Individual Travel Research Articles

Combining Individual Travel Preferences Into Destination Prediction: A Multi-Module Deep Learning Network

Accurate destination prediction over sub-trajectories is essential for a wide range of location-based services. Traditional trip matching methods fail to capture temporal dependence hidden in trajectories and may suffer from data sparsity problems. With the help of massive trajectory data, state-of-the-art approaches based on deep learning (DL) have achieved great success. However, existing DL approaches rarely consider the influence of individual travel preferences in destination prediction. When the trip is long but the known partial trajectory is short, DL models are unable to produce satisfactory results. Thus, we design a feature extraction mechanism to extract useful temporal features, spatial features, and static covariates for destination prediction, among which the spatial features characterize individual travel preferences by considering two main movement patterns in daily travel. Then, a hierarchical model including multiple modules is proposed to finely process heterogeneous features. Extensive experiments conducted on two public datasets demonstrate the superior performance of the proposed model compared to the state-of-the-art methods. Moreover, further experimental results show that the proposed model still performs well when trajectory prefix is short or travel duration is long, which confirms the effectiveness of integrating individual travel preferences.

Clustering-Based Travel Pattern for Individual Travel Prediction of Frequent Passengers by Using Transit Smart Card

Individual travel prediction is very important for the construction of intelligent urban transportation systems. Previous studies mainly focus on the improvement of algorithms, but pay little attention to the mining of data information. In this paper, the concept of the travel pattern is introduced into the field of individual travel prediction of frequent bus passengers. The travel pattern of passengers refers to the trip with similar boarding time and similar boarding and alighting stations of the same person. Through clustering the travel pattern by DBSCAN algorithm, the regularity of passenger travel can be better exploited and travel information can be integrated into a unified unit as well. In the process of prediction, we first predict whether the passenger will travel, and then, if so, predict the probability distribution of the next trip conditional on the previous one. The proposed method is tested using the Automatic Fare Collection data of Chengdu’s frequent bus passengers in May 2019. Based on travel pattern, the average accuracy of travel information prediction is about 41%, which is 13% higher than the method without using travel pattern. Furthermore, this paper also discusses the influence of spatial threshold in clustering on the prediction results.

The Trap of Visibility?

Sara Mills’ influential Foucauldian study of women’s travel writing, Discourses of Difference (1991), heralded a turn from the consideration of individual female travellers as exceptions towards an analysis of the discursive pressures similarly exerted on all of them, through the awareness of normative expectations regarding the production and the reception of their writings. This article revisits panopticism in the genre by showing how travel writing reveals the intersection between the material plane (travelling) and the discursive process (writing). Through the parallel analysis of three travel narratives, Anna Jameson’s Winter Studies and Summer Rambles in Canada (1838), Isabella Bird’s A Lady’s Life in the Rocky Mountains (1879), and Mary Kingsley’s Travels in West Africa (1897), I show how their clothing and behaviour are enacted as signs of femininity for the benefit of their contemporaries, in texts whose diaristic form articulates the writing of the self and its exhibition to the public. I thus analyse how these travel narratives illustrate the intersection of the individual and the social in power relations and self-fashioning, and how their authors negotiate surveillance in gender performance.

Does Destination, Relationship Type, or Migration Status of the Host Impact VFR Travel?

Visiting friends and relatives (VFR) travel hosts play a key role in influencing the trip characteristics of their VFR travel parties and the decisions and activities within those travel parties. However, how those trips are shaped in terms of travel decisions and activities is not well understood. This is the first quantitative study examining the hosting of VFRs by examining how migration, relationship type (VF versus VR), and destination type impact the characteristics and activities of VFR travel parties. The objective was to examine the extent of influence of different characteristics of VFR hosts on individual VFR travel decisions and activities. Estimation models were developed and tested through regression analysis to examine the impact that the characteristics of hosts have on decisions and activities within VFR travel. Such findings have provided a systematic framework for examining the multifaceted role of VFR hosts. The generalisability of the estimation models developed and tested in this study can be replicated and adapted in future studies.

Valuing Recreation in Italy's Protected Areas Using Spatial Big Data

Protected areas offer unique opportunities for recreation, but the non-market nature of these benefits presents a significant challenge when trying to represent value in the decision-making processes. The most common techniques to value recreation are based on resource-intensive primary surveys which are difficult to perform at a large scale or in remote locations. This is true in the case of Italy, where a large and diverse network of protected areas suffers from lack of data. Here, we offer an alternative data source for the valuation of recreation by integrating the metadata of geotagged photographs from social media into single-site, individual travel cost models for 67 Italian protected areas. Count data model results are generally consistent with standard economic and consumer demand theory for ordinary goods, with a zero-truncated Poisson model returning down sloping demand curves for 50 of 67 sites. A significant travel cost coefficient was returned for 33 sites (p-value <0.05) for which consumer surplus estimates were found in the range between €6.33 and €87.16, with a mean value per trip of €32.82. Although not without their own challenges, the results presented highlight the possibilities of new forms of spatial big data as a novel data source for environmental economists.

Valuasi Ekonomi Ekowisata Kawasan Ekosistem Esensial (KEE) Pantai Taman Kili-Kili Kabupaten Trenggalek

Ecotourism KEE Kili-Kili beach, located in Trenggalek Regency, is rich in biodiversity and natural beauty. Valuation is needed to determine the use value or benefits of resources and the environment. Economic value of resources that offer natural beauty, in general, are non-market (does not have a market price) because they are public goods. This study aims to estimate the potential economic value of KEE ecotourism at Taman Kili-Kili beach, Trenggalek Regency. This study is a quantitative study with multiple linear regression analysis to determine the factors that influence the number of tourist visits. Meanwhile, to find out the economic value, the individual travel cost method (ITCM) is used. The results showed that only the motivation variable had a significant effect on the number of visits variable. The economic potential of ecotourism KEE at Taman Kili-Kili beach reaches Rp. 34,580,440,612/year. The magnitude of the value of the economic benefits of natural resources and the ecotourism environment of the Taman Kili-Kili KEE coast is expected by managers and related stakeholders to improve ecotourism management by adding tourist facilities and attractions to provide more satisfaction for visitors. In addition, the improvement of the access road to the location is very necessary in order to provide convenience and comfort in reaching the location.

Individualized passenger travel pattern multi-clustering based on graph regularized tensor latent dirichlet allocation

Individual passenger travel patterns have significant value in understanding passenger’s behavior, such as learning the hidden clusters of locations, time, and passengers. The learned clusters further enable commercially beneficial actions such as customized services, promotions, data-driven urban-use planning, peak hour discovery, and so on. However, the individualized passenger modeling is very challenging for the following reasons: 1) The individual passenger travel data are multi-dimensional spatiotemporal big data, including at least the origin, destination, and time dimensions; 2) Moreover, individualized passenger travel patterns usually depend on the external environment, such as the distances and functions of locations, which are ignored in most current works. This work proposes a multi-clustering model to learn the latent clusters along the multiple dimensions of Origin, Destination, Time, and eventually, Passenger (ODT-P). We develop a graph-regularized tensor Latent Dirichlet Allocation (LDA) model by first extending the traditional LDA model into a tensor version and then applies to individual travel data. Then, the external information of stations is formulated as semantic graphs and incorporated as the Laplacian regularizations; Furthermore, to improve the model scalability when dealing with massive data, an online stochastic learning method based on tensorized variational Expectation-Maximization algorithm is developed. Finally, a case study based on passengers in the Hong Kong metro system is conducted and demonstrates that a better clustering performance is achieved compared to state-of-the-arts with the improvement in point-wise mutual information index and algorithm convergence speed by a factor of two.

Heuristic time-dependent personal scheduling problem with electric vehicles

In this paper, a heuristic method which contributes to the solution of the Daily Activity Chains Optimization problem with the use of Electric Vehicles (DACO-EV) is presented. The DACO-EV is a time-dependent activity-scheduling problem of individual travelers in urban environments. The heuristic method is comprised of a genetic algorithm that considers as its parameters a set of preferences of the travelers regarding their initial activity chains as well as parameters concerning the transportation network and the urban environment. The objective of the algorithm is to calculate the traveler’s optimized activity chains within a single day as they emerge from the improved combinations of the available options for each individual traveler based on their flexibility preferences. Special emphasis is laid on the underlying speed-up techniques of the GA and the mechanisms that account for specific characteristics of EVs, such as consumption according to the EV model and international standards, charging station locations, and the types of charging plugs. From the results of this study, it is proven that the method is suitable for efficiently aiding travelers in the meaningful planning of their daily activity schedules and that the algorithm can serve as a tool for the analysis and derivation of the insights into the transportation network itself.

Low-cost turn compensation control system for conserving seeds and increasing yields from maize precision planters

Inconsistencies in seed spacing can occur between rows when a traditional maize precision planter drives along a curve because the inner and outer rows travel faster or slower than the center rows. This results in the wastage of expensive seeds and a decrease in the yield. In this study, a low-cost turn compensation control system (TCCS), based on a dual-radar system, for maize precision planters was developed to address these problems. The system automatically modifies the seeding rates for different rows by individually adjusting the rotary speeds of the drive motors. During the research, a mathematical model for calculating the individual travel speed of each plant row was developed according to rigid body kinematics and the Ackerman steering principle. A simulation model was also built in the MATLAB Simulink software to qualitatively evaluate the primary factors (speed accuracy (SA), turning radius (TR), and turning speed (TS)) that affected the performance of the TCCS. Field trial results showed that the average seeding rate error (AEQ) did not exceed 4.52%, 2.12%, and 2.77% for TRs of 7 m, 14 m, and 28 m, respectively. These values were significantly lower than those at the equivalent TR conditions when the turn compensation function was turned off: 19.41%, 9.04%, and 5.47%, respectively. With the newly developed TCCS, a uniform seed spacing for each plant row was obtained, regardless of the changes in TR and TS. Additionally, the maximum average seed spacing variation coefficient (APREC) did not exceed 19.93%, a value lower than the requirements set by Chinese national standards. In summary, the proposed TCCS reduced maize production costs and improved net profits by ensuring the same seed spacing for all the plant rows. The total cost of the TCCS for a six-row precision planter was only $4,496.82, which is significantly less than that for functionally similar control systems produced by some well-known agricultural machinery manufacturers, making it more suitable for cost-sensitive farmers.

Valuasi Nilai Ekonomi Agrowisata Bukit Waruwangi Menggunakan Metode Biaya Perjalanan

Bukit Waruwangi Agrotourism is a new tourist destination in Serang Regency, Banten Province that offers the experience of enjoying a farm with grassland surrounded by beautiful hillside views. A good understanding of the visitors perception, contributory factors of the visit demand, as well as the potential value of tourism activities are fundamental in formulating effective farm management policies. This paper used the individual travel cost method to estimates the recreational value of Bukit Waruwangi Agrotourism. In general, visitors have a good perception of the farm. However, parking facilities, road access, and visitor shelters need to be improved. Travel costs, education level, and distance significantly affect the recreational demand. The value of a single farm visit is estimated to be Rp 18,266.00 per person and estimated annually at Rp 2,465,900,000.

Tracking discrepancies between expected and actual flows of tourists in an urban destination: An application of user-generated data

In tourism studies, new means of data collection (e.g., smartphone and Internet) have opened up new opportunities for unveiling spatial patterns at various scales. This paper aims to analyze the discrepancy between actual and expected flows between scenic spots in an urban destination at different distance ranges, on an urban scale, based on the individual travel tips data extracted from online sources. The results based on Nanjing, China, indicate that scenic spots with a high degree of centrality are more important in the network of expected flow compared to actual flow. Actual and expected flows of scenic spots are the consequence of the interaction among various factors, including inflow degree, outflow flow, and distance. Moreover, these flows are distance-sensitive at a low level, with a higher sensitivity of the actual flow. Because of the actual situation during the travel, tourists may adjust the itinerary from the expected flow and avoid the trip between two distant scenic spots due to various constraints. Lastly, implications are provided for destination planning and marketing.

A Testing and Quarantine Algorithm for Individual International Travelers Using Published Data on WHO-Approved Vaccines and Bayes' Theorem.

Policies such as border closures and quarantines have been widely used during the COVID-19 pandemic. Policy modifications and updates, however, must be adjusted as global vaccination rates increase. We calculated the risks of individual travelers based on their expected transmission and benchmarked them against that of an unvaccinated traveler quarantined for 14 days without testing. All individuals with a negative preboarding test can be released with a negative arrival test, when both tests have a sensitivity ≥ 90% and a specificity ≥ 97%, performance characteristics that could be accomplished by rapid antigen tests. This assumption is valid for an incidence rate up to 0.1 (prior to testing) and effective reproduction number (Rt) up to 4 in the arrival country. In a sensitivity analysis scenario where the incidence rate is 0.4 and Rt is 16, a negative preboarding test and a negative arrival test, both with a sensitivity ≥ 98% and a specificity ≥ 97%, can ensure that a traveler has a lower expected transmission than an unvaccinated person who is quarantined for 14 days. In most cases, fully vaccinated travelers (with or without booster) and a negative preboarding test can be released with a negative rapid antigen test upon arrival, allowing travelers to depart the airport within 30 min.

Research on Marketing Strategy of Railway Passenger Travel Behaviour Analysis in Competitive Section

The deep mining of passengers’ travel data can identify competitive segments and gain insights into passengers’ characteristics and differentiated demands. This can not only effectively support precise marketing strategy adjustment of railway transport but also improve its competitiveness in the passenger transportation market. In this paper, hidden railway travel behaviour is introduced and integrated with railway travel behaviour to create a complete passenger travel chain, based on existing distance-based competitive segment recognition methods. The loyalty index values of passengers are calculated using this travel chain to identify competitive segments. Furthermore, passenger classification and grouping currently ignore social relationships as well as personal travel characteristics. Therefore, a novel passenger grouping method is proposed; it integrates individuals’ travel characteristics and social relations. Individual travel labels are created for travellers based on their travel data. Social relation topologies, such as ticketing relation, the relation of travelling together, and benefit relation via point redemption, can be extracted using these labels. Social relation traits can be retrieved using graph attention networks and multigraph fusion. Finally, travellers are categorised based on their individual travel characteristics. As an example, and a case study, the grouping of Guangzhou–Shanghai passengers in 2020 is taken which shows that the suggested method has the potential to improve both the precision and the feasibility of grouping railway passengers. As a result, new ideas for passenger grouping in railway marketing might be offered.

Application of Choice Experiment and Individual Travel Cost Methods in Recreational Value Evaluation

Application of Choice Experiment and Individual Travel Cost Methods in Recreational Value Evaluation

Exploring regional sustainable commuting patterns based on dockless bike-sharing data and POI data

The dockless bike-sharing system, which provides a sustainable transportation mode available anytime and anywhere, has played an increasingly important role in urban daily commuting. However, urban structure complexity and job-housing imbalances present difficulties in understanding the characteristics of bicycling travel demand, especially with respect to the commuting patterns in megacities. Moreover, the functional properties of a region implying the different travel purposes of citizens have rarely been considered and incorporated into pattern extraction and analysis. Based on dockless bike-sharing data and point of interest (POI) data, this paper designed a regional indicator system with 24 features and established a set of random forest models to evaluate feature significance for different commuting purposes. The city of Shanghai was used as a case study, and sustainable commuting patterns were regionally extracted. The regional purpose composition can also be effectively derived with the average optimal accuracy of RMSE = 0.0734. The analysis results can help traffic operators and managers not only discover the regional commuting patterns of bike-sharing mobility but also interpret the patterns more specifically and purposefully. In terms of practical applications, the research could benefit the scientific and reasonable allocation of shared bicycles at the regional level to improve individual travel efficiency and comprehensively increase the attractiveness of such a sustainable travel mode.

Analyzing the impact of Сovid-19 on the hotel industry in Nepal

COVID-19 pandemic has significantly affected the tourism and hospitality sectors across the globe. Due to the increase in the number of COVID positive cases, governments of countries have imposed strict lockdown globally as a precautionary measure to control the spread of the coronavirus, which has led to restrictions on travel and mobility of individuals from one place to the other. One of the countries that have been severely affected due to the lockdown is the economy of Nepal. Being a tourist-friendly nation, every year, Nepal’s tourism and hospitality sector contributes significantly to its GDP. With a restriction on travel and cancellation of bookings, one of the most important departments under this sector, the hotel industry, is currently struggling to survive due to loss of revenue. The present study tries to understand the challenges and strategies planned by the hotel industry stakeholders in Nepal. A primary survey conducted with hoteliers from 10 hotels reveals major concerns about maintaining a steady financial performance and expectations for government aid to help this sector come back to normalcy.

Research on parking choice behavior of shared autonomous vehicle services by measuring users’ intention of usage

Shared autonomous vehicles (SAVs) are one of the important development directions of smart and green transportation. However, relevant researches are not sufficient at present. The factors influencing the intention to use SAVs and their parking choice behaviors need to be further analyzed. First, in order to better explain, predict, and improve travelers’ intention to use SAVs, the conceptual framework based on technology acceptance model was developed to establish the relationships between the travelers’ intention to use SAVs, social influence of SAVs, attitude toward behavior of SAVs, perceived risk of SAVs, perceived usefulness of SAVs and perceived ease of these use. Then structural equation model (SEM) was established to analyze the relationship between various variables. The results show that the perceived usefulness, behavior attitude, social influence, perceived ease of use, and perceived risk are the main factors that determine the intention to use SAVs. Through the test of direct effect, indirect effect, and total effect in the model, it is found that perceived usefulness has the largest total impact on intention to use SAVs, with a standardized coefficient of 0.765, followed by behavior attitude (0.732), social influence (0.597), perceived ease of use (0.462) and perceived risk of SAVs (−0.452). In addition, through the study of observed indicator variables ATB2 and BI3, it is found that perceived usefulness, perceived ease of use, social influence, perceived risk, attitude toward behavior, and behavior intention all have an impact on parking behavior. In order to study the specific influencing factors of parking choice behavior, a multinomial logit (MNL) model was established to analyze the relationships between travelers’ parking choice behaviors and the influential factors, which include travelers’ individual characteristics, travel attributes, and parking modes’ attributes by extracting from a questionnaire. The results show that the travel time, travel fees, parking charge, cruising fees, parking time and traffic emission are the main factors that determine travelers’ choices of parking. This paper provides advice for operators of SAVs.

Data-Driven Food Desert Metric to Understand Access to Grocery Stores Using Chi-Square Automatic Interaction Detector Decision Tree Analysis

A food desert is a geographic area lacking spatial and socioeconomic access to healthy foods. Disparities in food access and availability hinder public health and individual wellbeing. Access to healthy food has been evaluated by many agencies and researches yet they do not comparably demarcate food deserts or identify vulnerable populations in methodical terms. Existing literature suggests a link between food deserts, income level, and vehicle ownership. This study evaluates the existing methods and proposes a novel data-driven method to identify food deserts in Baltimore, Maryland. This study evaluates responses from 573 respondents for an in-depth analysis of individual grocery store choice and travel decisions. Chi-square automatic interaction detector (CHAID) decision trees are used to develop a user-generated food desert metric. Income level is found to be a key indicator for food desert demarcation, more than vehicle ownership. Network distance was applied to develop the prioritization matrix for a food desert. This research provides a replicable method for determining food-insecure areas in a locality by aggregating individual data to identify such areas. Such a metric can aid policymakers to make investment decisions and to direct resources to areas of need.

Learning Shared Mobility-Aware Knowledge for Multiple Urban Travel Demands

With the growth of Internet of Things (IoT) devices, smart travel methods, such as sharing-bike and ride-hailing become popular commuting methods. With people&#x2019;s growing needs and the rapid dynamics in a city environment, simply using a single travel demand for prediction may be insufficient. Alternatively, modeling multiple travel demands simultaneously can deepen our understanding toward the status of these potentially correlated demands and deploy the transportation in the city better. An important observation in this work is that multiple travel demands in a city often show common patterns, referred to as the shared mobility-aware knowledge. In addition, there are also unique patterns that characterize individual travel demand resulting in unique knowledge. To better leverage the shared and unique knowledge, we propose a novel framework (MultiST) to predict multiple spatial&#x2013;temporal sequences (multiple travel demands) via two components that extract the shared and unique spatial&#x2013;temporal dependencies, respectively. For the unique component, we use convolutional neural networks and gated recurrent units to embed unique knowledge. For the shared component, we design a recurrent Gaussian cell to extract temporal dependencies. Empirical results show that MultiST outperforms six state-of-the-art baseline methods and three variants of MultiST. We further visualize the temporal dependencies of the shared knowledge and discuss the practical implications.

Implementation Paper on Personalized Travel Recommendation by Mining People Attributes

Abstract: The recommendation system has growth choices in recent years. The recommendation system is existing in many applications which gives online travel information for individual travel package. A new model named travel recommendation using data mining techniques which extracts the features like locations, travel seasons of various landscapes. Thus, it possesses the material of the travel packages and interests of tourists. Further extending E-TRAST model with the tourist-relation-area season topic model includes relationship with tourists. It includes mining significant tourist locations based on the user search trajectories of users on web and also derives a personalized travel algorithm recommendation system using travelogues and users contributed photos with metadata of this photo by comparing existing different technique. To suggest personalized POI sequence, first famous routes are stratified as per the similarity between user package and route package. Keywords: Travel package, recommender systems, cocktail, topic modeling, and collaborative filtering