20 research outputs found
On the Evaluation of a Cluster-based Reputation Assessment Mechanism for Carpooling Applications
No full textCarpooling is a mobility concept that appears to be the answer when it comes to challenges in urban mobility derived by population growth. In carpooling, the same amount of people move with fewer vehicles leading to reduced traffic congestion and consequently to less CO2 emissions, fuel consumption and drivers frustration. However, there has always been scepticism around carpooling due to the inherent mistrust between drivers and passengers. In recent years, some reputation systems have been proposed to reduce the impact of mistrust on carpooling applications. Among them, the work of Salamanis et al. (Salamanis, 2018), in which a reputation assessment mechanism based on clustering users travel preferences, was introduced. In this paper, we provide an extended version of the previous mechanism and we thoroughly evaluate its robustness in relation with different types of malicious attacks and clustering algorithms. In addition, we compare our mechanism with a benchmarking reputation system that utilizes the simple arithmetic mean to calculate reputation values based on users ratings. The evaluation results indicate that the extended reputation assessment mechanism exhibits more robust behavior compared to the benchmarking system in all types of attacks when using the hierarchical clustering algorithm
A Probabilistic Framework for the Reliability Assessment of Crowd Sourcing Urban Traffic Reports
No full textAbstractIncidents produce heavy congestion in large urban traffic networks and therefore real time information about them (e.g. location, timestamp, type) can be very useful for the drivers. An efficient way of gathering this type of information is through a crowd sourcing reporting system that multimodal travellers may utilise for providing information about various incidents they witness to other interconnected users in the same network. After the incoming traffic reports are evaluated, they can be shared to other travellers who are approaching the location of the reported incidents. Travelers can use the reported information for improving their mobility status. Collecting information using crowd sourcing techniques has implications and risks that need to be addressed. One of the most important challenges in this regard is the estimation of the reliability of the incoming information, usually related to individual user reputation. To this end, the exploitation of a reliability assessment system is of profound importance for assuring that only accurate information is shared between interconnected users. This paper introduces an innovative crowd sourcing information assessment mechanism for urban travellers. The purpose of the proposed probabilistic framework is to estimate if a user-generated report is true or false, given a set of static and dynamic parameters. The latter describe contextual conditions occurring at the time when an incident is reported. The proposed model takes into account the current location and speed of the reporting user due to their impact on the reliability of an incoming report. The proposed probabilistic model was evaluated in a simulation environment. Preliminary results show that, based on a set of rational assumptions, the estimated reliability decreases with the distance from the reported event and the speed of the reporting user. Based on the estimates that our model produces, a reliable true/false recommendation system can be devised for evaluating the user generated reports
Evaluating the Effect of Time Series Segmentation on STARIMA-Based Traffic Prediction Model
No full textA Maintainable and Secure Backend Infrastructure for Carpooling Applications
No full textNowadays, carpooling is one of the most widely promoted options for urban and inter-urban mobility due to a number of advantages, such as reduction of travel cost and CO2 emissions. As a result, many carpooling services and associated supporting applications have been developed with various technical characteristics. One of the most critical components of these systems is the backend infrastructure, which acts as an orchestrator of the overall system’s functionality, having as main objective the integrity, security and maintainability of the information exchanged. In this technical report, we present the backend infrastructure of the SocialCar carpooling application, a European-funded research and innovation project aiming to incorporate carpooling into existing mobility systems, by means of powerful planning algorithms and big data integration from public transport, carpooling systems, and crowd sourcing
On the Evaluation of a Cluster-based Reputation Assessment Mechanism for Carpooling Applications
No full textLSTM-Based Deep Learning Models for Long-Term Tourism Demand Forecasting
No full textTourism demand forecasting comprises an important task within the overall tourism demand management process since it enables informed decision making that may increase revenue for hotels. In recent years, the extensive availability of big data in tourism allowed for the development of novel approaches based on the use of deep learning techniques. However, most of the proposed approaches focus on short-term tourism demand forecasting, which is just one part of the tourism demand forecasting problem. Another important part is that most of the proposed models do not integrate exogenous data that could potentially achieve better results in terms of forecasting accuracy. Driven from the aforementioned problems, this paper introduces a deep learning-based approach for long-term tourism demand forecasting. In particular, the proposed forecasting models are based on the long short-term memory network (LSTM), which is capable of incorporating data from exogenous variables. Two different models were implemented, one using only historical hotel booking data and another one, which combines the previous data in conjunction with weather data. The aim of the proposed models is to facilitate the management of a hotel unit, by leveraging their ability to both integrate exogenous data and generate long-term predictions. The proposed models were evaluated on real data from three hotels in Greece. The evaluation results demonstrate the superior forecasting performance of the proposed models after comparison with well-known state-of-the-art approaches for all three hotels. By performing additional benchmarks of forecasting models with and without weather-related parameters, we conclude that the exogenous variables have a noticeable influence on the forecasting accuracy of deep learning models
A User and Stakeholder-Driven Approach for Cross-Border, Seamless and Personalised MaaS Provision
No full textMobility as a Service (MaaS) is the new transport paradigm where service, transport and technology providers collaborate to deliver a seamless MaaS experience to travellers through the MaaS aggregator/issuer who, frequently, tackles the full service provision; from pre-trip planning to redemption. This manuscript presents the exploration of the design, the implementation and primary usability evaluation of an all-inclusive one stop shop that facilitates the transition to seamless MaaS, elaborating on the supported functions as well as the user/stakeholder centric design of the solution. Hybrid trip planning, matchmaking and personalisation, mobility tokens, business rules and back-office synergies collaborate to lead to a single Mobility Token of combinational MaaS packages for travellers to purchase and use. This work has been conducted in the context of MyCorridor H2020 project, with one of its key results being the recommendations towards a cross-border, inclusive and standardised MaaS
A generic sparse regression imputation method for time series and tabular data
No full textAlthough many missing data imputation methods have been proposed in the relevant literature, they focus on either time series or tabular data, but not on both. Hence, a generic sparse regression method for missing data imputation is proposed. The imputed values of a target feature are generated by solving a sparse least squares problem using a preconditioned iterative method based on generic approximate sparse pseudoinverse. Sparsity is introduced by dummy encoding existing or constructed (through discretization) categorical features. Extensive experiments were conducted on several datasets, and the results demonstrate the effectiveness of the method for both time series and tabular data.279411096
Benchmark Comparison of Methods for Approximate Neighborhood Estimation of Road Segments in Large-Scale Traffic Networks
No full text
