Efforts to reduce greenhouse gas emissions from the land transport sector revolve around replacing the Internal Combustion Engine with alternative power units. Indeed, governments within the European Union and beyond move to ban the sale of new internal combustion engine vehicles in the near future. A number of technologies are proposed as alternatives, such as electric motors powered by batteries or hydrogen fuel cells, and hybrid power units. These new technologies rely on new infrastructure (charging stations, electrical grid upgrades, hydrogen production, storage and fueling facilities), which will need to be put in place to meet the needs of a transforming vehicle fleet. As such, forecasting the demand for the different technologies will be crucial in planning investments. We use machine learning techniques, specifically a Multilayer Perceptron and an Adaptive Neural Fuzzy Inference System, to forecast the demand split from public perceptions as captured through an online survey.

Driver distraction is a growing problem, as it seems to be an important cause for several road accidents. This study was conducted with the aim to look into the contributory factors that may cause a driver’s distraction, some of which are the use of mobile devices, fatigue of the driver, consumption of food and beverages and smoking while driving. In this paper, we report on the findings of an online questionnaire survey in which 1214 Greek drivers willingly participated in a study that aspired to unveil drivers’ perspective on their own driving habits. The data collection tool was a questionnaire consisted of 27 questions and divided into seven parts. The first questions referred to participants’ profile such as gender, age, educational level and years of holding a driving license. The next questions focused on participants’ mobile phone use in their everyday activities and mobile phones use while driving, and on participants’ consumption of food, beverages and smoking during driving. Further questions examined driver’s fatigue and its frequency, the impact of driving with passengers in the vehicle and the extent to which the interaction with them affects a driver’s attention. Finally, participants were asked to grade their personal and other drivers driving skills and behavior. This survey can contribute to the improvement of road safety, as the findings help us quantify the negative effects of drivers’ habits that contribute to distracted driving and supports that the drivers should be better trained and authorities should pay more attention in this situation.

The feasibility of Pavement KPI approximation from crowdsourced data is examined. A dedicated smartphone application for the collection of positioning and accelerometer data as well as regular manual driver inputs is used. Smartphone application data is correlated with KPIs determined using pavement defect and International Roughness Index data collected with a Laser Crack Measuring System. Statistical and machine learning models are developed for the approximation of KPIs from smartphone data, and then the resulting models are used to predict pavement KPIs beyond the training dataset. The performance of alternative models is examined and the cost savings of such an approach in the deployment and running of a Pavement Asset Management System.

The utilization of conclusions from the data analysis of road traffic accidents is of high importance for the development of targeted traffic safety measures, which will effectively reduce the rate of road traffic accidents, thus promoting road safety. Considering the problems of time and money, it is not practical to improve road safety in all the places where road traffic accidents occur. Therefore, the process of identifying accident-prone locations, known as black spots, is a cost-effective and efficient way to analyze the causes of road accidents and reduce them. Identifying black spots is an effective strategy to reduce accidents. The core methods that may be used in the process of identifying the black spots of a road network are the sorting, grouping, and accident prediction methods. However, in practice, it is easy to overlook certain factors that significantly contribute to defining and characterizing a spot on the road network as black. Therefore, suggestions to carry out projects required to reduce security risks shall not be based on the above methods. Machine learning algorithms that in recent years have been widely used in the field of predicting a road traffic accident cover these weaknesses. They can effectively classify data sets and make a connection between factors and the severity of events. Machine learning algorithms include classification, regression, clustering, and dimensionality reduction. In this work, a study was conducted on road traffic accidents that took place on the national and provincial network of Northern Greece from 2014 to 2018, with the aim of determining the black spots. The study provided the general public access to a database of black spots on the road network of Northern Greece. At the same time, it created a point of reference for the recognition of the points in question located on the entire road network, and selected a black spot determination model, after having compared specific measures to determine the quality of a model, which resulted from the application of a logistic regression and machine learning algorithms.

Black spot identification, a spatiotemporal phenomenon, involves analysing the geographical location and time-based occurrence of road accidents. Typically, this analysis examines specific locations on road networks during set time periods to pinpoint areas with a higher concentration of accidents, known as black spots. By evaluating these problem areas, researchers can uncover the underlying causes and reasons for increased collision rates, such as road design, traffic volume, driver behaviour, weather, and infrastructure. However, challenges in identifying black spots include limited data availability, data quality, and assessing contributing factors. Additionally, evolving road design, infrastructure, and vehicle safety technology can affect black spot analysis and determination. This study focused on traffic accidents in Greek road networks to recognize black spots, utilizing data from police and government-issued car crash reports. The study produced a publicly available dataset called Black Spots of North Greece (BSNG) and a highly accurate identification method.

Within the last decades, the examination and definition of factors affecting the mode choice decision on school trips has gained much of attention, as the completion of such trips represent a vast percentage of total travel demand. Key players of the decision process are students' parents, deciding how their children will complete everyday trips from their residence to the school unit and vice versa. The current study examines the factors affecting parents' travel mode choice for school trips of both primary and high school students in Thessaloniki city, Greece. Data collected is based on a questionnaire survey in which, 512 parents participated, stating their perception regarding the use of several transport modes for school trips and the motives behind specific adopted travel behavioural aspects. Three main topics are examined and analysed related to the parents' attitudes and their travel habits in the choice of motorized and non-motorized transport modes, the parents' perception regarding the built environment safety, and the parents' perception regarding specific parameters which appear to motivate them in the mode choice decision process. For the research analysis, a number of statistical methods and techniques are deployed, starting with descriptive statistical and Pearson's correlation analysis and proceeding with the exploratory and confirmatory factor analysis. The results verify initial thoughts for critical factors which appear to affect parents' choices regarding their children’s school trips while they also gives an initial picture of parents' experiences regarding the school travel mode choice, in an urban environment of a typical Greek city.

Railway management deals with the most efficient organization of all components of the railway system, so as to achieve the best result, that is, the higher level of traffic and revenues with the lowest possible costs. As railways are a heavy and rigid industry, railway management should begin from a good understanding of the internal and external environment of railways, the conditions of the market and a reorientation from engineering to customer satisfaction. A critical decision is whether to keep railway unified or separate it to infrastructure and operation and decide the level of charges that operators must pay for the use of infrastructure. Understanding and control of costs, increase of yields and revenues, optimal allocation of resources, and higher rates of productivity are principal tasks for an efficient management, which should monitor continuously passengers’ exigencies through market surveys. Railway management can be based on some form of business or master plan and for big projects can employ the services of project management. A dilemma toward optimization of finances is whether to aim at increase of traffic or profit, while providing advantages to frequent travelers or to targeted segments of the market. Another condition of success is incorporation of rail freight within the logistics chain.

Travelling to and from school forms mobility habits and travel behavior aspects of students from a very young age, also adopted in later life. Parents are the key players of the whole mode choice process as in most cases they are the ones to decide how and by which transport mode their children will complete their everyday school trips. Understanding parents’ perceptions on different travel modes and studying the motives behind the mode choice decision in school trips, is a rather essential issue as it may provide useful information to policy-makers, transport and spatial planners on how to overcome possible barriers and difficulties in order to satisfactory cover all students’ future mobility needs. The paper provides an extensive literature review regarding a wide range of factors found to influence students’ travel, following a statistical exploratory factor analysis of a questionnaire survey took place in Thessaloniki, Greece. The initial analysis of the sample identifies key themes while it also develops a comprehensive picture of caregivers’ experiences about travel mode choice to school in a typical Greek urban environment. Some interesting findings verify that socio-economic and household demographic factors, built-environment variables, and parents’ attitudes regarding their daily trips and mobility habits, are important factors affecting the school mode choice procedure.

The paper introduces the features of a custom-developed software application on transportation forecasting. The proposed methodology was based on a hybrid approach that combines singular spectrum analysis (SSA) and artificial neural networks (ANN). The main research objective of the paper is to highlight the advantages while inhibiting the limitations of both hybrid component methodologies (SSA and ANN) and to deliver realistic testimony for the effectiveness of the proposed hybrid forecasting methodology. The methodology is designed and implemented upon a ready-to-use decision support software application toolbox. All necessary modules and components, such as software graphical user interface (GUI), functions that calculate several statistical measures, forecasting algorithms (ANN, SSA, and hybrid ANN-SSA), and graphical and arithmetical outputs, were designed and developed by the authors.

In this chapter, the successive steps for constructing a model of transport demand and the various methods of modeling are classified and succinctly presented. The structure and characteristics of a model are first identified. The various variables of a model are categorized (dependent–independent, deterministic–probabilistic, endogenous–exogenous, linguistic, etc.). Utility theories, which permit us to understand and forecast choices of travelers, are investigated and their specialization for transport, the generalized cost, is explored. The fundamental classification into quantitative and qualitative methods, advantages and disadvantages of each one, model selection, calibration, estimation, and validation are scrupulously detailed. A first presentation of qualitative methods (executive judgment, Delphi, scenario writing, and questionnaire survey methods) is given. The distinction of quantitative methods into causal and noncausal ones is clarified. A preliminary presentation of quantitative methods (time series, econometric, gravity) is conducted. Regression analysis, a basic statistical tool for all quantitative methods, is explained. More recent methods, such as the artificial neural network method and the fuzzy method, which can be also considered as efficient tools to construct transport demand models, are surveyed. The various criteria for the selection of the appropriate transport model are investigated: time range, nature and scope of the problem, availability, reliance and credibility of statistical data, identification of turning points, time and cost, skills and expertise required. The chapter ends with analysis of big data (characteristics, sources, technological aspects, compatibility with the existing legislation) and how they can be used for transport problems.

The paper presents a comparison of a hybrid methodology which combines Singular Spectrum Analysis (SSA) with Artificial Neural Networks (ANN) against conventional ANN, applied on time series analysis and forecasting of road traffic volume. The main research objective was to develop a short-term forecast of daily traffic volume at toll stations across the Greek National Highway Network. The proposed methodology was implemented and evaluated upon a custom developed integrated forecasting software, based on the Mathworks MatLab platform. Experimental outcomes on daily data, from specific toll stations, demonstrate a superior prediction accuracy of hybrid SSA–ANN forecasting methodology against conventional ANN, when compared to performances of statistical criteria such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and Coefficient of Determination (R2). A comparison of results revealed that the SSA–ANN hybrid model could improve the forecasting accuracy of the conventional ANN model in the case of daily traffic volume forecasting. An Intelligent Transport System with embedded hybrid SSA–ANN forecasting algorithm could manage and analyze big data traffic volume time series in real time, providing an advanced decision support system for transportation system management and maintenance, while it would enable proactive decisions to mitigate the economic and environmental impacts of traffic congestion.

This chapter deals with applications of artificial intelligence and more particularly of artificial neural network (ANN) methods for transport demand. First, the structure of a biological and of an artificial neuron, the fundamental functions of an ANN, analogies between artificial and biological neurons, and the activation function of an ANN are explained. The various types of ANN, algorithms, and software are presented afterward. The structure of an ANN (input layer, output layer, hidden layer), the propagation rule (feedforward, backpropagation, recurrent), the method of supervision of learning (supervised learning, reinforced learning, nonsupervised learning), and the learning rule (error correction, Hebbian, Boltzman, Perceptron) are extensively analyzed. Similarities and differences of ANN and statistical and econometric methods are surveyed: assumptions, mechanism and processes, nonlinearities, collinearities, fluctuations of data. A step-by-step analytical example of an application of ANN for the long-term forecast of air transport demand is scrupulously studied and explained: architecture of the ANN model, single and multiple inputs, data and software, propagation rule (feedforward, recurrent), number of iterations, errors. Another application of ANN for the analysis of rail demand is explained in detail. Applications of ANN for the analysis of other sectors of transport are also discussed: road traffic, road safety, driver behavior, self-driven vehicles, freight transport, maintenance needs, performance and quality of service, effects of unpredicted events, and transport economics.

The present paper provides a comparative evaluation of hybrid Singular Spectrum Analysis (SSA) and Artificial Neural Networks (ANN) against conventional ANN, applied on real time intraday traffic volume forecasting. The main research objective was to assess the applicability and functionality of intraday traffic volume forecasting, based on toll station measurements. The proposed methodology was implemented and evaluated upon a custom developed forecasting software toolbox, based on the software Mathworks MatLab, by using real data from Iasmos-Greece toll station. Experimental results demonstrated a superior ex post forecasting accuracy of the proposed hybrid forecasting methodology against conventional ANN, when compared to performance of usual statistical criteria (Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, Coefficient of Determination R2, Theil's inequality coefficient). The obtained results revealed that the hybrid model could advance forecasting accuracy of a conventional ANN model in intraday traffic volume forecasting, while embedding hybrid forecasting algorithm in an Intelligent Transport System could provide an advanced decision support module for transportation system maintenance, operation and management.

This chapter deals with factors affecting transport demand. First, the impact of transport on the various aspects of human life is assessed. The basic definitions and metrics of transport demand, along with an account of their historical evolution, are provided. This chapter explains how transport demand influences all components and activities of the transport system: planning, design, construction, maintenance, operation, level of saturation, fleet, personnel, commercial and tariff policy, revenues. The overwhelming and revolutionary effects of new technologies on transport demand are explored. The principal drivers (income and purchasing power, technological evolutions, travel costs, social attitudes and lifestyle, population, urban development, international trade, industrial evolutions) for both passenger and freight transport are identified and analyzed, and their evolution over time is examined. The correlation between transport demand and economic activity is studied extensively. This chapter also provides a survey of whether there exists some form of coupling (similar rates of growth of transport and gross domestic product [GDP]) or decoupling (a break in the link between transport and GDP). Indexes that testify as to the existence (or not) of coupling or decoupling and factors affecting the degree of decoupling are presented. Other factors of the internal and external environment of a transport activity (such as human resources, energy, environmental effects, institutional framework, globalization, and competition) are investigated. The various forms of elasticities are described.

This chapter deals with statistical methods, and more particularly with simple and multiple regression analysis, which are the basic tool when correlating transport demand to factors (such as time, cost, etc.) affecting it. After an overview of fundamentals of statistics such as terms, measures, hypothesis testing, probability distribution, and stationarity, the mathematical expression of the simple and multiple linear regression and the estimation of the various regression coefficients and the error term with the use of the ordinary least squares method are presented. Pearson correlation coefficient, coefficient of determination, and adjusted coefficient of determination as measures for the degree of correlation between one dependent and one or more independent variable(s) are analyzed. Tests of the significance of the coefficients of a regression analysis (Student's t-test and F-test) are presented afterward. Multicollinearity (correlation between independent variables), its detection, and techniques of removal are identified. The various characteristics and properties of residuals of a linear regression are surveyed with the help of the appropriate tests: probability distribution (skewness and kurtosis, Jarque–Bera test), influence of residuals and determination of outliers (Cook's distance), existence or not of serial correlation in the residuals (Durbin–Watson test, Durbin's h-test, Breusch–Godfrey Lagrange Multiplier test, Ljung–Box test). The various tests for the detection of heteroscedasticity in a regression analysis are analyzed: Breusch–Pagan test, Glesjer test, Harvey–Godfrey test, White test, autoregressive conditional heteroscedasticity test. Next, the various criteria for the evaluation of the forecasting accuracy of calibrated models are categorized, among them the Theil's inequality coefficient. All the above analysis, methods, tests, and criteria are extensively put into practice in a specific example of multiple linear regression analysis for the construction of an econometric model for transport demand.

This chapter deals with econometric, gravity, and the 4-step methods. The successive steps, assumptions, and the necessary conditions for the construction of an econometric model are first described. The selection of the independent variables of an econometric model, of the necessary statistical data, and of its functional form is discussed. The following statistical tests which testify the validity, accuracy, and forecasting ability of an econometric model are presented: stationarity test, Pearson correlation coefficient, calculation of coefficients of the econometric equation, coefficient of determination, tests for the significance of the independent variables, multicollinearity, residuals and outliers, serial correlation, and heteroscedasticity. The distinction between causality and correlation in an econometric model is made. Next, appropriate econometric equations, which permit a causal forecast of future transport demand in relation to the independent variables (some of the driving forces) of the problem, are given for air, rail, road, and public transport (both for passenger and freight) as well as for road safety and taxi services. For each econometric equation, the statistical tests that testify its validity are provided. The 4-step model for the forecast of transport demand at urban level is extensively analyzed afterward. Principles, assumptions, successive steps, and the theoretical basis (on utility theories) of the 4-step model are clarified. Models of trip generation (the first step of the 4-step model) are analyzed (growth factor models, cross-classification models, regression models) with analytical detailed examples. Models of trip distribution (the second step of the 4-step model) are presented (constrained growth factor models, gravity models) with analytical detailed examples. Models for the choice of transport mode (the third step of the 4-step model) are given and more particularly the Logit and Probit models with specific case-study applications. Trip assignment models (the fourth step of the 4-step model) and Wardrop principles are studied; more particularly the all-or-nothing model, the user equilibrium model, and the system optimum model are presented, with specific examples and applications. Finally, the appropriate modeling of freight transport demand (trend projection, application of the 4-step model, econometric and gravity models) is analyzed.

This chapter deals with applications of fuzzy methods, which give the ability to study quantitatively problems characterized by ambiguity, imprecision, uncertainty, linguistic variables, and missing or few or no data. The fuzzy method introduces another way of thinking: a statement, instead of being true or false, may be partially true or false. Thus, instead of taking into account the typically used fixed numerical values (such as, e.g., 2.34), the fuzzy method employs a set of plausible values (e.g., around the value 2.34) within a specific domain. Although this approach may look similar to the error of statistical methods, the fuzzy method can tackle situations (such as missing or vague data), for which classic methods are inefficient. The principles of fuzzy numbers, fuzzy sets, and fuzzy logic are presented. The case of symmetric triangular fuzzy numbers is analyzed in detail. Next, linear regression analysis with the use of fuzzy numbers is explained. A detailed application of fuzzy linear regression for a transport demand problem is surveyed analytically. The chapter includes many applications of fuzzy linear regression for the forecast of a variety of transport demand problems: air transport, rail transport, road transport, transport at urban level, and transport economics. Applications of the fuzzy method to other transport problems are explained: route choice, road safety, accident analysis, logistics and routing of freight vehicles, and the optimization of capacity of airports.

This chapter deals with the employment of qualitative methods for the forecast of transport demand. First, the executive judgment method is presented, more specifically the assumptions, characteristics, scientific background, and applications for transport demand problems. Next comes the Delphi method, which examines a transport problem by exploiting, analyzing, and synthesizing the anonymous judgments of a group of experts in successive rounds (from two up to five), during which the experts are informed about other experts' views and can change and improve their previous statement. Simple statistical methods, such as the degree of consensus and Kendall's coefficient of concordance, are analyzed and permit the evaluation of the validity of the Delphi method. Several cases of application of the Delphi method for transport problems are presented. Assessment of future demand can also be achieved with the construction of alternative scenarios, which describe plausible or desired situations as well as processes that can lead to future levels of transport demand. Various types of scenarios (projective, perspective, etc.) are explored, and statistical methods to check inconsistencies within the parameters of each scenario are attempted. Applications of the method for assessing the effects of factors of the internal and external environment on mobility and transport demand are presented. Survey methods based on a questionnaire are used to accurately monitor and detect present and plausible future characteristics, attitudes, and trends of demand. The various methods of sampling (random, stratified, cluster) are studied. The relationship between the sample explored and the population surveyed, the margin of error, the confidence level, and the required number of questionnaires are identified and quantified. The appropriate design of a questionnaire is suggested. The use of many types of scales to quantify respondents' answers is investigated. Stated preference and revealed preference methods are analyzed, and the theoretical background, characteristics, and areas of application of each one are conceptualized. Characteristics and representative types of questionnaires are given for each sector of transport: airports, airlines, railways, sustainable urban mobility, and sea transport.

This chapter deals with the evolution and trends of demand for the various sectors of transport. First, emphasis is placed on the impact of accurate, consistent, and valid data describing as objectively as possible the transport demand of the past. The methods of collection, their characteristics, and sources of data are described both for conventional techniques and for big data sources provided by the Internet, mobile telephones, and global positioning system. Second, the evolution and trends of modal split of each transport mode for both passenger and freight traffic are surveyed over the recent decades. Third, the evolution and trends of passenger and freight air transport demand are analyzed: the factors affecting it, rates of growth, low margins of profit, cyclic fluctuations, number of passengers and tonnes carried by air, number of flight departures, demand in airports, and the rise of demand of low-cost airlines. Next comes the analysis for rail transport: the number of passengers and tonnes carried by rail, the rise and decline of railways, demand for high-speed trains, and the evolution of the global railway technologies market. Following this, there is an overview of road transport: the private car ownership index, road traffic and its fluctuations, the production of new cars, the electric car, road safety, and the number of fatalities. Similar analysis is presented for metro and tram systems. Prospects for the technology of electric cars are examined. The chapter ends with analysis of the evolution of sea transport: traffic, number of tonnes of the various products transported by sea, container traffic, and the world fleet.