Showing papers in "Geoinformatics FCE CTU in 2007"

An overview of the methods of GIS-based land-use suitability analysis

Abstract: The land-use suitability mapping and analysis is one of the most useful applications of GIS for planning and management. There are four objectives of this paper: (a) to present a historical overview of methods and techniques of GIS-based land-use suitability analysis, (b) to overview multi-criteria synthetically overlay land-use evaluation models, (c) to discuss GIS-based land-use evaluation system, (d) to identify the trends, challenges and prospects of GIS-based land-use suitability analysis. There are two focused perspectives of GIS-based land-use suitability analysis in the paper, the techno-positivist perspective and the socio-political, public participation perspectives. It is organized into six chapters. Chapter 1 defines land-use suitability analysis, and provides an introduction to GIS-based land-use suitability analysis along with a historical perspective. Chapter 2 gives an overview of the development of methods and techniques of GIS-based land-use suitability analysis. The multi-criteria synthetically overlay land-use analysis models is discussed in chapter 3. Chapter 4 offers GIS-based land-use evaluation system. Chapter 5 introduces expert systems for GIS-based land-use suitability evaluation. The concluding chapter summarizes the main points of the papers and discusses problems and prospects from GIS-based land-use suitability analysis. Along with the in-depth development of land research and the constant advancement of GIS technology, GIS-based land-use suitability analysis will toward greater depth.

Remote sensing image segmentation based on self-organizing map at multiple-scale

Abstract: This paper proposes a segmentation method based on K-mean and SOM network. Firstly remote sensing image is decomposed by wavelet transform at multiple-scale. Secondly the directional eigenvector of the image is constructed based on the wavelet transform. At coarser scale, we construct 4-dimension eigenvector with feature images, and the images are roughly segmented by K-means algorithm. Then we construct 4-dimension eigenvector with other feature images at fine scale. Based on the results in K-means segmentation and the eigenvector of remote-sensing images at fine scale the images are segmented by SOM network. The experiments about the images segmentation are done in two different ways, one of which is K-means and SOM network simultaneously, and the other of which is mere K-mean. The experiments show that the former has better segmentation results and higher efficiency.

DEM based investigation of loess shoulder-line

Abstract: The existence of shoulder line is a typical and important characteristic of loess relief, which also plays a significant role in the study of loess landform and erosion process. The construction of a classification and quantifying indexes system are the essential work in the cognition of loess shoulder line. On one hand, along with the development of stream networks, shoulder lines extend themselves in the drainage area, the type and the indexes vary correspondingly as well; on the other hand, a specific type of a shoulder line and its character are the representation of gully development phases. High precision DEMs proves to be a suitable information source in the extraction of loess shoulder lines. Experiment in this study show that 5 meter resolution DEMs is available in extracting of loess shoulder lines after some specific processing. Mathematic morphological method is employed in the process to creating a consecutive shoulder line. Based on proper derivation method and the quantifying indexes system, a deep study of shoulder could be achieved. Shoulder line spatial distribution result is accordant to that of the loess relief character. The study of shoulder line temporal distribution gives an even deeper and comprehensive understanding to the development of loess relief development.

Terrain complexity : definition, index and DEM resolution

Abstract: Digital terrain data are useful for all kinds of applications in digital terrain analysis (DTA). Recently, terrain feature extraction are generally based on grid DEM because most terrain data are organized in a raster format. Terrain complexity is very important terrain feature in digital terrain analysis, however, unlike aspect or slope, terrain complexity is an ambiguous conception that till now no optimal index to quantify it. The traditional terrain complexity definitiones can be classified as statistical, geometrical and semantic indices, these indices can quantify terrain complexity to some extent, but can not evaluate some special terrain. This paper wants to seek an optimal Terrain complexity index (TCI) to evaluate the terrain complexity. The total curvature is a synthesis idex of latitude derivative fxx, longitude derivative fyy, and diagonal derivative fxy, it is a sound solution to the terrain anisotropy. In order to test this index, 3 study area with typical terrain of plain, gully, and hill are selected for experimentation, the result shows total curvature is a sound terrain parameter to evaluate terrain complexity. Terrain complexity is a regional feature, while total cuvature is a local index, so the statistic (Mean TCI, Maximum TCI and SD TCI) are proper indicator to evaluate terrain complexity. The derivative of specific points on the mathematic curve is the ratio of the change in the angle of a tangent that moves over a given arc to the length of the arc, the shorter the arc is, the more arcurate the ratio curvature is. As to grid DEM, the length of arc can be consier as the DEM resolution. Result shows, the Mean TCI, Maximum TCI and SD of TCI have strong correlation with DEM resolution according to regression analysis, the R2 is higher than 0.96.

Integrating computational fluid dynamics (CFD) models with GIS: an evaluation on data conversion formats

Abstract: Computational fluid dynamics (CFD) models are powerful computational tools to simulate urban-landscape scale atmospheric dispersion events. They are proven to be very useful for security management and emergency response. Essential inputs to CFD models include landscape characteristics, which are often captured by various GIS data layers. While it is logical to couple GIS and CFD models to take advantage of available GIS data and the visualization and cartographic rendering capabilities of GIS, the integration of the two tools have been minimal. In this paper, we took the first step to evaluate the use of GIS data in CFD modeling. Specifically, we explore how efficient is to use GIS data in CFD models and how sensitive the CFD results are to different GIS data formats. Using campus topography and building data, and the FEFLO-URBAN CFD model, we performed atmospheric release simulations using topographic data in contour and raster formats. We found that using raster format was quite efficient and contour data required significant effort. Though the simulation outputs from the two data formats were not identical, their overall outcomes were similar and did not post alarming discrepancies. We concluded that using GIS data have tremendous potential for CFD modeling.

An object-based classification approach for high-spatial resolution imagery

Abstract: With the recent availability of commercial high resolution remote sensing multispectral imagery from sensors such as IKONOS and QuickBird, we can't get the accuracy of land-cover classification expected using pixel-based approach. In this paper, we bring about object-based approach combined with the nearest neighbor to classify the QuickBird image of LianYungang city. Firstly, the image is segmented into object feature, we make the shape feature and contextual relation feature join the new feature space which is used to classify. And then we compare the classification of object-based approach accuracy with the nearest neighbor method of classification result, we can draw a conclusion that the method of classification in this paper can recognize geo-types much better. And the overall accuracy is 92.19%; the coefficient of Kappa is 0.8835. Salt and pepper effect is decreased effectively. The result indicates that the approach of land-cover classification combined object features with the nearest neighbor approach supplies another new technique for interpreting high resolution remote sensed imagery.

Quantitative analysis and spatial distribution of slope spectrum : A case study in the Loess Plateau in north Shaanxi province

Abstract: Slope spectrum is defined as a statistic model of slope distribution in a certain area. Previous researches mainly focus on morphology depiction of the slope spectrum; its spatial distribution is unknown yet, especially in the Loess Plateau. Theory and methodology of information entropy and statistics are applied for the objective of quantitatively analyzing the slope spectrum and its spatial distribution in the Loess Plateau in North Shaanxi province. Experiment results show that slope spectrum's information entropy ( H ), skewness of slope spectrum (S) and terrain driving force factor ( T d ) can appropriately depict the slope spectrum and its spatial distribution from different points of view. Spatial distribution of the slope spectrum represents spatial distribution of loess landform types, and it is correlatable with spatial distribution of soil erosion intensity in the Loess Plateau. H , T d and gully density, surface incision depth show positive correlation: gully density and surface incision increase as H , T d increase. On the contrary, the S and gully density, surface incision depth show negative correlation. Lastly, spatial relationship between slope spectrum and loess landform types are qualitatively analyzed, and loess landform evolution as well.

Spatial regression analysis on the variation of soil salinity in the Yellow River Delta

Abstract: In this paper, spatial autocorrelation analysis, ordinary least square (OLS) and spatial regression models were applied to explore spatial variation of soil salinity based on samples collected from the Yellow River Delta. Generally, spatial data, like soil salinity, elevation height etc., are characterized by spatial effects such as spatial dependence and spatial structure. Inasmuch as these effects exist, the utilization of OLS model may lead to inaccurate inference about predictor variable. Moreover, the traditional regression models used to analyze spatial data often have autocorrelated residuals which violate the assumption of Guess-Markov Theorem. This indicates that conventional regression models cannot be used in analyzing variability of soil salinity directly. To overcome this limitation, spatial regression model was introduced to explore the relationship between soil salinity and environmental factors (including elevation height, pH value and organic matter concentration). By verifying Moran's I scatterplot of residuals, we found no autocorrelation in spatial regression model compared with high significant (p < 0.001) positive autocorrelation in the OLS model; besides, the spatial regression model had a significant (p < 0.01) estimations and good-fit-it in our study. Finally, an approach of specifying optimal spatial weight matrix was also put forward.

Earth science framework research based on the digital earth platform

Abstract: This paper explains the basic points of earth science research, reviews the notion of digital earth and suggests the basic concept of digital earth platform. Taking the theory of digital earth as an essence point and the framework of digital earth platform as a main clue, we mainly discuss: the basic theories of digital earth platform, a comparatively flawless model of earth science research framework based on the digital earth platform. The discussing issues involves the unified coordinate projecting, data updating, data transferring, data processing and analyzing and data displaying and a series of researches relating to energy sources, eco-system and disasters monitoring and forecasting with a combination of the suggested model of earth science research framework.

Fusion of multisensor images based on the curvelet transform

Abstract: The research presented in this paper is aimed at the development of multisensor image fusion. The proposed approach is suitable for integration pan-sharpening of multispectral (MS) bands and SAR imagery based on intensity modulation through the a-trous wavelet transform (ATWT) and the curvelet transform(CT). The ATWT is suitable for dealing with objects where the interesting phenomena, e.g., singularities, are associated with exceptional points, and CT as a new multiscale geometric analysis algorithm is more appropriate for the analysis of the image edges and has better approximation precision and sparsity description. This proposed fusion algorithm makes full use of advantages of these multiscale analysis tools, thus it extracts SPOT-Pan high-pass details from the panchrmomatic image by means of the ATWT and SAR texture and edges by details and rationing the despeckled SAR image to its lowpass approximation derived from the CT.SPOT-Pan high-pass details and SAR texture and edges are used to modulate intensity derived from IHS transform of MS bands. SPOT-Pan, Landsat-MS and Radarsat-SAR images covering a region of sanshui in Guangdong province are used to evaluate the effect of the proposed method. The experiment result shows that the proposed algorithm has greatly improved spatial resolution while it keeps the spectral fidelity.

Study on the complex network characteristics of urban road system based on GIS

Abstract: Urban road system is the basic bone of urban transportation and one of the most important factors that influent and controls the urban configuration. In this paper, an approach of modeling, analyzing and optimizing urban road system is described based on complex network theory and GIS technology. The urban road system is studied on three focuses: building the urban road network, modeling the computational procedures based on urban road networks and analyzing the urban road system of Changzhou City as the study case. The conclusion is that the urban road network is a scale-free network with small-world characteristic, and there is still space for development of the whole network as a small-world network, also the key road crosses should be kept expedite.

Establishing a neurocognition-based taxonomy of graphical variables for attention-guiding geovisualisation

Abstract: It is a delicate task to design suitable geovisualisations that allow users an efficient visual processing of geographic information. In digital era, such a design task is confronted with a three-fold challenge: the ever growing amount of geospatial data at various granularity levels, the diversified applications and the continuously expanding range of display sizes. A geovisualisation system that strives for a high usability must satisfy the crucial prerequisite of immediately directing the user's gaze to the location of relevant geographic information and of easy decidability of the underlying semantic meanings. To this end, the cognitive skill of visual attention contributes to mnemonic and executive processes. Attention is indispensable for the visual selection. It facilitates the relevant information retrieval, processing and storage. On the basis of neurocognitive visual information processing, the paper addresses the interdisciplinary approach of attention-guiding design of geovisualisations with the intention to establish a taxonomy of scientifically testable variables. The authors try to relate attention-guiding attributes with graphical variables that cartographers apply to encode geographic information. The work is driven by the motivation to enhance the efficiency of geovisualisations and to enable a more precise neurocognition-based evaluation of geovisualisations.

Geo-ontology design and its logic reasoning

Abstract: With the increasing application of geographic information system (GIS), GIS is faced with the difficulty of efficient management and comprehensive application of the spatial information from different resources and in different forms. In order to solve these problems, ontology is introduced into GIS field as a concept model which can represent object on semantic and knowledge level. Ontology not only can describe spatial data more easily understood by computers in semantic encoding method, but also can integrate geographical data from different sources and in different forms for reasoning. In this paper, a geo-ontology "GeographicalSpace" is built with Web Ontology Language (OWL) after analyzing the research and application of geo-ontology. A geo-ontology reasoning framework is put forward in which three layers are designed. The three layers are presentation layer, semantic service layer and spatial application server layer. By using the geo-ontology repository module and reasoning module in this framework, some more complex spatial location relationships in depth can be mined out. At last, an experiment is designed to demonstrate geo-ontology's ability to execute more intelligent query that can't be implemented in traditional GIS.

Monitoring variation of water turbidity and related environmental factors in Poyang Lake National Nature Reserve, China

Abstract: There are pronounced spatial-temporal patterns in water turbidity in Poyang Lake National Nature Reserve (NNR), China. A most suitable empirical model validated by the field data between Moderate Resolution Imaging Spectroradiometer (MODIS) reflectance and Secchi Disk Depth (SDD) selected as the indicator of water turbidity is used to map the spatio-temporal dynamics. High water transparency values are observed during the summer season, while the most turbid situations always occur in winter. In different years, the trend is similar while the occurrence of detailed peaks is a little different in the same lake. Comparing the situation in different seasons, the most turbid places show in different directions. Different lakes have their specific situations. The turbidity difference in the low-water season is less than the varying in the other seasons. Statistical methods were used to quantify the influence of factors such as water level, wind speed, temperature and rainfall. Further statistic analysis is used to judge the accuracy of the model. Some ancillary environmental factors which can also play a role such as fishing, dredging, vegetation and bird's influence are analyzed by theoretical deduction, supported by field investigations and historical data.

Evaluation of the surface reflectance retrieval on the satellite data

Abstract: Electromagnetic radiance acquired by sensors is distorted mainly by atmospheric absorbing and scattering. Atmospheric correction is required for quantitatively analysis of remote sensing information. Radiation transfer model based atmospheric correction usually needs some atmospheric parameters to be chosen and estimated reasonably in advance when atmospheric observation data is lacked. In our work, a radiometric calibration was applied on the satellite data using revised coefficients at first. Then several parameters were determined for the correction process, taking into account the earth's surface and atmospheric properties of the study area. Moreover, the atmospheric correction was implemented using 6S code and the surface reflectance was retrieved. Lastly, the influence of atmospheric correction on spectral response characteristics of different land covers was discussed in respects of the spectral response curve, NDVI and the classification process, respectively. The results showed that the reflectance of all land covers decreases evidently in three visible bands, but increases in the near-infrared and shortwave infrared bands after atmospheric correction. NDVI of land covers also increases obviously after atmospheric influence was removed, and NDVI derived from the surface reflectance is the highest comparing to that from the original digital number and the top of atmosphere reflectance. The accuracy of the supervised classification is improved greatly, which is up to 87.23%, after the atmospheric effect is corrected. Methods of the parameter determination can be used for reference in similar studies.

Comparison of object-oriented with pixel-based classification techniques on urban classification using TM and IKONOS imagery

Abstract: During the last decades, researchers have mainly focused on improving of the pixel-based classification methods and their applications. As the image resolution improved, it can't get good classification result. In order to overcome this problem, the object-oriented approaches are introduced. In this paper, two methods were compared on urban area. A part of Nanjing city in china was selected as study area; TM and IKONOS imagery were employed. Three pixel-based classification methods, the maximum likelihood, ISODATA (Iterative Self-Organizing Data Analysis Technique), minimum distance method, and an object-oriented technique, the nearest neighbor method, were used to classify image, and evaluate the result. For TM imagery, the accuracy assessment of the results showed that the object-oriented classification approach couldn't get better classification result comparing to the pixel-based classification method, the salt-pepper phenomena of the pixel-based classification result images were not obvious. For IKONOS imagery, classification results provided by the object-oriented classification method were better than the pixel-based classification approaches. So, for urban classification using TM imagery, the traditional classification method could be used to get classification information and an acceptable result could be acquired. But when the IKONOS imagery was used to investigate the urban class, the object-oriented method could find the expected result.

A review of research on ecosystem of arid area using RS-GIS in China

Abstract: Arid area is classical mountain-oasis-desert ecosystem in North-west China. As the ecosystem has its nature geography character obviously, it has superior to research with remote-sensing and geography information system. The study on arid ecosystem in RS-GIS' way is focused on that the landscape spatial pattern of complex MODS ecosystem, the dynamic development of Land use/land cover, the security of ecological environment of eco-tone and so on. At the same time, the research on the single system is more and more, which has provided more ways and deeper fields of arid area using RS-GIS. Through the use of RS-GIS, desertification, oasis' development, urbanization etc. can be known, which would provide precaution for human-being and suitable ways to adjust the problems.

Application and comparing of IDW and Kriging interpolation in spatial rainfall information

Abstract: Geostatistics analyst is based on the fundamental geographic principal, namely, things that are closer together tend to be more alike than things that are farther apart and widely used in many fields. In this paper, taking Ganjiang Drainage as sample region, we select IDW, Ordinary Kriging and Simple Kriging interpolation of geostatistics analyst to interpolate rainfall data and use cross-validation to compare the results of interpolation. In order to find out the most suitable interpolation method, we respectively use different interpolation methods with same parameters, same method with different semivariogram model as well as considering trend influence and anisotropy to interpolate the rainfall data. Comparing the results, we draw the following conclusions: (1) Under the premise of knowing mean, Simple Kriging owns the highest interpolation precision. (2) Kriging has fine feature to reflect rainfall trend changing of larger-scale extent. On the contrary, IDW can depict local detailed changing well. (3) Rainfall data exists weak autocorrelation. (4) Exponential model of semivariogram has the highest precision than others. (5) Ignoring trend influence and anisotropy will not decrease the precision of interpolation.

Modeling spatial-temporal change of Poyang Lake using multi-temporal Landsat imagery

Abstract: Exchanging water with the lower branch of Yangtze River, Poyang Lake is a seasonal lake. During the spring and summer flooding season it inundates a large area while in the winter it shrinks considerably creating a large tract of marshland for wild migratory birds. A better knowledge on the water coverage duration and the beginning and ending dates for the vast range of marshlands surrounding the lake is important for the measurement, modeling and management of marshland ecosystems. In addition, the abundance of a special type of snail ( Oncomelania hupensis ) (the intermediate host of parasite schistosome ( Schistosoma japonicum ) in this region) is also heavily dependent on the water coverage information. However, there is no accurate DEM for the lake bottom and the inundated marshland, nor is there sufficient water level information over this area. In this study, we assess the feasibility on the use of multitemporal Landsat images in mapping the spatial-temporal change of Poyang Lake water body and the temporal process of water inundating of marshlands. All eight Landsat Thematic Mapper images that are cloud free during a period of one year were used in this study. We used NDWI and MNDWI methods to map water bodies. We then examine the annual spatial-temporal change of the Poyang Lake water body. Finally we attempt to obtain the duration of water inundation of marshlands based on the temporal sequence of water extent determined from the Landsat images. The results showed although the images can be used to capture the snapshots of water coverage in this area, they are insufficient to provide accurate estimation on the spatial-temporal process of water inundating over the marshlands through linear interpolation.

Developing a decision tree framework for mining spatial association patterns from GIS database

Abstract: Spatial data mining and knowledge discovery (SDMKD) is a whole process of discovering implicit but useful knowledge from GIS databases. From the first law of geography, spatial association patterns are the realizations of processes that operate across the geographic space. This paper attempts to present a decision tree framework to assist in analyzing spatial association patterns. Based on the problem, the representation of data or data model should be identified firstly. Secondly, geostatistical, lattice and point pattern data can be distinguished through the characteristics of spatial domain. The main task of third level of the decision tree is to apply different spatial data analysis methods to different spatial data types. For lattice data, the work is to apply exploratory spatial data analysis (ESDA) to find spatial association patterns, and then identify the driving forces which cause the observed spatial association patterns by confirmatory spatial data analysis (CSDA). The fourth level is to verify the precision and accuracy of spatial association models. All in all, spatial association pattern analysis is a process of acquiring useful spatial patterns by circulation and repetition.

Integration of spatial information technology for digital urban planning

Abstract: Integration of spatial information technology for digital urban planning (DUP) was studied in this paper based on analyzing the challenges of digital city upon current urban planning as well as its developing trend. Three subjects related to the spatial information technology and integration were discussed in this paper. First of all, the technology methodology system of digital urban planning was built up, and the position and functions of spatial information technology in digital urban planning were defined. Secondly, the technical integratation approaches of spatial information technology for digital urban planning was discussed in three levels, which include data level, function level, and platform level. Thirdly, the integrated application approaches of spatial information technology for digital urban planning were suggested according to the characteristics of master urban planning and detailed urban planning, which include three steps, such as DUP data preparation, DUP scheme creation, and DUP scheme submission.

Role-based access control model for GIS

Abstract: Access control of Geographical Information System (GIS) has more complex spatial constraints than the general MIS system, it makes the classic role-based access control model(RBAC) can't be used in GIS. To achieve an effective Access Control Model for GIS, an extension model of the RBAC is presented in the paper. Firstly, this paper introduce the three kinds spatial constraints that included layer constraints, region constraints and spatial object constraints; Then the paper expanded the basic RBAC model, added regional class, layers class and so on; Finally, the paper has given the system RABC control model as well as the realization method in view of GIS. An extension model of the RBAC is applicable to mobile computing, wireless access and system about location is concluded by analyzing.

Establishment of Beijing underground pipeline information system based on ArcSDE

Abstract: Using GIS, network and database technologies, Beijing underground pipeline information system is established After detailed analysis of the actuality and specialty of the present underground pipeline database managed by Beijing Institute of Surveying and Mapping (BISM), the paper systematically presents the studying purpose, meanings and primary contents According to the study of pipeline data features, a spatio-temporal pipeline database classified by pipeline types is built Based on the database, the urban underground pipeline information system is designed and developed by BISM, which unifies data from planning department and other departments, realizing modernized managements of underground pipeline data input, management, analysis and output

PyWPS 2.0.0: The presence and the future

Abstract: This paper presents current status of PyWPS program, which implements OGC Web Processing Service standard. PyWPS 0.2.0, which was released only recently, implements OGC WPS 0.4.0. Nowadays, OGC is preparing the WPS 1.0.0 standard, with slightly different characteristics. Next versions of PyWPS should implement this version too.

Object-based classification for mangrove with VHR remotely sensed image

Abstract: In remotely sensed imagery with high spatial resolution, more detail spatial information of mangrove forest can be shown. It is important to find a method to effectively use the spatial information so as to improve the accuracy of mangrove forest classification. In the study, different classification schemes (including pixel-based classification and object-based classification), different classifiers, and different texture features have been conducted. The classification results of SPOT-5 image of Matang Mangrove Forest Reserve in Malaysia show that the performances of object-based classifications are better than that of pixel-based classifications. However, the classifier type is important for object-based classification. The accuracies of nearest neighborhood classifiers, which are widely used in object-based classifications, were obviously lower that that of maximum likelihood classifiers and support vector Machines. It is also shown that the involvement of second-order texture features can't effectively improve the classification accuracy of neither object-based classifications nor pixel-based classifications.

Mobile agent based online integration modeling for traffic information services

Abstract: With the rapid development of urban economy and urbanization construction in China, traffic load rises sharply because of the larger vehicle occupancy within many urban areas, which has already led to serious traffic congestion problem. GIS-T is an efficient technological solution and core information infrastructure for solving modern urban transportation problems. High-level traffic systems must integrate real-time traffic information and spatial data of road to supply timely and efficient public services and guarantee a better orderly transportation. However, for traffic information is multisource, complex and massive, traffic information service must have fast, powerful capabilities for online integration processing. Online integration of traffic information emphasizes the traffic resources share and services optimization, and solve assignment, scheduling, monitoring and feedback of integration computing tasks in dynamic and distributed network. This paper firstly analyzes traffic data and existing problems of online integration, and then discusses mobile agent technology, and finally proposes a mobile agent based unified online integration model of traffic information. This model will achieve cooperative computing and more accessible, flexible and reliable traffic information services.

Neural network classification with optimization by genetic algorithms for remote sensing imagery

Abstract: On the remote sensing imagery classification, the traditional methods based on statistical principle has the difficulties in distinguishing the objects with similar spectral characteristics, while the back propagation neural network method has the difficulties in sufficiency and convergence. Therefore, a new method based on neural network classification with optimization by genetic algorithms for remote sensing imagery is proposed in this paper. On the basis of the back propagation( BP )neural network classification, the optimization method by genetic algorithms is presented, including the numbers, the thresholds and the connection weights of nerve nodes of the hide layer in BP neural network. An approach on float coding with alterative length for genetic algorithms is proposed, and the evolution method is improved to obtain an optimal BP neural network. In the end, an experimental test on the remote sensing classification using TM image of Dianshan Lake is carried out, and higher classification accuracy has obtained compared to other methods, which is proved the feasibility and validity of the proposed approach.

Data organization appproach to spatio-temporal GIS in campus real estate

Abstract: Driving by a happened event, entities vary from one state to another. Based on the rule, this paper analyzed the relations between events of entities and its states, and made an improvement on base state with amendments model. The improved model is named as multi base state with amendments model. The key idea of this method is to build more than one historical base state according to the frequency of event happens and the amount of data updates. And for the state between every historical base state, we merely stored the changed part but did not re-store the unchanged part. It overcomes the weakness of snapshot method which leads a great deal of redundant data, and also overcomes the drawback of base state with amendments method which will need a great amount of complex computation when historical state is rebuild. This model has been successfully applied to organize the spatio-temporal data of GIS in campus real estate information system. It is very convenient to rebuild house historical state.

A DEM-based partition adjustment for the interpolation of annual cumulative temperature in China

Abstract: The spatial interpolation of meteorological elements has more important application value. The interpolation methods of air temperature data have been wildly applied in the large scale region. It has been paid more attentions that taking altitude as a variable was introduced into the interpolation models so as to improve the interpolation precision of air temperature data. In a large area, it is difficult to find the relationship between annual cumulative temperature and altitude according to the distribution of meteorological stations. Compared whit it dividing the study area, introducing interpolation models modified by DEM in the smaller region, we can availably improve the spatial interpolation precision of the annual cumulative temperature. The result shows that: Applied in the partition study area, inverse distance squared method modified by DEM can reduce complexity of spatial data analysis in the process of annual cumulative temperature interpolation. Partition interpolation methods take into account some factors that affect the interpolation results, such as the spatial distribution imbalance of the meteorological stations, altitude and region difference. The methods are fit for the interpolation analysis of the large-scale region. Compared with the tradition interpolation methods such as Kriging, Inverse distance interpolation method, etc., inverse distance squared method modified by DEM has higher interpolation precision of annual cumulative temperature in China.

Assisting video surveillance in micro-spatial environments with a GIS approach

Abstract: The paper presents a GIS-based approach to assisting video surveillance in micro-spatial environments, such as inside a building. The approach consists of a node-arc network model representing the accessibility in a building and a topological data structure maintaining the locational relationships among the accessibility network, accessible places, and cameras' FOV (field of vision). Human walking behavior is considered in order to determine the spatial extent of nodes and arcs in the accessibility network. Different measures are employed to deal with some special scenarios in a building, such as spaces between two floors and large open spaces. Based on the network model and the data structure, a number of applications can be realized. One of them elaborated in the paper is to quickly locate suspicious moving objects. Besides the procedure, a detailed description is given to explain how to implement the procedure and how to link the above research output to monitors and cameras.