• ETRI Journal
• /
• v.43 no.2
• /
• pp.272-287
• /
• 2021

This article presents a multi-dimensional spatial pattern analysis of crime events in San Francisco. Our analysis includes the impact of spatial resolution on hotspot identification, temporal effects in crime spatial patterns, and relationships between various crime categories. In this work, crime prediction is viewed as a classification problem. When predictions for a particular category are made, a binary classification-based model is framed, and when all categories are considered for analysis, a multiclass model is formulated. The proposed crime-prediction model (HotBlock) utilizes spatiotemporal analysis for predicting crime in a fixed spatial region over a period of time. It is robust under variation of model parameters. HotBlock's results are compared with baseline real-world crime datasets. It is found that the proposed model outperforms the standard DeepCrime model in most cases.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.208-219
• /
• 2022

Crime amount prediction is crucial for optimizing the police patrols' arrangement in each region of a city. First, we analyzed spatiotemporal correlations of the crime data and the relationships between crime and related auxiliary data, including points-of-interest (POI), public service complaints, and demographics. Then, we proposed a crime amount prediction model based on 2D convolution and long short-term memory neural network (2DCONV-LSTM). The proposed model captures the spatiotemporal correlations in the crime data, and the crime-related auxiliary data are used to enhance the regional spatial features. Extensive experiments on real-world datasets are conducted. Results demonstrated that capturing both temporal and spatial correlations in crime data and using auxiliary data to extract regional spatial features improve the prediction performance. In the best case scenario, the proposed model reduces the prediction error by at least 17.8% and 8.2% compared with support vector regression (SVR) and LSTM, respectively. Moreover, excessive auxiliary data reduce model performance because of the presence of redundant information.

• Korean Institute of Interior Design Journal
• /
• v.24 no.6
• /
• pp.119-127
• /
• 2015

Sou Fujimoto is well known as the 3rd Japanese architect to participate in the Serpentine Pavilion project, especially youngest of all architects. His projects seem very experimental yet inviting, modern yet comforting and these feeling may be resulted in his metaphor of 'Forest' that is very often mentioned in his writings which originally comes from his personal experience of the city and nature. The purpose of this paper is to understand the Fujimoto's metaphor of 'Forest' and design language he uses to express this very idea. The researchers have analyzed Fujimoto's writings and interviews in order to understand his general design ideas and process, then extracted wordings describing 'Forest' in his works. Four main concepts were found and categorized as follows: blurring territorial boundaries, proliferation of parts, manipulating spatial relationships, and ambiguity in function. Then two or three projects were selected and analyzed in each category to understand design methods used. The results show that Fujimoto enjoys using gradation of density to blur territorial boundaries in order to express ambiguous outline of forest, and fractal reproductions in proliferation of parts to uses express wavering whole and modifying angles in manipulating spatial relationships to show hidden order.

• Spatial Information Research
• /
• v.10 no.3
• /
• pp.421-438
• /
• 2002

Abstraction of geographic data within a spatial database context must deal with geometrical simplification, modification or maintenance of the integrity of features, spatial and aspatial data, topology within class, and relationships between classes. This research is to propose a method to abstract a spatial database into a high level database. This study refines operators to carry out the modifications required by the abstraction process in the spatial database. Then, a set of operator sequences (workflows) is suggested to specify operators required to abstract a given feature class and to arrange them in order. Finally, a prototype system is developed, based on rule management with a graphic user interface. When the abstraction process is implemented sequentially we demonstrate that a preferential ordering of operations improves efficiency and reduces loss and distortion in the information.

• Journal of the Korean Geographical Society
• /
• v.48 no.6
• /
• pp.978-993
• /
• 2013

It can be advantage as well as disadvantage to use the spatial weight matrix in a spatial regression model; it would benefit from explicitly quantifying spatial relationships between geographical units, but necessarily involve subjective judgment while specifying the matrix. We took Incheon City as a study area and investigated how the fitness of a spatial regression model changed by constructing various spatial weight matrices. In addition, we explored neighborhood segmentation in the study area and analyzed any influence of it on the model adequacy of two basic spatial regression models, i.e., spatial lagged and spatial error models. The results showed that it can help to improve the adequacy of models to specify the spatial weight matrix strictly, that is, interpreting the neighborhood as small as possible when estimating land price. It was also found that the spatial error model would be preferred in the area with serious spatial heterogeneity. In such area, we found that its spatial heterogeneity can be alleviated by delineating sub-neighborhoods, and as a result, the spatial lagged model would be preferred over the spatial error model.

• Economic and Environmental Geology
• /
• v.37 no.4
• /
• pp.425-436
• /
• 2004

The purpose of this study is to analyze the spatial relationship between the landslides occurred by typhoon, Rusa in 2002 and geospatial dataset. Landslide locations were detected using satellite image and field survey. Topogra-phy, soil, forest, geology and land use data sets were constructed as a spatial database in GIS. From the database, slope, aspect, curvature, water system, type of topography, texture, material, drainage, effective thickness of soil, type, age, diameter, density of wood, lithology, lineament of geology, land use and lineament were used as the land-slide occurrence factors. Using a frequence ratio model, the spatial relationships between the landslides and the factors were extracted. The spatial relationships is helpful to explain the characteristics of the landslide, and to make landslide susceptibility map.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.5
• /
• pp.487-496
• /
• 2020

This study introduces how GISs (Geographic Information Systems) are used to assess spatial disparities in urban green spaces in the Chicago. Green spaces provide us with a variety of benefits, namely environmental, economic, and physical benefits. This study seeks to explore socioeconomic relationships between green spaces and their surrounding communities and to evaluate spatial disparities from a variety of perspectives, such as health-related, socioeconomic, and physical environment factors. To achieve this goal, this study used spatial statistics, such as optimized hotspot analysis, network analysis, and space-time cluster analysis, which enable conclusions to be drawn from the geographic data. In particular, 12 variables within the three factors are used to assess spatial disparities in the benefits of the use of green spaces. Finally, the variables are standardized to rank the community areas and identify where the most vulnerable community areas or parks are. To evaluate the benefits given to the community areas, this study used the z- and composite scores, which are compared in the three different combinations. After identifying the most vulnerable community area, crime data is used to spatially understand when and where crimes occur near the parks selected. This work contributes to the work of urban planners who need to spatially evaluate community areas in considering the benefits of the uses of green spaces.

• Journal of Korean Institute of Industrial Engineers
• /
• v.20 no.2
• /
• pp.65-76
• /
• 1994

The most effective computer algorithms for facility layout that have been found are mainly based on the improvement heuristic such as CRAFT. In this paper, we present a new algorithm which is based on the Kohonen neual network. The algorithm firstly forms a self-organizing feature map where the most important similarity relationships among the facilities are converted into their spatial relationships. A layout is then obtained by a minor adjustment to the map. Some simulation results are given to show the performance of the algorithm.

• The Korean Journal of Ecology
• /
• v.23 no.3
• /
• pp.241-253
• /
• 2000

The degree to which microenvironmental factors are linked to spatial patterns of vegetational factors within ecosystems has important consequences for our understanding of how ecosytems are structured and for conservation of rare species in ecosystems. We studied this relationships between the spatial patterns of microenvironmental factors and vegetational factors in temperate hardwood forest in Mt. Jumbong Biological Reserve Area, Korea. To do this, environmental and vegetational factors from 196 micropoints in a 0.49 ha plot were investigated. Most of all environmental factors and vegetational factors showed the variations among micropoints. Microtopographic factors, litter depth, soil moisture content and relative light intensity at this site were spatially dependent at a scale of 14∼62 m. Coverage of tree and shrub layer and species diversity of herb layer in autumn were spatially dependent at a scale of < 15 m. Species richness and species diversity of herb layer in spring and species richness of herb layer in autumn were spatially dependent at a scale of 28∼48 m. Multiple regression analysis showed that spatial patterns of species richness and species diversity of herb layer in spring and autumn were affected by litter depth, slope, subtree layer, shrub, Sasa borealis etc. The best predictor for the spatial patterns of species richness and species diversity of herb layer at this site was the spatial pattern of litter depth. Species richness and species diversity of herb layer showed strongly negative correlation with litter depth. We estimate that the spatial pattern of litter depth at this site were affected by direction of wind, microtopography and spatial pattern of shrub layer.

• KIISE Transactions on Computing Practices
• /
• v.21 no.12
• /
• pp.774-779
• /
• 2015

In this paper, we present the design and implementation of a large-scale qualitative spatial reasoner using Apache Spark, an in-memory high speed cluster computing environment, which is effective for sequencing and iterating component reasoning jobs. The proposed reasoner can not only check the integrity of a large-scale spatial knowledge base representing topological and directional relationships between spatial objects, but also expand the given knowledge base by deriving new facts in highly efficient ways. In general, qualitative reasoning on topological and directional relationships between spatial objects includes a number of composition operations on every possible pair of disjunctive relations. The proposed reasoner enhances computational efficiency by determining the minimal set of disjunctive relations for spatial reasoning and then reducing the size of the composition table to include only that set. Additionally, in order to improve performance, the proposed reasoner is designed to minimize disk I/Os during distributed reasoning jobs, which are performed on a Hadoop cluster system. In experiments with both artificial and real spatial knowledge bases, the proposed Spark-based spatial reasoner showed higher performance than the existing MapReduce-based one.