The Development of a Web-based Demographic Data Extraction Tool for Population Monitoring

Transactions in GIS

Transactions in GIS, August 2011, Volume 15, Issue 4

T. Edwin Chow, Yan Lin, and W. Derek Chan

“The Internet contains a great wealth of information available online. People search engines, such as WhitePages (http://www.whitepages.com), gather personal-level demographic data, including full name, address, age and household members. Requiring only a surname and locational reference (e.g. city or postal code) as the minimum search criteria, such people search engines can be perceived as a gigantic database of demographic records.

Geocoded Vietnamese-Americans (VA) in Texas solicited from WhitePages

Geocoded Vietnamese-Americans (VA) in Texas solicited from WhitePages

“The objective of this article is to outline the development of a web-based demographic data extraction tool for population monitoring. In this study, a web prototype was developed to extract web demographics of the Vietnamese-American (VA) population in Texas, an ethnic minority with unique migration history, from WhitePages. After post-processing, the personal-level demographic data represent 40.3% of 202,003 VA in Texas reported by the American Community Survey (ACS) 2009. While all enumeration strategies, the web approach included, have their own strengths and weaknesses, this study suggests an alternative approach that is complementary to existing enumeration strategies. More research and development are needed to validate the accuracy of web demographics and further enhance data navigation and extraction rules. The utilization and release of web demographics must be cautious with regards to privacy and integrity of personal identity.”

A Neural Network for Modeling Multicategorical Parcel Use Change

International Journal of Applied Geospatial Research International Journal of Applied Geospatial Research, Vol. 2, Issue 3, 2011

Kang Shou Lu, John Morgan, and Jeffery Allen

“This paper presents an artificial neural network (ANN) for modeling multicategorical land use changes. Compared to conventional statistical models and cellular automata models, ANNs have both the architecture appropriate for addressing complex problems and the power for spatio-temporal prediction. The model consists of two layers with multiple input and output units. Bayesian regularization was used for network training in order to select an optimal model that avoids over-fitting problem. When trained and applied to predict changes in parcel use in a coastal county from 1990 to 2008, the ANN model performed well as measured by high prediction accuracy (82.0-98.5%) and high Kappa coefficient (81.4-97.5%) with only slight variation across five different land use categories. ANN also outperformed the benchmark multinomial logistic regression by average 17.5 percentage points in categorical accuracy and by 9.2 percentage points in overall accuracy. The authors used the ANN model to predict future parcel use change from 2007 to 2030.”

Keynote Speakers at URISA’s 2011 GIS in Public Transportation Conference

URISA and the University of South Florida’s National Center for Transit Research at the Center for Urban Transportation Research (CUTR) are pleased to feature two keynote speakers for the 2011 GIS in Public Transportation Conference, which will take place at the Hilton Bayfront in St. Petersburg, Florida, September 13-15, 2011.

The opening keynote address on the morning of September 14 is Missed Opportunity: Transit and Jobs in Metropolitan America.

Against the backdrop of rising gas prices, growing suburban poverty, continued sprawl and uneven transit availability in cities and suburbs, the Metropolitan Policy Program at the Brookings Institution has completed a first-of-its-kind analysis that shows how transit systems link workers to jobs in metropolitan America. The analysis covers 371 transit agencies in the 100 largest U.S. metro areas, and provides information that can inform critical policy and investment decisions at a time of scarce public and private resources.

The general session keynote address on September 15 is Open Trip Planner: Open Source Multimodal Trip Planner.

The OpenTripPlanner (OTP) project is an international effort to create a flagship open source platform for multimodal trip planning and analysis. As free and open source software, OTP can be freely downloaded, deployed, and modified by anyone, and is optimized for use with open data sources and standards such as OpenStreetMap for base network data and the General Transit Feed Specification (GTFS) for transit system data. OTP was established in the summer of 2009 to bring together a number of previously independent open source trip planning projects into a unified effort, and the project and its associated development community have since grown rapidly. In addition to the United States, there are now live OTP deployments in Canada, Poland, India, Spain, Ireland, and Israel. Later this fall, Portland’s TriMet will formally launch a beta trip planning application built entirely on the OpenTripPlanner platform and open data sources, marking the first official deployment of a fully open source / open data trip planner by a major U.S. transit agency. This keynote session will provide an overview of OTP’s history and current capabilities, including live demos, as well as a roadmap for development of the project going forward.

A poster session (still accepting submissions), exhibition and networking events round out the conference experience. Registration and hotel discounts are available through the end of August. For complete conference, exhibits, travel and registration information, visit http://www.urisa.org/gis_transit today!

[Source: URISA press release]

Estimating Secondary School Catchment Areas and the Spatial Equity of Access

Computers, Environment and Urban SystemsComputers, Environment and Urban Systems, Volume 35, Issue 3, May 2011, Pages 241-249

Alex D. Singleton, Paul A. Longley, Rebecca Allen, and Oliver O’Brien

“Research highlights:

  • Develops a novel method for identifying the actual extent of catchment areas that govern school admissions in the UK.
  • Makes novel and innovative use of spatial analysis techniques to delineate school catchment areas.
  • Demonstrates the importance and potential of public sector information in supporting individual and household decisions.

“Following the Educational Reform Act of 1988, families in England and Wales have been free to identify a preferred school for their children’s secondary education. However, as part of this open selection, the demand from parents opting to send their children to the best performing schools far outstrips the supply of available places at them, and consequently many schools ration places using entry criteria that favour those pupils domiciled close to the school. Through this geographic selection process, choice is spatially sorted and access to the best schools is often crucially dependent upon where parents live. After illustrating this problem, this paper develops an automated modelling technique that can be used to define and map school catchment areas based on the home locations of pupils attending every publically funded school in England. It then develops this framework to create a web based decision support tool to aid parents seeking secondary school places.”