Copyright (c) 2010 All rights reserved. http://works.bepress.com/sungsoon_hwang Recent documents in Sungsoon Hwang en-us Thu, 09 Sep 2010 01:31:11 PDT 3600 http://works.bepress.com/sungsoon_hwang/13 http://works.bepress.com/sungsoon_hwang/13 Tue, 07 Sep 2010 20:14:27 PDT We describe a framework for implementing computational thinking in a broad variety of general education courses. The framework is designed to be used by faculty without formal training in information technology in order to understand and integrate computational thinking into their own general education courses. The framework includes examples of computational thinking in a variety of general education courses, as well as sample in-class activities, assignments, and other assessments for the courses. The examples in the different courses are related and differentiated using categories taken from Denning Great Principles of Computing, so that similar types of computational thinking appearing in different contexts are brought together. This aids understanding of the computational thinking found in the courses and provides a template for future work on new course materials. Specific examples of computational thinking in the design category are provided in the context of three distinct courses. Ljubomir Perkovi´c Geographic Information Science http://works.bepress.com/sungsoon_hwang/12 http://works.bepress.com/sungsoon_hwang/12 Mon, 08 Jun 2009 11:21:21 PDT Spatial sorting of housing market in a metropolitan area is relatively well studied, but its implications in transportation are understudied. Housing market segmentation is defined as a degree to which a metropolitan area is divided into spatial housing submarkets. The book looks at how housing market segmentation is related to commute length at a metropolitan scale. The analysis is preceded by delineating housing submarkets by fuzzy clustering methods, and defining the index of housing market segmentation that measures the separation among housing submarkets. Results show that metropolitan areas characterized by incongruous housing market are more likely to be associated with longer vehicle miles of commute while other factors are controlled for. It is speculated that deepening housing market segmentation constrains housing choice, and residents compensate for the constraint by longer commute. The book will be useful for those interested in land use–transportation interaction and the application of fuzzy classification to socioeconomic data. Sungsoon Hwang Land use/transportation interaction http://works.bepress.com/sungsoon_hwang/10 http://works.bepress.com/sungsoon_hwang/10 Thu, 30 Apr 2009 23:32:31 PDT This study investigates whether a fuzzy clustering method is of any practical value in delineating urban housing submarkets relative to clustering methods based on classic (or crisp) set theory. A fuzzy c-means algorithm is applied to obtain fuzzy set membership degree of census tracts to housing submarkets defined within a metropolitan area. Issues of choosing algorithm parameters are discussed on the basis of applying fuzzy clustering to 85 metropolitan areas in the U.S. The comparison between results of fuzzy clustering and those of crisp set counterpart shows that fuzzy clustering yields statistically more desirable clusters. Sungsoon Hwang Geographic Information Science http://works.bepress.com/sungsoon_hwang/9 http://works.bepress.com/sungsoon_hwang/9 Thu, 30 Apr 2009 23:29:11 PDT This paper presents how hot spot detection methods can be extended to allow for temporal dimensions. Major concerns are how temporal dimension is incorporated into the framework of point pattern analysis, while maintaining the capability of multi-scale analysis. The study elaborates on expanding the scope of (space) K function in order to count time in the analysis. With the explicit treatment of time as well as space, K function falls into three category depending on the way space and time are controlled; (1) space K function, (2) time K function, (3) space-time K function. Space K function is equivalent to the original K function, the method for detecting spatial hot spots where time is controlled. Time K function is the method for etecting temporal hot spots where space is controlled. Space-time K function is broken down to three distinct types: The first type examines spatial pattern of observations disaggregated into temporal category. The second type examines temporal pattern of observations disaggregated into spatial category. The third type detects spatio-temporal pattern, or any interaction between space and time. A set of K function is tested on traffic crash data. The case study illustrates how each category of K function can be used to answer different queries, such as whether there is significant spatial/temporal hot spots, in which scale, and where if any. In addition, temporal variation of spatial hot spots can be explored using the first type of space-time K function. This study demonstrates the explicit treatment of temporal dimensions can enhance the process of knowledge discovery. Newly formulated K functions can provide the methodological framework for exploring spatial, temporal, and spatio-temporal patterns of point events across varying scales. Sungsoon Hwang Geographic Information Science http://works.bepress.com/sungsoon_hwang/6 http://works.bepress.com/sungsoon_hwang/6 Fri, 20 Mar 2009 13:19:55 PDT The impact of job accessibility on housing prices is examined in the Buffalo and Seattle metropolitan areas using a hedonic regression modeling framework. Global hedonic regression results show that job accessibility is positively associated with housing price in the two study areas. Local hedonic regression modeling is also conducted to test whether the response of the housing market to job accessibility is spatially stationary. The statistical analysis reveals that the role of job accessibility in the house price-setting process varies locally in each metropolitan area. Empirical challenges with unraveling relationship between transportation and land use, and the policy implications of our findings, are discussed. Sungsoon Hwang Land use/transportation interaction Geographic Information Science Geographic Information System http://works.bepress.com/sungsoon_hwang/5 http://works.bepress.com/sungsoon_hwang/5 Fri, 20 Mar 2009 13:17:56 PDT Sungsoon Hwang Geographic Information System http://works.bepress.com/sungsoon_hwang/4 http://works.bepress.com/sungsoon_hwang/4 Fri, 20 Mar 2009 13:14:10 PDT It has long been argued that the housing market is spatially compartmentalized within a metropolitan area. The argument has important implications in explaining how the housing market works – should the status quo be seen as an equilibrium state, or if no equilibrium is reached how do loosely interlaced submarkets function both independently and interdependently? The authors note that this body of literature has leaned toward testing the distinctiveness of housing submarkets given a priori housing submarkets. However, there seems to be lack of interest in developing methods for empirically deriving housing submarkets. Fuzzy clustering is well suited to this problem given that the boundary of housing submarkets is not often sharply delineated. The study applies a fuzzy c-means (FCM) algorithm to identify housing submarkets in the Buffalo-Niagara Falls region. The study is distinct from other FCM applications in three respects. First, we reflect on issues tied to choosing parameters of fuzzy clustering. Second, we introduce overlap measures to characterize the relationship between clusters produced. Third, we evaluate the performance of fuzzy clustering in terms of hedonic prediction accuracy. Results show that stratified hedonic models predict house price better than a market-wide hedonic model. Fuzzy clustering solutions also yield better prediction compared to hard clustering. Sungsoon Hwang Housing submarkets http://works.bepress.com/sungsoon_hwang/3 http://works.bepress.com/sungsoon_hwang/3 Fri, 20 Mar 2009 12:43:13 PDT The Atlas and Database of Air Medical Services (ADAMS) is a web-based, password-protected, geographic information system containing data on air medical service main and satellite base helipads, communication centers, rotorwing aircraft, and major receiving hospitals for trauma in the United States. ADAMS initially was developed to provide the geographic information needed to support realtime, wireless routing of automatic crash notification (ACN) alerts from a crashed motor vehicle to the nearest air medical transport service and trauma center. This coupling of ADAMS and ACN technology to enhance emergency communications is expected to speed delivery of emergency medical care to crash victims and thereby reduce the deaths and disabilities caused each year. In addition to its planned use in ACN response, ADAMS is also a valuable data resource for trauma system research and homeland security applications. This article begins with an overview of ADAMS and briefly describes the features and rationale for its development. ADAMS is then used as a tool to assess the extent of air medical rotor-wing service coverage nationwide. Both geographic area and populations covered are determined for all 50 states. The correlation between increased air medical service coverage and reduced motor vehicle crash fatality rates is then examined. Marie Flanigan Geographic Information System http://works.bepress.com/sungsoon_hwang/2 http://works.bepress.com/sungsoon_hwang/2 Fri, 20 Mar 2009 12:28:33 PDT It is often the case that locality boundaries are not sharply delineated in our mental maps. This paper examines the level of uncertainty involved in perceiving qualitative boundaries of urban vs. rural localities. To measure location indeterminacy of locality, we begin with modeling locality as fuzzy region or also known as egg-yolk model which is composed of core, boundary, and exterior. The more a specific locality (e.g., Buffalo, Amherst) is geocoded within core, the more locality is location-determinant. 5460 fatal traffic accidents gathered from the Fatality Analysis Reporting System (FARS) in New York State from year 1996 to 2001 are classified into urban vs. rural cases, and are compared in terms of location indeterminacy. Location indeterminacy of rural localities are significantly higher than urban counterparts. It implies that perceiving boundaries of urban localities is less error prone than those of rural localities. The study shows that uncertainty is inherent in human cognition of geographic knowledge, and it poses challenges in geocoding imperfect data such as FARS. Sungsoon Hwang Geographic Information Science http://works.bepress.com/sungsoon_hwang/1 http://works.bepress.com/sungsoon_hwang/1 Fri, 20 Mar 2009 12:15:41 PDT With increasingly available amount of data on a geographic space, spatial data mining has attracted much attention in a geographic information system (GIS). In contrast to the prevalent research efforts of developing new algorithms, there has been a lack of effort to re-use existing algorithms for varying domain and task. Researchers have not been quite attentive to controlling factors that guide the modification of algorithms suited to differing problems. In this study, ontology is examined as a means to customize algorithms for different purposes. We also propose the conceptual framework for a spatial data mining (system) driven by formal ontology. The case study demonstrated that formal ontology enabled algorithms to reflect concepts implicit in domain, and to adapt to users’ view, not to mention unburdened efforts to develop new algorithms repetitively. Sungsoon Hwang Geographic Information Science