Intelligent Transport Systems, From Research and Development to the Market Uptake

Technological advances and the use of mobile solutions to make smartphone users’ daily life easier is a mindset that has revolutionized the society lifestyle in the past years. In the public transport sector, mobile ticketing is an example of the applicability of mobile solutions in a real context. Using one smartphone to purchase and validate tickets is a revolutionary idea that has acquired fans around the world. The convenience of use and time savings throughout the process are positive aspects, however, the success of the adoption of such services is limited.

Based on the case of Porto, Portugal and particularly of the mobile app And, this study intends to understand customer churn factors of mobile ticketing services by analysing data from customer complaints and from usage history. Thus, an analysis of the complaints, the complainers and the effects of complaints is presented. A strategy for capturing and retaining users is also proposed considering four stages of mobile ticketing apps lifecycle: user onboarding, user engagement, user retention and user reinstall.

The development of the Internet of Things and mobile technology is connecting people and cities and generating large volumes of geolocated and space-time data. This paper identifies patterns in the Lisbon GIRA bike-sharing system (BSS), by analyzing the spatiotemporal distribution of travel distance, speed and duration, and correlating with environmental factors, such as weather conditions. Through cluster analysis the paper finds novel insights in origin-destination BSS stations, regarding spatial patterns and usage frequency. Such findings can inform decision makers and BSS operators towards service optimization, aiming at improving the Lisbon GIRA network planning in the framework of multimodal urban mobility.

The rapid growth in the number of road users and poor road management have been deemed responsible for the upsurge in road congestions and fatalities in recent times. Many of the lives lost was due to inadequate or inefficient public-accessible alerts system and rerouting mechanisms during emergencies. The Intelligent Transportation System (ITS) was anticipated as a solution to the numerous road networks usage problems. Recently, some developed countries have implemented some forms of ITS initiatives. But the transition of the road networks to a fully integrated ITS has been slow and daunting due to the huge cost of implementation. The use of mobile devices as backbone infrastructure for ITS networks during public emergencies has been proposed. Despite the advantage of being a cheap alternative, low computing power of mobile devices limit their potentials to support the expected Big Data ITS traffic. In this paper, we propose a cloud-based context-sensitive ITS infrastructure that uses the cloud as a primary aggregator of traffic messages plus a hybrid Data Analytics algorithm. The algorithm combines the enhanced features of Apache-Spark and Kafka frameworks blended with collaborative filtering using the ensemble machine learning classifier. The novelty of our approach stems from its ability to provide load balancing routing services based on the users’ profiles, and avoid congestion-using the Dynamic Round Robin scheduling algorithm to reroute users with similar profiles.

Intelligent transportation systems are advanced software applications that support innovative requirements related to several transportation devices. Those applications are vital to mitigate traffic congestion and consequent environmental issues, becoming the transport more efficient and sustainable. In this context, appears the carpooling system idea, which can be described as a facilitator for sharing available seats in a private vehicle that performs a journey.

The main goal of this paper is to argue about the design of a distributed aggregator, which is a new paradigm, to handle information from carpool clubs according to a previously negotiated agreement. The aggregator emerges as a coordinator of carpooling systems, with their own administrations that autonomously manage rewards, penalties and admissions maintaining the privacy and trust among its restricted group.

For this, it is proposed a pure P2P unstructured architecture to support the aggregation of the carpooling systems. The experimental evaluation of this architecture was carried out by developing and installing a demonstrator composed by three instances of carpooling systems, based on a proposed reference implementation, which unify and upgrade, the most common requirements in the market highlighting users’ privacy and trust. In order to represent hypothetical carpool clubs each carpooling system instance was populated with its own fictional data.

This article demonstrates an approach to the simulation of Demand Responsive Transport (DRT) – a flexible transport mode that typically operates as a combination of taxi and bus modes. Travellers request individual trips and DRT is capable of adjusting its routes or schedule to the needs of travellers. It has been seen as a part of the public transport network, which has the potential to reduce operational costs of public transport services, to provide better service quality for population groups with limited mobility and to improve transport fairness. However, a DRT service needs to be thoroughly planned to target the intended user groups, attract a sufficient demand level and maintain reasonable operational costs. As the demand for DRT is dynamic and heterogeneous, it is difficult to simulate it with a macro approach. To address this problem, we develop and evaluate an individual-based simulation comprising models of traveller behaviour for both supply and demand sides. Travellers choose a trip alternative with a mode choice model and DRT vehicle routing utilises a model of travellers’ mode choice behaviour to optimise routes. This allows capturing supply-side operational costs and demand-side service quality for every individual, what allows for designing a personalised service that can prioritise needy groups of travellers improving transport fairness. By simulating different setups of DRT services, the simulator can be used as a decision support tool.

Future embedded systems and services will be seamlessly connected and will interact on all levels with the infrastructure and cloud. For safety-critical applications this means that it is not sufficient to ensure dependability in a single embedded system, but it is necessary to cover the complete service chain including all involved embedded systems as well as involved services running in the edge or the cloud. However, for the development of such Cyber-Physical Systems-of-Systems (CPSoS) engineers must consider all kinds of dependability requirements. For example, it is not an option to ensure safety by impeding reliability or availability requirements. In fact, it is the engineers’ task to optimize the CPSoS’ performance without violating any safety goals.

In this paper, we identify the main challenges of developing CPSoS based on several industrial use cases and present our novel approach for designing cloud-based safety-critical applications with optimized performance by the example of an automated valet parking system. The evaluation shows that our monitoring and recovery solution ensures a superior performance in comparison to current methods, while meeting the system’s safety demands in case of connectivity-related faults.

At airports, the runways are always troubled by the presence of ice, water, cracks, foreign objects, etc. To avoid such problems the runway is supposed to be monitored regularly. To monitor the runways a large number of techniques are available such as runway inspection mobile vans. These techniques are largely human dependent and need interruptions in the runway’s operations for inspection. In this position paper, we suggest an alternative way to monitor the runway. This method is non-invasive in nature with the involvement of Light Detection and Ranging (LIDAR) sensors. In the methodology, we describe the schemes of labelling the data obtained from LIDAR using MARWIS sensors fitted in a mobile van. We describe the entire system and the underlying technology involved in developing the system. The proposed system has the potential of developing an efficient runway monitoring system because the LIDAR technology has proved its efficiency in several terrestrial mapping and monitoring systems.

The world nowadays and business processes, in particular, are changing towards digitalization and reduction of time-consuming processes. Provenance and safety of products are becoming key factors for customers’ trust, so traceability solutions are arising. One of the most up-and-coming disruptive technologies today is a Blockchain (BC). The aim of this article is to provide tentative framework of how to assess the level of success of BC technology in supply chain (SC) and the methods that should be used in such assessment. The fish SC will be used to illustrate the discussion and the traceability and trust issues will be enhanced. The pilot shows that BC can promote strategic alignment, provides convenience and could be used as market leverage issue by promoting traceability and consequently trust in the product available. Methods to be used or such endeavor are suggested. A future understanding of the importance for BC technology use, as a traceability provider from the perspective of a final customer, is detected as a path for further research .

Cooperative Vehicular Platooning (CoVP), has been emerging as a challenging Intelligent Traffic Systems application, promising to bring-about several safety and societal benefits. Relying on V2V communications to control such cooperative and automated actions brings several advantages. In this work, we present a Look Ahead PID controller for CoVP that solely relies upon V2V communications, together with a method to reduce the disturbance propagation in the platoon. The platooning controller also implements a solution to solve the cutting corner problem, keeping the platooning alignment. We evaluate its performance and limitations in realistic simulation scenarios, analyzing the stability and lateral errors of the CoVP, proving that such V2V enabled solutions can be effectively implemented.

In this paper, we apply a data-driven approach to analyse the temporal characteristics of charging sessions performed at a slow charging infrastructure. By using the variable selection ability of the Lasso method, combined with the bootstrap driven post-selection inference, we evaluate measures quantifying the potential impacts of charging infrastructure surroundings. We derive the description of the surroundings of the charging infrastructure from several publicly available datasets, representing social, demographic, business and physical environments. From the temporal characteristics, we focus on the average and standard deviation of the connection and charging time. We uncover a nonlinear relationship between the connection time and the charging time. The main driving factors behind the connection time are linked with the employment-related predictors and certain types of traffic influencing the variation of the connection time. The charging time is mainly affected by the economic wealth of residents. This study extends the knowledge about the electric vehicle driver charging behaviour and can be used to inform charging infrastructure deployment strategies.

The current awareness about climate change creates the urgency in adjusting the services provided in public transport towards more sustainable operations. Recent studies have shown that the integration of electric vehicles into existing fleets is an alternative that allows reducing CO₂ emissions, thus contributing to a more sustainable provision of services in the sector. When the aim is to achieve a full electrification of a bus fleet, several decisions need to be planned, such as i) the number of buses that are required, ii) the types of batteries used in those vehicles, iii) the charging technologies and strategies, iv) the location of the charging stations, and v) the frequency of charging. Nevertheless, although several planning studies have focused on the full electrification of a bus fleet, no study was found considering all these planning decisions that are deemed as essential for an adequate planning. Our study thus contributes to this gap in the literature, by proposing an optimization-based planning model that considers all these planning dimensions in the decision-making process related to the integration of electric buses in a public bus transport system – the MILP4ElectFleet model. All these decisions are evaluated while ensuring the minimization of investment and operating costs. The MILP4ElectFleet model is applied to the Carris case study, a Portuguese public transport operator in the metropolitan area of Lisbon.

This study reviews the logistical infrastructure of the automotive industry of Germany and Poland; to be specific, the factories in Poland which are run by German automobile companies are studied, in order to assess the benefit in the movement of factories from Germany to Poland. Quantitative data of Poland’s logistical structure, German and Polish economies, production output figures and values, etc. are studied under scholarly literature for qualitative assessments. Critical analysis has been made with comparison to each other and Czech Republic as well which is a neighbor and strong competitor of Poland in the industry. Furthermore, data is restructured to assess the economic benefits of German companies and the effect on Polish economy to ascertain the feasibility to produce in a neighboring country in order to save on wages and continue to pay for transportation, rather than producing in the home country of the companies. Findings are drawn in conclusion and a tentative benefit of savings has been noted. Manufacturing volume, vehicular exports, automotive parts exports as well as railway density, carriage of goods and road transport has been analyzed during the process.

Camera systems capture images from the surrounding environment and process these datastreams to detect and classify objects. However, these systems are prone to errors, often caused by adverse weather conditions such as fog. It is well known that fog has a negative effect on the camera’s view and thus degrades sensor performance. This is caused by microscopic water droplets in the air, that scatter light, reduce contrast and blur the image. Object detection algorithms show severely worse performance and high uncertainty when exposed to fog. However, they need to work safe and reliable in all weather conditions to enable full autonomous driving in the future. This work focuses on the evaluation of several state-of-the-art object detectors in normal and foggy environmental conditions. It is shown that the detection performance deteriorates considerably when exposed to fog. Further, the results suggest that some algorithms are more robust towards fog than others.

With the development of automated driving functions, more and more environmental sensors are combined for the vehicle perception. A problem that arises with the extensive use of radar sensing is called interference. It describes the confounding effects from the wave overlay of two or more radar sensors operating in the same frequency-band. At this point, methods for interference avoidance and mitigation come to apply. For a valid design and development of such methods, real sensor measurements were required in the past. This publication instead proposes a novel sensor modelling technique that represents the interference mechanisms within the radar sensor signals. It is based on a full radar time signal simulation coupled with a broad range of influencing factors. The concept is validated by comparing the simulated signal processing steps to the real sensor measurement behavior. As a result, mitigation methods for the sensor fault behavior can be fully assessed within a simulation environment. The opportunity for applying new scenario data and a variable set of radar sensors underlines the importance of this approach in the development of future radar systems.

Tollgates are known as the bottleneck of the highways, which cause long waiting queues in rush-hour times of the day. This brings many undesirable consequences such as higher carbon emission and road safety issues. To avoid this scenario, traffic control authorities need accurate travel time forecasts at tollgates to take effective action to monitor potential traffic load and improve traffic safety. Accurate forecasting of the traffic travel time will help traffic regulators to prevent arising problems by taking action. The main objective of this study is to improve the short-term forecasting (minutes) of the traffic flow on highway tollgates by improving a novel hybrid forecasting method that combines Empirical Mode Decomposition with Support Vector Regression (EMD-SVR). Results claim that compared with SVR, the new proposed hybrid prediction model, EMD-SVR, can effectively improve prediction accuracy. Better forecasting of the traffic load will provide safer roads but will also lower the carbon emissions caused by longer traveling times.

Runway safety-related accidents represent the most significant source of aviation accidents worldwide. Runway contaminants are typically associated with extreme weather conditions but can also include other safety-issues such as foreign object debris, cracks, and pavement deformation. Although airports are required to perform periodic runway inspections, it is clear that manual inspections alone are not sufficient to mitigate this type of threat. The paper outlines the need to implement automated procedures for runway inspections, seeking to improve runway safety.

The paper presents a project with an innovative approach for automated runway inspections using laser scanning equipment. The compliance with airport regulation, standards, and business logic has driven the architectural solution, co-designed with end-users to increase understandability, and to create a product that provides the best possible user experience, addressing relevant concerns and information needs. The project solution provides a set of data analysis services addressing the Analytics-as-a-Service (AaaS) paradigm, where the concepts of information visualization and context-awareness are essential in supporting the surveillance of the runway status, in particular, for events which may lead to aquaplaning phenomena. Monitoring such water-events enables the detection of drainage problems as well as the identification of areas that might compromise runway safety.