Search

With the rapid development of information technologies such as the Internet, the Internet of Things and cloud computing, network big data is widely used in various fields of society, and making good use of network big data is great significance to the sustainable development of cities. Based on the network big data as the data source, this paper analyzes the spatial distribution and spatial-temporal pattern of house prices in the main city zone of Kunming through the Getis-Ord Gi* index and Kriging method, and quantifies the spatial-temporal changes of house prices through statistical analysis and spatial overlay analysis. The result shows that in hot and cold spot analysis, hot spot (high house price agglomeration area) is surrounded by cold spot (low house price agglomeration area), and Chenggong District is the cold spot dominant area. The house price in the main city zone of Kunming forms two high-value areas in the spatial distribution, and presents a pile-shaped ring structure with a central high price and low price in circumference. During the study period, the overall house price fluctuations were small, showing a pattern of north high and south low. The results of statistical analysis and spatial overlay analysis show that there is a significant difference in house prices among various administrative districts. The high-value clusters and low-value clusters in house prices are randomly distributed in various administrative regions. The price changes in Chenggong District are the most significant, and Panlong District has the smallest change.

Urbanization has created a significant gap between the Three Northeast Provinces (TNP) and the Yangtze River Delta (YRD) since China’s reform and opening-up. In this study, we explain this problem ...

With the development of economy, growth of population and urbanization, urban land is increasing and the speed of urban expansion is speeding up. Mastering the spatial-temporal process of urban expansion is of great significance for natural environment and human development. In this paper, taking the Dianchi Lake Basin as an example, based on the TM and OLI image data from 1990 to 2015, every five years as a time node, the decision tree classification method is used to extract and analyze the urban land for each period of image data. The results showed that the area of urban land in Dianchi Lake Basin increased from 1990 to 2015 with 462km2, with an average annual growth rate of 5.9%, of which the fastest expansion rate has occurred from 2010 to 2015. The impervious surface expansion is radiation-like growth centered around the urban area of Kunming, mainly in the eastern and northern parts of Dianchi.

Change in urban construction land use is an important factor when studying urban expansion. Many scholars have combined cellular automata (CA) with data mining algorithms to perform relevant simulation studies. However, the parameters for rule extraction are difficult to determine and the rules are simplex, and together, these factors tend to introduce excessive fitting problems and low modeling accuracy. In this paper, we propose a method to extract the transformation rules for a CA model based on the Classification and Regression Tree (CART). In this method, CART is used to extract the transformation rules for the CA. This method first adopts the CART decision tree using the bootstrap algorithm to mine the rules from the urban land use while considering the factors that impact the geographic spatial variables in the CART regression procedure. The weights of individual impact factors are calculated to generate a logistic regression function that reflects the change in urban construction land use. Finally, a CA model is constructed to simulate and predict urban construction land expansion. The urban area of Xinyang City in China is used as an example for this experimental research. After removing the spatial invariant region, the overall simulation accuracy is 81.38% and the kappa coefficient is 0.73. The results indicate that by using the CART decision tree to train the impact factor weights and extract the rules, it can effectively increase the simulation accuracy of the CA model. From convenience and accuracy perspectives for rule extraction, the structure of the CART decision tree is clear, and it is very suitable for obtaining the cellular rules. The CART-CA model has a relatively high simulation accuracy in modeling urban construction land use expansion, it provides reliable results, and is suitable for use as a scientific reference for urban construction land use expansion.

In order to guide the city's waterlogging control, it's very necessary to research the urban waterlogging occurrence rules and how urbanization affects the urban waterlogging. In this paper, we select the catchment area located in Kunming Dongfeng East Road as study area to construct the urban waterlogging simulation model based on GIS and SWMM model. The procedure of model building contains sub-basin division, drainage system generalization, and parameter settings. Then different urbanization degrees and different rainfall return period settings will be tested on the constructed model. The results show that the model can be used for dynamically simulating urban waterlogging. Both runoff volume and peak flow increased significantly with increasing return period. In addition, with the development of urbanization, urban impervious area increased rapidly, but decreased in rainfall infiltration, while the risk of floods increased. This impact was more obvious in the short return period rainfall conditions.

In 1989, HIV was detected amongst injecting drug users (IDUs) in Yunnan province. Needle sharing drove the epidemic and HIV spread rapidly to IDUs in neighboring cities and along drug trafficking routes. By 2002, HIV was present amongst IDUs in all mainland Chinese provinces. It is believed that IDUs may have been the core source for all later sub-epidemics in China. Agent-based modeling (ABM) is the dominant paradigm in social complex network simulation which allows one to simulate the complex systems emerge from the bottom-up are composed of a multitude of heterogeneous objects called agents. This article puts forward an HIV/AIDS spatial and temporal transmission model of IDUs based on the multivalent system and geographic information systems (GIS) in an urban environment, and simulates the HIV/AIDS spatial and temporal transmission process among injection drug users during 10 years on the Repast Simphony1.2 platform. In the model, the crowd is classified into 5 types: healthy person, HIV person, AIDS person, IDU person and HIV-IDU person. Individuals represented by agents are associated to places where they interact with each other. The relationship among different agents is described with random social network. To better represent individuals in reality, each agent has its only sex, age, career, education, geographic location and other attributes. In each time step, the model defines these agents' specific behavioral rules. The model is implemented using the propagation of HIV/AIDS among injection drug users in Yunnan province southwest of China as a case study. The simulation results show that the number of initial HIV in injection drug users, the proportion of needle sharing and individual social impact have influence on the spread of HIV/AIDS in Kunming. The results also reveal the increasing HIV/AIDS transmission among injection drug users and interpret the necessity of carrying out solutions to contain the transmission of HIV/AIDS.

Having analyzed the current status and existing problems of Geographic Information Systems (GIS) applications in epidemiology, this chapter proposes a method to establish a spatial decision support system (SDSS) for the prevention of epidemic diseases by integrating the COM GIS, spatial database, gps, remote sensing, and communication technologies, as well as ASP and ActiveX software development technologies. One important issue in constructing the SDSS for epidemic disease prevention concerns the incorporation of epidemic spread models in a GIS. The chapter begins with a description of the capabilities of GIS in epidemic prevention. Some established models of an epidemic spread are studied to extract essential computational parameters. A technical schema is then proposed to integrate epidemic models using a GIS and relevant geospatial technologies. The GIS and modeling platforms share a common spatial database and the modeled results can be visualized spatially by desktop and Web clients. A complete solution for establishing the SDSS for epidemic disease prevention based on the model integrating methods and the ArcGIS software is suggested in this chapter. The proposed SDSS comprises several sub-systems: data acquisition, network communication, model integration, epidemic disease information spatial database, epidemic disease information query and statistical analysis, epidemic disease dynamic surveillance, epidemic disease information spatial analysis and decision support, as well as epidemic disease information publishing based on the Web GIS technology. The design process and sample VC and VB programming codes of the epidemic case precaution are used as an example to illustrate the basic principles and methods of the system development that integrates GIS functions with models of epidemic spread. A case study of AIDS in the Yunnan Province of China exemplifies the systems spatial analytical functions through its spatial database access and statistical analysis tools.