The potential of regression factor analysis to predict highway traffic in conditions of high tourism seasonality

Climate change mitigation in the tourism sector is expanding research areas due to the importance of this sector and its rapid expansion. Aviation's contribution was found to be the most important source of GHG emissions from tourism. Also, the hospitality sector contributes a lot to GHG emissions in tourism destinations. Hospitality, constituting an essential component of the tourism industry, is a sector that has a high potential to reduce GHG and use of energy and water resources. Therefore, it is important to monitor the climate change mitigation performance of tourism destinations to achieve decarbonization of the tourism sector. The main objectives of this paper are to develop indicators of climate change mitigation performance of tourism destinations based on GHG indicators for the transport and hospitality sectors and apply this framework to assessment and ranking based on climate change mitigation performance of 4 main EU geographical regions as tourism destinations: Central, Northern, Southern, and Western Europe. This paper's main methodological approach is comparing and ranking different geographical regions in the European Union by assessing their climate change mitigation performance as tourist destinations. The study's main results showed that Finland, representing North Europe, is the best-performing country in climate change mitigation in tourism destinations. The second-best-performing geographical region is Western Europe. The worst-performing EU region based on climate change mitigation in tourism destinations was Central Europe. The South Europe region was found to be in a slightly better position than Central Europe but worse in comparison with Western Europe and especially in comparison to Northern Europe. The study's main implications provide policy recommendations for Central Europe as a tourism destination to increase energy and water use efficiency and the carbon footprint of the tourism sector.

Autonomous Vehicles (AVs) and Connected Autonomous Vehicles (CAVs) are being widely tested and rapidly developed over the past few years. With the development and increasing number of AVs and CAVs in mixed traffic flow, it is necessary to analyze their impact on traffic safety, flow, speed, fuel consumption, and emissions. Also, appropriate traffic control algorithms need to be developed before they can be fully implemented and integrated into the traffic environment. To do so, such mixed traffic flows must be simulated in various traffic scenarios. Traffic flow simulators paired with communication network simulators are commonly used to perform multiple simulations of such traffic flows. In this paper, three often used traffic simulators VISSIM, AIMSUN, and SUMO paired with network simulators NS-3 and OMNET++ with their features to model AVs and CAVs in a simulation environment are analyzed. According to currently available and tested simulators in the research community, the most used ones were compared. Results of the synthesized technical aspects of each suggest that AIMSUN Next is more suitable for a less complex traffic model. At the same time, VISSIM is more suitable for a more complex traffic model.

Abstract: This study evaluated the impact of on-street parking on traffic speed under mixed traffic conditions in Nekemte City, Ethiopia. Data on the traffic volume, speed, and parking parameters were collected at selected mid-block locations during peak hours. The results showed that the speed of vehicles, particularly heavy vehicles and trucks, decreased significantly with increased traffic volume compared with other categories. The vehicular speed noticeably diminished as parking levels increased. A multiple linear regression model was developed using the SPSS software to analyze the percentage reduction in speed. The model indicated that for a given road width at a location with on-street parking, as parking turnover, duration, accumulation, or traffic volume increased, the percentage reduction in speed also increased. Conversely, as the road width increased, the percentage reduction in speed decreased, and vice versa, whereas the other parameters remained constant. The study concluded that the volume-speed relationship capacity of each road in the parking area and away from it could be determined, and models for percentage speed reduction could be developed using road width, parking parameters, and traffic composition. This study provides recommendations for maintaining a maximum speed reduction of 40% at selected locations for street parking based on the road width, traffic volume, parking turnover, duration, and accumulation.

PurposeThis paper aims to assess how a hotel geographical location in different parts of Central and Eastern Europe influences the complexity of perception of pro-environmental behavior.Design/methodology/approachTo find out, whether hotel location in a specific country influences the complexity of environmental practices, this study used two closely connected multivariate statistical techniques analyzing gradients: principal components analysis and partial redundancy analysis. The research comprises data collection from seven countries in Central and Eastern Europe. In all, 25 randomly selected hotels (based on star rating) from various countries were approached to complete a questionnaire. Environmental practices were studied based on motivations, perception of barriers, perception of support from different levels of public sector, will of managers to promote pro-environmental measures based on sufficient funding, perception of legislation and perception of various other important factors.FindingsThe study reveals significant differences between hotels in Central Europe and Eastern Europe in the perception of the complexity in implementation of the environmental practices by hotel managers. The character of the present study, however, needs to address the identification of particular aspects that are relevant to the geographical differences among the studied countries.Research limitations/implicationsResearch was limited to a selection of Central and Eastern European (CEE) countries. There is still probability that managers in hotels from Poland and Croatia could possess different preferences. Other limitation of this study is that only special part of hotels were asked – hotels certified by star grading, out of our scope remained other hotels. It is also known that important factor is precise location of hotel within country – hotels in established tourism destination behave other way that those outside recreational areas. These factors deserve further study within this topic. There are many aspects of sustainability and environmental protection regarding hotel industry. As we have found in our principal correspondence analysis, different environmental measures were different location in biplot – some were affected by country, the other by star grading and affiliation to hotel chain. The complexity deserves to be studied in depth.Practical implicationsThe importance lies first in the identification of the aspects that are governed by geographical differences among the countries studied. These aspects are the initiatives and support from the government and the local governments, which counteract the perception that there is a lack of financial resources and the return on investments is slow. So, based on the data, which included information from various types of hotels from seven CEE countries, the activities of national and local authorities were identified to be the main differentiating variable. The support of the environment-friendly conduct of business in the hotel industry is appreciated by hotel managers from Central Europe. On the other hand, hotel managers from Eastern Europe do not feel any significant support from either national or other public institutions. The second factor of differentiation is represented by the perception of the lack of funds. Hotel managers from Eastern Europe feel strongly about funds limitation. The coherence of both those factors is obvious in the results, as they show the same direction but opposite orientation. It has already been discussed above. When looking at the results, the authors find the perception of availability of funds to be a fundamental difference between hotel management in Central Europe and in Eastern Europe. The lack of funds is perceived more intensively in Eastern Europe than in Central Europe, particularly because of a stronger awareness of direct or indirect support for such activities by national and other public institutions in Central Europe.Social implicationsThe differentiation of the aspects mentioned above comes from the social and culture policies, company policies and business cultures between these two sub-realms. Pro-environmental actions are apparently promoted less publicly in Eastern European countries than in Central European countries. The reaction to the trend for demand of greener hotels is stronger in the West, and its hotels are more likely to have legislation requirements and public support as an incentive to adopt pro-environmental measures in their business operations.Originality/valueThe study is based on data obtained from seven countries. The results revealed a problem of the macro-environmental influence on hotels’ potential to implement environmentally sustainable approaches and procedures throughout the industry.

In recent year, the rise of economic growth and technology advance leads to improve the quality of service of traditional transport system. Intelligent Transportation System (ITS) has become more and more popular. At present, the collection of real-time traffic information is executed in two ways: (1) Stationary Vehicle Detectors (VD) and (2) Global Position System (GPS)-based probe cars reporting. However, VD devices need a large sum of money to build and maintain. Therefore, we propose the linear regression model to infer the equation between vehicle speed and traffic flow. The traffic flow can be estimated from the speed which is obtained from GPS-based probe cars. In experiments, the Speed Error Ratio (SER) and Flow Error Ratio (FER) of linear regression model are 4.60% and 24.63% respectively. The estimated speed and traffic flow by using linear regression model is better than by using linear model, power law model, exponential model, and normal distribution model. Therefore, the linear regression model can be used to estimate traffic information for ITS.

The paper presents a model for predicting short term traffic flow using structure pattern and regression. The relationship between traffic flow on the current section and upstream stations are used for predicting the short-term traffic flow and is exposed by the traffic flow structure pattern. The structure pattern of the traffic flow can be pinched from freeway toll data based on which, a new prediction model has been proposed. Locally weighted learning is used to predict the next instance’s traffic flow of current section by considering the traffic flow of current section and the next station entrance flow. This learning model deploys both linear and non-linear models to fit the nearby points and then applies those values to forecast the values of the query points. Experimental results illustrates that the short term prediction method based on structure pattern and regression is an effective approach for traffic flow prediction, this is applicable especially during the abnormal traffic states. The proposed system outperforms the conventional systems in terms of accuracy and proves to facilitate in conserving energy. The proposed work benefits the travelers by rerouting and saves fuel consumption.

Dynamic traffic flow prediction is one of the important topics in traffic engineering and intelligent transportation systems. The traffic flow has stochastic nature and nonlinear dynamics which make accurate prediction of traffic flow a challenging process. In most existing methods, the nonlinear and stochastic qualities of traffic flow have not been taken into consideration simultaneously and these methods do not possess satisfactory accuracy either. In this paper, in order to reduce the prediction error based on traffic flow characteristics, we applied two different methods. At first, we applied a locally linear neuro-fuzzy method using local linear model tree learning algorithm for nonlinear identification of traffic flow. Then, to eliminate the noisy components and also to increase the prediction accuracy, we proposed a method, which is the combination of singular spectrum analysis (SSA) and locally linear neuro-fuzzy model (LLNF). In this method, firstly, the principal components of the traffic flow time series were extracted, several noisy and unimportant components were thrown out and then every remained important component was modeled by using a LLNF network, the trained networks were utilized for one-step-ahead prediction, and finally the predicted patterns were combined to construct the general prediction. Moreover, we compared the results of these two methods with each other and also with those of several other intelligent methods such as multi-layer perceptron, radial-basis function, network and adaptive network fuzzy inference system. The simulation results revealed that the proposed SSA + LLNF approach for traffic flow prediction had promising and superior performance.

Traffic speed has been traditionally used as a measure of traffic performance. Predicting the traffic speed is fundamental for efficient traffic management and control strategy. This study explores the influences of freeway attributes, weather, and air condition on traffic speed. A quantitative model is also introduced to predict the traffic speed as per the identified influencing factors. Empirical data of traffic flow and potential influencing factors are collected from multiple sources for analysis and model calibration. The principal component analysis is firstly conducted to select the significant variables influencing the traffic speed. Afterward, a multiple linear regression model is calibrated to quantitatively model the impacts of different factors and investigate their weights. The results show that the attributes of freeway, the humidity of the area, the temperature, the horizontal visibility, the station maker, the air quality, and the PM quality have influences on the traffic speed. Among all of the variables, the weight of the existence of toll station is highest, indicating the largest influence on the traffic speed.

Traffic flow is a worldwide problem. It has many influencing factors and it is the complex system. Fractional calculus is a powerful tool for dealing with complex systems. Fractional calculus is a direct way of extending traditional integer order calculus, which allows the order to be a fraction. Fractional order model achieves better results than the integer order model. A linear fractional order model based on Grunwald–Letnikov’s definition for traffic flow is proposed in this paper. City road traffic flow system is composed of a large number of complex dynamic behaviors of traffic participant. It is a highly nonlinear and non-stationary complex system. Firstly, fractional order calculus is introduced. Then the linear fractional order traffic flow model is proposed based on fractional calculus. The fractional order parameters can be determined by a large number of data and mathematical statistics method. The proposed model was simulated and applied to actual Linghai town road traffic flow. The practicability and effectiveness of the method have been validated.

Traffic flow management (TFM) decision support relies heavily on forecasting of future air traffic demand. Flow managers need to anticipate situations and intervene where appropriate in a proactive rather than reactive mode. The accuracy of the prediction function is of critical importance. The prediction function is accomplished by means of a model, a representation of salient features of the real world. This paper investigates and compares some predictive models. No attempt is made to find or build the ultimate, best predictive model; rather the aim is to explore a framework for comparing models and metrics.The comparison of predictive models of arrival flows was performed by comparing the model currently used by flow managers with several linear regression models. Not knowing in advance what measure of predictive accuracy was best, we selected seven metrics for comparison. Since TFM manages air traffic flows as opposed to individual flights, these metrics generally are oriented toward aggregates of flights. For the comparison, 42 test data sets of flights subject to departure-delay-type flow management for 14 major arrival airports around the country during 1992-1993 were used. An historical database of about 15,000 flights was used for the model building.The selection of best model was not straightforward, since other independent variables, namely performance metric and arrival airport, may also explain differences in predictive accuracy. An analysis of variance (ANOVA) model with the following form was therefore employed to examine the significance of effects:predictive accuracy = f(predictive model, performance metric, arrival airport)The ANOVA model is explicitly a linear function of the (categorical) independent variables. Both main effects and interaction effects were examined.

Abstract. Urban traffic analysis has acted an important role in the process of urban development, which can provide insights for urban planning, traffic management and resource allocation. Meanwhile, the advancement of Intelligent Transportation Systems has produced a variety of traffic-related data from sensors and cameras to monitor urban traffic conditions in high spatio-temporal resolution. This research applies spatial regression models combined with computer vision and deep learning to analyse traffic flow distributions via various factors in the urban areas and traffic flow data. We include road characteristics and surrounding environments such as land use/cover, nearby points of interest (POI) and Google Street View images. The results show that the daily average traffic flow on main roads is much higher than smaller roads, and nearby POIs numbers have positive effect on traffic flows. The impact of land cover type is insignificant in the linear regression model, while demonstrates significant contribution to traffic flows in spatial regression models. Although the spatial autocorrelation still exists after the spatial regression, the spatial error model generates a better fit on the dataset. Further analysis will focus on extend the current model with the time parameters and understand what influence the changes of traffic flow in the different spatio-temporal scales.

Heavy vehicles and passenger cars differ in their manoeuvrability and acceleration capabilities. Heavy vehicles thus influence other traffic in a different manner to passenger vehicles, causing different levels of traffic instability. Increasing number and proportion of heavy vehicles in the traffic stream may result in quite different traffic flow characteristics. Car-following (CF) models are fundamental to replicating traffic flow and thus they have received considerable attention over the last few decades. They are in a continuous state of improvement due to their significant role in traffic micro-simulations, intelligent transportation systems and safety engineering models. However, model estimates of the traffic flow could be degraded since existing CF models do not consider the interactions between these vehicles and passenger cars drivers satisfactorily. This oversight was revealed through a comprehensive literature review conducted in this study in which the existing CF models are classified into classic and artificial intelligence models and are critically reviewed. This research investigates the different car-following behaviour of drivers in congested mixed traffic conditions. The congested traffic conditions refer to the level of service (LOS) “E” and “F” according to the Highway Capacity Manual (HCM 2010). More specifically, this study investigates whether the existence of heavy vehicles in the traffic stream influence car-following behaviour between heavy vehicles and passenger cars? A detailed data analysis is conducted to explore this question using a rich trajectory data set recorded from a 503-meter a segment of freeway in the USA. Four combinations of car-following are considered based on the classes of the vehicles involved in the car-following process. These include heavy vehicle following passenger car (H-C), passenger car following heavy vehicle (C-H), passenger car following passenger car (C-C), and heavy vehicle following heavy vehicle (H-H). This research investigates the headways between the vehicles, driver’s reaction time, relative speed-space headway between the vehicles, and analysis of the vehicle accelerations during car-following process. The study explores the stimuli which can affect driver’s car-following behaviours. It also reconstructs the car-following thresholds for different combinations. The findings showed the fundamental differences amongst the car-following combinations suggesting further investigation and model development. Two CF models are developed in this thesis: one classic model and one artificial intelligence model. This study develops a psychophysical CF model in which four sets of perceptual thresholds are considered to estimate drivers’ car-following behaviour. This means each car-following combination is associated with one specific set of thresholds. The model is calibrated by evolutionary algorithm which is implemented using traffic micro-simulation. A parallel particle swarm optimisation (Parallel PSO) algorithm is implemented in this study to reduce the execution time using multithread methodology. The results show the better performance of the developed model compared to the existing models to estimate traffic measurements used in the traffic micro-simulation. As an alternative model, a new artificial intelligence CF model was developed which specifically considered heavy vehicles. The model used the local linear model tree (LOLIMOT) approach to predict the car-following behaviour of drivers with consideration of the classes of their vehicle and the immediate vehicles in front. The model and the ways of defining the localities and training of the model are explained. The performance of the developed model is evaluated by an independent data set. This evaluation is conducted through the comparison between the predictions of the developed model and the actual traffic measurements. Additionally, the performance for the developed model is compared with the existing CF models. The results showed a good performance of the developed model. This method could be considered as a new approach to modelling car-following behaviour of drivers in mixed traffic providing the opportunity for incorporating human perceptual imperfections into a rigorous modelling framework. This study concludes that the consideration of vehicle heterogeneity in modelling longitudinal behaviours of derivers could result in better representation of traffic flow. This study could be useful for the researchers and transport planners who wish to consider heavy vehicles in traffic stream. The model could be used in traffic micro-simulations to enhance their accuracy and modelling capability.

Traffic flow prediction is an important part of intelligent transportation systems (ITS). However, the performance of current traffic flow prediction methods does not meet the expectation. Weather factors such as precipitation in residential areas and tourist destinations affect traffic flow on the surrounding roads. In this paper, we attempt to take precipitation impact into consideration when predicting traffic flow. To realize this idea, we propose a deep traffic flow prediction architecture by introducing a deep bi-directional long short-term memory model, precipitation information, residual connection, regression layer and dropout training method. The proposed model has good ability to capture the deep features of traffic flow. Besides, it can take full advantage of time-aware traffic flow data and additional precipitation data. We evaluate the prediction architecture on the dataset from Caltrans Performance Measurement System (PeMS) with precipitation data from California Data Exchange Center (CDEC) and the dataset from KDD Cup 2017. The experiment results demonstrate that the proposed model for traffic flow prediction obtains high accuracy and generalizes well compared with other models.

Predicting large-scale transportation network traffic flow has become an important and challenging topic in recent decades. However, accurate traffic flow prediction is still hard to realize. Weather factors such as precipitation in residential areas and tourist destinations affect traffic flow on the surrounding roads. In this paper, we attempt to take precipitation impact into consideration when predicting traffic flow. To realize this idea, we propose a deep traffic flow prediction architecture by introducing a deep bi-directional long short-term memory model, precipitation information, residual connection, regression layer and dropout training method. The proposed model has good ability to capture the deep features of traffic flow. Besides, it can take full advantage of time-aware traffic flow data and additional precipitation data. We evaluate the prediction architecture on taxi trajectory dataset in Chongqing and taxi trajectory dataset in Beijing with corresponding precipitation data from China Meteorological Data Service Center (CMDC). The experiment results demonstrate that the proposed model for traffic flow prediction obtains high accuracy compared with other models.

The paper presents a critical analysis of current approaches to reorganizing urban transportation routes. It proposes addressing the problem of optimizing traffic flows as a multidimensional issue encompassing social and economic aspects. An economic-information model for continuous monitoring and optimization of urban traffic flow configurations based on the criterion of congestion wait time has been developed. The calculation of the economic consequences of such waiting time is proposed. The developed system has practical significance and can be applied in managing traffic flows as an economic subsystem of the city within its socio-economic system. Urban transportation infrastructure in Ukraine faces significant challenges due to social changes, including increasing passenger flow, extended waiting times, and the need to adhere to modern urban planning standards. Current trends involve redistributing street and road space based on principles of equal access and safety. This includes pilot actions, intermediate reconstruction, and comprehensive reorganization of urban space and transportation routes. Proposed methods for enhancing transportation infrastructure include improving government management, implementing proactive management strategies, executing investment projects, establishing public-private partnerships, temporarily reducing tax burdens, developing comprehensive solutions for consumers, and optimizing transportation pricing. These strategies aim to address the pressing problems in Ukraine's transport sector and facilitate sustainable development and growth. The study focuses on the financing of infrastructural projects in Dnipro city through the municipal budget. It proposes integrating economic-mathematical models into a unified economic-information system for optimizing traffic flows, allowing for continuous monitoring and improvement. This system emphasizes minimizing congestion wait times and can adapt to dynamic changes in traffic patterns, ensuring efficient and effective urban traffic management. By implementing this system, the city can enhance its transportation network, contributing to overall economic efficiency and better quality of life for its residents.