This paper proposes a region-based travel time and traffic speed prediction method using sequence prediction. Floating Car Data collected from 8,317 vehicles during 34 days are used for evaluation purposes. Twelve districts are chosen and the spatio-temporal non-linear relations are learned with Recurrent Neural Networks. Time estimation of the total trip is solved by travel time estimation of the divided sub-trips, which are constituted between two consecutive GNSS measurement data. The travel time and final speed of sub-trips are learned with Long Short-term Memory cells using sequence prediction. A sequence is defined by including the day of the week meta-information, dynamic information about vehicle route start and end positions, and average travel speed of the road segment that has been traversed by the vehicle. The final travel time is estimated for this sequence. The sequence-based prediction shows promising results, outperforms function mapping and non-parametric linear velocity change based methods in terms of root-mean-square error and mean absolute error metrics.

The daily travel patterns (DTPs) present short-term and timely characteristics of the users’ travel behaviour, and they are helpful for subway planners to better understand the travel choices and regularity of subway users (SUs) in details. While several well-known subway travel patterns have been detected, such as commuting modes and shopping modes, specific features of many patterns are still confused or omitted. Now, based on the automatic fare collection (AFC) system, a data-mining procedure to recognize DTPs of all SUs has become possible and effective. In this study, DTPs are identified by the station sequences (SSs), which are modelled from smart card transaction data of the AFC system. The data-mining procedure is applied to a large weekly sample from the Beijing Subway to understand DTPs. The results show that more than 93% SUs of the Beijing Subway travel in 7 DTPs, which are remarkably stable in share and distribution. Different DTPs have their own unique characteristics in terms of time distribution, activity duration and repeatability, which provide a wealth of information to calibrate different types of users and characterize their travel patterns.

This paper provides a framework for solving the Time Dependent Vehicle Routing Problem (TDVRP) by using historical data. The data are used to predict travel times during certain times of the day and derive zones of congestion that can be used by optimization algorithms. A combination of well-known algorithms was adapted to the time dependent setting and used to solve the real-world problems. The adapted algorithm outperforms the best-known results for TDVRP benchmarks. The proposed framework was applied to a real-world problem and results show a reduction in time delays in serving customers compared to the time independent case.

Traffic-related deaths and severe injuries may affect every person on the roads, whether driving, cycling or walking. Toronto, the largest city in Canada and the fourth largest in North America, aims to eliminate traffic-related fatalities and serious injuries on city streets. The aim of this study is to build a prediction model using data analytics and machine learning techniques that learn from past patterns, providing additional data-driven decision support for strategic planning. A detailed exploratory analysis is presented, investigating the relationship between the variables and factors affecting collisions in Toronto. A learning-based model is proposed to predict the fatalities and severe injuries in traffic collisions through a comparison of two predictive models: Lasso Regression and Random Forest. Exploratory data analysis results reveal both spatio-temporal and behavioural patterns such as the prevalence of collisions in intersections, in the spring and summer and aggressive driving and inattentive behaviours in drivers. The prediction results show that the best predictor of injury severity for drivers, cyclists and pedestrians is Random Forest with an accuracy of 0.80, 0.89, and 0.80, respectively. The proposed methods demonstrate the effectiveness of machine learning application to traffic and collision data, both for exploratory and predictive analytics.

Inadequate consideration of the elderly people crossing demand on the signalized intersections would bring great potential safety hazards, especially the speed through the crosswalk. By observing the pedestrian walking speed at three signalized crosswalks and a relatively spacious sidewalk in Chongqing, China, this paper has obtained the walking speed values of 658 elderly people and 1,176 adults at the signalized crosswalks, as well as the walking speed parameters of 868 adults and 422 elderly people on a relatively spacious sidewalk section. Comparing the walking speed of adults walking along the sidewalk section and on signalized crosswalks, the data show that there is no significant difference between these two site speeds. Similarly, when comparing the two site data of the elderly, it is found that their walking speed at the signalized crosswalk is significantly higher than that on the sidewalk section. That is to say, the speed setting for the old people crossing the crosswalk has not been fully considered. Subsequently, taking the elderly’s walking speed as input parameter, establishing the simulation models under different proportions of the elderly and different pedestrian flows, and then gain the walking speed values of the pedestrians with different quantities and different proportion of the elderly pedestrians. With the help of the unknown breakpoint Regression method, under the setting of the elderly pedestrian speed crossing the street, the proportion threshold of the elderly crossing the street at the signalized intersection is obtained. The results show that when the proportion of the elderly is more than 15% of the pedestrians crossing the street, the pedestrian crossing speed value for the signal time is suggested to be 0.97 m/s.

Forecasting short-term traffic flow using historical data is a difficult goal to achieve due to the randomness of the event. Due to the lack of a solid approach to short-term traffic prediction, the researchers are still working on novel approaches. This study aims to develop an algorithm that dynamically updates the training set of models in order to make more accurate predictions. For this purpose, an algorithm called Periodic Clustering and Prediction (PCP) has been developed for use in short-term traffic forecasting. In this study, PCP was used to improve Artificial Neural Networks (ANN) predictive performance by improving the training set of ANN to predict short-term traffic flow using selected clusters. A large amount of traffic data collected from the US and UK motorways was used to determine the PCP ability to increase the ANN performance. The robustness of the proposed approach was determined by the performance measures used in the literature and the mean prediction errors of PCP were significantly below other approaches. In addition, the studies showed that the percentage errors of PCP predictions decreased in response to increasing traffic flow values. Considering the obtained positive results, this method can be used in real-time traffic control systems and in different areas needed.

In this paper, a two-step meta-heuristic approach is proposed for vehicle assignment problem with geometric shape-based clustering and genetic algorithm. First, the geometric shape-based clustering method is used and then the solution of this method is given to the genetic algorithm as initial solution. The solution process is continued by genetic algorithm. There are 282 bus lines in İstanbul European side. Those buses should be assigned to six bus garages. The proposed method is used to determine the minimum distance between the bus lines and garages by assigning buses to garages. According to the computational results, the proposed algorithm has better clustering performance in terms of the distance from each bus-line start point to each bus garage in the cluster. The crossover rate changing method is also applied as a trial in order to improve the algorithm performance. Finally, the outputs that are generated by different crossover rates are compared with the results of the k-Nearest Neighbour algorithm to prove the effectiveness of the study.

Prije odabira projektnog rješenja raskrižja važan korak jeste provjera opravdanosti izgradnje temeljem definiranih kriterija. Jedan od ključnih kriterija jeste analiza propusne moći (kapaciteta). U svijetu postoji velik broj modela kapaciteta kružnih raskrižja koji su uglavnom prilagođeni uvjetima zemlje iz koje potječu, te ih je potrebno kalibrirati za lokalne uvjete. Ključni parametri za kalibraciju su kritična vremenska praznina i vrijeme slijeda. Vrijeme slijeda se može direktno mjeriti na terenu, a kritična praznina ne može, već se procjenjuje. Postoji veliki broj metoda procjene kritične vremenske praznine (preko 30) i sve daju različite vrijednosti. Različite vrijednosti kritične vremenske praznine rezultiraju različitim vrijednostima procjene kapaciteta. Stoga se nameće pitanje koja metoda daje realnije procijene u određenim uvjetima. U ovom radu su odabrane 4 najčešće korištene metode procjene kritične vremenske praznine (RAFF, MLM, WU, LOGIT) kako bi se testirale usporedbom rezultata teorijskih modela kapaciteta i stvarnog mjerenog kapaciteta na malom urbanom kružnom raskrižju.

Analizirani su kriteriji infrastrukture javnog prijevoza, koji značajno utječu na zadovoljstvo korisnika. Primarna pažnja bila je usmjerena na ocjenjivanje tih kriterija od najviše do najmanje važnih. Analiza znanstvenih radova, stručne literature, propisa Europske unije, litavskog zakonodavstva i preporuka korištena je za istraživanje potrebnih kriterija koji imaju značajan utjecaj na popularnost javnog prijevoza, njegovu funkcionalnost i daje referencu kako poboljšati učinkovitost gradsko stanovništvo bira javni prijevoz. Stručna i društvena istraživanja korištena su za utvrđivanje kriterija procjene infrastrukture javnog prijevoza te za istraživanje stanja tih kriterija. Ti su kriteriji ocijenjeni i rangirani prema prioritetima putem višekriterijske analize. Rezultati odražavaju prioritete kriterija parametara infrastrukture javnog prijevoza. Ovi parametri imaju najznačajniji utjecaj na poboljšanje razine usluge infrastrukture javnog prijevoza u urbanim područjima.

The purpose of this study was to explore outsourcing as a possible source of competitive advantage for road freight operators, with the empirical research directed towards the road freight transportation sector. Methodologically, this study drew on the data collected from a sample of Croatian road freight transporters. Because a certain number of transportation companies tend to outsource their resources, the insight into outsourcing activities was gained through analysing (1) the number of hired vehicles in the fleet (outsourced vehicles), and (2) the number of hired drivers (outsourced drivers). A variance inflation test, correlation and multiple regression analysis were conducted to test the model assumptions. The research results confirmed the connection between the externalised resources and the differentiation of services and staff. The main contribution and managerial implications included that the companies with a more significant number of hired vehicles in their fleet should differentiate their services. In contrast, the companies that own the majority of their vehicles should build their competitive advantage through staff differentiation.

Tunnels are critical areas for highway safety because the severity of crashes in tunnels tends to be more serious. Controlling vehicle speed is regarded as a feasible measure to reduce the accident rate in the tunnel entrance and exit areas. This paper aims to evaluate the effectiveness of three types of speed reduction markings (SRMs) in tunnel entrance and exit zones by conducting a driving simulation experiment. For this study, 25 drivers completed the driving tasks in the day and night scenarios. The vehicle speed and acceleration data were collected for analysing and the relative speed contrast, time mean speed and acceleration were adopted as indices to evaluate the effectiveness of SRMs. The repeated ANOVA test results revealed that SRMs have a significant effect in reducing vehicle speed, especially in the exit zone. Colour Anti-skid Markings (CASMs) produced a more obvious deceleration in the entrance zone. In the entrance zone, a similar downward trend was performed in the situation of NSRMs and SRMs, but a lower speed occurred in case of SRMs. Besides, CASMs work better and cause an obvious gap of 10 km/h in daytime and 5 km/h at night compared to the speed without SRMs. In the exit zone, the present study supports the conclusion that the drivers are prone to accelerate. Our results showed that the drivers accelerated in case of NSRMs, while they slowed down in case of SRMs. Thus, SRMs are necessarily implemented in the highway tunnel entrance and exit zones. Our study also indicates that though CASMs result in lower speed at night, the Transverse Speed Reduction Markings
(TSRMs) have a better performance than CASMs in daytime. The investigation provides essential information for developing a new marking design criterion and intelligent driver support systems in the highway tunnel zones.

Intention is the main embodiment of human cerebral conscious activities, which has an important influence on guiding the realization of human behaviour. It is a vital prerequisite for analysing the dynamic characteristics of pilots with different intentions. Considering the intention law of the generation, transfer and reduction, this paper analyses dynamic characteristics of pilots with different intentions, starting from the factors of effect on the intention. Taking airfield traffic pattern as an example for simulating flight experiments, the pilot’s multi-source dynamic data of human – aircraft – environment system under different intentions and their psycho-physiological-physical characteristics were recorded. Based on Matlab, one-way analysis of variance was used to extract variables with significant changes, and the variables under different intentions were compared and analysed. The results show that the conventional pilots are more conducive to control the aircraft to keep a stable flight attitude. This study is of great significance for perfecting the warning system of flight safety and improving the pilot’s micro-behaviour assessment system.