Jiwon Baik
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jiwon Baik has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Alan T. Murray
Department of Geography, University of California at Santa Barbara, Santa Barbara, USA
8 shared publications - Enbo Zhou
Department of Geography, College of Letters and Science, University of California, Santa Barbara, CA 93106, USA
4 shared publications - Jing Xu
Department of Geography, University of California at Santa Barbara, Santa Barbara, CA 93106, USA
3 shared publications - B. Amelia Pludow
Department of Geography, University of California Santa Barbara, Santa Barbara, 93106, United States
1 shared publication - Evgeny Noi
Department of Geography, UC Santa Barbara, USA
1 shared publication - Iraklis Anagnostopoulos
School of Electrical, Computer and Biomedical Engineering Southern Illinois University Carbondale IL U.S.A
1 shared publication
Latest Publications
- Open Access
- 6 December 2024
- Published by MDPI AG in Proceedings
- Vol. 110 (1) , 25
Geospatial Analytics to Support District Efficiency, Fairness and Equity
Districting is essential in establishing efficient, fair, and equitable boundaries across various domains such as trade and service provision, land-use development, school attendance, and political representation. This paper introduces a robust spatial optimization model tailored to delineate a districting strategy that accounts for issues of equinumerosity, compactness, and contiguity, among others. The model is designed to ensure an even distribution of population across districts while ensuring compact and contiguous boundaries. By integrating advanced GIScience and spatial optimization techniques, the model aims to maximize compactness metrics and balance population, producing districts that are both geometrically efficient and demographically representative. Explicit contiguity constraints are imposed to guarantee geographical connectedness among districts. To assess the efficacy of the proposed methodology, application to a school district in California is considered. Our findings highlight GIScience capabilities to identify district boundaries that outperform traditional districting schemes in addressing population balance and compactness.
- 6 December 2024
- Published by MDPI AG in Proceedings
- Vol. 110 (1) , 25
Open AccessGeospatial Analytics to Support District Efficiency, Fairness and Equity
Districting is essential in establishing efficient, fair, and equitable boundaries across various domains such as trade and service provision, land-use development, school attendance, and political representation. This paper introduces a robust spatial optimization model tailored to delineate a districting strategy that accounts for issues of equinumerosity, compactness, and contiguity, among others. The model is designed to ensure an even distribution of population across districts while ensuring compact and contiguous boundaries. By integrating advanced GIScience and spatial optimization techniques, the model aims to maximize compactness metrics and balance population, producing districts that are both geometrically efficient and demographically representative. Explicit contiguity constraints are imposed to guarantee geographical connectedness among districts. To assess the efficacy of the proposed methodology, application to a school district in California is considered. Our findings highlight GIScience capabilities to identify district boundaries that outperform traditional districting schemes in addressing population balance and compactness.
- Open Access
- 5 December 2024
- Published by MDPI AG in Proceedings
- Vol. 110 (1) , 18
Spatial Optimization for Facilities with Anisotropic Coverage
Locating facilities such as directional sensors and lights represents a challenging problem given their anisotropic coverage. This paper proposes a spatial optimization model to locate and orient facilities simultaneously. A finite dominating set approach considering occlusion is presented to reformulate the problem as an integer programming problem. The model is then solved exactly using branch and bound. Applications to surveillance camera deployment in a university context demonstrate the performance of the proposed approach. The results show a pivotal enhancement in the estimation of coverage provided by the facility system.
- 5 December 2024
- Published by MDPI AG in Proceedings
- Vol. 110 (1) , 18
Open AccessSpatial Optimization for Facilities with Anisotropic Coverage
Locating facilities such as directional sensors and lights represents a challenging problem given their anisotropic coverage. This paper proposes a spatial optimization model to locate and orient facilities simultaneously. A finite dominating set approach considering occlusion is presented to reformulate the problem as an integer programming problem. The model is then solved exactly using branch and bound. Applications to surveillance camera deployment in a university context demonstrate the performance of the proposed approach. The results show a pivotal enhancement in the estimation of coverage provided by the facility system.
- 11 September 2024
- Published by Wiley in Transactions in GIS
- Vol. 28 (7) , 2412-2424
Emergency Response Planning: A Framework to Assess Hydrant–Structure Access
Accessibility between fire hydrants and buildings is paramount in emergency response, significantly influencing the efficiency and effectiveness of firefighting operations in the event of an incident. However, assessing this relationship within a geographic information system (GIS) framework presents challenges on two fronts. Obtaining the path avoiding building and parcel obstructions to hydrants is not trivial. Further, determining the furthest extent around a building exterior from hydrants is complicated, yet it is critically important given the spatial limitations of equipment reach. To assess furthest extent, an analytical framework is introduced based on the Euclidean shortest path problem. The proposed approach offers a comprehensive, automated GIS‐based methodology tailored to evaluate the dynamic relationship between hydrants and buildings. The developed methods are able to accurately and precisely identify the furthest point around a building structure from hydrant, facilitating risk assessment as well as fire code compliance. This enables a comprehensive evaluation of potential loss and structure vulnerability at property, street, neighborhood, and regional levels.
- 11 September 2024
- Published by Wiley in Transactions in GIS
- Vol. 28 (7) , 2412-2424
Emergency Response Planning: A Framework to Assess Hydrant–Structure Access
Accessibility between fire hydrants and buildings is paramount in emergency response, significantly influencing the efficiency and effectiveness of firefighting operations in the event of an incident. However, assessing this relationship within a geographic information system (GIS) framework presents challenges on two fronts. Obtaining the path avoiding building and parcel obstructions to hydrants is not trivial. Further, determining the furthest extent around a building exterior from hydrants is complicated, yet it is critically important given the spatial limitations of equipment reach. To assess furthest extent, an analytical framework is introduced based on the Euclidean shortest path problem. The proposed approach offers a comprehensive, automated GIS‐based methodology tailored to evaluate the dynamic relationship between hydrants and buildings. The developed methods are able to accurately and precisely identify the furthest point around a building structure from hydrant, facilitating risk assessment as well as fire code compliance. This enables a comprehensive evaluation of potential loss and structure vulnerability at property, street, neighborhood, and regional levels.
- Open Access
- 11 March 2024
- Published by Taylor & Francis in Cartography and Geographic Information Science
- Vol. 51 (3) , 404-420
Mapping 3-D classroom seats based on partial object point cloud completion
- 11 March 2024
- Published by Taylor & Francis in Cartography and Geographic Information Science
- Vol. 51 (3) , 404-420
Open AccessMapping 3-D classroom seats based on partial object point cloud completion
- Open Access
- 1 January 2024
- Published by HICSS Conference Office
Location Analytics to Support Wildfire Response Prepositioning
This study addresses wildfire resource prepositioning in a region. Location analytics is utilized for prepositioning decision-making, relying on bi-objective spatial optimization to identify a strategic location for monitoring and response that considers two objectives: optimizing the visibility of potential ignition sites and optimizing response access. The study broadens the conventional definition of coverage by incorporating visibility from the preposition. Despite the inherent complexity of the problem, the proposed solution approach guarantees the identification of the complete set of Pareto optimal solutions in an efficient manner, supporting real-time decision-making. This research contributes significantly to spatial decision-making by integrating viewshed analysis into location analytics. Additionally, the approach has broad applications in various domains, including facility location planning, wireless network design, environmental monitoring, and urban planning. To facilitate decision-making, an interactive web application (www.wri-ucsb.com:8000) is developed, allowing the selection of specific regions of interest and model parameter refinement.
- 1 January 2024
- Published by HICSS Conference Office
Open AccessLocation Analytics to Support Wildfire Response Prepositioning
This study addresses wildfire resource prepositioning in a region. Location analytics is utilized for prepositioning decision-making, relying on bi-objective spatial optimization to identify a strategic location for monitoring and response that considers two objectives: optimizing the visibility of potential ignition sites and optimizing response access. The study broadens the conventional definition of coverage by incorporating visibility from the preposition. Despite the inherent complexity of the problem, the proposed solution approach guarantees the identification of the complete set of Pareto optimal solutions in an efficient manner, supporting real-time decision-making. This research contributes significantly to spatial decision-making by integrating viewshed analysis into location analytics. Additionally, the approach has broad applications in various domains, including facility location planning, wireless network design, environmental monitoring, and urban planning. To facilitate decision-making, an interactive web application (www.wri-ucsb.com:8000) is developed, allowing the selection of specific regions of interest and model parameter refinement.
- Open Access
- 12 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1767-1775
Pareto Optimization of CNN Models via Hardware-Aware Neural Architecture Search for Drainage Crossing Classification on Resource-Limited Devices
Embedded devices, constrained by limited memory and processors, require deep learning models to be tailored to their specifications. This research explores customized model architectures for classifying drainage crossing images. Building on the foundational ResNet-18, this paper aims to maximize prediction accuracy, reduce memory size, and minimize inference latency. Various configurations were systematically probed by leveraging hardware-aware neural architecture search, accumulating 1,717 experimental results over six benchmarking variants. The experimental data analysis, enhanced by nn-Meter, provided a comprehensive understanding of inference latency across four different predictors. Significantly, a Pareto front analysis with three objectives of accuracy, latency, and memory resulted in five non-dominated solutions. These standout models showcased efficiency while retaining accuracy, offering a compelling alternative to the conventional ResNet-18 when deployed in resource-constrained environments. The paper concludes by highlighting insights drawn from the results and suggesting avenues for future exploration.
- 12 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1767-1775
Open AccessPareto Optimization of CNN Models via Hardware-Aware Neural Architecture Search for Drainage Crossing Classification on Resource-Limited Devices
Embedded devices, constrained by limited memory and processors, require deep learning models to be tailored to their specifications. This research explores customized model architectures for classifying drainage crossing images. Building on the foundational ResNet-18, this paper aims to maximize prediction accuracy, reduce memory size, and minimize inference latency. Various configurations were systematically probed by leveraging hardware-aware neural architecture search, accumulating 1,717 experimental results over six benchmarking variants. The experimental data analysis, enhanced by nn-Meter, provided a comprehensive understanding of inference latency across four different predictors. Significantly, a Pareto front analysis with three objectives of accuracy, latency, and memory resulted in five non-dominated solutions. These standout models showcased efficiency while retaining accuracy, offering a compelling alternative to the conventional ResNet-18 when deployed in resource-constrained environments. The paper concludes by highlighting insights drawn from the results and suggesting avenues for future exploration.
- Open Access
- 1 October 2022
- Published by Springer Nature in Urban Informatics
- Vol. 1 (1) , 1-9
Urban informatics and spatial optimization
There has been much concern for sustainability issues, recognizing the significant impacts that humans have had and continue to have on the Earth. Urban informatics has much to offer city systems in terms of understanding, management and design, particularly associated with sustainability. Efficiency that characterizes sustainable systems, and strategic goals to achieve them, does not happen by chance, but rather is the byproduct of concerted efforts driven by informed decision making. This paper focuses on strategic decision making, and the role of spatial optimization as a component of urban informatics. Strategic siting involving access and coverage demonstrates the capabilities of spatial optimization, but more importantly highlights the significance of an urban informatics perspective.
- 1 October 2022
- Published by Springer Nature in Urban Informatics
- Vol. 1 (1) , 1-9
Open AccessUrban informatics and spatial optimization
There has been much concern for sustainability issues, recognizing the significant impacts that humans have had and continue to have on the Earth. Urban informatics has much to offer city systems in terms of understanding, management and design, particularly associated with sustainability. Efficiency that characterizes sustainable systems, and strategic goals to achieve them, does not happen by chance, but rather is the byproduct of concerted efforts driven by informed decision making. This paper focuses on strategic decision making, and the role of spatial optimization as a component of urban informatics. Strategic siting involving access and coverage demonstrates the capabilities of spatial optimization, but more importantly highlights the significance of an urban informatics perspective.
- Open Access
- 16 July 2022
- Published by Elsevier in Papers in Regional Science
- Vol. 101 (5) , 1199-1218
Locating a facility to simultaneously address access and coverage goals
- 16 July 2022
- Published by Elsevier in Papers in Regional Science
- Vol. 101 (5) , 1199-1218
Open AccessLocating a facility to simultaneously address access and coverage goals
- 13 September 2020
- Published by Wiley in Geographical Analysis
- Vol. 52 (4) , 480-493
Overview of Contributions inGeographical Analysis: Waldo Tobler
The academic contributions of Waldo Tobler are noteworthy and significant, spanning essentially all disciplines that involve the study of geographic phenomena. While much attention has been given to his observations of the first law of geography, there is much more substance to his larger body of research. It is especially fitting that this commemorative special issue is appearing inGeographical Analysisas Tobler published extensively in the journal, beginning in the first volume in 1969 up to volume 42 in 2010, making important contributions to quantitative theoretical geography. His research helped to build and sustain the journal, laying the foundation for what is the premier quantitative geography outlet today. This article reviews his publication activity inGeographical Analysis.
- 13 September 2020
- Published by Wiley in Geographical Analysis
- Vol. 52 (4) , 480-493
Overview of Contributions inGeographical Analysis: Waldo Tobler
The academic contributions of Waldo Tobler are noteworthy and significant, spanning essentially all disciplines that involve the study of geographic phenomena. While much attention has been given to his observations of the first law of geography, there is much more substance to his larger body of research. It is especially fitting that this commemorative special issue is appearing inGeographical Analysisas Tobler published extensively in the journal, beginning in the first volume in 1969 up to volume 42 in 2010, making important contributions to quantitative theoretical geography. His research helped to build and sustain the journal, laying the foundation for what is the premier quantitative geography outlet today. This article reviews his publication activity inGeographical Analysis.