Matching Items (4)
Filtering by
- All Subjects: Geographic Information Science and Geodesy
- All Subjects: spatial statistics
- Creators: Kuby, Michael
Description
In today's world, unprecedented amounts of data of individual mobile objects have become more available due to advances in location aware technologies and services. Studying the spatio-temporal patterns, processes, and behavior of mobile objects is an important issue for extracting useful information and knowledge about mobile phenomena. Potential applications across a wide range of fields include urban and transportation planning, Location-Based Services, and logistics. This research is designed to contribute to the existing state-of-the-art in tracking and modeling mobile objects, specifically targeting three challenges in investigating spatio-temporal patterns and processes; 1) a lack of space-time analysis tools; 2) a lack of studies about empirical data analysis and context awareness of mobile objects; and 3) a lack of studies about how to evaluate and test agent-based models of complex mobile phenomena. Three studies are proposed to investigate these challenges; the first study develops an integrated data analysis toolkit for exploration of spatio-temporal patterns and processes of mobile objects; the second study investigates two movement behaviors, 1) theoretical random walks and 2) human movements in urban space collected by GPS; and, the third study contributes to the research challenge of evaluating the form and fit of Agent-Based Models of human movement in urban space. The main contribution of this work is the conceptualization and implementation of a Geographic Knowledge Discovery approach for extracting high-level knowledge from low-level datasets about mobile objects. This allows better understanding of space-time patterns and processes of mobile objects by revealing their complex movement behaviors, interactions, and collective behaviors. In detail, this research proposes a novel analytical framework that integrates time geography, trajectory data mining, and 3D volume visualization. In addition, a toolkit that utilizes the framework is developed and used for investigating theoretical and empirical datasets about mobile objects. The results showed that the framework and the toolkit demonstrate a great capability to identify and visualize clusters of various movement behaviors in space and time.
ContributorsNara, Atsushi (Author) / Torrens, Paul M. (Thesis advisor) / Myint, Soe W (Committee member) / Kuby, Michael (Committee member) / Griffin, William A. (Committee member) / Arizona State University (Publisher)
Created2011
Description
Equity concerning food access has gained a lot of attention in the past decades. This problem can be seen in the dearth of supermarkets offering healthy food at reasonable prices in disadvantaged neighborhoods. Numerous studies show that the disparity in the distribution of food outlets has resulted in disparities in health outcomes. To mitigate the issue, various intervention strategies have been proposed and implemented, including introducing new supermarkets, mobile food markets, community gardens, and city farms in these neighborhoods. Among these strategies, mobile food markets have gained the attention of practitioners and policymakers for their low costs and service flexibility. Challenges remain in identifying the sites for best serving the people in need given limited resources. In this study, a new spatial optimization model is proposed to determine the best locations for mobile food markets in the City of Phoenix. The new model aims to cover the largest number of people with food access challenges while minimizing transportation costs. Compared with the existing mobile market sites, the sites provided by the new model can increase the coverage of low-food access residents with a shorter transportation distance. The new model has also been applied to help expand the service provider of the existing mobile food markets. In addition to mobile food markets, the method provided in this study can be extended to support the planning of other food outlets and food assistance services.
ContributorsLu, Junzhou (Author) / Tong, Daoqin (Thesis advisor) / Connor, Dylan (Committee member) / Kuby, Michael (Committee member) / Arizona State University (Publisher)
Created2022
Description
Spatial regression is one of the central topics in spatial statistics. Based on the goals, interpretation or prediction, spatial regression models can be classified into two categories, linear mixed regression models and nonlinear regression models. This dissertation explored these models and their real world applications. New methods and models were proposed to overcome the challenges in practice. There are three major parts in the dissertation.
In the first part, nonlinear regression models were embedded into a multistage workflow to predict the spatial abundance of reef fish species in the Gulf of Mexico. There were two challenges, zero-inflated data and out of sample prediction. The methods and models in the workflow could effectively handle the zero-inflated sampling data without strong assumptions. Three strategies were proposed to solve the out of sample prediction problem. The results and discussions showed that the nonlinear prediction had the advantages of high accuracy, low bias and well-performed in multi-resolution.
In the second part, a two-stage spatial regression model was proposed for analyzing soil carbon stock (SOC) data. In the first stage, there was a spatial linear mixed model that captured the linear and stationary effects. In the second stage, a generalized additive model was used to explain the nonlinear and nonstationary effects. The results illustrated that the two-stage model had good interpretability in understanding the effect of covariates, meanwhile, it kept high prediction accuracy which is competitive to the popular machine learning models, like, random forest, xgboost and support vector machine.
A new nonlinear regression model, Gaussian process BART (Bayesian additive regression tree), was proposed in the third part. Combining advantages in both BART and Gaussian process, the model could capture the nonlinear effects of both observed and latent covariates. To develop the model, first, the traditional BART was generalized to accommodate correlated errors. Then, the failure of likelihood based Markov chain Monte Carlo (MCMC) in parameter estimating was discussed. Based on the idea of analysis of variation, back comparing and tuning range, were proposed to tackle this failure. Finally, effectiveness of the new model was examined by experiments on both simulation and real data.
In the first part, nonlinear regression models were embedded into a multistage workflow to predict the spatial abundance of reef fish species in the Gulf of Mexico. There were two challenges, zero-inflated data and out of sample prediction. The methods and models in the workflow could effectively handle the zero-inflated sampling data without strong assumptions. Three strategies were proposed to solve the out of sample prediction problem. The results and discussions showed that the nonlinear prediction had the advantages of high accuracy, low bias and well-performed in multi-resolution.
In the second part, a two-stage spatial regression model was proposed for analyzing soil carbon stock (SOC) data. In the first stage, there was a spatial linear mixed model that captured the linear and stationary effects. In the second stage, a generalized additive model was used to explain the nonlinear and nonstationary effects. The results illustrated that the two-stage model had good interpretability in understanding the effect of covariates, meanwhile, it kept high prediction accuracy which is competitive to the popular machine learning models, like, random forest, xgboost and support vector machine.
A new nonlinear regression model, Gaussian process BART (Bayesian additive regression tree), was proposed in the third part. Combining advantages in both BART and Gaussian process, the model could capture the nonlinear effects of both observed and latent covariates. To develop the model, first, the traditional BART was generalized to accommodate correlated errors. Then, the failure of likelihood based Markov chain Monte Carlo (MCMC) in parameter estimating was discussed. Based on the idea of analysis of variation, back comparing and tuning range, were proposed to tackle this failure. Finally, effectiveness of the new model was examined by experiments on both simulation and real data.
ContributorsLu, Xuetao (Author) / McCulloch, Robert (Thesis advisor) / Hahn, Paul (Committee member) / Lan, Shiwei (Committee member) / Zhou, Shuang (Committee member) / Saul, Steven (Committee member) / Arizona State University (Publisher)
Created2020
Description
Geographically Weighted Regression (GWR) has been broadly used in various fields to
model spatially non-stationary relationships. Classic GWR is considered as a single-scale model that is based on one bandwidth parameter which controls the amount of distance-decay in weighting neighboring data around each location. The single bandwidth in GWR assumes that processes (relationships between the response variable and the predictor variables) all operate at the same scale. However, this posits a limitation in modeling potentially multi-scale processes which are more often seen in the real world. For example, the measured ambient temperature of a location is affected by the built environment, regional weather and global warming, all of which operate at different scales. A recent advancement to GWR termed Multiscale GWR (MGWR) removes the single bandwidth assumption and allows the bandwidths for each covariate to vary. This results in each parameter surface being allowed to have a different degree of spatial variation, reflecting variation across covariate-specific processes. In this way, MGWR has the capability to differentiate local, regional and global processes by using varying bandwidths for covariates. Additionally, bandwidths in MGWR become explicit indicators of the scale at various processes operate. The proposed dissertation covers three perspectives centering on MGWR: Computation; Inference; and Application. The first component focuses on addressing computational issues in MGWR to allow MGWR models to be calibrated more efficiently and to be applied on large datasets. The second component aims to statistically differentiate the spatial scales at which different processes operate by quantifying the uncertainty associated with each bandwidth obtained from MGWR. In the third component, an empirical study will be conducted to model the changing relationships between county-level socio-economic factors and voter preferences in the 2008-2016 United States presidential elections using MGWR.
model spatially non-stationary relationships. Classic GWR is considered as a single-scale model that is based on one bandwidth parameter which controls the amount of distance-decay in weighting neighboring data around each location. The single bandwidth in GWR assumes that processes (relationships between the response variable and the predictor variables) all operate at the same scale. However, this posits a limitation in modeling potentially multi-scale processes which are more often seen in the real world. For example, the measured ambient temperature of a location is affected by the built environment, regional weather and global warming, all of which operate at different scales. A recent advancement to GWR termed Multiscale GWR (MGWR) removes the single bandwidth assumption and allows the bandwidths for each covariate to vary. This results in each parameter surface being allowed to have a different degree of spatial variation, reflecting variation across covariate-specific processes. In this way, MGWR has the capability to differentiate local, regional and global processes by using varying bandwidths for covariates. Additionally, bandwidths in MGWR become explicit indicators of the scale at various processes operate. The proposed dissertation covers three perspectives centering on MGWR: Computation; Inference; and Application. The first component focuses on addressing computational issues in MGWR to allow MGWR models to be calibrated more efficiently and to be applied on large datasets. The second component aims to statistically differentiate the spatial scales at which different processes operate by quantifying the uncertainty associated with each bandwidth obtained from MGWR. In the third component, an empirical study will be conducted to model the changing relationships between county-level socio-economic factors and voter preferences in the 2008-2016 United States presidential elections using MGWR.
ContributorsLi, Ziqi (Author) / Fotheringham, A. Stewart (Thesis advisor) / Goodchild, Michael F. (Committee member) / Li, Wenwen (Committee member) / Arizona State University (Publisher)
Created2020