arXiv subjects

Yoonjin Yoon

Publications and source records attributed to Yoonjin Yoon.

At least 19 recordsLinked to original sources

arXiv2026

Synergistic Fusion of Topological Structure and Temporal Semantics of Mobility for Urban Region Embedding

Urban region embeddings have shown promising results in diverse urban sensing tasks such as crime, income, and service-call prediction. Recent methods improve representation quality by integrating mobility data with auxiliary modalities, using cross-view attention or contrastive objectives to align heterogeneous features into a unified region representation. However, leveraging the temporal dynamics of human mobility remains under-explored. Regional inflow and outflow fluctuate throughout the day, and inter-region connections emerge, persist, and dissolve over time. Moreover, prevailing fusion strategies combine views additively and miss the joint signal that emerges only when views co-occur. To address these gaps, we propose Mobility Stream-Structure Synergy (MoSS), which derives complementary views from mobility data: a Sequence view that preserves each region's hourly inflow/outflow profile, and a Structure view based on zigzag persistence diagrams that capture how regional connectivity emerges, persists, and dissolves over time. A synergy module then extracts emergent representations from the co-occurrence of these views through multi-degree interactions, explicitly capturing higher-order signal across views. Extensive experiments on New York City and Chicago show that MoSS achieves state-of-the-art performance across three downstream tasks using mobility data alone, outperforming baselines that rely on auxiliary modalities.

cs.LG↗

arXiv2026

HypLTSF: A Hyperbolic Geometric View of Multi-Scale Hierarchies for Long-Term Time Series Forecasting

Multi-scale modeling has become an effective approach for long-term time series forecasting, capturing temporal patterns that range from fine-grained local dynamics to coarse global trends. Representations across these temporal scales are inherently hierarchical, with coarser scales abstracting and aggregating information from finer ones. While existing approaches readily exchange information across these scales, the hierarchy itself is typically left as an emergent byproduct of such interactions rather than captured as a geometric structure in its own right. In this paper, we introduce HypLTSF, a framework that endows the multi-scale hierarchy with a concrete geometric form by embedding scale-wise representations into the Poincar\'e ball, whose exponentially expanding volume naturally accommodates hierarchical structures. To align this geometry with the temporal hierarchy, HypLTSF imposes two constraints: (1) a radial constraint that orders embeddings by their level of abstraction, and (2) an angular constraint that groups fine-scale patterns sharing a common coarser-scale ancestor. Extensive experiments on long-term time series forecasting benchmarks show that HypLTSF achieves state-of-the-art performance, suggesting that explicitly modeling the multi-scale hierarchy as a geometric structure is effective for forecasting.

cs.LG↗

arXiv2026

Cooperative Informative Sensing for Monitoring Dynamic Indoor Environments via Multi-Agent Reinforcement Learning

Monitoring human activity in indoor environments is important for applications such as facility management, safety assessment, and space utilization analysis. While mobile robot teams offer the potential to actively improve observation quality, existing multi-robot monitoring and active perception approaches typically rely on coverage or visitation based objectives that are weakly aligned with the accuracy requirements of human-centric monitoring tasks. In this work, we formulate cooperative active observation as a decentralized control problem in which multiple robots adjust their motion to directly optimize monitoring accuracy under partial observability. We propose a learning-based framework for cooperative policies from decentralized observations using multi-agent reinforcement learning (MARL), supported by an architecture that handles variable numbers of humans and temporal dependencies. Simulation results across diverse indoor environments and monitoring tasks show that the proposed approach consistently outperforms classical coverage, persistent monitoring, and learning-free multi-robot baselines, while remaining robust to changes in the number of observed humans.

cs.RO↗

arXiv2025

AgentSUMO: An Agentic Framework for Interactive Simulation Scenario Generation in SUMO via Large Language Models

The growing complexity of urban mobility systems has made traffic simulation indispensable for evidence-based transportation planning and policy evaluation. However, despite the analytical capabilities of platforms such as the Simulation of Urban MObility (SUMO), their application remains largely confined to domain experts. Developing realistic simulation scenarios requires expertise in network construction, origin-destination modeling, and parameter configuration for policy experimentation, creating substantial barriers for non-expert users such as policymakers, urban planners, and city officials. Moreover, the requests expressed by these users are often incomplete and abstract-typically articulated as high-level objectives, which are not well aligned with the imperative, sequential workflows employed in existing language-model-based simulation frameworks. To address these challenges, this study proposes AgentSUMO, an agentic framework for interactive simulation scenario generation via large language models. AgentSUMO departs from imperative, command-driven execution by introducing an adaptive reasoning layer that interprets user intents, assesses task complexity, infers missing parameters, and formulates executable simulation plans. The framework is structured around two complementary components, the Interactive Planning Protocol, which governs reasoning and user interaction, and the Model Context Protocol, which manages standardized communication and orchestration among simulation tools. Through this design, AgentSUMO converts abstract policy objectives into executable simulation scenarios. Experiments on urban networks in Seoul and Manhattan demonstrate that the agentic workflow achieves substantial improvements in traffic flow metrics while maintaining accessibility for non-expert users, successfully bridging the gap between policy goals and executable simulation workflows.

cs.HC↗

arXiv2025

How Well Do Vision--Language Models Understand Cities? A Comparative Study on Spatial Reasoning from Street-View Images

Effectively understanding urban scenes requires fine-grained spatial reasoning about objects, layouts, and depth cues. However, how well current vision-language models (VLMs), pretrained on general scenes, transfer these abilities to urban domain remains underexplored. To address this gap, we conduct a comparative study of three off-the-shelf VLMs-BLIP-2, InstructBLIP, and LLaVA-1.5-evaluating both zero-shot performance and the effects of fine-tuning with a synthetic VQA dataset specific to urban scenes. We construct such dataset from segmentation, depth, and object detection predictions of street-view images, pairing each question with LLM-generated Chain-of-Thought (CoT) answers for step-by-step reasoning supervision. Results show that while VLMs perform reasonably well in zero-shot settings, fine-tuning with our synthetic CoT-supervised dataset substantially boosts performance, especially for challenging question types such as negation and counterfactuals. This study introduces urban spatial reasoning as a new challenge for VLMs and demonstrates synthetic dataset construction as a practical path for adapting general-purpose models to specialized domains.

cs.CV↗

arXiv2025

USE-LFA: A Data-Driven Framework for UAM Site Evaluation using Latent Factor Analysis

Urban air mobility (UAM) introduces new challenges for infrastructure planning, requiring data driven approaches for sustainable site selection. This study proposes USE-LFA (Urban Site Evaluation using Latent Factor Analysis), a framework designed to support equitable and environmentally conscious siting of urban ports. Applying latent factor analysis to 25 urban attributes in Seoul, the framework identifies six latent factors, grouped into two dimensions: Suitability and Attractiveness. These dimensions are combined through a tunable prioritization metric, enabling alignment with local strategic goals. The analysis uncovers spatial typologies and clustered siting patterns, highlighting regional disparities in site potential. Sensitivity analysis demonstrates that small adjustments in the Suitability Attractiveness weighting substantially affect viable site candidates, emphasizing the need for calibrated decision-making. USE-LFA facilitates interpretable and transferable analysis across different urban contexts and datasets, offering a scalable approach to integrating UAM and other emerging mobility systems into urban environments, while advancing sustainable and inclusive transport infrastructure development.

stat.AP↗

arXiv2025

MobiCLR: Mobility Time Series Contrastive Learning for Urban Region Representations

Recently, learning effective representations of urban regions has gained significant attention as a key approach to understanding urban dynamics and advancing smarter cities. Existing approaches have demonstrated the potential of leveraging mobility data to generate latent representations, providing valuable insights into the intrinsic characteristics of urban areas. However, incorporating the temporal dynamics and detailed semantics inherent in human mobility patterns remains underexplored. To address this gap, we propose a novel urban region representation learning model, Mobility Time Series Contrastive Learning for Urban Region Representations (MobiCLR), designed to capture semantically meaningful embeddings from inflow and outflow mobility patterns. MobiCLR uses contrastive learning to enhance the discriminative power of its representations, applying an instance-wise contrastive loss to capture distinct flow-specific characteristics. Additionally, we develop a regularizer to align output features with these flow-specific representations, enabling a more comprehensive understanding of mobility dynamics. To validate our model, we conduct extensive experiments in Chicago, New York, and Washington, D.C. to predict income, educational attainment, and social vulnerability. The results demonstrate that our model outperforms state-of-the-art models.

cs.LG↗

arXiv2025

TopoCL: Topological Contrastive Learning for Time Series

Universal time series representation learning is challenging but valuable in real-world applications such as classification, anomaly detection, and forecasting. Recently, contrastive learning (CL) has been actively explored to tackle time series representation. However, a key challenge is that the data augmentation process in CL can distort seasonal patterns or temporal dependencies, inevitably leading to a loss of semantic information. To address this challenge, we propose Topological Contrastive Learning for time series (TopoCL). TopoCL mitigates such information loss by incorporating persistent homology, which captures the topological characteristics of data that remain invariant under transformations. In this paper, we treat the temporal and topological properties of time series data as distinct modalities. Specifically, we compute persistent homology to construct topological features of time series data, representing them in persistence diagrams. We then design a neural network to encode these persistent diagrams. Our approach jointly optimizes CL within the time modality and time-topology correspondence, promoting a comprehensive understanding of both temporal semantics and topological properties of time series. We conduct extensive experiments on four downstream tasks-classification, anomaly detection, forecasting, and transfer learning. The results demonstrate that TopoCL achieves state-of-the-art performance.

cs.LG↗

arXiv2025

Integrating Urban Air Mobility with Highway Infrastructure: A Strategic Approach for Vertiport Location Selection in the Seoul Metropolitan Area

This study focuses on identifying suitable locations for highway-transfer Vertiports to integrate Urban Air Mobility (UAM) with existing highway infrastructure. UAM offers an effective solution for enhancing transportation accessibility in the Seoul Metropolitan Area, where conventional transportation often struggle to connect suburban employment zones such as industrial parks. By integrating UAM with ground transportation at highway facilities, an efficient connectivity solution can be achieved for regions with limited transportation options. Our proposed methodology for determining the suitable Vertiport locations utilizes data such as geographic information, origin-destination volume, and travel time. Vertiport candidates are evaluated and selected based on criteria including location desirability, combined transportation accessibility and transportation demand. Applying this methodology to the Seoul metropolitan area, we identify 56 suitable Vertiport locations out of 148 candidates. The proposed methodology offers a strategic approach for the selection of highway-transfer Vertiport locations, enhancing UAM integration with existing transportation systems. Our study provides valuable insights for urban planners and policymakers, with recommendations for future research to include real-time environmental data and to explore the impact of Mobility-as-a-Service on UAM operations.

cs.CY↗

arXiv2024

PGCN: Progressive Graph Convolutional Networks for Spatial-Temporal Traffic Forecasting

The complex spatial-temporal correlations in transportation networks make the traffic forecasting problem challenging. Since transportation system inherently possesses graph structures, many research efforts have been put with graph neural networks. Recently, constructing adaptive graphs to the data has shown promising results over the models relying on a single static graph structure. However, the graph adaptations are applied during the training phases and do not reflect the data used during the testing phases. Such shortcomings can be problematic especially in traffic forecasting since the traffic data often suffer from unexpected changes and irregularities in the time series. In this study, we propose a novel traffic forecasting framework called Progressive Graph Convolutional Network (PGCN). PGCN constructs a set of graphs by progressively adapting to online input data during the training and testing phases. Specifically, we implemented the model to construct progressive adjacency matrices by learning trend similarities among graph nodes. Then, the model is combined with the dilated causal convolution and gated activation unit to extract temporal features. With residual and skip connections, PGCN performs the traffic prediction. When applied to seven real-world traffic datasets of diverse geometric nature, the proposed model achieves state-of-the-art performance with consistency in all datasets. We conclude that the ability of PGCN to progressively adapt to input data enables the model to generalize in different study sites with robustness.

cs.LG↗

arXiv2022

Design, Field Evaluation, and Traffic Analysis of a Competitive Autonomous Driving Model in a Congested Environment

Recently, numerous studies have investigated cooperative traffic systems using the communication among vehicle-to-everything (V2X). Unfortunately, when multiple autonomous vehicles are deployed while exposed to communication failure, there might be a conflict of ideal conditions between various autonomous vehicles leading to adversarial situation on the roads. In South Korea, virtual and real-world urban autonomous multi-vehicle races were held in March and November of 2021, respectively. During the competition, multiple vehicles were involved simultaneously, which required maneuvers such as overtaking low-speed vehicles, negotiating intersections, and obeying traffic laws. In this study, we introduce a fully autonomous driving software stack to deploy a competitive driving model, which enabled us to win the urban autonomous multi-vehicle races. We evaluate module-based systems such as navigation, perception, and planning in real and virtual environments. Additionally, an analysis of traffic is performed after collecting multiple vehicle position data over communication to gain additional insight into a multi-agent autonomous driving scenario. Finally, we propose a method for analyzing traffic in order to compare the spatial distribution of multiple autonomous vehicles. We study the similarity distribution between each team's driving log data to determine the impact of competitive autonomous driving on the traffic environment.

cs.RO↗

arXiv2022

Data-driven risk analysis of unmanned aircraft system operations considering spatiotemporal characteristics of population distribution

One of the challenges of Unmanned Aircraft System (UAS) operations is to operate an unmanned aircraft with minimal risk to people on the ground. The purpose of this study is to define and measure such risks as population risk, by incorporating spatiotemporal changes in population density. Unlike previous studies, we use high-resolution de facto population data instead of residential population data to reflect the spatiotemporal characteristics of population distribution. Furthermore, we analyze the impact of mitigation measures based on population risk in the context of airspace management. We set a restricted airspace by using population risk and an acceptable level of safety. Scenario analysis of the study area in Seoul, South Korea provides a richer set of findings regarding spatiotemporal differences in restricted airspace. During the daytime, there are many restricted airspaces around commercial areas, but few around residential areas. Additionally, we observe the difference between restricting airspace based on population risk derived from the residential population and from the de facto population. These findings confirm the importance of accurately considering population density when assessing and mitigating the population risk associated with UAS operations. Sensitivity analysis also reveals the need to precisely estimate population density when estimating population risk with combinations of multiple parameter values. The proposed approach captures spatiotemporal characteristics of population distribution when assessing the population risk associated with UAS.

stat.AP↗

arXiv2022

A Comparative Study on Basic Elements of Deep Learning Models for Spatial-Temporal Traffic Forecasting

Traffic forecasting plays a crucial role in intelligent transportation systems. The spatial-temporal complexities in transportation networks make the problem especially challenging. The recently suggested deep learning models share basic elements such as graph convolution, graph attention, recurrent units, and/or attention mechanism. In this study, we designed an in-depth comparative study for four deep neural network models utilizing different basic elements. For base models, one RNN-based model and one attention-based model were chosen from previous literature. Then, the spatial feature extraction layers in the models were substituted with graph convolution and graph attention. To analyze the performance of each element in various environments, we conducted experiments on four real-world datasets - highway speed, highway flow, urban speed from a homogeneous road link network, and urban speed from a heterogeneous road link network. The results demonstrate that the RNN-based model and the attention-based model show a similar level of performance for short-term prediction, and the attention-based model outperforms the RNN in longer-term predictions. The choice of graph convolution and graph attention makes a larger difference in the RNN-based models. Also, our modified version of GMAN shows comparable performance with the original with less memory consumption.

cs.LG↗

arXiv2022

Risk Analysis of Unmanned Aerial System Operations in Urban Airspace Considering Spatiotemporal Population Dynamics

This study aims to estimate the fatality risk of Unmanned Aerial System (UAS) operations from a population perspective using high-resolution de facto population data. In doing so, it provides more practical risk values compared to the risk values derived from the residential population data. We then set restricted airspace using the risk values and the acceptable level of safety. We regard the restricted airspace as airspace being blocked by a dynamic obstacle. Scenario analysis on the study area in Seoul, South Korea presents a richer set of results for time-dependent differences in restricted airspace. Especially during the daytime, the restricted airspace is clustered around commercial and business areas. The difference between restricting airspace based on residential population-derived risk and restricting airspace based on de facto population-derived risk is also observed. The findings confirm the importance of accurately taking into account population density when assessing and mitigating the risk of UAS operations. Sensitivity analysis also reveals the importance of an accurate estimate of population density when estimating the risk.

stat.AP↗

arXiv2022

Effective Urban Region Representation Learning Using Heterogeneous Urban Graph Attention Network (HUGAT)

Revealing the hidden patterns shaping the urban environment is essential to understand its dynamics and to make cities smarter. Recent studies have demonstrated that learning the representations of urban regions can be an effective strategy to uncover the intrinsic characteristics of urban areas. However, existing studies lack in incorporating diversity in urban data sources. In this work, we propose heterogeneous urban graph attention network (HUGAT), which incorporates heterogeneity of diverse urban datasets. In HUGAT, heterogeneous urban graph (HUG) incorporates both the geo-spatial and temporal people movement variations in a single graph structure. Given a HUG, a set of meta-paths are designed to capture the rich urban semantics as composite relations between nodes. Region embedding is carried out using heterogeneous graph attention network (HAN). HUGAT is designed to consider multiple learning objectives of city's geo-spatial and mobility variations simultaneously. In our extensive experiments on NYC data, HUGAT outperformed all the state-of-the-art models. Moreover, it demonstrated a robust generalization capability across the various prediction tasks of crime, average personal income, and bike flow as well as the spatial clustering task.

cs.LG↗

arXiv2021

Incorporating dynamicity of transportation network with multi-weight traffic graph convolutional network for traffic forecasting

Traffic forecasting problem remains a challenging task in the intelligent transportation system due to its spatio-temporal complexity. Although temporal dependency has been well studied and discussed, spatial dependency is relatively less explored due to its large variations, especially in the urban environment. In this study, a novel graph convolutional network model, Multi-Weight Traffic Graph Convolutional (MW-TGC) network, is proposed and applied to two urban networks with contrasting geometric constraints. The model conducts graph convolution operations on speed data with multi-weighted adjacency matrices to combine the features, including speed limit, distance, and angle. The spatially isolated dimension reduction operation is conducted on the combined features to learn the dependencies among the features and reduce the size of the output to a computationally feasible level. The output of multi-weight graph convolution is applied to the sequence-to-sequence model with Long Short-Term Memory units to learn temporal dependencies. When applied to two urban sites, urban-core and urban-mix, MW-TGC network not only outperformed the comparative models in both sites but also reduced variance in the heterogeneous urban-mix network. We conclude that MW-TGC network can provide a robust traffic forecasting performance across the variations in spatial complexity, which can be a strong advantage in urban traffic forecasting.

stat.ML↗

arXiv2020

The effect of adaptive mobility policy to the spread of COVID-19 in urban environment: intervention analysis of Seoul, South Korea

Although severe mobility restrictions are recognized as the key enabler to contain COVID-19, there has been few scientific studies to validate such approach, especially in urban context. This study analyzes mobility pattern changes in Seoul, South Korea that adopted adaptive approach toward mobility. Intervention analyses reveal that major mobility reduction did occur two weeks before the city's case peak. Such voluntary adjustments exhibit strong preference shift toward private mode from public transit. Large reductions occurred in non-essential and high-contact activities of shopping and dining, while work and Starbucks trips were less affected. The collective evaluation reveal that major changes in epidemiology, mobility and policy occurred simultaneously, with no lagging nor leading contributors. Our study demonstrates that collective understanding the mutual aspects among mobility, epidemiology and policy is essential. Incremental and flexible mobility restriction is not only possible but necessary, especially for a pandemic of extensive spatial and temporal scales.

physics.soc-ph↗

arXiv2020

Running the COVID-19 marathon: the behavioral adaptations in mobility and facemask over 27 weeks of pandemic in Seoul, South Korea

Battle with COVID-19 turned out to be a marathon, not a sprint, and behavioral adjustments have been unavoidable to stay viable. In this paper, we employ a data-centric approach to investigate individual mobility adaptations and mask-wearing in Seoul, South Korea. We first identify six epidemic phases and two waves based on COVID-19 case count and its geospatial dispersion. The phase-specific linear models reveal the strong, self-driven mobility reductions in the first escalation and peak with a common focus on public transit use and less-essential weekend/afternoon trips. However, comparable reduction was not present in the second wave, as the shifted focus from mobility to mask-wearing was evident. Although no lockdowns and gentle nudge to wear mask seemed counter-intuitive, simple and persistent communication on personal safety has been effective and sustainable to induce cooperative behavioral adaptations. Our phase-specific analyses and interpretation highlight the importance of targeted response consistent with the fluctuating epidemic risk.

cs.CY↗