User Travel Research Articles

Planning of fast charging stations with consideration of EV user, distribution network and station operation

Despite the benefits of electric vehicles (EV) as a sustainable alternative to fossil fuel-powered vehicles, the lack of suitable fast charging stations (FCS) continues to be a barrier to widespread EV adoption. Different factors affecting EV user, distribution network and CS operation must be taken into account when selecting CS locations and capacity. The purpose of this study is to design a FCS location and capacity planning framework that considers EV user travel time and waiting time, distribution network power loss, and station utilization aspects. Besides, a prior utilization rate-based queuing algorithm is proposed to determine the CS capacity, which simultaneously reduce user waiting time and affirms adequate station utilization. Then binary atom search optimization algorithm is employed to solve the FCS location and capacity problem. The proposed model is tested on an integrated transportation network and distribution network and the numerical results are provided and analysed from the perspectives of the distribution network, EV user, and CS operation.

A Picture-Based Approach to Tourism Recommendation System

Due to the subjective nature of the experience, it is challenging to classify travel products according to uniform criteria as physical products, which poses a significant challenge for recommendation techniques. In practical application scenarios, this study introduces an alternative image-based approach as an implicit elicitation of user preferences for travel products to accurately recommend products to travellers with different tastes. We developed a model based on exploratory factor analysis. First, based on exploratory factor analysis, we compared the pictures tapped by users to five types of travel preferences. Then, we use the Euclidean algorithm to project the images and scenic spot features into a five-dimensional space. It calculates the distance, thus quantifying the relationship between the travel and the user's favourite pictures. The final result shows that the model effectively improves the user's travel matching and effectively contributes to the field of travel destination recommendation.

Travel-time prediction using neural-network-based mixture models

Accurate estimation of travel times is an important step in smart transportation and smart building systems. Poor estimation of travel times results in both frustrated users and wasted resources. Current methods that estimate travel times usually only return point estimates, losing important distributional information necessary for accurate decision-making. We propose using neural network-based mixture distributions to predict a user's travel times given their origin and destination coordinates. We show that our method correctly estimates the travel time distribution, maximizes utility in a downstream elevator scheduling task, and is easy to retrain—making it a versatile and an inexpensive-to-maintain module when deployed in smart crowd management systems.

RETRACTED ARTICLE: Research on Service Design for People with Mental Disorders: Take Curing Digital Cloud Tourism App Media in the Post-Epidemic Era as an Example.

In today's era, the number of people suffering from mental disorders has increased significantly, which has become a public health event, and its treatment plans and means are difficult, especially in the special environment of the post-epidemic era, traditional simple treatment cannot meet the ever-changing diseases. This article from the current situation of mental health and its treatment environment in our country, in the face of mental disorder crowd healing the practical significance of the innovation design, digital media curative cloud travel APP the research path of service design, technical implementation, operation methods, innovative thinking dimensions to explore how to age for people in the face of disorder in the outbreak of curative services digital media design. In order to provide some reference and reference value for the development of spiritual healing industry, the design ideas and methods of smart cloud tourism APP service are designed and studied in terms of user travel experience, service process optimization, service interface innovation and service contact point design.

Deslocamento intermunicipal como barreira de acesso ao aborto previsto em lei. Brasil, 2010-2019

Abstract Objectives: to analyze abortions provided by law (APL) carried out in Brazil between 2010 and 2019 regarding the need for travel of users, as well as the expenditure of time and money on these trips. Methods: descriptive study of records of outpatient care and hospitalizations for APL between 2010 and 2019. The municipal provision and the inter-municipal flows for the realization of the APL, the availability of public transportation for this travel, as well as its cost and time, were identified. Results: 2.6% of Brazilian municipalities had a sustained provision of APL between 2010 and 2019. Of the 15,889 APL performed, 14.8% occurred in municipalities other than those where the user lived. The smaller the population size of the municipality of residence, the higher the percentage of the need for travel. Of these inter-municipal trips, 16.0% had regular round-trip links by public transport. The total travel time ranged from 26 minutes to 4 and a half days, and the cost from R$2.70 to R$1,218.06; the highest medians were among residents of the Midwest region. Conclusions: the concentration of services, the deficiency of inter-municipal public transport, and the expenditure on travel to access the APL are barriers to users that need the health service, demanding public policies to overcome them.

Alignment Work for Urban Accessibility: A Study of How Wheelchair Users Travel in Urban Spaces

Mobility is the key for people with disabilities to have full participation in life. To support their mobility, previous work primarily focused on accessibility as an attribute of the external environment to be evaluated, labeled, visualized, and improved. Relatively less work has looked at how people with disabilities go out and move around in practice and work to achieve mobility. This paper presents a qualitative study of 14 wheelchair users' travel practices in everyday life in China, highlighting urban accessibility as alignment work -- the use of an awareness of the conditions along the journey to continuously align and re-align various resources to ensure accessibility and mobility across contexts and moments. By highlighting alignment work, we present another side of the story of urban accessibility, and broaden design considerations to support mobility for wheelchair users.

Cost-oriented optimization of the location and capacity of charging stations for the electric Robotaxi fleet

Large-scale adoption of Robotaxi requires a comprehensive charging infrastructure as a guarantee, but the problems of insufficient capacity, low utilization, and unreasonable deployment of electric vehicle charging stations (EVCSs) are still common. In this context, this study proposed a multi-stage optimization strategy consisting of fleet sizing, charging demand simulation, model construction and solution to achieve the location and capacity optimization of EVCSs for the electric Robotaxi fleet. In stage one, a vehicle shareable network model based on graph theory was developed to determine the minimum Robotaxi fleet size required to adequately meet user travel demand, which was solved using the Hopcroft-Karp algorithm. In stage two, the specific spatio-temporal distribution of fleet charging demand was obtained by Monte Carlo simulation, considering the decision-making characteristics of Robotaxi operation and charging process. In stage three, a charging station location and capacity optimization model was established with the objective of minimizing the comprehensive costs, and an improved particle swarm optimization algorithm applying genetic operators to improve the population diversity was proposed. Finally, the effectiveness of the proposed model and algorithm was analyzed and discussed based on a case study using the real passenger order and geographic data from the city of Chengdu, China.

A new spatial database framework for pedestrian indoor navigation based on the OpenStreetMap tag information

AbstractIt is widely acknowledged that the tools for pedestrian navigation in indoor environments have been increasing while the internal spaces of buildings continue to grow in complexity. The majority of mobile applications for indoor navigation are mostly dependent on access to radio‐frequency identification (RFID) and WiFi, which are particularly limited and expensive in most of Sub‐Saharan Africa. In addition, data from Volunteered Geographic Information such as OpenStreetMap (OSM) lacked clear framework and specification for database design for indoor navigation. Accordingly, this study proposed and illustrated a new database framework for indoor navigation by taking advantage of the popular OSM tag information structure. The proposed framework characterized the indoor environment based on horizontal and vertical partitions, together with description of indoor features by using cardinal directions and qualitative descriptions. The framework was demonstrated by creating sample database records, and retrieval of step‐by‐step travel information for different internal configurations of the indoor environment. A key contribution of this framework is its simplistic and low‐cost nature, where user travel information is retrieved from the database with no need for communication signals from Global Positioning Systems, RFID, or WiFi, making it advantageous for low‐cost applications where access to these communication infrastructure are limited.

An Efficient Algorithm of Star Subgraph Queries on Urban Traffic Knowledge Graph

Knowledge graph has wide applications in the field of computer science. In the knowledge service environment, the information is large and explosive, and it is difficult to find knowledge of common phenomena. The urban traffic knowledge graph is a knowledge system that formally describes urban traffic concepts, entities and their interrelationships. It has great application potential in application scenarios such as user travel, route planning, and urban planning. This paper first defines the urban traffic knowledge graph and the star subgraph query of the urban traffic knowledge graph. Then, the road network data and trajectory data are collected to extract the urban traffic knowledge, and the urban traffic knowledge graph is constructed with this knowledge. Finally, a star subgraph query algorithm on the urban traffic knowledge graph is proposed. The discussion of the star subgraph query mode gives the corresponding application scenarios of our method in the urban traffic knowledge graph. Experimental results verify the performance advantages of this method.

POI recommendation with queuing time and user interest awareness

Point-of-interest (POI) recommendation is a challenging problem due to different contextual information and a wide variety of human mobility patterns. Prior studies focus on recommendation that considers user travel spatiotemporal and sequential patterns behaviours. These studies do not pay attention to user personal interests, which is a significant factor for POI recommendation. Besides user interests, queuing time also plays a significant role in affecting user mobility behaviour, e.g., having to queue a long time to enter a POI might reduce visitor’s enjoyment. Recently, attention-based recurrent neural networks-based approaches show promising performance in the next POI recommendation task. However, they are limited to single head attention, which can have difficulty in finding the appropriate user mobility behaviours considering complex relationships among POI spatial distances, POI check-in time, user interests and POI queuing times. In this research work, we are the first to consider queuing time and user interest awareness factors for next POI recommendation. We demonstrate how it is non-trivial to recommend a next POI and simultaneously predict its queuing time. To solve this problem, we propose a multi-task, multi-head attention transformer model called TLR-M_UI. The model recommends the next POIs to the target users and predicts queuing time to access the POIs simultaneously by considering user mobility behaviours. The proposed model utilises POIs description-based user personal interest that can also solve the new categorical POI cold start problem. Extensive experiments on six real-world datasets show that the proposed models outperform the state-of-the-art baseline approaches in terms of precision, recall, and F1-score evaluation metrics. The model also predicts and minimizes the queuing time. For the reproducibility of the proposed model, we have publicly shared our implementation code at GitHub (https://github.com/sajalhalder/TLR-M_UI).

Estimating charging demand from the perspective of choice behavior: A framework combining rule-based algorithm and hybrid choice model

It is of great significance to study the generation and spatio-temporal variation of electric vehicle charging demand for guiding the planning, construction and operation of charging facilities. Based on users' daily travel laws and behaviors, this paper proposed a framework for charging demand estimation, which combines rule-based algorithm and discrete choice model. The generation process of charging demand is divided into two choice stages. Stage one is before travel, where users choose whether to charge in the trip chain. Stage two is during travel, where users choose the charging location. The hybrid choice model based on the mixed logit model is constructed for the two choice stages respectively. This model can comprehensively consider the influence of several factors on charging choice behavior, including individual attitudes, preference heterogeneity, electric vehicle status, traffic attributes, parking place attributes and charging service level. In addition, the rule-based algorithm can establish the correlation within a trip chain, which refers to influence of the previous episode on the current episode. It can also update the status changes of battery electric vehicles and trips. In this way, the spatio-temporal coupling estimation of charging demand is achieved. Next, two stated preference surveys are conducted through online platform and field survey. The estimation results show that both probabilistic models have achieved high goodness-of-fit, and the proposed model can both characterize the influence of psychological attitude and preference heterogeneity of electric vehicle users on choice behavior. The parameter calibration results show that the user's travel plan plays a very important role in the process of generating charging demand. Besides, the attributes of the parking place and the service quality of the charging facilities are important factors affecting the choice of the charging location. The research results can guide the formulation of charging facility planning and operation strategies.

A Federated Mixed Logit Model for Personal Mobility Service in Autonomous Transportation Systems

Looking ahead to the future-stage autonomous transportation system (ATS), personal mobility service (PMS) aims to provide the recommended travel options based on both microscopic individual travel demand and the macroscopic supply system objectives. Such a goal relies on massive heterogeneous data to interpret and predict user travel intentions, facing the challenges caused by prevalent centralized approaches, such as an unbalanced utilization rate between cloud and edge, and data privacy. To fill the gap, we propose a federated logit model (FMXL), for estimating user preferences, which integrates a discrete choice model—the mixed logit model (MXL), with a novel decentralized learning paradigm—federated learning (FL). FMXL supports PMS by (1) respectively performing local and global estimation at the client and server to optimize the load, (2) collaboratively approximating the posterior of the standard mixed logit model through a continuous interaction mechanism, and (3) flexibly configuring two specific global estimation methods (sampling and aggregation) to accommodate different estimation scenarios. Moreover, the predicted rates of FMXL are about 10% higher compared to a flat logit model in both static and dynamic estimation. Meanwhile, the estimation time has been reduced by about 40% compared to a centralized MXL model. Our model can not only protect user privacy and improve the utilization of edge resources but also significantly improve the accuracy and timeliness of recommendations, thus enhancing the performance of PMS in ATS.

Multi-objective economic emission dispatch of thermal power-electric vehicles considering user's revenue.

In recent years, the rapid development of electric vehicles has increased the load power system and brought new challenges to the safe and stable operation of the gird. Although the vehicle-to-grid technology can reduce the load that electric vehicles put on the grid, without any incentives, electric vehicle owners are more inclined not to use vehicle-to-grid services. In this paper, therefore, a new dynamic economic emission model based on electric vehicles (DEED_EV) is proposed to maximize the electric vehicle user’s revenue, as well as minimize the fuel cost and emission of the thermal power unit. In the DEED_EV model, the stochastic of electric vehicles user’s travel and wear of the battery, as well as some constraints such as electric vehicles charging/discharging rate and status, electric vehicles remain power, electric vehicles travel power capacity, ramp limits, up and down reserves, and the system balance are considered. To solve the DEED_EV model, a multi-objective evolutionary algorithm based on decomposition with a step-by-step constraint handling strategy is developed. Different test cases based on the 10-unit are simulated to verify the proposed model and method. The results show that the DEED_EV model not only encourages more electric vehicles to plug into the grid but also reduces the fuel cost and emission of the thermal power unit. Besides, the electric vehicles in the DEED_EV completely realizes the peak shaving and valley filling of the load.

EV Response Capability Assessment Considering User Travel Demand and Cyber System Reliability

With the increasing penetration rate of electric vehicles (EVs), EV demand response holds great significance for promoting the optimal and secure operation of the power system. This paper proposes an EV response capability assessment method that considers EV users’ travel demands and the reliability of the cyber systems integrated into both the power grid and the transportation network. A novel framework for an integrated cyber–power–transportation system is proposed for the first time, and a reliability model for the cyber system is provided. A method is further proposed to calculate the state of an EV when it is plugged in, considering the reliability of traffic guidance information and the reliability of the release of such information. The degree of relaxation in the EV charging demand is proposed to reflect the user’s travel demand, based on which the EV response capability can be assessed. Extensive test results on a cyber–power–transportation system containing RBTS BUS6 and the Beijing transportation network are conducted to show the efficiency of the proposed method. The impact of cyber reliability on the EV trip and response capability is analyzed.

SMINet: State-Aware Multi-Aspect Interests Representation Network for Cold-Start Users Recommendation

Online travel platforms (OTPs), e.g., bookings.com and Ctrip.com, deliver travel experiences to online users by providing travel-related products. Although much progress has been made, the state-of-the-arts for cold-start problems are largely sub-optimal for user representation, since they do not take into account the unique characteristics exhibited from user travel behaviors. In this work, we propose a State-aware Multi-aspect Interests representation Network (SMINet) for cold-start users recommendation at OTPs, which consists of a multi-aspect interests extractor, a co-attention layer, and a state-aware gating layer. The key component of the model is the multi-aspect interests extractor, which is able to extract representations for the user's multi-aspect interests. Furthermore, to learn the interactions between the user behaviors in the current session and the above multi-aspect interests, we carefully design a co-attention layer which allows the cross attentions between the two modules. Additionally, we propose a travel state-aware gating layer to attentively select the multi-aspect interests. The final user representation is obtained by fusing the three components. Comprehensive experiments conducted both offline and online demonstrate the superior performance of the proposed model at user representation, especially for cold-start users, compared with state-of-the-art methods.

A Serendipity-Oriented Personalized Trip Recommendation Model

Personalized trip recommendation attempts to recommend a sequence of Points of Interest (POIs) to a user. Compared with a single POI recommendation, the POIs sequence recommendation is challenging. There are only a couple of studies focusing on POIs sequence recommendations. It is a challenge to generate a reliable sequence of POIs. The two consecutive POIs should not be similar or from the same category. In developing the sequence of POIs, it is necessary to consider the categories of consecutive POIs. The user with no recorded history is also a challenge to address in trip recommendations. Another problem is that recommending the exact and accurate location makes the users bored. Looking at the same kind of POIs, again and again, is sometimes irritating and tedious. To address these issues in recommendation lies in searching for the sequential, relevant, novel, and unexpected (with high satisfaction) Points of Interest (POIs) to plan a personalized trip. To generate sequential POIs, we will consider POI similarity and category differences among consecutive POIs. We will use serendipity in our trip recommendation. To deal with the challenges of discovering and evaluating user satisfaction, we proposed a Serendipity-Oriented Personalized Trip Recommendation (SOTR). A compelling recommendation algorithm should not just prescribe what we are probably going to appreciate but additionally recommend random yet objective elements to assist with keeping an open window to different worlds and discoveries. We evaluated our algorithm using information acquired from a real-life dataset and user travel histories extracted from a Foursquare dataset. It has been observationally confirmed that serendipity impacts and increases user satisfaction and social goals. Based on that, SOTR recommends a trip with high user satisfaction to maximize user experience. We show that our algorithm outperforms various recommendation methods by satisfying user interests in the trip.

An Electric Fence-Based Intelligent Scheduling Method for Rebalancing Dockless Bike Sharing Systems

With a new generation of bike sharing services emerging, the development of dockless bike sharing services results in considerable socioeconomic and environmental benefits but also creates new issues, such as inappropriate parking behaviors and bike imbalances. To solve the inappropriate parking problem, electric fences have been introduced to guide users to park bikes in designated zones. Considering the role of electric fences in restricting user parking behaviors, an electric fence-based intelligent scheduling method for rebalancing dockless bike sharing systems is proposed in this paper. As a dynamic method that considers the real-time usage of bike sharing systems, an electric fence adjusts its capacity based on real-time information, which guides users to return bikes to electric fences with greater urgency. Because existing approaches require prespecified models and are unable to consider all the intricacies in the dynamic optimization problem, a model-free intelligent scheduling approach based on deep Q-learning that can adapt to the changing distributions of customer arrivals, available bikes, bike locations, and user travel times is used to solve the problem. Finally, a case study involving Beihang University is employed, which shows that the method performs well in rebalancing the bike sharing system and improving the mean utilization (MU) and customer satisfaction (CS).

Influence-Aware Successive Point-of-Interest Recommendation

In recent years, with the rapid development of mobile applications, user check-in histories have been increasing. Successive point-of-interest (POI) recommendation has gained growing attention. Existing successive point-of-interest recommendation methods learn long- and short-term user preferences through historical check-in sequences to provide more personalized services. However, due to sparse data and complicated temporal patterns, the application of such technique is still limited by two challenges: 1) difficulty meeting user travel needs in time; 2) difficulty capturing users complicated behavior patterns. To address this problem, we propose a new Influence-Aware successive POI recommendation Model (InfAM), which can learn the influence of POIs in a short-term sequence fragment for next point-of-interest recommendation. To capture periodic patterns of user movements, InfAM takes a user’s check-in data within a day as an input sequence to address the current travel needs of the user. In addition, based on multihead attention mechanism and user embedding, InfAM focuses on the influence of POIs in short-term sequences and general user preferences in these sequences. Therefore, InfAM integrates three specific dependencies, which can fully learn the dynamic interaction between short-term preferences: the influence of POIs in short-term sequence fragments (POI-poi), user preferences (POI-user), and the periodicity of check-ins (POI-time). Evaluation results on real-world datasets show that InfAM achieves state-of-the-art recommendation performance.

Adaptive gamification in collaborative location collecting systems: a case of traveling behavior detection

Collaborative location collecting systems (CLCS) is a particular case of collaborative systems where a community of users collaboratively collects data associated with a geo-referenced location. Gamification is a strategy to convene participants to CLCS. However, it cannot be generalized because of the different users’ profiles, and so it must be tailored to the users and playing contexts. A strategy for adapting gamification in CLCS is to build game challenges tailored to the player’s spatio-temporal behavior. This type of adaptation requires having a user traveling behavior profile. Particularly, this work is focused on the first steps to detect users’ behavioral profiles related to spatial-temporal activities in the context of CLCS. Specifically, this article introduces: (1) a strategy to detect patterns of spatial-temporal activities, (2) a model to describe the spatial-temporal behavior of users based on (1), and a strategy to detect users’ behavioral patterns based on unsupervised clustering. The approach is evaluated over a Foursquare dataset. The results showed two types of behavioral atoms and two types of users’ behavioral patterns.

New energy vehicles taking into account user needs participate in the FM model

In this paper, a new energy vehicle participation FM model considering user needs is established and verified by simulation. It has been proved that the model can guarantee user travel needs. The new energy vehicle participation FM model is divided into three parts: energy storage calculation, power constraint and energy constraint. Energy storage calculation is to model and analyse the available energy of new energy vehicles participating in FM, and get the variation of participating FM capacity in a day considering the user SOC demand. Power constraint is the charge and discharge power constraint of new energy vehicles, which is the necessary condition to ensure that new energy vehicles do not violate the technical conditions of new energy vehicles and ensure that the energy constraint of user demand participates in frequency modulation.