Figure - uploaded by Jonas Harz
Content may be subject to copyright.
Source publication
With growing city tourism, there is an increasing need for urban travel demand models to consider traffic generated by visitors. Existing research has concentrated on socio-demographic and journey-related factors to determine what influences the mode choice of tourists. In contrast, revealed preference data, such as travel time, is almost never con...
Similar publications
OpenStreetMap (OSM) data are geographical data that are easy and open to access and therefore used for a large set of applications including travel demand modeling. However, often there is a limited awareness about the shortcomings of volunteered geographic information data, such as OSM. One important issue for the application in travel demand mode...
Citations
... Tourists' movement patterns are affected by the activities of the visited touristic destination (Masiero and Zoltan, 2013). Tourists make several decisions during their visit, where one critical aspect is the selection of a series of activities that form their daily activity pattern, which influences their choices of transport modes (Harz and Sommer, 2022). Without using transport modes, all tourism-related activities would be restricted since tourists could no longer reach their attractions (Palhares, 2003). ...
... In terms of research methodologies, quantitative approaches frequently focus on singular modes of transportation (Gutiérrez & Miravet, 2016;Le-Klähn et al., 2014;Romão & Bi, 2021). However, several studies have expanded this scope, examining the decisions tourists make between different modes of transportation (Harz & Sommer, 2022). Notably, a subset of this research specifically addresses sustainable mobility (Maltese & Zamparini, 2023;Zamparini & Vergori, 2021). ...
... The Multinomial Logit (MNL) models are commonly employed in the analysis of discrete choice behavior, which are characterized by their extensive usage and popularity due to their simple calibration and applicability. (O'Flaherty, 2018;Migliore and Ciccarelli, 2020;Harz and Sommer, 2022). The model structure is as follows (Elharoun, Shahdah and El-Badawy, 2018): ...
Intelligent methods including Machine Learning (ML) techniques have been increasingly employed in transportation mode choice modeling, which is more complex than other demand models, since it has to reliably and accurately reflect a wide range of related categorical and continuous variables, concerning the travelers, transportation system, and trip characteristics. ML techniques can capture such complex relationships. So that, they can provide a more nuanced understanding of the travelers' decision process. Most research studies focused mainly on the evaluation of the model accuracy, where little has been done to evaluate the models' performance toward transport attributes. This research aims to calibrate the transportation choice models using ML techniques , then conduct a comparison with the Multinomial Logit (MNL) model to identify the impact on the model accuracy and performance and quantify to what extent the ML models are sensitive to transport policies compared to the traditional MNL model. To this end, eight ML classifiers were examined. As a case study, the models were calibrated to reflect the choice behavior of trip makers in Alexandria City, Egypt. The models were successfully calibrated with satisfying accuracy; however, the ML models have better calibration results in terms of predictability, outperforming the MNL model, where the GBDT classifier records the best prediction accuracy. Finally, the sensitivity analysis test was performed to quantify the elasticity of the models to transport policies. The results show the ML models' structure is more comprehensively and accurately built than the MNL model providing better indicative and reliable sensitivity analysis results.
... Moreover, as a high-capacity low-carbon public travel mode, ARIT has the potential to alleviate congestion and environmental issues at high-demand airports and promote the sustainable development of the aviation and railway and transportation departments will not keep adding flight routes or rail tracks. The classic solutions of discrete choice problems involve constructing models of logistic regression families to research how factors influence travelers' choices, and such studies are commonly based on self-reported surveys (Harz and Sommer 2022;Liao et al. 2020;Li and Sheng 2016;McFadden 1977). However, the traditional discrete choice models require a strict data distribution and presume linear model structures (Ben-Akiva et al. 1985;Train 2009), which cannot achieve high prediction accuracy and reveal the actual complex nonlinear or interactive effects. ...
The transfer city is a key point in air-to-rail intermodal travel (ARIT) that directly influences the service level of the entire system. Although some studies have investigated factors that influence passengers’ ARIT preferences based on subjective surveys, an in-depth understanding of their nonlinear and interactive impacts on passengers’ actual behavior is still lacking. Using passengers’ online booking data in China, this study implements an interpretable ensemble machine learning framework that incorporates decision-making theory to unveil feature importance and the complex nonlinear and interactive effects of various attributes on passengers’ choice of transfer city in the crucial ARIT scenario. The results show that (1) the extreme gradient boosting (XGBoost) model achieves better performance in predicting ARIT transfer city choice than the conventional discrete choice model; (2) attributes related to intermodal services (e.g., ticket price, in-vehicle duration, transfer duration, quantities of flights and trains) are more important than personal demographic characteristics (e.g., age and gender); (3) factors related to service economy and efficiency display nonlinear impacts with fluctuations and critical thresholds; and (4) individuals with different characteristics present heterogeneous preferences for ARIT transfer cities. These findings can provide useful managerial implications for policymakers.
Dear Colleagues and Friends, dear All
Welcome to the second edition of the International Conference on Sustainable Transport (SuTra 2024). This book of abstracts reflects our collective journey toward this event in which you are participating.
In a world where globalization is rapidly evolving, the transportation of goods and people faces growing challenges. To meet the increasing demand across various transport modalities, we must focus on the sustainability of these systems. The SuTra conference aims to promote multidisciplinary research and practical experiences that explore solutions to reduce transportation's environmental impact. The topics discussed highlight the need for a comprehensive, interdisciplinary approach covering all modes of transport—maritime, rail, road, air, and inland waterways—and combining both professional and scientific perspectives,
with a focus on sustainable forms of mobility and the help of intelligent transport systems.
Our goal is to foster collaboration among academia, industry, and government, creating a platform for stakeholders committed to advancing sustainable transport. The ideas and innovations shared here will contribute to developing more sustainable and efficient transportation practices.
This year's conference is being held at Terme Sveti Martin Resort in Croatia. The resort provides an ideal setting for our gathering, with excellent amenities in a peaceful environment nestled in the Međimurje region. Međimurje County was awarded with the prestigious Green Destination award for sustainable tourism, becoming the first region in Croatia to receive this certificate. For this reason, we would like to especially thank the Tourism Board of Međimurje County for their cooperation in organizing the conference, and we believe that this green and
natural venue environment, recognised as a destination of excellence, completely reflects the vision and the mission of the SuTra Conference. The location is easily accessible from major airports in Zagreb, Graz, and Ljubljana, making it a convenient venue for participants.
We look forward to insightful discussions, meaningful collaborations, and a successful conference. We extend our gratitude to all supporting partners who have contributed to the realization of this event.
Thank you for joining us at SuTra 2024 and contributing to the advancement of sustainable
transportation and looking forward to see you again on SuTra 2026.
Best regards,
SuTra 2024 Chairs
Integrating Decision Support Systems (DSS) in navigation represents a
progressive phase in the evolution towards greater connectivity among vessels
and overall situational awareness of the navigators. However, there is a
significant gap in the understanding and exploration of navigation systems
from the users’ point of view. It is important to recognize that a decision made
at a navigational bridge is influenced by the navigator’s experience,
understanding, and application of the international rules.
The SafeNav project aims to develop an artificially intelligent collision
avoidance system as a crucial step towards achieving automated ships. The
project focuses on designing an innovative DSS system tailored to maritime
applications. Future DSS systems will be integrated into the Integrated
Navigation System (INS) on the vessels' navigation bridge to enhance
navigation safety and environmental protection. The system will utilize data
collected from onboard navigation sensors and incorporate sensor data from
multiple sources in DSS through advanced digital technology.
Developing and validating COLREG-compliant DSS systems for maritime
navigation necessitates rigorous adherence to the International Regulations for
Preventing Collisions at Sea (COLREG) rules. Furthermore, this study presents
a comprehensive framework for designing navigation scenarios to validate
COLREG-compliant DSS in the open sea. These scenarios encompass a wide
range of maritime situations, including head-on encounters, crossing and
overtaking situations, multi-vessel interactions, operations in reduced visibility,
adherence to responsibilities between vessel rules, and scenarios in heavy
traffic.
Each scenario is meticulously crafted using Full Mission Bridge (FMB) Wärtsilä
- Transas Marine Navi Trainer Professional (NTPro) 5000 to simulate realistic
conditions, ensuring the DSS can make appropriate and timely decisions to
avoid collisions and navigate safely. After extracting data from the Wärtsilä
simulator, numerical and computational tasks were conducted in
MATLAB_R2018b programming language and numerical computing
environment. The validation process involves executing these scenarios in a
controlled simulation environment, monitoring the DSS’s decisions, and
evaluating its performance against established COLREG standards. This study
provides a crucial step towards enhancing maritime safety by developing
advanced, COLREG-compliant navigation support technologies facing an
autonomous future.
In diesem Beitrag werden die Methodik und Ergebnisse der Modellierung der Verkehrsmoduswahl von Städtereisenden zur Anreise an den Urlaubsort vorgestellt. Das ermittelte Modell ist in ein Framework zur Modellierung der touristischen Verkehrsnachfrage in Großstädten eingebettet und ermöglicht Prognosen zur Verkehrsmittelverfügbarkeit der Gäste. Als Basis für die Modellschätzungen wurden Daten einer Gästebefragung genutzt. Durch Rekonstruktion der alternativenspezifischen Variablen wurden Choice Sets zur Schätzung von Wahlmodellen erstellt. Es zeigte sich, dass ein Großteil der Varianz durch den Reisezeitunterschied und den Pkw-Besitz im Haushalt erklärt wird. Des Weiteren zeigte sich, dass das Geschlecht der reisenden Person, die Größe der Reisegruppe, der Ausgangspunkt von Tagesausflügen sowie die Raumtypologie des Wohnortes signifikant waren.
Park and ride facilities can be a potential instrument for addressing the rising congestion problems and ensuring sustainable urban mobility in major Indian cities, equipped with fast and excellent metro systems. The present study attempts to under- stand the travel behavior of commuters (four-wheeled private vehicle users only) in relation to the introduction of park and ride as a sustainable and economical alternative mode of travel to driving alone in a private vehicle in the context of Delhi, India. The present study measures the perceived benefit to drive-alone users in Delhi with regard to their willingness to pay (WTP) for switching to a better-quality park and ride service instead of using their private vehicles. Choice-based responses along with socioeconomic and travel information were collected from 559 drive-alone users using a tablet-based stated pre- ference survey instrument. The responses were then analyzed using a multinomial logit (MNL) model. Further, WTP esti- mates of the noncost attributes were calculated to derive the perceived benefit to drive-alone users if they were to switch to using a park and ride service. The study also developed a generalized cost (GC) equation using the parameter and WTP esti- mates derived from the MNL model. Finally, the study conducted a post-estimation analysis using the GC equation to exam- ine the influences of identified explanatory attributes on the GC for drive-alone users who switched to park and ride. ‘‘Trip length,’’ ‘‘parking cost,’’ and ‘‘parking type’’ exerted a significant influence on the generalized cost, indicating that drive-alone users could expect considerable savings (perceived benefit with regard to utility gain) if they were to choose park and ride.
