arXiv subjects

Huanfa Chen

Publications and source records attributed to Huanfa Chen.

8 recordsLinked to original sources

arXiv2026

Spatial accessibility to food banks hinders food parcel uptake in England and Wales, particularly in rural areas

Food bank use in the UK has soared in recent years. The combination of a global pandemic, over-stretched and underfunded public services, and a cost-of-living crisis has meant that millions of people cannot afford basic essentials such as food, heating, housing, and baby supplies. Food bank use is driven by a complex range of factors, including poverty, health emergencies, income shocks, delays to universal credit payments, housing issues, and homelessness. In this study we identify an urban-rural divide in spatial accessibility to food banks. In cities, food banks tend to be highly accessible by public transport to deprived populations but, on average, have shorter opening hours. In rural areas, however, despite generally longer opening hours, food banks are typically not highly accessible except for the most deprived residents. This matters. We find that spatial accessibility to a Trussell food bank centre is a key predictor of food parcel uptake, with a significantly stronger relationship than factors emphasised in the literature such as disability and Universal Credit. Importantly, this relationship is markedly stronger for rural populations, suggesting an unmet need in deprived rural areas far from food banks. Our work has important implications for food bank policy, suggesting a need for improved public transport in rural areas, and optimising current food bank locations and delivery models.

econ.GN↗

arXiv2025

Defining the urban "local" with low dimensional manifolds of human mobility networks

Urban science has largely relied on universal models, rendering the heterogeneous and locally specific nature of cities effectively invisible. Here we introduce a topological framework that defines and detects localities in human mobility networks. We empirically demonstrate that these human mobility network localities are rigorous geometric entities that map directly to geographic localities, revealing that human mobility networks lie on manifolds of dimension <=5. This representation provides a compact theoretical foundation for spatial embedding and enables efficient applications to facility location and propagation modeling. Our approach reconciles local heterogeneity with universal representation, offering a new pathway toward a more comprehensive urban science.

physics.soc-ph↗

arXiv2024

Evolutionary Greedy Algorithm for Optimal Sensor Placement Problem in Urban Sewage Surveillance

Designing a cost-effective sensor placement plan for sewage surveillance is a crucial task because it allows cost-effective early pandemic outbreak detection as supplementation for individual testing. However, this problem is computationally challenging to solve, especially for massive sewage networks having complicated topologies. In this paper, we formulate this problem as a multi-objective optimization problem to consider the conflicting objectives and put forward a novel evolutionary greedy algorithm (EG) to enable efficient and effective optimization for large-scale directed networks. The proposed model is evaluated on both small-scale synthetic networks and a large-scale, real-world sewage network in Hong Kong. The experiments on small-scale synthetic networks demonstrate a consistent efficiency improvement with reasonable optimization performance and the real-world application shows that our method is effective in generating optimal sensor placement plans to guide policy-making.

cs.CY↗

arXiv2024

V-RoAst: Visual Road Assessment. Can VLM be a Road Safety Assessor Using the iRAP Standard?

Road safety assessments are critical yet costly, especially in Low- and Middle-Income Countries (LMICs), where most roads remain unrated. Traditional methods require expert annotation and training data, while supervised learning-based approaches struggle to generalise across regions. In this paper, we introduce \textit{V-RoAst}, a zero-shot Visual Question Answering (VQA) framework using Vision-Language Models (VLMs) to classify road safety attributes defined by the iRAP standard. We introduce the first open-source dataset from ThaiRAP, consisting of over 2,000 curated street-level images from Thailand annotated for this task. We evaluate Gemini-1.5-flash and GPT-4o-mini on this dataset and benchmark their performance against VGGNet and ResNet baselines. While VLMs underperform on spatial awareness, they generalise well to unseen classes and offer flexible prompt-based reasoning without retraining. Our results show that VLMs can serve as automatic road assessment tools when integrated with complementary data. This work is the first to explore VLMs for zero-shot infrastructure risk assessment and opens new directions for automatic, low-cost road safety mapping. Code and dataset: https://github.com/PongNJ/V-RoAst.

cs.CV↗

arXiv2024

Uncertainty-Aware Probabilistic Graph Neural Networks for Road-Level Traffic Accident Prediction

Traffic accidents present substantial challenges to human safety and socio-economic development in urban areas. Developing a reliable and responsible traffic accident prediction model is crucial to addressing growing public safety concerns and enhancing the safety of urban mobility systems. Traditional methods face limitations at fine spatiotemporal scales due to the sporadic nature of highrisk accidents and the predominance of non-accident characteristics. Furthermore, while most current models show promising occurrence prediction, they overlook the uncertainties arising from the inherent nature of accidents, and then fail to adequately map the hierarchical ranking of accident risk values for more precise insights. To address these issues, we introduce the Spatiotemporal Zero-Inflated Tweedie Graph Neural Network STZITDGNN -- the first uncertainty-aware probabilistic graph deep learning model in roadlevel traffic accident prediction for multisteps. This model integrates the interpretability of the statistical Tweedie family model and the expressive power of graph neural networks. Its decoder innovatively employs a compound Tweedie model,a Poisson distribution to model the frequency of accident occurrences and a Gamma distribution to assess injury severity, supplemented by a zeroinflated component to effectively identify exessive nonincident instances. Empirical tests using realworld traffic data from London, UK, demonstrate that the STZITDGNN surpasses other baseline models across multiple benchmarks and metrics, including accident risk value prediction, uncertainty minimisation, non-accident road identification and accident occurrence accuracy. Our study demonstrates that STZTIDGNN can effectively inform targeted road monitoring, thereby improving urban road safety strategies.

cs.LG↗

arXiv2024

SMA-Hyper: Spatiotemporal Multi-View Fusion Hypergraph Learning for Traffic Accident Prediction

Predicting traffic accidents is the key to sustainable city management, which requires effective address of the dynamic and complex spatiotemporal characteristics of cities. Current data-driven models often struggle with data sparsity and typically overlook the integration of diverse urban data sources and the high-order dependencies within them. Additionally, they frequently rely on predefined topologies or weights, limiting their adaptability in spatiotemporal predictions. To address these issues, we introduce the Spatiotemporal Multiview Adaptive HyperGraph Learning (SMA-Hyper) model, a dynamic deep learning framework designed for traffic accident prediction. Building on previous research, this innovative model incorporates dual adaptive spatiotemporal graph learning mechanisms that enable high-order cross-regional learning through hypergraphs and dynamic adaptation to evolving urban data. It also utilises contrastive learning to enhance global and local data representations in sparse datasets and employs an advance attention mechanism to fuse multiple views of accident data and urban functional features, thereby enriching the contextual understanding of risk factors. Extensive testing on the London traffic accident dataset demonstrates that the SMA-Hyper model significantly outperforms baseline models across various temporal horizons and multistep outputs, affirming the effectiveness of its multiview fusion and adaptive learning strategies. The interpretability of the results further underscores its potential to improve urban traffic management and safety by leveraging complex spatiotemporal urban data, offering a scalable framework adaptable to diverse urban environments.

cs.LG↗

arXiv2023

Uncertainty Quantification in the Road-level Traffic Risk Prediction by Spatial-Temporal Zero-Inflated Negative Binomial Graph Neural Network(STZINB-GNN)

Urban road-based risk prediction is a crucial yet challenging aspect of research in transportation safety. While most existing studies emphasize accurate prediction, they often overlook the importance of model uncertainty. In this paper, we introduce a novel Spatial-Temporal Zero-Inflated Negative Binomial Graph Neural Network (STZINB-GNN) for road-level traffic risk prediction, with a focus on uncertainty quantification. Our case study, conducted in the Lambeth borough of London, UK, demonstrates the superior performance of our approach in comparison to existing methods. Although the negative binomial distribution may not be the most suitable choice for handling real, non-binary risk levels, our work lays a solid foundation for future research exploring alternative distribution models or techniques. Ultimately, the STZINB-GNN contributes to enhanced transportation safety and data-driven decision-making in urban planning by providing a more accurate and reliable framework for road-level traffic risk prediction and uncertainty quantification.

cs.CE↗

arXiv2023

Unraveling the Variations of the Society of England and Wales through Diffusion Maps Analysis on Census 2011

We propose a new approach to identifying geographical clustering and hotspots of inequality from decadal census data. We use diffusion mapping to study the 181,408 Output Areas in England and Wales, which allows us to decompose the feature structures of countries in the census data space. Additionally, we develop a new localization metric inspired by statistical physics to uncover the importance of minority groups in London. The results of our study can be applied to other census-like data constructions that include spatial localization and differentiation from low degrees of freedom. This new approach can help us better understand the patterns of social deprivation and segregation across the country and aid in the development of policies to address these issues.

physics.soc-ph↗