Zhang, Jinlei; Chen, Feng; Shen, Qing. (2019). Cluster-based LSTM Network for Short-term Passenger Flow Forecasting in Urban Rail Transit. Ieee Access, 7, 147653 – 147671.
View Publication
Abstract
Short-term passenger flow forecasting is an essential component for the operation of urban rail transit (URT). Therefore, it is necessary to obtain a higher prediction precision with the development of URT. As artificial intelligence becomes increasingly prevalent, many prediction methods including the long short-term memory network (LSTM) in the deep learning field have been applied in road transportation systems, which can give critical insights for URT. First, we propose a novel two-step K-Means clustering model to capture not only the passenger flow variation trends but also the ridership volume characteristics. Then, a predictability assessment model is developed to recommend a reasonable time granularity interval to aggregate passenger flows. Based on the clustering results and the recommended time granularity interval, the LSTM model, which is called CB-LSTM model, is proposed to conduct short-term passenger flow forecasting. Results show that the prediction based on subway station clusters can not only avoid the complication of developing numerous models for each of the hundreds of stations, but also improve the prediction performance, which make it possible to predict short-term passenger flow on a network scale using limited dataset. The results provide critical insights for subway operators and transportation policymakers.
Keywords
Traffic Flow; Neural-network; Prediction; Ridership; Models; Volume; Lstm; Short-term Passenger Flow Forecasting; Urban Rail Transit; K-means Clustering; Deep Learning
Mooney, Stephen J.; Bobb, Jennifer F.; Hurvitz, Philip M.; Anau, Jane; Theis, Mary Kay; Drewnowski, Adam; Aggarwal, Anju; Gupta, Shilpi; Rosenberg, Dori E.; Cook, Andrea J.; Shi, Xiao; Lozano, Paula; Moudon, Anne Vernez; Arterburn, David. (2020). Impact of Built Environments on Body Weight (The Moving to Health Study): Protocol for a Retrospective Longitudinal Observational Study. Jmir Research Protocols, 9(5).
View Publication
Abstract
Background: Studies assessing the impact of built environments on body weight are often limited by modest power to detect residential effects that are small for individuals but may nonetheless comprise large attributable risks. Objective: We used data extracted from electronic health records to construct a large retrospective cohort of patients. This cohort will be used to explore both the impact of moving between environments and the long-term impact of changing neighborhood environments. Methods: We identified members with at least 12 months of Kaiser Permanente Washington (KPWA) membership and at least one weight measurement in their records during a period between January 2005 and April 2017 in which they lived in King County, Washington. Information on member demographics, address history, diagnoses, and clinical visits data (including weight) was extracted. This paper describes the characteristics of the adult (aged 18-89 years) cohort constructed from these data. Results: We identified 229,755 adults representing nearly 1.2 million person-years of follow-up. The mean age at baseline was 45 years, and 58.0% (133,326/229,755) were female. Nearly one-fourth of people (55,150/229,755) moved within King County at least once during the follow-up, representing 84,698 total moves. Members tended to move to new neighborhoods matching their origin neighborhoods on residential density and property values. Conclusions: Data were available in the KPWA database to construct a very large cohort based in King County, Washington. Future analyses will directly examine associations between neighborhood conditions and longitudinal changes in body weight and diabetes as well as other health conditions.
Keywords
Residential Location Choice; Physical-activity; Risk-factors; Food Desert; Neighborhood; Obesity; Association; Outcomes; Bmi; Accelerometer; Electronic Health Records; Built Environment; Washington; Geography; Longitudinal Studies
Duncan, Glen E.; Hurvitz, Philip M.; Moudon, Anne Vernez; Avery, Ally R.; Tsang, Siny. (2021). Measurement of Neighborhood-Based Physical Activity Bouts. Health & Place, 70.
View Publication
Abstract
This study examined how buffer type (shape), size, and the allocation of activity bouts inside buffers that delineate the neighborhood spatially produce different estimates of neighborhood-based physical activity. A sample of 375 adults wore a global positioning system (GPS) data logger and accelerometer over 2 weeks under free-living conditions. Analytically, the amount of neighborhood physical activity measured objectively varies substantially, not only due to buffer shape and size, but by how GPS-based activity bouts are identified with respect to containment within neighborhood buffers. To move the neighborhood-effects literature forward, it is critical to delineate the spatial extent of the neighborhood, given how different ways of measuring GPS-based activity containment will result in different levels of physical activity across different buffer types and sizes.
Keywords
Built Environment; Walking; Home; Accelerometry; Geographic Information Systems; Gps; Neighborhood; Physical Activity
Shen, Qing; Wang, Yiyuan; Gifford, Casey. (2021). Exploring Partnership Between Transit Agency And Shared Mobility Company: An Incentive Program For App-based Carpooling. Transportation, 48(5), 2585 – 2603.
View Publication
Abstract
How should public transit agencies deliver mobility services in the era of shared mobility? Previous literature recommends that transit agencies actively build partnerships with mobility service companies from the private sector, yet public transit agencies are still in search of a solid empirical basis to help envision the consequences of doing so. This paper presents an effort to fill this gap by studying a recent experiment of shared mobility public-private partnership, the carpool incentive fund program launched by King County Metro in the Seattle region. This program offers monetary incentives for participants who commute using a dynamic app-based carpooling service. Through descriptive analysis and a series of logistic regression models, we find that the monetary incentive to encourage the use of app-based carpooling generates some promising outcomes while having distinctive limitations. In particular, it facilitates the growth of carpooling by making carpooling a competitive commuting option for long-distance commuters. Moreover, our evidence suggests that the newly generated carpooling trips mostly substitute single-occupancy vehicles, thus contributing to a reduction of regional VMT. The empirical results of this research will not only help King County Metro devise its future policies but also highlight an appealing alternative for other transit agencies in designing an integrated urban transportation system in the era of shared mobility.
Keywords
Shared Mobility; Public-Private Partnership; App-based Carpooling; Incentive Fund; Transit Agencies; Incentives; Commuting; Public Transportation; Mobility; Regression Analysis; Regression Models; Partnerships; Vehicles; Car Pools; Private Sector; Occupancy; Transportation Systems; Mass Transit; Transportation Planning; Empirical Analysis; Urban Transportation
Bassok, Alon; Hurvitz, Phil M.; Bae, C-H. Christine; Larson, Timothy. (2010). Measuring Neighbourhood Air Pollution: The Case of Seattle’s International District. Journal Of Environmental Planning & Management, 53(1), 23 – 39.
View Publication
Abstract
Current US regulatory air quality monitoring networks measure ambient levels of pollutants and cannot capture the effects of mobile sources at the micro-scale. Despite the fact that overall air quality has been getting better, more vulnerable populations (children, the elderly, minorities and the poor) continue to suffer from traffic-related air pollution. As development intensifies in urban areas, more people are exposed to road-related air pollution. However, the only consideration given to air quality, if any, is based on ambient measures. This paper uses an inexpensive, portable Particle Soot Absorption Photometer (PSAP) to measure Black Carbon (BC) emissions, a surrogate for diesel fuels emissions, in Seattle's International District. With the aid of a GPS receiver, street-level BC data were geocoded in real space-time. It was found that pollution levels differed substantially across the study area. The results show the need for street-level air pollution monitoring, revisions in current land use and transportation policies, and air quality planning practice.
Keywords
Emission Standards; Air Pollution; Atmospheric Deposition; Social Groups; Waste Products; Sanitary Landfills; Black Carbon; Freeway Air Pollution Sheds (faps); Land Use; Mobile Monitoring; Neighbourhood Air Quality; Aerosol Light-absorption; Respiratory Health; Coefficient; Exposure; Symptoms; Children; Pollutants; Particles; Exhaust; Asthma
Stover, Victor W.; Bae, C.-H. Christine. (2011). Impact of Gasoline Prices on Transit Ridership in Washington State. Transportation Research Record, 2217, 1 – 10.
View Publication
Abstract
Gasoline prices in the United States have been extremely volatile in recent years and rose to record high levels during the summer of 2008. According to the U.S. Energy Information Administration, the average U.S. gasoline price for the year 2008 was $3.26 a gallon, which was the second highest yearly average in history when adjusted for inflation. Transportation agencies reported changes in travel behavior as a result of the price spike, with transit systems experiencing record ridership and state departments of transportation reporting reductions in traffic volumes. This study examined the impact of changing gasoline prices on transit ridership in Washington State by measuring the price elasticity of demand of ridership with respect to gasoline price. Ordinary least-squares regression was used to model transit ridership for transit agencies in 11 counties in Washington State during 2004 to 2008. The price of gasoline had a statistically significant effect on transit ridership for seven systems studied, with elasticities ranging from 0.09 to 0.47. A panel data model was estimated with data from all 11 agencies to measure the overall impact of gasoline prices on transit ridership in the state. The elasticity from the panel data model was 0.17. Results indicated that transit ridership increased as gasoline prices increased during the study period. The findings were consistent with those from previous studies on the topic.
Keywords
Time-series Analysis; Gas Prices; Elasticities; Demand
Hong, Jinhyun; Shen, Qing. (2013). Residential Density and Transportation Emissions: Examining the Connection by Addressing Spatial Autocorrelation and Self-Selection. Transportation Research Part D-transport And Environment, 22, 75 – 79.
View Publication
Abstract
This paper examines the effect of residential density on CO2 equivalent from automobile using more specific emission factors based on vehicle and trip characteristics, and by addressing problems of spatial autocorrelation and self-selection. Drawing on the 2006 Puget Sound Regional Council Household Activity Survey data, the 2005 parcel and building database, the 2000 US Census data, and emission factors estimated using the Motor Vehicle Emission Simulator, we analyze the influence of residential density on road-based transportation emissions. In addition, a Bayesian multilevel model with spatial random effects and instrumental variables is employed to control for spatial autocorrelation and self-selection. The results indicate that the effect of residential density on transportation emissions is influenced by spatial correlation and self-selection. Our results still show, however, that increasing residential density leads to a significant reduction in transportation emissions. (C) 2013 Elsevier Ltd. All rights reserved.
Keywords
Urban Form; Travel; Transportation Emissions; Residential Density; Confounding By Location; Self-selection
Hong, Jinhyun; Shen, Qing; Zhang, Lei. (2014). How Do Built-Environment Factors Affect Travel Behavior? A Spatial Analysis at Different Geographic Scales. Transportation, 41(3), 419 – 440.
View Publication
Abstract
Much of the literature shows that a compact city with well-mixed land use tends to produce lower vehicle miles traveled (VMT), and consequently lower energy consumption and less emissions. However, a significant portion of the literature indicates that the built environment only generates some minor-if any-influence on travel behavior. Through the literature review, we identify four major methodological problems that may have resulted in these conflicting conclusions: self-selection, spatial autocorrelation, inter-trip dependency, and geographic scale. Various approaches have been developed to resolve each of these issues separately, but few efforts have been made to reexamine the built environment-travel behavior relationship by considering these methodological issues simultaneously. The objective of this paper is twofold: (1) to better understand the existing methodological gaps, and (2) to reexamine the effects of built-environment factors on transportation by employing a framework that incorporates recently developed methodological approaches. Using the Seattle metropolitan region as our study area, the 2006 Household Activity Survey and the 2005 parcel and building data are used in our analysis. The research employs Bayesian hierarchical models with built-environment factors measured at different geographic scales. Spatial random effects based on a conditional autoregressive specification are incorporated in the hierarchical model framework to account for spatial contiguity among Traffic Analysis Zones. Our findings indicate that land use factors have highly significant effects on VMT even after controlling for travel attitude and spatial autocorrelation. In addition, our analyses suggest that some of these effects may translate into different empirical results depending on geographic scales and tour types.
Keywords
Land-use; Urban Form; Multilevel Models; Physical-activity; Neighborhood; Choice; Impact; Specification; Accessibility; Causation; Built Environment; Travel Behavior; Self-selection; Spatial Autocorrelation; Bayesian Hierarchical Model
Estiri, Hossein; Krause, Andy; Heris, Mehdi P. (2015). Phasic Metropolitan Settlers: A Phase-Based Model for the Distribution of Households in US Metropolitan Regions. Urban Geography, 36(5), 777 – 794.
View Publication
Abstract
In this article, we develop a model for explaining spatial patterns in the distribution of households across metropolitan regions in the United States. First, we use housing consumption and residential mobility theories to construct a hypothetical probability distribution function for the consumption of housing services across three phases of household life span. We then hypothesize a second probability distribution function for the offering of housing services based on the distance from city center(s) at the metropolitan scale. Intersecting the two hypothetical probability functions, we develop a phase-based model for the distribution of households in US metropolitan regions. We argue that phase one households (young adults) are more likely to reside in central city locations, whereas phase two and three households are more likely to select suburban locations, due to their respective housing consumption behaviors. We provide empirical validation of our theoretical model with the data from the 2010 US Census for 35 large metropolitan regions.
Keywords
Residential-mobility; Life-course; Housing Consumption; Family; Satisfaction; Migration; Geography; Context; Age; Distribution Patterns; Us Metropolitan Regions; Household
Drewnowski, Adam; Aggarwal, Anju; Cook, Andrea; Stewart, Orion; Moudon, Anne Vernez. (2016). Geographic Disparities in Healthy Eating Index Scores (HEI-2005 and 2010) by Residential Property Values: Findings from Seattle Obesity Study (SOS). Preventive Medicine, 83, 46 – 55.
View Publication
Abstract
Background. Higher socioeconomic status (SES) has been linked with higher-quality diets. New GIS methods allow for geographic mapping of diet quality at a very granular level. Objective. To examine the geographic distribution of two measures of diet quality: Healthy Eating Index (HEI 2005 and HEI 2010) in relation to residential property values in Seattle-King County. Methods. The Seattle Obesity Study (SOS) collected data from a population-based sample of King County adults in 2008-09. Socio-demographic data were obtained by 20-min telephone survey. Dietary data were obtained from food frequency questionnaires (FFQs). Home addresses were geocoded to the tax parcel and residential property values were obtained from the King County tax assessor. Multivariable regression analyses using 1116 adults tested associations between SES variables and diet quality measured (HEI scores). Results. Residential property values, education, and incomes were associated with higher HEI scores in bivariate analyses. Property values were not collinear with either education or income. In adjusted multivariable models, education and residential property were better associated with HEI, compared to than income. Mapping of HEI-2005 and HEI-2010 at the census block level illustrated the geographic distribution of diet quality across Seattle-King County. Conclusion. The use of residential property values, an objective measure of SES, allowed for the first visual exploration of diet quality at high spatial resolution: the census block level. (C) 2015 Elsevier Inc. All rights reserved.
Keywords
Obesity Treatment; Prevention Of Obesity; Disease Mapping; Socioeconomics; Multivariate Analysis; Population Geography; Census; Diet; Housing; Nutrition Policy; Questionnaires; Research Funding; Socioeconomic Factors; Body Mass Index; Health Equity; Cross-sectional Method; Economics; Seattle (wash.); Washington (state); Diet Quality; Geographic Information Systems; Healthy Eating Index; Residential Property Values; Socio-economic Status; Local Food Environment; Vitamin-e Consumption; Socioeconomic Position; United-states; Social-class; Energy-density; Association; Indicators; Trends