arXiv subjects

Constantinos Antoniou

Publications and source records attributed to Constantinos Antoniou.

12 recordsLinked to original sources

arXiv2026

GUIDED Network-Agnostic Feature Initialization for Spatial Transferability in GNN-based Models

The Traffic Assignment Problem is a fundamental but computationally expensive component of transportation planning. While Graph Neural Networks have emerged as fast, data-driven surrogates, their practical deployment is severely constrained by a spatial generalization gap. Standard models rely on transductive feature initializations that tie travel demand to fixed network topologies, preventing seamless transfer to new urban environments. To overcome this structural limitation, this research proposes a network-agnostic initialization layer, termed Geometrically Unconstrained Inductive Demand EmbeDding (GUIDED). By injecting travel demand as a scalar attribute on auxiliary virtual links rather than as specific node features, this modular framework standardizes the input space regardless of network scale. Extensive experimental evaluation across multiple urban topologies demonstrates that a Heterogeneous Graph Attention Network (HetGAT) model integrated with the proposed GUIDED layer maintains state-of-the-art predictive accuracy on single-network tasks, while demonstrating superior robustness to out-of-distribution demand patterns and maintaining a distinct performance advantage over the baseline even under severe data scarcity. Notably, the proposed feature initialization enables highly parameter-efficient domain adaptation for inter-network transfer learning without artificial input homogenization, establishing a robust foundation for truly inductive models. At the same time, the optimized scatter operations of the initialization layer yield an approximate 50% reduction in training time per epoch compared to the baseline approach. Furthermore, while demonstrated on vehicular traffic, this fundamental abstraction of spatial topology provides a versatile blueprint for generalized origin-destination spatial problems, such as freight logistics and multimodal network optimization.

cs.LG↗

arXiv2026

LLMs on Tabular Data with Limited Semantics: Evidence from Industrial Car Retrofit Prediction

Industrial retrofit planning depends on structured operational data rather than free text: planners must estimate whether a newly registered prototype will require a retrofit, which retrofit package it will need, and how long the work will take. We study an industrial dataset linking a prototype-registration system (284,271 vehicles) with a retrofit-management system (48,716 cleaned visits), and compare strong tabular machine learning baselines with three LLM-based strategies on row-serialized inputs: embedding features (Amazon Titan), direct prompted classification (Claude Sonnet 4), and an ML+LLM stacking approach. Across binary occurrence prediction, 15-way retrofit-type classification, per-visit duration regression, and an aggregated monthly benchmark, classical tree ensembles remain the strongest standalone models. However, the LLM results reveal a consistent pattern: embeddings remain useful on tables (binary AUC = 0.982), direct prompting collapses once semantic signal is stripped by hashing (binary AUC = 0.500; multiclass weighted F1 = 0.018), and hybrid stacking yields the best manually built multiclass model (weighted F1 = 0.626). On the monthly benchmark, lag-based machine learning outperforms time-series foundation models, though Chronos-small remains competitive in zero-shot forecasting. The results suggest that on privacy-constrained industrial tables, LLMs are more effective as complementary components than as replacements for strong tabular baselines.

cs.LG↗

arXiv2026

Efficient Traffic Prediction at Scale: A Systematic Study of STGCN Architectural Depth

Spatio-temporal graph neural networks (STGNNs) have become the dominant approach for traffic prediction, yet their computational requirements pose challenges for practical deployment in intelligent transportation systems (ITS). While recent work has proposed efficient alternatives to STGNNs, a fundamental question remains unexplored: are these architectures themselves over-parameterised? We examine this question using the Spatio-Temporal Graph Convolutional Network (STGCN), one of the most widely adopted models in this domain. Through systematic experiments across four diverse traffic datasets, we compare 1-block, 2-block (standard), and 3-block STGCN variants. Our findings reveal that the single-block architecture achieves optimal performance for short-term prediction (10 mins) on three of four datasets, while incurring only marginal degradation ($\leq$1.8% relative error) at longer horizons. Crucially, the 2-block variant incurs 61% higher CPU inference latency and 37% lower throughput relative to 1-block -- substantial overhead for resource-constrained ITS deployment. The 3-block architecture offers no favourable tradeoff, more than doubling computational cost for $<$0.5% relative improvement. These results suggest that the default 2-block STGCN may be over-parameterised for many applications, with implications for both practitioners deploying traffic prediction systems and researchers benchmarking efficiency-focused methods.

cs.LG↗

arXiv2025

Quantifying the Improvement of Accessibility achieved via Shared Mobility on Demand

Shared Mobility Services (SMS), e.g., demand-responsive transport or ride-sharing, can improve mobility in low-density areas, which are often poorly served by conventional Public Transport (PT). Such improvement is generally measured via basic performance indicators, such as waiting or travel time. However, such basic indicators do not account for the most important contribution that SMS can provide to territories, i.e., increasing the potential, for users, to reach surrounding opportunities, such as jobs, schools, businesses, etc. Such potential can be measured by isochrone-based accessibility indicators, which count the number of opportunities reachable in a limited time, and are thus easy for the public to understand. % The potential impact of SMS on accessibility has been qualitatively discussed and implications on equity have been empirically studied. However, to date, there are no quantitative methods to compute isochrone-based indicators of the accessibility achieved via SMS. This work fills this gap by proposing a first method to compute isochrone accessibility of PT systems composed of conventional PT and SMS, acting as a feeder for access and egress trips to/from PT hubs. This method is grounded on spatial-temporal statistical analysis, performed via Kriging. It takes as input observed trips of SMS and summarizes them in a graph. On such a graph, isochrone accessibility indicators are computed. We apply the proposed method to a MATSim simulation study concerning demand-responsive transport integrated into PT, in the suburban area of Paris-Saclay.

cs.CY↗

arXiv2025

Development of a graph neural network surrogate for travel demand modelling

As urban environments grow, the modelling of transportation systems becomes increasingly complex. This paper advances the field of travel demand modelling by introducing advanced Graph Neural Network (GNN) architectures as surrogate models, addressing key limitations of previous approaches. Building on prior work with Graph Convolutional Networks (GCNs), we introduce GATv3, a new Graph Attention Network (GAT) variant that mitigates over-smoothing through residual connections, enabling deeper and more expressive architectures. Additionally, we propose a fine-grained classification framework that improves predictive stability while achieving numerical precision comparable to regression, offering a more interpretable and efficient alternative. To enhance model performance, we develop a synthetic data generation strategy, which expands the augmented training dataset without overfitting. Our experiments demonstrate that GATv3 significantly improves classification performance, while the GCN model shows unexpected dominance in fine-grained classification when supplemented with additional training data. The results highlight the advantages of fine-grained classification over regression for travel demand modelling tasks and reveal new challenges in extending GAT-based architectures to complex transport scenarios. Notably, GATv3 appears well-suited for classification-based transportation applications, such as section control and congestion warning systems, which require a higher degree of differentiation among neighboring links. These findings contribute to refining GNN-based surrogates, offering new possibilities for applying GATv3 and fine-grained classification in broader transportation challenges.

cs.LG↗

arXiv2025

Guided Persona-based AI Surveys: Can we replicate personal mobility preferences at scale using LLMs?

This study explores the potential of Large Language Models (LLMs) to generate artificial surveys, with a focus on personal mobility preferences in Germany. By leveraging LLMs for synthetic data creation, we aim to address the limitations of traditional survey methods, such as high costs, inefficiency and scalability challenges. A novel approach incorporating "Personas" - combinations of demographic and behavioural attributes - is introduced and compared to five other synthetic survey methods, which vary in their use of real-world data and methodological complexity. The MiD 2017 dataset, a comprehensive mobility survey in Germany, serves as a benchmark to assess the alignment of synthetic data with real-world patterns. The results demonstrate that LLMs can effectively capture complex dependencies between demographic attributes and preferences while offering flexibility to explore hypothetical scenarios. This approach presents valuable opportunities for transportation planning and social science research, enabling scalable, cost-efficient and privacy-preserving data generation.

cs.CL↗

arXiv2023

On the Computation of Accessibility Provided by Shared Mobility

Shared Mobility Services (SMS), e.g., Demand-Responsive Transit (DRT) or ride-sharing, can improve mobility in low-density areas, often poorly served by conventional Public Transport (PT). Such improvement is mostly quantified via basic performance indicators, like wait or travel time. However, accessibility indicators, measuring the ease of reaching surrounding opportunities (e.g., jobs, schools, shops, ...), would be a more comprehensive indicator. To date, no method exists to quantify the accessibility of SMS based on empirical measurements. Indeed, accessibility is generally computed on graph representations of PT networks, but SMS are dynamic and do not follow a predefined network. We propose a spatial-temporal statistical method that takes as input observed trips of a SMS acting as a feeder for PT and summarized such trips in a graph. On such a graph, we compute classic accessibility indicators. We apply our method to a MATSim simulation study concerning DRT in Paris-Saclay.

cs.CY↗

arXiv2022

Car-Sharing Subscription Preferences: The Case of Copenhagen, Munich, and Tel Aviv-Yafo

Car-sharing services have been providing short-term car access to their users, contributing to sustainable urban mobility and generating positive societal and often environmental impacts. As car-sharing business models vary, it is important to understand what features drive the attraction and retention of its members in different contexts. For that, it is essential to examine individuals preferences for subscriptions to different business models and what they perceive as most relevant, as well as understand what could be attractive incentives. This study aims precisely to examine individuals preferences for the subscription of different car-sharing services in different cities. We designed a stated preference experiment and collected data from three different urban car-sharing settings, namely Copenhagen, Munich, and Tel Aviv-Yafo. Then a mixed logit model was estimated to uncover car-sharing plan subscription and incentives preferences. The results improve our understanding of how both the features of the car-sharing business model and the provision of incentives can maintain and attract members to the system. The achieved insights pave the road for the actual design of car-sharing business models and incentives that can be offered by existing and future car-sharing companies in the studied or similar cities.

econ.GN↗

arXiv2021

Improving the Accuracy and Efficiency of Online Calibration for Simulation-based Dynamic Traffic Assignment

Simulation-based Dynamic Traffic Assignment models have important applications in real-time traffic management and control. The efficacy of these systems rests on the ability to generate accurate estimates and predictions of traffic states, which necessitates online calibration. A widely used solution approach for online calibration is the Extended Kalman Filter (EKF), which -- although appealing in its flexibility to incorporate any class of parameters and measurements -- poses several challenges with regard to calibration accuracy and scalability, especially in congested situations for large-scale networks. This paper addresses these issues in turn so as to improve the accuracy and efficiency of EKF-based online calibration approaches for large and congested networks. First, the concept of state augmentation is revisited to handle violations of the Markovian assumption typically implicit in online applications of the EKF. Second, a method based on graph-coloring is proposed to operationalize the partitioned finite-difference approach that enhances scalability of the gradient computations. Several synthetic experiments and a real world case study demonstrate that application of the proposed approaches yields improvements in terms of both prediction accuracy and computational performance. The work has applications in real-world deployments of simulation-based dynamic traffic assignment systems.

eess.SY↗

arXiv2021

Utilizing Import Vector Machines to Identify Dangerous Pro-active Traffic Conditions

Traffic accidents have been a severe issue in metropolises with the development of traffic flow. This paper explores the theory and application of a recently developed machine learning technique, namely Import Vector Machines (IVMs), in real-time crash risk analysis, which is a hot topic to reduce traffic accidents. Historical crash data and corresponding traffic data from Shanghai Urban Expressway System were employed and matched. Traffic conditions are labelled as dangerous (i.e. probably leading to a crash) and safe (i.e. a normal traffic condition) based on 5-minute measurements of average speed, volume and occupancy. The IVM algorithm is trained to build the classifier and its performance is compared to the popular and successfully applied technique of Support Vector Machines (SVMs). The main findings indicate that IVMs could successfully be employed in real-time identification of dangerous pro-active traffic conditions. Furthermore, similar to the "support points" of the SVM, the IVM model uses only a fraction of the training data to index kernel basis functions, typically a much smaller fraction than the SVM, and its classification rates are similar to those of SVMs. This gives the IVM a computational advantage over the SVM, especially when the size of the training data set is large.

stat.ML↗

arXiv2019

Incorporating Trip Chaining within Online Demand Estimation

Time-dependent Origin-Destination (OD) demand flows are fundamental inputs for Dynamic Traffic Assignment (DTA) systems and real-time traffic management. This work introduces a novel state-space framework to estimate these demand flows in an online context. Specifically, we propose to explicitly include trip-chaining behavior within the state-space formulation, which is solved using the well-established Kalman Filtering technique. While existing works already consider structural information and recursive behavior within the online demand estimation problem, this information has been always considered at the OD level. In this study, we introduce this structural information by explicitly representing trip-chaining within the estimation framework. The advantage is twofold. First, all trips belonging to the same tour can be jointly calibrated. Second, given the estimation during a certain time interval, a prediction of the structural deviation over the whole day can be obtained without the need to run additional simulations. The effectiveness of the proposed methodology is demonstrated first on a toy network and then on a large real-world network. Results show that the model improves the prediction performance with respect to a conventional Kalman Filtering approach. We also show that, on the basis of the estimation of the morning commute, the model can be used to predict the evening commute without need of running additional simulations.

cs.DS↗

arXiv2019

A low dimensional model for bike sharing demand forecasting

Big, transport-related datasets are nowadays publicly available, which makes data-driven mobility analysis possible. Trips with their origins, destinations and travel times are collected in publicly available big databases, which allows for a deeper and richer understanding of mobility patterns. This paper proposes a low dimensional approach to combine these data sources with weather data in order to forecast the daily demand for Bike Sharing Systems (BSS). The core of this approach lies in the proposed clustering technique, which reduces the dimension of the problem and, differently from other machine learning techniques, requires limited assumptions on the model or its parameters. The proposed clustering technique synthesizes mobility data quantitatively (number of trips) and spatially (mean trip origin and destination). This allows identifying recursive mobility patterns that - when combined with weather data - provide accurate predictions of the demand. The method is tested with real-world data from New York City. We synthesize more than four million trips into vectors of movement, which are then combined with weather data to forecast the daily demand at a city-level. Results show that, already with a one-parameters model, the proposed approach provides accurate predictions.

physics.soc-ph↗