Future Travel Demand Research Articles

Advanced Digital Technologies for Promoting Indian Culture and Tourism through Cinema

Abstract: Culture and Tourism are two mainly interrelated elements that contribute a lot to achieving Sustainable Development for any developing country especially India, which has an extremely rich historical and cultural background. Tourism Industry is the fastest growing sector in a local economy creating several job opportunities which ultimately raise the standard of living of people which further raises the consumption level of goods and services, resulting in a rise in the Gross Domestic Product (GDP) of a country. However, various studies pointed out major promotional strategies concerning tourism and culture but an amalgamated promotional approach for both was still missing. With this motivation, the current study aims at providing an amalgamated promotional approach in assimilation with the latest Industry 4.0 technologies such as Artificial Intelligence (AI), Machine Learning (ML), Big Data, Blockchain, Virtual Reality (VR), Digital Twin and Metaverse to the Indian tourism industry by reviewing prior research studies. The findings of the current study are establishing an online future travel demands forecasting system, an online tourists’ destination personalized recommendation system, an online tourist’s review analysis recommendation system, and an online destination image recommendation system and provide the practical design for it through 1+5 Architectural Views Model and by applying several ML algorithms such as CNN, BPNN, SVM, Collaborative Filtering, K-means Clustering, API Emotion, and Naïve Bayes algorithms. Finally, this study has discussed challenges and suggested vital recommendations for future work with the assimilation of Industry 4.0 technologies.

An approach for two-dimensional convolutional neural networks for hourly passenger boarding demand prediction based on uneven smart-card data

An invaluable resource for understanding passenger boarding patterns and forecasting future travel demand is the tap-on smart-card data. Positive instances, on the other hand—boarding at a given bus stop at a certain time—are less common than negative instances when looking at the smart-card data (or instances) by boarding stops and by time of day. Machine learning algorithms that are used to estimate hourly boarding numbers at a certain location have been shown to be much less accurate when the data is imbalanced. Before using the smart-card data to forecast bus boarding demand, this research tackles the problem of data imbalance in the data. To create fake traveling instances to add into a synthetic training dataset containing more evenly distributed traveling and non-traveling examples, we suggest using deep generative adversarial networks (Deep-GAN). Next, a deep neural network, or DNN, is trained on the synthetic dataset to predict which instances from a given stop in a certain time frame will travel and which ones won't. According to the findings, resolving the data imbalance problem may greatly enhance the predictive model's functionality and make it more accurate in predicting ridership profiles. The suggested strategy may create a synthetic training set with a better similarity so diversity and, therefore, a stronger prediction capability, according to a comparison of the Deep-GAN's performance with other conventional resampling techniques. The study emphasizes the importance of the issue and offers helpful recommendations for enhancing the quality of the data and model performance for individual travel behavior analysis and travel behavior prediction.

Factors influencing travelers' intention by environmental changes of destination: Cross‐country evidence from Far‐East Asia

AbstractTravel intentions are influenced by not only personal background but also external factors such as national disasters, infectious diseases, and government policy. While international flights and the travel market are sharply recovering from the effects of the COVID‐19 pandemic, travel risk will affect future travel demand. This study analyzed the relationship between potential risk of destination and travel avoidance intention using the stimulus‐organism‐response (SOR) model. The survey was conducted with 303 Chinese and 253 South Korean respondents living in countries adjacent to Japan. The results reveal that travel avoidance intentions may be influenced by emotional reactions to the complexity of the geopolitical environment or the diverse protection motivation perceptions of travelers. This study proposes that nationality has a moderate effect on tentative travel avoidance intention compared to gender.

PODE: privacy-enhanced distributed federated learning approach for origin-destination estimation

The statewide consumer transportation demand model analyzes consumers’ transportation needs and preferences within a particular state. It involves collecting and analyzing data on travel behavior, such as trip purpose, mode choice, and travel patterns, and using this information to create models that predict future travel demand. Naturalistic research, crash databases, and driving simulations have all contributed to our knowledge of how modifications to vehicle design affect road safety. This study proposes an approach named PODE that utilizes federated learning (FL) to train the deep neural network to predict the truck destination state, and in the context of origin-destination (OD) estimation, sensitive individual location information is preserved as the model is trained locally on each device. FL allows the training of our DL model across decentralized devices or servers without exchanging raw data. The primary components of this study are a customized deep neural network based on federated learning, with two clients and a server, and the key preprocessing procedures. We reduce the number of target labels from 51 to 11 for efficient learning. The proposed methodology employs two clients and one-server architecture, where the two clients train their local models using their respective data and send the model updates to the server. The server aggregates the updates and returns the global model to the clients. This architecture helps reduce the server’s computational burden and allows for distributed training. Results reveal that the PODE achieves an accuracy of 93.20% on the server side.

Terra Incognita: California Transit Agency Perspectives on Demand, Service, and Finance in the Age of COVID-19

The COVID-19 pandemic upended transit use, finance, and management. To investigate these effects two years into the pandemic, we conducted 21 semi-structured interviews with senior managers at transit agencies in the most populous U.S. state, California. We found that the pandemic generated many operational and managerial challenges for transit agencies. Ridership plummeted, then slowly recovered, but is still well below pre-pandemic levels at most agencies. Commuter trips to and from major job centers were especially slow to return. In response to decreased demand, public health concerns, and uncertain finances, many agencies cut services and spending early on. As a result, fare revenues declined, in some cases precipitously. However, federal pandemic relief funds proved essential in filling budgetary gaps, stabilizing finances, preventing layoffs, and maintaining services. Other transit subsidies mostly bounced back robustly. Our interviews suggest that, though California transit agencies experimented with free fares, few fareless programs were made permanent. Their challenges include considerable uncertainty associated with future travel demand, looming financial shortfalls at systems that formerly had high farebox recovery and are still drawing on federal pandemic funds to backfill their fare revenue losses, and protracted labor shortages of drivers and mechanics that are preventing many systems from providing desired levels of service.

Using system dynamics to understand long-term impact of new mobility services and sustainable mobility policies: an analysis pre- and post-COVID-19 pandemic in Rio de Janeiro, Brazil

ABSTRACT Sustainable transport policies are fundamental to adapt transport capacity to existing and future travel demand. In this context, this study aims to develop a System Dynamics (SD), to verify the effects of these policies, focusing on congestion and air pollution. Combined with the SD, the discrete choice utility approach was used to predict the modal share in different policy spaces. In addition, it is carried out a case study in Rio de Janeiro in two realities: pre- and post-pandemic. The results show how mitigation policies can reduce transport externalities (congestion and pollution). The encouragement of high-capacity public transport and car ownership control are the best measures, obtaining high simulation scores. The post-pandemic scenario shows that reducing travel demand is the key to achieving better results. All scores obtained in this scenario are better than in pre-pandemic scenario. Finally, results point out that ride-hailing should be used in a conscious way.

The relations between working from home and travel behaviour: a panel analysis

AbstractPolicies to increase the amount of time people spend working from home were widely used during the COVID-19 pandemic. Since research suggests that the resulting increase in working from home will outlast these policies themselves, policymakers want to understand the relations between working from home and travel behaviour. We apply longitudinal modelling techniques to estimate the relations between working from home and travel behaviour using panel data from the Netherlands Mobility Panel spanning the years 2017 through 2021. This allows us to separate between-persons and within-persons relations and effects and to see whether these effects changed during the pandemic. We find a negative effect of working from home on commute travel time both before and during the pandemic and a positive effect on leisure travel time only before the pandemic. The sizes of these effects remained roughly similar during the pandemic, although the extent to which working from home affected commute travel time increased during the pandemic. The net effect of working from home on travel time is negative, indicating that working from home policies could be used to reduce travel time. The results also show that some of the relationships between working from home and travel behaviour have changed during the pandemic. As a result, policymakers and transport operators should be careful when estimating future travel demand based on extrapolations of relationships found only before or during the pandemic.

Robust Design of Electric Charging Infrastructure Locations under Travel Demand Uncertainty and Driving Range Heterogeneity

The rising demand for electric vehicles (EVs), motivated by their environmental benefits, is generating an increased need for EV charging infrastructure. Also, it has been recognized that the adequacy of such infrastructure helps promote EV use. Therefore, to facilitate EV adoption, governments seek guidance on continued investments in EV charging infrastructure development. Such investment decisions, which include EV charging station locations and capacities, and the timing of such investments require robust estimates of future travel demand and EV battery range constraints. This paper develops and implements a framework to establish an optimal schedule and locations for new charging stations and decommissioning gasoline refueling stations over a long-term planning horizon, considering the uncertainty in future travel demand forecasts and the driving range heterogeneity of EVs. A robust mathematical model is proposed to solve the problem by minimizing not only the worst-case total system travel cost but also the total penalty for unused capacities of charging stations. This study uses an adaptation of the cutting-plane method to solve the proposed model. Based on two key decision criteria (travelers’ cost and charging supply sufficiency), the results indicate that the robust scheme outperforms its deterministic counterpart.

Predicting Hourly Boarding Demand of Bus Passengers Using Imbalanced Records From Smart-Cards: A Deep Learning Approach

The tap-on smart-card data provides a valuable source to learn passengers’ boarding behaviour and predict future travel demand. However, when examining the smart-card records (or instances) by the time of day and by boarding stops, the positive instances (i.e. boarding at a specific bus stop at a specific time) are rare compared to negative instances (not boarding at that bus stop at that time). Imbalanced data has been demonstrated to significantly reduce the accuracy of machine-learning models deployed for predicting hourly boarding numbers from a particular location. This paper addresses this data imbalance issue in the smart-card data before applying it to predict bus boarding demand. We propose the deep generative adversarial nets (Deep-GAN) to generate dummy travelling instances to add to a synthetic training dataset with more balanced travelling and non-travelling instances. The synthetic dataset is then used to train a deep neural network (DNN) for predicting the travelling and non-travelling instances from a particular stop in a given time window. The results show that addressing the data imbalance issue can significantly improve the predictive model’s performance and better fit ridership’s actual profile. Comparing the performance of the Deep-GAN with other traditional resampling methods shows that the proposed method can produce a synthetic training dataset with a higher similarity and diversity and, thus, a stronger prediction power. The paper highlights the significance and provides practical guidance in improving the data quality and model performance on travel behaviour prediction and individual travel behaviour analysis.

How do expected changes in life affect young people's stated ownership of privately-owned autonomous vehicles: A comparative study

Autonomous vehicles (AVs) are expected to bring various changes in people's lives. Such expected changes in life may affect people's decisions on the ownership of privately-owned AVs (PAVs) and even future travel demand structure. However, such effects remained unclear due to the lack of relevant studies. By targeting young people, this study fills this research gap by implementing a nation-wide expectation and stated preference (SP) survey in Japan, by comparing with older people. In the survey, respondents first reported their expected changes in life caused by AVs and then chose the most preferred vehicle from a choice set with three types of PAVs (conditional, high, and full automation) and a conventional car. The survey was implemented in 2016 and 3,006 valid SP responses were collected from 1,002 respondents (417 are young people). It is found that young people expected more changes in life and are more likely to choose PAVs with high and full automation than older people, which is consistent with the reported willingness-to-pay. By estimating a mixed logit model with panel data, it is revealed that expected changes in life affect the two age groups' choices of PAVs. There are more inconsistent influences of expected changes in life between the two groups than consistent influences, suggesting the presence of age-related structural differences of responses to future expectations. Diverse responses to future expectations are revealed, which policy implications are discussed. The findings support a life-oriented paradigm shift of travel behavior research and cross-sectoral transport policymaking and future sustainable society design.

Passenger Flow Scale Prediction of Urban Rail Transit Stations Based on Multilayer Perceptron (MLP)

Accurately predicting passenger flow at rail stations is an effective way to reduce operation and maintenance costs, improve the quality of passenger travel while meeting future passenger travel demand. The improvement of data acquisition capability allows fine-grained and large-scale built environment data to be extracted. Therefore, this paper focuses on investigating the relationship between the built environment around the station and the station passenger flow and discusses whether the built environment data can be applied to the station passenger flow prediction. Firstly, the evaluation system of station passenger flow influencing factors is built based on multisource data. The inner relationship between built environment factors and station passenger flow is investigated using the Pearson correlation analysis. Based on this, a multilayer perceptron (MLP)-based passenger flow prediction model was developed to predict the passenger flow at key stations. The study results show that the built environment factors impact station passenger flow, and the MLP prediction model has better prediction accuracy and applicability. The results of the study can be applied to predict the passenger flow scale of rail stations without historical passenger flow data and thus are also applicable to new rail stations.

Determining contract conditions in a PPP project among deep uncertainty in future outturn travel demand

Determining contract conditions in a PPP project among deep uncertainty in future outturn travel demand

A Two-Step Model for Predicting Travel Demand in Expanding Subways

In many cities, subways are expanding with new or extended lines being built and put into operations. The prediction of future travel demand in subway with the planned expansion is of significant importance because such information is crucial for new line planning and new network operations. In this study, we identify the determinant features from potential influential factors of passenger travel demand and develop a two-step model for predicting passenger travel demand in expanding subways. The proposed model is tested in an actual subway with a new line being put into operations, and achieves higher prediction accuracy than the benchmark models.

Improving future travel demand projections: a pathway with an open science interdisciplinary approach

Transport accounts for 24% of global CO2 emissions from fossil fuels. Governments face challenges in developing feasible and equitable mitigation strategies to reduce energy consumption and manage the transition to low-carbon transport systems. To meet the local and global transport emission reduction targets, policymakers need more realistic/sophisticated future projections of transport demand to better understand the speed and depth of the actions required to mitigate greenhouse gas emissions. In this paper, we argue that the lack of access to high-quality data on the current and historical travel demand and interdisciplinary research hinders transport planning and sustainable transitions toward low-carbon transport futures. We call for a greater interdisciplinary collaboration agenda across open data, data science, behaviour modelling, and policy analysis. These advancemets can reduce some of the major uncertainties and contribute to evidence-based solutions toward improving the sustainability performance of future transport systems. The paper also points to some needed efforts and directions to provide robust insights to policymakers. We provide examples of how these efforts could benefit from the International Transport Energy Modeling Open Data project and open science interdisciplinary collaborations.

An improved methodology for evaluating energy service demand for China's passenger transport sector

China's energy service demand statistics for the passenger transport sector only cover travel activities for business purpose. The incomplete data have made it very difficult to conduct long-term scenario analysis for this sector. Thus, this study develops a methodology by refining and combining vehicle activity and travel behavior methods. By taking advantage of the two methods, the extent of uncertainty in estimates can be reduced. A detailed description of China's energy service demand in the passenger transport sector for the years 2013, 2015, and 2017 are produced. Results show that there is a significant underestimation of total passenger transport turnover in governmental statistics. After reevaluation, the total passenger turnover doubled and increased by 146%, 167%, and 187%, resulting in national total passenger turnover of 6783, 8031, and 9406 billion passenger kilometers in 2013, 2015, and 2017, respectively. The majority of missing statistics are caused by not accounting for non-operational road transport, which is dominated by private vehicles. After adjustment, the road sector share in total passenger turnover grew substantially from 30% to 40% to approximately 75%, with the proportion of urban travel continuing to increase. We found that without complete data on China's passenger turnover, it may result in more than three-fold overestimation for future travel demand, leading to inaccurate projections with much higher energy consumption and CO2 emissions. It is therefore very important to have a detailed and precise calculation of energy service demand in the passenger transport sector. The estimation framework and step-by-step process can also be applied to other developing countries which are confronting similar statistical issues.

Traffic Impact Assessment, Diversion and Management Plan for Surat Metro Line 1, Package –CS3, Surat

Abstract: Package CS3 of Metro Line 1 in Surat City includes 3 stations i.e. Surat railway station, Maskati Hospital and Chowk Bazar. As per proposed Metro plan of Surat city, this line will originate from Sarthana station and will terminate at Dream City. The length of Line 1 is 21.61KM of which 14.59km is elevated whereas 7.02km is Underground and consists of 20 Stations. This metro line envisages use of public transport system in Surat city and shall cater the present and future travel demand of the catchment area and shall also reduce load from road based transport system of the corridor. During the construction phase of any Mass Rapid Transit System (MRTS) running along the Right of Way (ROW) of existing roadway system, Traffic diversion and management plan implementation becomes absolute mandatory to reduce congestion, conflicts increase level of safety and ease construction process. Similarly, for package CS3 of Surat Metro line 1, there is need of preparing an implementing Traffic Diversion and Management plan to create a synergy amongst construction activities, traffic flow, safety of pedestrian and construction worker with minimal impact on surrounding catchment. This study shall provide Traffic diversion and management plan which may help to cater the existing traffic and stir them in a smooth and non-congested flow with the help of signage’s, road markings, etc.

The impact of migration background, ethnicity and social network dispersion on air and car travel in the UK

While there is a saturation of car mileage per head in developed countries, international air travel has grown rapidly until 2020, making it crucial to better understand its drivers. An often-overlooked factor here is migration. Previous research suggests that individuals with migration background and/or from ethnic minorities tend to have more environmentally sustainable everyday travel patterns, due to lower car use. Yet there is evidence suggesting that their air travel-related emissions are higher than average, possibly due to visits to the home country and the trips required to maintain spatially distant social ties. However, migration background and social network attributes are typically not included in quantitative studies of air travel. In this paper, we analyse data from the 2011–2013 UKHLS survey, which provides information on annual car mileage and frequency of air travel for private purposes, allowing us to derive rough estimates of greenhouse gas emissions. We estimate regression models for these outcomes, including migration background, ethnicity, and social network predictors. We find that: i) first-generation migration background is associated with lower car mileage, but higher levels of air travel; ii) this effect is less pronounced or absent for less recently-arrived migrants and second- and third-generation migrants; iii) spatially dispersed social networks are positively associated with both air and car travel; iv) the association between migration background and air travel is partly accounted for by social network dispersion. We conclude by discussing implications for future research and air travel demand management policies.

Safety Concerns and Travel Behavior of Generation Z: Case Study from the Czech Republic

Generation Z has been online since the beginning, the online space is an integral part of their lives and personalities, and they make up about 30% of the world’s population. It is claimed that this youngest cohort is already the most numerous generation on the Earth. The most important holiday parameters for them are price and location. They want to explore new places and be active while abroad. The study examines the impact of safety concerns on changes in travel behavior during the COVID-19 pandemic. We focused on members of Generation Z who study the Tourism and the Recreation and Leisure Studies programs, so these students have a positive attitude towards traveling. Data were collected via internal university systems at two periods of time connected to different stages of the pandemic outbreak. The sample was chosen randomly. The sample of Period 1 (n = 150) was composed in 2020, after the lifting of restrictions at the end of the first wave of the COVID-19 pandemic in the Czech Republic. The sample of Period 2 (n = 126) was collected one year later, after the lifting of restrictions at the end of the third wave of the COVID-19 pandemic in the Czech Republic. Correspondence analysis was used for better understanding and representation. This is a unique research study on Generation Z in the Czech Republic and Central Europe. As a result of the contemporary demographic changes in the world, this generation will shape future travel demand. Hence, understanding these youngest travelers will be key to predicting how tourism trends could evolve in the next few years and how these could influence worldwide tourism. The respondents thought they would not change their travel habits in the next five years because of the pandemic. When Periods 1 and 2 were compared after one year of the pandemic, the respondents preferred individual trips to group trips and individual accommodation to group accommodation facilities. On the other hand, our findings revealed a significant increase in safety concerns related to changes in travel behavior when the above-mentioned periods were compared. The research contributes to mapping young people’s attitudes towards travel in the constrained and changing conditions resulting from the COVID-19 pandemic. The findings help analyze the consumer behavior of the target group.

Fully automated vehicles: A cost-based analysis of the share of ownership and mobility services, and its socio-economic determinants

• Cost-based modelling of the share of different modes of vehicle use. • We consider: manual and autonomous vehicle (AV) ownership and on-demand AV services. • Heterogeneity in travel and cost pattern considered by using representative data. • Ownership (manual or automated) is the least cost option for most cases. • High income, business use, rurality and primary vehicle are associated with ownership. A major uncertainty in the diffusion of autonomous vehicles is the split between ownership and automated mobility services. We calculate total cost of ownership and use (TCOU) to compare four alternatives: private manually driven vehicles, private automated vehicles, automated on-demand exclusive use mobility services (ridesourcing) and automated on-demand pooled mobility services (ridesplitting), for both conventional and electric propulsions. We also included potential usefulness of travel time in the driverless vehicles in the TCOU calculations, thus including some of the non-financial factors in travel decision making. While nearly all current studies are limited to comparing average representative trips or mileage of existing vehicles, we calculate TCOUs for every vehicle in the UK National Travel Survey dataset, considering heterogeneity in mileage patterns, trip purposes, time spent driving, value of time, vehicle age, depreciation and other factors between different vehicles. The results suggest that a near-total transition to automated ride services is highly unlikely, since ownership of (automated or manually driven) vehicles continues to be the least-cost option in most cases. Even in the most pro-mobility service test case, ownership remains more cost-effective for one third of the current vehicle fleet. Regression analysis shows that higher income of the main driver, business use of the vehicle, rural location of the household or being the main household vehicle leads to a higher likelihood that automated vehicle ownership will be lower cost compared to automated mobility services. Within automated on-demand ride services, exclusive use services are cost effective for more cases compared to pooled, shared-use type options, with uncertain consequences for future travel demand.

Short-term prediction of traffic state, statistical approach versus machine learning approach

Traffic short-term prediction helps intelligent transportation systems manage future travel demand. The objective of this paper is to predict the traffic state for Karaj to Chaloos, a suburban road in Iran. For this, two approaches, statistical and machine learning are investigated. We evaluate the performance of the multinomial logit model, the support vector machine, and the deep neural network as two machine learning techniques. The principal component analysis is used to reduce the dimension of the data in order to use the MNL model. SVM and DNN predict traffic state using both primary and reduced datasets (ALL and PCA). MNL can be used not only to compare the accuracy of models but also to estimate their explanatory power. SVM employing primarily datasets outperforms other models by 79% accuracy. Next, the prediction accuracy for SVM-PCA, MNL, DNN-PCA, and DNN-ALL are equal to 78%, 73%, 68%, and 67%. SVM-ALL has better performance for predicting light, heavy, and blockage states, while the semi-heavy state is predicted more accurately by MNL. Using the PCA dataset increases the accuracy of DNN but decreases SVM accuracy by 1%. More precision is achieved for the first three months of testing compared to the second three months.