The rapid growth of population and the permanent increase in the number of vehicles engender several issues in transportation systems, which in turn call for an intelligent and cost-effective approach to resolve the problems in an efficient manner. A cost-effective approach for improving and optimizing transportation-related problems is to unlock hidden knowledge in ever-increasing spatiotemporal and crowdsourced information collected from various sources such as mobile phone sensors (e.g., GPS sensors) and social media networks (e.g., Twitter). Data mining and machine learning techniques are the major tools for analyzing the collected data and extracting useful knowledge on traffic conditions and mobility behaviors. Deep learning is an advanced branch of machine learning that has enjoyed a lot of success in computer vision and natural language processing fields in recent years. However, deep learning techniques have been applied to only a small number of transportation applications such as traffic flow and speed prediction. Accordingly, my main objective in this dissertation is to develop state-of-the-art deep learning architectures for resolving the transport-related applications that have not been treated by deep learning architectures in much detail, including (1) travel mode detection, (2) vehicle classification, and (3) traffic information system. To this end, an efficient representation for spatiotemporal and crowdsourced data (e.g., GPS trajectories) is also required to be designed in such a way that not only be adaptable with deep learning architectures but also contains efficient information for solving the task-at-hand. Furthermore, since the good performance of a deep learning algorithm is primarily contingent on access to a large volume of training samples, efficient data collection and labeling strategies are developed for different data types and applications. Finally, the performance of the proposed representations and models are evaluated by comparing to several state-of-the-art techniques in literature. The experimental results clearly and consistently demonstrate the superiority of the proposed deep-learning based framework for each application. / PHD / The rapid growth of population and the permanent increase in the number of vehicles engender several issues in transportation systems, which in turn call for an intelligent and cost-effective approach to resolve the problems in an efficient manner. Furthermore, the recent advances in positioning tools (e.g., GPS sensors) and ever-popularity of social media networks have enabled generation of massive spatiotemporal and crowdsourced data. This dissertation aims to leverage the advances in artificial intelligence so as to unlock the rick knowledge in the recorded data and in turn, optimizing the transportation systems in a cost-effective way. In particular, this dissertation seeks for proposing end-to-end frameworks based on deep learning models, as an advanced branch of artificial intelligence, as well as spatiotemporal and crowdsourced datasets (e.g., GPS trajectory and social media) for improving three transportation problems. (1) Travel Mode Detection, which is defined as identifying users’ transportation mode(s) (e.g., walk, bike, bus, car, and train) when traveling around the traffic network. (2) Vehicle Classification, which is defined as identifying the vehicle’s type (e.g., passenger car and truck) while moving in a traffic network. (3) traffic information system based on social media networks, which is defined as detecting traffic events (e.g., crash) and capturing traffic information (e.g., traffic congestion) on a real-time basis from users’ tweets. The experimental results clearly and consistently demonstrate the superiority of the proposed deep-learning based framework for each application.

<p>This report is a technical verification and validation of Traffic Information Service Broadcast (TIS-B) using the data link VDL Mode 4. </p><p>The main objective of the report is to examine the usefulness of TIS-B considering the results from tests performed in the Stockholm Terminal Area and for the Advanced Surface Movement Guidance and Control System (A-SMGCS) at Arlanda airport. The results are compared with the requirements that have been set by the standardisation organisations ICAO, RTCA, Eurocontrol and Eurocae. TIS-B is however such a new concept, so most of the operational requirements have not yet been defined.</p><p>The process for performing the evaluation of TIS-B involves three stages: </p><p>· Study the requirements on TIS-B, ADS-B, radar and A-SMGCS. </p><p>· Verify TIS-B by performing tests at Arlanda airport. </p><p>· Validate the test results through analysis. </p><p>A theoretical study of slot allocation optimisation is performed to decide how the slot allocation is to be implemented. </p><p>The report includes a Functional Hazard Analysis (FHA). The FHA is done to see if the applications for TIS-B are ready for implementation or if more hazard preventing actions has to be taken, before any operational actions can be performed. </p><p>The report also involves a theoretical introduction to Air Traffic Management (ATM), Surveillance techniques and TIS-B. </p><p>All parts included in the report results in conclusions and recommendations regarding the TIS-B service.</p>

This report is a technical verification and validation of Traffic Information Service Broadcast (TIS-B) using the data link VDL Mode 4. The main objective of the report is to examine the usefulness of TIS-B considering the results from tests performed in the Stockholm Terminal Area and for the Advanced Surface Movement Guidance and Control System (A-SMGCS) at Arlanda airport. The results are compared with the requirements that have been set by the standardisation organisations ICAO, RTCA, Eurocontrol and Eurocae. TIS-B is however such a new concept, so most of the operational requirements have not yet been defined. The process for performing the evaluation of TIS-B involves three stages: · Study the requirements on TIS-B, ADS-B, radar and A-SMGCS. · Verify TIS-B by performing tests at Arlanda airport. · Validate the test results through analysis. A theoretical study of slot allocation optimisation is performed to decide how the slot allocation is to be implemented. The report includes a Functional Hazard Analysis (FHA). The FHA is done to see if the applications for TIS-B are ready for implementation or if more hazard preventing actions has to be taken, before any operational actions can be performed. The report also involves a theoretical introduction to Air Traffic Management (ATM), Surveillance techniques and TIS-B. All parts included in the report results in conclusions and recommendations regarding the TIS-B service.

Das Verkehrs-Analyse-, -Management- und -Optimierungs-System VAMOS nimmt die Aufgaben zur Datenaufbereitung als Grundlage für gezielte operative Verkehrsmanagementmaßnahmen im Ballungsraum Dresden wahr. Zur Modellierung von Verkehrs- und Infrastrukturdaten finden auf die Spezifika des Verkehrsgeschehens in urbanen Ballungsräumen zugeschnittene Ansätze Verwendung. Zur Verknüpfung von Verkehrssteuerungs- sowie Verkehrsinformationssystemen und dem Verkehrslagebild findet eine vorteilhafte Strategie zur Entkopplung von Datenerfassungs- und Steuerungssystemen erfolgreiche Anwendung. / The operational traffic management system VAMOS realises specific data processing as general basis for aimed measures to influence traffic flow in the Dresden agglomeration. Approaches adapted to specific requirements of traffic activities in dense urban road networks were used for modelling traffic flow and infrastructural conditions. To annex traffic control systems as well as traffic information systems to the traffic conditions chart an advantageous strategy decoupling detection and control devices were implemented successfully.

The 4th Symposium on Management of Future Motorway and Urban Traffic Systems (MFTS) was held in Dresden, Germany, from November 30th to December 2nd, 2022. Organized by the Chair of Traffic Process Automation (VPA) at the “Friedrich List” Faculty of Transport and Traffic Sciences of the TU Dresden, the proceedings of this conference are published as volume 9 in the Chair’s publication series “Verkehrstelematik” and contain a large part of the presented conference extended abstracts. The focus of the MFTS conference 2022 was cooperative management of multimodal transport and reflected the vision of the professorship to be an internationally recognized group in ITS research and education with the goal of optimizing the operation of multimodal transport systems. In 14 MFTS sessions, current topics in demand and traffic management, traffic control in conventional, connected and automated transport, connected and autonomous vehicles, traffic flow modeling and simulation, new and shared mobility systems, digitization, and user behavior and safety were discussed. In addition, special sessions were organized, for example on “Human aspects in traffic modeling and simulation” and “Lesson learned from Covid19 pandemic”, whose descriptions and analyses are also included in these proceedings.:1 Connected and Automated Vehicles 1.1 Traffic-based Control of Truck Platoons on Freeways 1.2 A Lateral Positioning Strategy for Connected and Automated Vehicles in Lane-free Traffic 1.3 Simulation Methods for Mixed Legacy-Autonomous Mainline Train Operations 1.4 Can Dedicated Lanes for Automated Vehicles on Urban Roads Improve Traffic Efficiency? 1.5 GLOSA System with Uncertain Green and Red Signal Phases 2 New Mobility Systems 2.1 A New Model for Electric Vehicle Mobility and Energy Consumption in Urban Traffic Networks 2.2 Shared Autonomous Vehicles Implementation for a Disrupted Public Transport Network 3 Traffic Flow and Simulation 3.1 Multi-vehicle Stochastic Fundamental Diagram Consistent with Transportations Systems Theory 3.2 A RoundD-like Roundabout Scenario in CARLA Simulator 3.3 Multimodal Performance Evaluation of Urban Traffic Control: A Microscopic Simulation Study 3.4 A MILP Framework to Solve the Sustainable System Optimum with Link MFD Functions 3.5 On How Traffic Signals Impact the Fundamental Diagrams of Urban Roads 4 Traffic Control in Conventional Traffic 4.1 Data-driven Methods for Identifying Travel Conditions Based on Traffic and Weather Characteristics 4.2 AI-based Multi-class Traffic Model Oriented to Freeway Traffic Control 4.3 Exploiting Deep Learning and Traffic Models for Freeway Traffic Estimation 4.4 Automatic Design of Optimal Actuated Traffic Signal Control with Transit Signal Priority 4.5 A Deep Reinforcement Learning Approach for Dynamic Traffic Light Control with Transit Signal Priority 4.6 Towards Efficient Incident Detection in Real-time Traffic Management 4.7 Dynamic Cycle Time in Traffic Signal of Cyclic Max-Pressure Control 5 Traffic Control with Autonomous Vehicles 5.1 Distributed Ordering and Optimization for Intersection Management with Connected and Automated Vehicles 5.2 Prioritization of an Automated Shuttle for V2X Public Transport at a Signalized Intersection – a Real-life Demonstration 6 User Behaviour and Safety 6.1 Local Traffic Safety Analyzer (LTSA) - Improved Road Safety and Optimized Signal Control for Future Urban Intersections 7 Demand and Traffic Management 7.1 A Stochastic Programming Method for OD Estimation Using LBSN Check-in Data 7.2 Delineation of Traffic Analysis Zone for Public Transportation OD Matrix Estimation Based on Socio-spatial Practices 8 Workshops 8.1 How to Integrate Human Aspects Into Engineering Science of Transport and Traffic? - a Workshop Report about Discussions on Social Contextualization of Mobility 8.2 Learning from Covid: How Can we Predict Mobility Behaviour in the Face of Disruptive Events? – How to Investigate the Mobility of the Future / Das 4. Symposium zum Management zukünftiger Autobahn- und Stadtverkehrssysteme (MFTS) fand vom 30. November bis 2. Dezember 2022 in Dresden statt und wurde vom Lehrstuhl für Verkehrsprozessautomatisierung (VPA) an der Fakultät Verkehrswissenschaften„Friedrich List“ der TU Dresden organisiert. Der Tagungsband erscheint als Band 9 in der Schriftenreihe „Verkehrstelematik“ des Lehrstuhls und enthält einen Großteil der vorgestellten Extended-Abstracts des Symposiums. Der Schwerpunkt des MFTS-Symposiums 2022 lag auf dem kooperativen Management multimodalen Verkehrs und spiegelte die Vision der Professur wider, eine international anerkannte Gruppe in der ITS-Forschung und -Ausbildung mit dem Ziel der Optimierung des Betriebs multimodaler Transportsysteme zu sein. In 14 MFTS-Sitzungen wurden aktuelle Themen aus den Bereichen Nachfrage- und Verkehrsmanagement, Verkehrssteuerung im konventionellen, vernetzten und automatisierten Verkehr, vernetzte und autonome Fahrzeuge, Verkehrsflussmodellierung und -simulation, neue und geteilte Mobilitätssysteme, Digitalisierung sowie Nutzerverhalten und Sicherheit diskutiert. Darüber hinaus wurden Sondersitzungen organisiert, beispielsweise zu „Menschlichen Aspekten bei der Verkehrsmodellierung und -simulation“ und „Lektionen aus der Covid-19-Pandemie“, deren Beschreibungen und Analysen ebenfalls in diesen Tagungsband einfließen.:1 Connected and Automated Vehicles 1.1 Traffic-based Control of Truck Platoons on Freeways 1.2 A Lateral Positioning Strategy for Connected and Automated Vehicles in Lane-free Traffic 1.3 Simulation Methods for Mixed Legacy-Autonomous Mainline Train Operations 1.4 Can Dedicated Lanes for Automated Vehicles on Urban Roads Improve Traffic Efficiency? 1.5 GLOSA System with Uncertain Green and Red Signal Phases 2 New Mobility Systems 2.1 A New Model for Electric Vehicle Mobility and Energy Consumption in Urban Traffic Networks 2.2 Shared Autonomous Vehicles Implementation for a Disrupted Public Transport Network 3 Traffic Flow and Simulation 3.1 Multi-vehicle Stochastic Fundamental Diagram Consistent with Transportations Systems Theory 3.2 A RoundD-like Roundabout Scenario in CARLA Simulator 3.3 Multimodal Performance Evaluation of Urban Traffic Control: A Microscopic Simulation Study 3.4 A MILP Framework to Solve the Sustainable System Optimum with Link MFD Functions 3.5 On How Traffic Signals Impact the Fundamental Diagrams of Urban Roads 4 Traffic Control in Conventional Traffic 4.1 Data-driven Methods for Identifying Travel Conditions Based on Traffic and Weather Characteristics 4.2 AI-based Multi-class Traffic Model Oriented to Freeway Traffic Control 4.3 Exploiting Deep Learning and Traffic Models for Freeway Traffic Estimation 4.4 Automatic Design of Optimal Actuated Traffic Signal Control with Transit Signal Priority 4.5 A Deep Reinforcement Learning Approach for Dynamic Traffic Light Control with Transit Signal Priority 4.6 Towards Efficient Incident Detection in Real-time Traffic Management 4.7 Dynamic Cycle Time in Traffic Signal of Cyclic Max-Pressure Control 5 Traffic Control with Autonomous Vehicles 5.1 Distributed Ordering and Optimization for Intersection Management with Connected and Automated Vehicles 5.2 Prioritization of an Automated Shuttle for V2X Public Transport at a Signalized Intersection – a Real-life Demonstration 6 User Behaviour and Safety 6.1 Local Traffic Safety Analyzer (LTSA) - Improved Road Safety and Optimized Signal Control for Future Urban Intersections 7 Demand and Traffic Management 7.1 A Stochastic Programming Method for OD Estimation Using LBSN Check-in Data 7.2 Delineation of Traffic Analysis Zone for Public Transportation OD Matrix Estimation Based on Socio-spatial Practices 8 Workshops 8.1 How to Integrate Human Aspects Into Engineering Science of Transport and Traffic? - a Workshop Report about Discussions on Social Contextualization of Mobility 8.2 Learning from Covid: How Can we Predict Mobility Behaviour in the Face of Disruptive Events? – How to Investigate the Mobility of the Future

Mit dem sechsten Band der Schriftenreihe Verkehrstelematik wird ein Überblick über die intermodalen Forschungsthemen des Jahres 2015 der Professur für Verkehrsleitsysteme und ‑prozessautomatisierung der Fakultät Verkehrswissenschaften „Friedrich List“ der Technischen Universität Dresden anhand ausgewählter Veröffentlichungen gegeben. Sieben ausgewählte Artikel der Mitarbeiter, hauptsächlich veröffentlicht im Rahmen nationaler und internationaler Konferenzen, wurden dafür zusammengestellt. Die ersten Schwerpunkte bilden dabei die energieoptimale Steuerung und das Verkehrsmanagement im Schienenverkehr. Hier wird der Frage nachgegangen, wie Störungen des Bahnbetriebs im Echtzeit-Betriebsmanagement mit mathematischen Methoden begegnet werden kann. Als ein Ansatzpunkt wird das Erzeugen von robusten, stabilen und dabei auch energieeffizienten Fahrplänen diskutiert. Weiterhin wird versucht, im Rahmen des Betriebsmanagements mittels Konfliktlösungsalgorithmen operativ aktualisierte Fahrpläne so aufzubereiten, dass eine Umsetzung mit fahrzeugseitigen Fahrerassistenzsystemen ermöglicht und ein energieeffizienter Betrieb sichergestellt ist. Im zweiten Teil des Bandes wird gezeigt, wie die Methoden und Algorithmen der energieoptimalen Fahrweise und eines entsprechenden Fahrerassistenzsystems auf die Straßenbahn und auch den Bus übertragen werden können. Anschließend wird gänzlich auf den Individualverkehr fokussiert und der Frage der Reichweitenoptimierung elektrischer Fahrzeuge durch energieeffiziente Routing-Algorithmen unter Berücksichtigung von Echtzeit-Verkehrslagedaten nachgegangen. Wie im Schienenverkehr wird das Finden der optimalen Fahrstrategie auch hier durch Fahrerassistenzsysteme unterstützt.

Der nunmehr achte Band der Schriftenreihe Verkehrstelematik widmet sich den Forschungsthemen und ausgewählten Veröffentlichungen des Jahres 2016 der Professur für Verkehrsleitsysteme und -prozessautomatisierung der Fakultät Verkehrswissenschaften „Friedrich List“ der Technischen Universität Dresden. Elf Beiträge von nationalen und internationalen Konferenzen und aus Zeitschriftenveröffentlichungen der Mitarbeiter mit den Themengebieten Bahnverkehr, ÖPNV, Straßenverkehr und Radverkehr zeigen das breite Spektrum verkehrstelematischer Anwendungen und Forschungen der Professur. Im Bereich der energieoptimalen Steuerung im Schienenverkehr werden Ergebnisse des EU-geförderten Projektes ON-TIME mit Fragestellungen zum echtzeitfähigen Verkehrsmanagement, zur Fahrerassistenz sowie Fahrplanbewertung und -optimierung in Bahnsystemen vorgestellt. Beiträge zum EU-Projekt CAPACITY4RAIL ergänzen die Betrachtungen um Fragestellungen zu Datenaustauschformaten und formalen Beschreibungen von Störungsmanagementprozessen im Eisenbahnbetrieb. Neue Einsatzfelder für Fahrerinformations- und -assistenzsysteme werden mit Beiträgen zu BikeNow – einer mobilen Applikation für Fahrradfahrer – sowie COSEL – einem System für Straßenbahnen gezeigt. Zwei Artikel stellen die vielversprechenden Ergebnisse der ersten Praxisanwendung der Systeme vor. Und auch im Bereich des Verkehrsmanagements des Straßenverkehrs sind automatisierte Fahrfunktionen und Fahrerassistenzsysteme ein Forschungsthema. Für das Projekt REMAS wird hier beispielhaft auf Simulationsuntersuchungen mit SUMO eingegangen. Ferner wurde im Rahmen des Qualitätsmanagements für das Dresdner Verkehrsmanagementsystem VAMOS analysiert, welche Güte bei der Verkehrslageeinschätzung erreicht wird und wie diese durch Nutzung eines aktuellen Verkehrslagebilds und Verkehrslageinformationen aufgewertet werden kann.:Inhaltsverzeichnis / Gliederung - Störungsmanagement bei Extremwetter-Ereignissen 1 - Datenformate, -modelle und -konzepte für den Eisenbahnbetrieb – Ausgewählte Ergebnisse des Arbeitspakets 3.4 im EU-Projekt CAPACITY4RAIL 11 - The ON-TIME real-time railway traffic management framework: a proof-ofconcept using a scalable standardised data communication architecture 31 - Zur Kopplung von Konfliktlösung und Fahrerassistenz – Herausforderungen, Lösungsansätze, Ergebnisse 77 - Erschließung neuer Anwendungsfelder mittels RailTopoModel für Planung, Simulation und Betrieb bei Eisenbahnen 89 - A three-level framework for performance-based railway timetabling 101 - Einsatz von Informationssystemen zum energieeffizienten Fahren im städtischen Personennahverkehr 141 - Simulation of highly automated vehicles using SUMO 153 - Einsatzmöglichkeiten von Biofunktionsmesswerten in verkehrstelematischen Anwendungen 159 - Verkehrslageprognose unter Berücksichtigung der dynamischen Kapazitäten an LSA-abhängigen Knotenpunkten 173 - BikeNow: A Pervasive Application for Crowdsourcing Bicycle Traffic Data 189 - Mitarbeiter der Professur für Verkehrsleitsysteme und -prozessautomatisierung 201

本研究以警察廣播電臺台北臺為例，探討身為交通專業電台的警察廣播電台，在面對電視與其他廣播媒體，紛紛加入路況資訊提供的競爭下，是否仍具有其優勢？以因工作需要而必需長時間使用道路的計程車駕駛人為研究對象，探討大台北地區計程車駕駛人收聽警廣節目的主要目的為何？在什麼情況下容易轉台？節目內容與傳播設備等因素，是否也會影響計程車駕駛人的轉台意願？ 研究發現，收聽警廣台北臺節目的計程車駕駛人，只有兩種類型，一種為「計劃型」收聽，另一種則採取「再評估模式」。計程車駕駛人因警廣路況報導正確而收聽，但卻也會因為資訊不夠即時而轉台；收聽時間大多集中在上、下班的尖峰時間。最欣賞的節目主持人，則以「路況報得好、報得專業」最獲青睞，甚至有六成以上的計程車駕駛人會因為喜歡某個節目主持人，而固定收聽其節目；另外，聲音悅耳、節目多元豐富與音樂好聽與否，也是吸引計程車駕駛人是否繼續收聽的重要因素。除了路況資訊的獲得外，計程車駕駛人對於生活資訊的需求，遠高於新聞氣象、綜藝音樂及公共事務。至於車上有無其他音響設備，亦將影響計程車駕駛人的轉台行為。 / The purpose of this study is to determine whether the Police Radio Station (PRS), specifically the one in Taipei, is still necessary since television and many other forms of media provide the same service of traffic broadcasting. The research subjects for this study are Taipei taxi drivers who spend long hours on the road each day. Four questions form the basis of this study: 1. What is the main reason that taxi drivers listen to PRS? 2. Under what circumstances do they switch channels? 3. Does the content of the program affect their listening choices? 4. Does the type of broadcasting equipment affect their listening choices? The results indicate that there are two kinds of taxi drivers who listen to the programs of the PRS in Taipei. The first kind follows the "planning strategy" and the other kind follows the "re-evaluation strategy." Drivers listen to the PRS for its accuracy of traffic information; however, they will switch to another channel when there is a lack of substantial information being broadcast. Their listening time usually occurs during the rush hours, when they are getting on or getting off work. Drivers primarily prefer anchors whose information is "not only great but also professional." More than 60 percent of the drivers in this study report that they will continuously listen to one program if it is hosted by the anchor whom they favor. In addition, three other factors affect the drivers' listening habits: (1) the voice of the anchor, (2) the richness of the program content, and (3) the quality of the music being played. Besides traffic information, taxi drivers also need or desire to listen to information about other aspects of daily life, than (1) news and weather, (2) entertainment, and (3) public affairs. Finally, one other factor affects the listening behavior of taxi drivers: whether or not there is more than one form of listening device inside the car.

Master’s thesis deals with implementation of a European standard DATEX II. This standard specifies the data format for information transmission in road transport. The road traffic is flowing streams of current information. For the work was selected network of meteorological stations, which will publish the measured data, ie weather conditions of road transport. Measured data will be available to consumers in the format DATEX II. Implementation will be operational in its entirety meteorological station from design to the actual web service that will produce data information for consumers.