Volume 23 (2022): Issue 4 (November 2022)

The usage of mobile phones is nowadays reaching full penetration rate in most countries. Smartphones are a valuable source for urban planners to understand and investigate passengers’ behavior and recognize travel patterns more precisely. Different investigations tried to automatically extract transit mode from sensors embedded in the phones such as GPS, accelerometer, and gyroscope. This allows to reduce the resources used in travel diary surveys, which are time-consuming and costly. However, figuring out which mode of transportation individuals use is still challenging. The main limitations include GPS, and mobile sensor data collection, and data labeling errors. First, this paper aims at solving a transport mode classification problem including (still, walking, car, bus, and metro) and then as a first investigation, presents a new algorithm to compute waiting time and access time to public transport stops based on a random forest model. Several public transport trips with different users were saved in Rome to test our access trip phase recognition algorithm. We also used Convolutional Neural Network as a deep learning algorithm to automatically extract features from one sensor (linear accelerometer), obtaining a model that performs well in predicting five modes of transport with the highest accuracy of 0.81%.

Highway users can apprehension to certain subjects with utilizing of Vehicular Ad-hoc Networks (VANET) applications if the rules for safe overtaking movement are violated to make the lane change maneuver between vehicles on the highway road. In our research, we suggest an algorithm for semi-automated vehicles S-AV compliant lane change to emphasize rules for safe overtaking between vehicles on the highway. The proposed algorithm technique classify the safe overtaking into major categories and critically analyzed them depending on various classes of lane change movements between vehicles interrelated to road condition based on different performance criteria; this technique will add awareness to drivers traveling on highway to increasing the comfort and safety of driving. Finally, we have conclude and suggest research issues associated to Vehicular Ad-hoc Networks to investigate and ensure the real-time decision of safe overtaking between vehicles on the highway, which is important research task to motivate researchers to connect the semi-automated vehicles with driver face emotion detection and increase driving safety.

Predicting the most favorable traveling routes for Vehicles plays an influential role in Intelligent Transportation Systems (ITS). Shortest Traveling Routes with high congestion grievously affect the driving comfort level of VANET users in populated cities. As a result, increase in journey time and traveling cost. Predicting the most favorable traveling routes with less congestion is imperative to minimize the driving inconveniences. A major downside of existing traveling route prediction models is to continuously learn the real-time road congestion data with static benchmarking datasets. However, learning the new information with already learned data is a cumbersome task. The main idea of this paper is to utilize incremental learning on the Hybrid Learning-based traffic Congestion and Timing Prediction (HL-CTP) to select realistic, congestion-free, and shortest traveling routes for the vehicles. The proposed HL-CTP model is decomposed into three steps: dataset construction, incremental and hybrid prediction model, and route selection. Firstly, the HL-CTP constructs a novel Traffic and Timing Dataset (TTD) using historical traffic congestion information. The incremental learning method updates the novel real-time data continuously with the TDD during prediction to optimize the performance efficiency of the hybrid prediction model closer to real-time. Secondly, the hybrid prediction model with various deep learning models performs better by taking the route prediction decision based on the best sub-predictor results. Finally, the HL-CTP selects the most favorable vehicle routes selected using traffic congestion, timing, and uncertain environmental information and enhances the comfort level of VANET users. In the simulation, the proposed HL-CTP demonstrates superior performance in terms of Mean Square Error (MSE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE).

The aim of this article is to assess the carbon dioxide (CO₂) emissions of three types of cars: two internal combustion cars and one Fuel Cell Electric Vehicle (FCEV), measured on the basis of type approval regulations.

The article also assesses the CO₂ emission costs resulting from the production of fuel and the production of the car.

It was assumed as a research hypothesis that the development and growing serial production of vehicles with different power systems will bring measurable changes in CO₂ emissions from road transport. Based on their own research, the authors also analyzed the credibility of the assumptions made about the benefits related to emissions resulting from replacing the classic vehicle with hydrogen one. They estimated the duration and intensity of use of a hydrogen vehicle that offers CO₂ benefits compared to a conventional vehicle.

Conducting a safe briefing is essential to educate aircraft maintenance personnel, who very often encounter various unexpected and dangerous incidents. Their reaction to situations should be quick and adequate. To train aircraft maintenance professionals who cannot be practiced in real life due to high cost, danger, time or effort, virtual training seems like an obvious choice. This paper is devoted to the development of a calculation algorithm for assessing the risk of actions taken at the aircraft repair site, which was implemented in the training version of the virtual reality (VR) simulation. It includes a number of factors and elements that form the simulation scenario, influencing the degree of its complexity and the assessment of the performance of each exercise. Various components of the algorithm are presented, which allow assessing the skills of students of aviation specialist courses. The criterion for the acceptability of the developed algorithm is the correct assessment of the student’s skills in the course of training.

Many shipping companies tackle the challenge of potentially replacing conventional trucks with electric ones in economically developed countries. The aim of this work is to describe the principle of scaling models for analysing the operation of a fleet of vehicles, when the decision to use a particular type of model is made considering the accuracy and completeness of the initial data, as well as the goals of modelling. At the end of the report, information is provided on the TraPodSim simulation system developed by the authors, which is based on a multi-agent simulation model created using AnyLogic software.

The paper considers modelling methods aimed at assessing the physical indicators of the transportation process. Various aspects of using three types of mathematical models are discussed: a) analytical deterministic models, b) analytical models using the Monte Carlo method and c) simulation models.

The article was prepared using research output received implementing the ePIcenter project funded by the European Union program HORIZON 2020. A brief description of the project is presented. The paper presents theoretical research regarding essential data requirements that may be important for improving logistics processes. After identifying the main data requirements, scientific research is presented. Analysis of valid legal acts to determine the regulatory criteria and aspects of the relevance and availability of data is performed. Essential areas of data exchange, their importance and trends are identified, taking into account business and governmental organisations. Trends and possible development perspectives are presented.

The paper is based on the research project ePIcenter (www.ePIcenterproject.eu) supported by the EU HORIZON 2020 Programme. ePIcenter connects thirty-six partners: port authorities, logistic service providers, manufacturers, academic institutions, and technology partners. The main goal is to develop and test AI driven logistic software solutions, apply new technologies and methodologies to increase the efficiency of global supply chains and reduce their environmental impact. One of the significant aspect the project focusses on is optimisation, using AI, digitalisation, automation and innovations in freight transport and handling technologies. Finally, modelling powerful solutions to enable resilient, efficient and environment friendly supply chains.

Knowledge sharing is one of powerful tool for researchers, policymakers, service providers and other stakeholders to develop a holistic and comprehensive common knowledge base. First, a theoretical framework had been developed through identification and review knowledge available from previous projects funded through the European Commission as well as other international funding projects. Second, lessons learned and success stories from previous EC-funded projects and other international research programmes were reviewed and provided in the first year of project implementation.