Publikace

informace pocházejí z univerzitní databáze V3S

Autoři:
MSc. Halil Cevik; Ing. André Maia Pereira, Ph.D.; prof. Ing. Ondřej Přibyl, Ph.D.
Publikováno:
2024, ETC Conference Papers 2024, Association for European Transport), ISSN 2313-1853
Anotace:
Understanding travel demand patterns is crucial for effective traffic management, policy-making, and transportation evaluations. Digital twins have emerged as a significant tool in tackling this challenge, where accurate traffic simulation outcomes depend on high-quality data. Essential to most transportation analysis is the knowledge of road users’ origin and destination (OD), enabling route planning, traffic pattern assessment, and system optimization. This information is typically represented in an Origin-Destination (OD) matrix. However, direct observation of every traveler’s origins and destinations is impractical, necessitating the estimation of time-dependent OD flows from available data — a persistent challenge in the field. Direct methods like measurements, interviews, or surveys are often too costly and challenging to implement. Instead, aggregation methods using traffic counts and other data sources offer reasonable estimates. This paper reviews several approaches for estimating OD matrices for vehicles, bicycles, and pedestrians. This review considers various data sources, methodologies, and preprocessing techniques tailored to each mode of transportation. Subsequently, we propose an integrated framework for OD estimation across these modes, factoring in the unique travel demand influencers and available data for each. We acknowledge practical constraints and provide a meaningful contribution to demand modeling that serves as a baseline for digital twins
Typ:
Stať ve sborníku z mezinár. konf.

Autoři:
MSc. Halil Cevik; prof. Ing. Ondřej Přibyl, Ph.D.; Samandar, S.
Publikováno:
2024, Neural Network World, 34 (4), p. 219-241), ISSN 2336-4335
Anotace:
Understanding individual travel behavior is crucial for developing effective travel demand management strategies and informed transportation policies. This study investigates the factors influencing individuals’ mode choices by analyzing data from a comprehensive travel survey. We employ a deep neural network model to explore the relationships between survey variables and respondents’ transportation mode preferences, focusing on both observable and latent factors. The SHAP method is applied to interpret the model’s outputs, providing global and local explanations that offer detailed insights into the contribution of each variable to mode choice decisions. By identifying the key determinants of mode selection and uncovering the complex interactions between these factors, this research provides valuable insights for designing targeted policies that can better address transportation needs and influence sustainable travel behavior.
DOI:
Typ:
Článek v periodiku excerpovaném SCI Expanded