data sources commonly used in urban environmental assessment including street view image, remote sensing image and geo-tagged social media data, and summarized the advantages of street view image in urban environmental assessment. Then we classified the methods used in urban environment assessment based on street view image into the following four categories : methods based on image analysis, statistical analysis, artificial intelligence and spatial analysis. Next, from the urban physical, social, economic and aesthetic environment, we summarized the research and application of street view image in urban environmental assessment. Finally, we pointed out the innovations, limitations and future research directions of the urban environmental assessment based on street view image. On one hand, the application of artificial intelligence represented by deep learning promotes the research progress of urban environmental assessment on large-scale and fine-scale. On the other hand, in the era of big data, the integration of data source represented by street view image, remote sensing image, and geo-tagged social media data will help promote urban environmental assessment research from multiple perspectives and multi-level.
The rapid growth of nation's economy has driven the unprecedented pace of urbanization in China over the past several decades. Urbanization process is a complicated geographical phenomenon involving human-nature interactions, such as population aggregation, land use change, infrastructure construction and eco-environmental changes. Hence, an understanding of the spatiotemporal dynamics of urban development is increasingly important for a variety of issues including research, planning, management and policy decision making. Owing to a spatially and temporally explicit manner of sensed information with respect to the magnitude of socio-economic activity related to urban development, the recent emergence of satellite-derived nighttime light data provides new means for investigating urban patterns and urbanization processes. In the present study, four kinds of quantitative information, including the spatial lighting area, temporal turning point, the spatial transformation of different types of lit areas and the velocity of spatial disperse of nighttime lightings signals, have been obtained and quantitatively analyzed based on time series of big data of annual composite products of nighttime light radiances during the period 1992-2013 from the Defense Meteorological Satellite Program (DMSP). Analysis results reveal the spatiotemporal patterns of China's urbanization over the past 22 years from the perspective of remotely sensed big data of artificial nighttime lighting signals in context of the spatial expansion, the distribution of urbanization onset time, the evolution of spatial structure and the urbanization velocity. This study can provide new insights into the understating of the fundamental spatiotemporal features of the rapid urbanization process in the present-day China using the remotely sensed big data of observed anthropogenic nighttime lighting signals.
With the rapid development of regional integration, nowadays the regional inter-city migration gets the more attention of the scholars at home and abroad. Micro-blog, as one of the most popular application in China, has become a hotspot of research in areas such as sociology and computer. Check-in, as one of Micro-blog's functions, can reflect the flow of inter-city population in real time. We used the crawler program to collect the research samples in the Chengdu-Chongqing urban agglomeration in January 2014. The information includes the Micro-blog's unique ID number, the grid coordinates of Micro-blog sending place, and the city code of the registered place, etc. By running this program, a total of 804204 valid Micro-blog check-in data weare obtained from the Chengdu-Chongqing urban agglomeration. Based on Micro-blog checking areas, this study analyzeds the spatial structure of the Chengdu-Chongqing urban agglomeration. And Wwe combined the micro-blog data with the traditional socioeconomic data, in order to analyze the impact factors of the regional migration. The results indicates that the spatial structure of micro-blog shows the characteristics of "many centers of dual-core" group in this area. There are only two cities whose micro-blog flows are more than 100,000. They are Chengdu and Chongqing, forming athe “dual-core”. The direction of Micro-blog flow is affected by administrative division, and the intensity of Micro-blog flow presents a certain grade difference. The network shows an obvious hierarchy, and it closely correlatesnnects with the actual social-economic area closely, such as GDP, population size and the strength of traffic connection. For Chengdu and Chongqing, its GDP ranksed first and second,1, 2 respectively, with athe population size all of greater than 7.59 million and both as a regional transport hubs, it makes their micro-blogWeibo flows areintensity in ranked 1st and, 2nd, places respectively. Lastly, there are still some differences between Micro-blog's space and the actual geographic space inof Chengdu-Chongqing urban agglomeration. In the background of the national Yangtze River Economic Belt and China's new urbanization, we put the network information into the geographical space. Actually In this paper we discovered the spatial network characteristics of Chengdu-Chongqing urban agglomeration, and then this paper pointeds out the influence of socioeconomic factors on Micro-blog cyberspace flow. Of course, there may still be other factors behind Micro-blog's cyberspace, which need to be explored and analyzed in the future.
With the development of technology and the popularity of social media in recent years, more and more people like to express their true thoughts and emotions through social media. Therefore, a large amount of data that contains a variety of information such as geographic location, text content, and emotions is being generated. It provides a new data source for urban and personal perception research in the era of big data. Based on the analysis of big data generated by Weibo users, this study uses Python to perform word frequency analysis and topic analysis on Weibo data. The purpose is to explore the emotional expressions and concerns of people on traditional Chinese festivals, including Spring Festival, Lantern Festival, Tomb-sweeping Day, Dragon Boat Festival and Mid-Autumn festival, and to find out people’s perception changes and regional characteristics of Chinese traditional festivals under the influence of urbanization and globalization. Through the analysis, this study has several findings. First, people have the strongest perception of the Spring Festival. To be specific, they mostly express good wishes for the New Year, and the emotions are relatively positive. The second one is the Mid-Autumn festival, and people focus on going home to reunite with relatives. Moreover, Valentine's Day has become a more popular holiday, showing that globalization has a certain impact on traditional Chinese festivals. Second, the change of transportation has both positive and negative impacts on the quality of the festival and people's perception. During traditional festivals, the main way to travel is by air and by car. Airports and highways are places that are closely related to the festival activities. Third, people have a good perception of the traditional common customs. However, there are differences in the forms of festivals and dietary customs among different regions, and the differences are gradually decreasing. Therefore, it is of great necessity to promote the implementation of traditional Chinese festival revitalization projects, to inherit and promote the Chinese traditional festival customs.
Improving urban functions and enhancing urban carrying capacity become new targets for urban planning and development. Quantifying urban space quality has become the research focus of urban planning in recent years. However, the lack of dynamic continuity and spatial accuracy in measuring the space quality weakens the practical value in urban planning. This study used the dynamic population information derived from cellular signaling data of one day and the Analytic Hierarchy Process (AHP) method to establish a framework for evaluating dynamic spatial quality continuously at the functional block scale. The center region of Beijing within the fifth Ring were selected as a case study to test the evaluation framework. The time-varying spatial quality patterns and the correlation with dynamic population distribution were comprehensively investigated. The results show that the imbalance of the space quality in Beijing varies as the population distribution changes, and the significant differentiation in spatial-temporal and functional dimensions are manifested in the following aspects: We find that there exists spatial heterogeneity in the inner ring and outer ring of the city, which is more significant between the southern and northern parts of the city. On the time dimension, the spatial quality in the research area generally presents the unstable trend of "steep drop-low value stability-steep rise-high stability". On the dimension of function type, there are special changing modes on different functional types’ blocks and larger gap in the mean spatial quality values between functional areas. The quality of the living space in the night block has significant level differences in the city. These results show that the spatial quality is significantly differentiated in the time, space and functional nature of the city. Meanwhile, the analysis of the relationship between population activity and spatial quality can evaluate the rationality of current resource allocation in various types of blocks. These results can offer supportive references and recommendations for more scientific and rational urban planning at the microscopic scale.
During the process of urbanization, the interactions between urban and suburb areas are becoming increasingly close through substantial exchanges of people, products, information etc. To accurately identify and quantify such interactions has become a key to understanding urban-rural relationships and achieving more effective resource allocation and scientific urban planning. Mobile phone data has high user penetration rate and low cost on data collection, making it an important source of for investigating human dynamics. We reconstructed composite user trajectories from the raw mobile phone data of Beijing in a weekend day. After data preprocessings including cleaning missing data, correcting error data, and coordinate conversion are performed, this study inferred the types of spatial interactions by integrating the point of interest (POI) data along the trajectories and the pre-knowledge of human activities, and investigated the spatio-temporal characteristics of the distant and the intensive interactions of different types between urban and rural areas. Through the decomposition of interaction types, complex urban-rural anomaly interaction patterns can be decomposed into 49 basic types. By calculating the ratio of the intensity of one flow type in a certain direction to the intensity of the same type in both directions, the characteristics of urban and rural interaction in Beijing can be obtained. The results showed that the urban-rural interactions among different regions of Beijing exhibit multi-scale patterns and distance attenuation patterns, and unveiled the spatio-temporal patterns of very long-distance interactions with the approaches of the stay-point extraction and the Gaussian kernel density function. It can be seen from the results that the overall pattern of spatial interaction among the internal regions of Beijing presents a trend of decreasing from the center of the city to the periphery. The method proposed in this paper attempts to reflect the distribution difference of public resources and infrastructure between urban and rural areas by mining the spatial interaction of human activities. It reveals the spatial structure and resource allocation characteristics of Beijing, and provides a scientific basis for the urban and rural planning policy formulation.
With the acceleration of the urbanization, residents' traffic demand has been continuously increasing, resulting in increasingly severe traffic congestion in large cities. The concept of traffic demand management(TDM） has become an important theoretical basis for relevant policies, but the existing research also shows that TDM has a significant adjustment effect on travel with higher flexibility, while the regulation of travel with lower flexibility is not obvious.Research on mobility behaviors such as travel flexibility has become increasingly urgent, and the new spatio-temporal data, such as smart traffic card data, has provided new opportunities to explore the complex of the residents' travel behavior. Travel elasticity refers to the traveler’s preference for the choice of decision variables over a long period of time. It is the selected probability and discreteness of the selection in the travel decision. It is usually used to measure the room for changes in the travel choice behavior, including time elasticity, travel mode flexibility, route flexibility, fare elasticity, etc. In this paper, we measured the travel elasticity of the residents' departure time who takes the subway to work and analyzed the spatial and temporal distribution features based on the smart traffic card data of residents in Beijing in March 2014. The results showed: (1) The average travel elasticity of residents in Beijing who go to work by subway is 0.521. It shows that the overall travel of residents is still relatively flexible, and it also confirms the effectiveness of this research method in revealing the characteristics of residents' travel behavior. (2) There are spatial and temporal differences in the flexibility of Beijing residents. The elasticity of the individual's is higher in the rest days than that of the working day. The elasticity during the peak hours is higher than that in off-peak hours. (3) There are also spatial agglomerations of travel flexibility. Travel elasticity has spatial autocorrelation, tends to agglomerate in space, and there are obvious hot spot areas. At the same time ,the inner city residents' travel flexibility is significantly higher than that of the outskirts of the city.
Weather conditions have a substantial impact on urban residents' daily travel activities. They usually determine the travel demand within a specific spatial location by land use type, as well as the route selection strategy between a pair of travel origin and destination. This information is crucial for stakeholders including urban dwellers, city planners and transport managers to optimize urban mobility, facility allocation and transportation resilience. In this paper, we apply spatiotemporal statistics, multiple linear regression and clustering analysis on taxi data and weather records of Wuhan City, China to understand the spatiotemporal characteristics of residents' travel demand and taxi drivers' route selection under different weather conditions. As a result, the dominant weather condition factors influencing residents' travel activities are revealed on space and time. First, taxi demand is more vulnerable to weather changes on weekdays than weekends. It is negatively proportional to the increasement of rainfall, temperature and wind speed. Second, at city scale taxi demand decreases along with raining on weekdays while the demand increases on weekends. In particular, the short-distance travels increase while medium- and long-distance travels decrease. Third, taxi demand is more vulnerable to weather changes within the urban area than the suburban area. On rainy days, medium-distance travels within the urban area decrease, whereas short-distance travels within the suburban area increase. Fourth, taxi demand on residential area increases, whereas the demand on commercial area decreases on rainy days. Last, taxi drivers are found to prefer the shortest path on sunny days and the fastest path on rainy days. Those research results can assist urban planners and municipal managers to enhance their understanding of urban residents' mobility pattern and their spatiotemporal dynamics more deeply.
Spatial outlier mining can find the spatial objects whose non-spatial attribute values are significantly different from the values of their neighborhood. Faced with the explosion of spatial data and problems such as single machine performance bottleneck and difficult expansion, the traditional centralized processing mode has gradually failed to meet the needs of applications. In this paper, we propose a parallel spatial outlier mining algorithm and its prototype system which are based on Constrained Spatial Outlier Mining (C-SOM) and make full use of the advantages of a parallel computing framework Spark's fast memory computing and scalability. The parallel algorithm uses C-SOM algorithm as the core algorithm, executes the C-SOM algorithm on a Spark cluster composed of multiple nodes for a global dataset and many local datasets concurrently to get the global outliers and the local outliers. Datasets are divided into multiple regional datasets according to the administrative division. A region dataset is considered as a local dataset and the global dataset contains all of the selected local datasets to be mined. The lightweight prototype system implements the parallel algorithm based on Spark and adopts Browser/Server architecture to provide users with a visualized operation interface which is concise and practical. Users can select the region datasets and set the parameters of C-SOM algorithm on interfaces. The prototype system will execute the parallel algorithm on a Spark cluster and finally list both the global and local outliers which have the top largest outlier factor values so that users can make further analysis. At last, we use the soil geochemical investigation data from Fujian eastern coastal zone area in China and a series of artificial datasets to carry out experiments. The results of the soil geochemical datasets experiments validate the rationality and effectiveness of the parallel algorithm and its prototype system. The results of the artificial datasets experiments show that, compared to single machine implementation, our parallel system can support analysis for much more datasets and its efficiency is much higher when the number of datasets is big enough. This study confirms the local instability characteristics of spatial outliers and demonstrates the rationality, and effectiveness of the parallel algorithm and its prototype system to detect global and local spatial outliers simultaneously.
