Refine
Has Fulltext
- yes (34) (remove)
Year of publication
Document Type
- Master's Thesis (15)
- Bachelor Thesis (11)
- Book (4)
- Report (4)
Institute
Language
- English (34) (remove)
The book 'Reinforcement Learning: An Introduction' by Sutton and Barto is the standard text book for introductory courses to reinforcement learning. Next to concrete algorithms and extensive examples the book contains several fundamental results related to Markov decision processes (MDPs) and Bellman equations in Chapters 3 and 4. Unfortunately some proofs are missing, some theorems lack precise formulation, and for some results the line of arguments is quite garbled.
In this note we provide all missing proofs, give precise formulations of theorems and untangle the line of arguments. Further, we avoid using random variables and their expected values. Since we (like Sutton/Barto) restrict our attention to finite MDPs all expected values can be made explicit avoiding overloaded notation and murky conclusions.
This article bridges the gap between introductory literature like Sutton/Barto and research literature containing exact formulations and proofs of relevant results, but being less accessible to beginners due to higher generality and complexity.
OpenStreetMap (OSM) is a large open database for geographic data created and maintained by volunteers. OSM's main data use is rendering an extremely detailed map of the world. Data quality is an important issue for applications like routing of pedestrians to public transport facilities. In this report we describe different schemes for mapping bus stops in OSM and we provide statistics on usage of those schemes, the good ones and the not so good ones.
The book is the second of four volumes on data science and artificial intelligence. This second volume covers data visualization tool and techniques as well as fundamentals of supervised machine learning: linear regression, artificial neural networks, support-vector machines, decision trees, ensemble methods and more.
The traffic calming measures aim to slow down traffic speed, accident frequency, and reduction of through traffic caused mainly by motorized vehicles in residential areas. These measures are primarily addressed to the specific streets and lead the necessary or remaining traffic to drive in a restrained or considerate manner. While these measures are designed to prevent conflicts between pedestrians and motorists, they impose unstable traffic patterns and are sometimes unable to accommodate the increasing motor vehicle flows, as they are concentrated only on certain streets.
This paper investigates area-wide urban traffic calming techniques from existing projects. It explains how traffic regulatory and structural measures link together or separately to restrict the movement of motor vehicles traveling through neighborhood streets and divert them to main roads. The implemented sample measures were illustrated and described with photos of their current locations.
In this thesis, the district Äußere Neustadt was defined as a model area in Dresden to analyze and redesign the existing mobility plan in order to reduce the MIV flows with the main objectives of giving space for pedestrians, cyclists, and public transport. The district's street infrastructure is heavily impacted by the presence of parked vehicles, raising challenges to the safe movement of both bicyclists and oncoming motor vehicles. In the frame of the model project initiative - "Woche des guten Lebens", the volunteer team has designed a traffic experiment and carried out an online survey to assess citizens' opinions of the Äußere Neustadt. The analyses demonstrate and emphasize the necessity of political support and interactive communication with citizens regarding the area-wide radical sustainable mobility plan. Considering the positive feedback of the citizens, the new mobility plan was realized in this paper.
Area-specific traffic calming techniques such as diagonal or cross barriers, zone speed limits, offsets, one-way streets, etc. were analyzed from the implemented projects to determine the appropriate solutions for the specified streets. The district's existing traffic network and the new solutions offered were visualized using QGIS software.
The implemented new traffic plan will lead to more space for pedestrians and bicycle traffic and a reduction in traffic noise.
BIM (Building information modeling) is becoming a reliable method for the planning, design, implementation, and maintenance stages of construction projects due to its ability to improve the quality of project stages, reduce project time, and ensure costs. From 2000 onwards, the trend of using BIM method increased in the world. And in the last decade, many developed countries have introduced BIM as a reasonable and efficient method with the aim of optimizing project stages, and many employers have paid attention to training and persuading consulting and contracting companies.
In the meantime, the BIM method is constantly being updated. Many researchers are looking to modify existing sub-methods to help the project achieve all of the great BIM goals.
Although BIM has great goals such as those mentioned, in some cases, projects are not able to achieve all of them for various reasons.
This thesis has put its hypothesis on the existence of deficiencies in the content of the EIR (Employer's Information Requirements) document and its writing methods.
This document, which is a kind of project guide in BIM format, is compiled by the client and its task is to announce the needs of the client to the members involved in the project and to clarify the different stages of the project. In many construction projects, due to the complexity of the EIR, the employer's lack of attention to some information, or the failure to include the opinions and views of the project's stakeholders in the writing of this document, the EIR cannot fulfill its key role with its maximum potential performance in the project.
This thesis is written with the aim of finding a comprehensive solution to maximize the power of the BIM method in a project through correct and complete document writing.
Also, this thesis seeks to prove its claims by focusing on the ABS 38 project as a case study. In addition, a literature review on important and key issues in the field of BIM and EIR documents has been done. After that, a scoring system (Relative rating method) was used to find the best variant and compare it to prove the proposed hypothesis.
In this project we develop an intelligent water meter based on software solutions offered by the IOTA Foundation. The water meter allows the customer to map water usage in real-time and pay water on demand, as well as the water provider to map water usage on a greater scale, regulate water supply during low- demand phases and offers regulatory functions to prepare for drought or humid climate, and to incentivise sustainable water usage in high-demand fields like agriculture. This functionality is phrased into a research issue:
Invention of a working prototype to demonstrate the IOTA Streams and Wallet protocols for a meter with additional focus on economic efficiency and the technical preparation of scalability.
Utilizing the IOTA streams protocol, a next generation secure data connection is established between the water meter and a server-sided software application. On this connection, water consumption is mapped into a data bench, and informative data and commands are issued to the graphical interface of the meter.
The IOTA wallet library is leveraged to provide customer accounts corresponding to their meter. IOTA tokens can be send to the account, which grants access to water in a matter of seconds. Depending on the regulatory scenario, water flow can be stopped as soon as the account is exhausted (i.e. public well), or an overdraw can be established in order to guarantee fulfilment of basic human rights (i.e. private households).
Since pricing data can be calculated server-sided and water consumption is mapped in very narrow intervals of as low as 4 seconds, the price can be used as tool to regulate consumption.
The physical components include an electrical ball valve to shut down water flow automatically, a command line interface to provide informative data,, a Raspberry Pi running the client-sided software application, and a water meter with MBus-Interface, as well as a Controlling Board to connect the Raspberry Pi with both peripheral devices.
The finished prototype shows, that water consumption can be mapped on a highly secure level, in near real-time, from afar, flexible for most applications.
Despite lacking sufficient evidence, the shift to automated mobility has often been regarded as progress towards a safer road transport system. Following the introduction of the first production car that has been officially certified as Level 3 earlier in 2022, the driver can shift their role to only as a fallback when the automated driving system reaches its limit of the Operational Design Domain. In the event of an accident, though, the matter will only get even more complicated, especially in the process of unravelling the party that was performing the Dynamic Driving Task at the time of the collision. An accident investigation is done to provide insight into how it occurred and uncover the liable parties. This thesis reviews various methods reconstructing an accident scene, such as photogrammetry and laser scanning, as well as elaborating the relevant data that has already available in the vehicle and from the infrastructure. Recommendations are also presented on for the future data collection, specifically in the scenario of automated driving, to improve such practice.
Automotive transportation plays an important role in everyday urban life. The motorization is increasing along with rising population every year. The constant increase of cars causes various problems in big cities. One of the major problems is parking. Parking search traffic contributes to about 30% of the traffic volume in city centers. This leads to problems like congestion, road accidents, increase of fuel emission due to the circling of cars inside the city looking for parking facilities, environmental pollution etc. Most of the cities face this problem not because of the unavailability of parking spots in parking facilities but rather because drivers don't have the right information on where to park. This can be solved by providing proper guidance about the parking facilities to the drivers. For this, efficient parking space management including the design of a suitable parking guidance system is required. The Entsorgungs and Vekehrsbetrieb (EVB) Wismar has been responsible for the parking space management in the city since 2012 and is implementing the parking space concept in Wismar that was approved by the town council. So far, there is a static parking guidance system in Wismar, which consists of 20 locations with signs pointing to six parking facilities. The Entsorgungs und Vekehrsbetrieb (EVB) intends to replace the static parking guidance system of the Hanseatic City of Wismar with a dynamic parking guidance system (DPGS). The aim of my master thesis is to create a concept for the development of a dynamic parking guidance system in the Hanseatic city of Wismar, including the technical operation and possible implementation, taking autonomous driving into account.
This research investigates the Leipzigerstraße and Gießereistraße intersection in Rackwitz to enhance safety and sustainable transportation. The study analyzes existing designs that experience accidents and proposes a design plan of mini roundabout to improve safety while using the guideline Anlage von Kreisverkehren. In this project, the roundabout is planned according to the currently valid guidelines from phase 2 of the HOAI (Fee Structure for Architects and Engineers). Rainwater management strategies and traffic quality of the roundabout are considered. Additionally, cyclist-friendly paths connecting Rackwitz and Zschölkau are developed in line by using guideline ERA. The proposed roundabout design and elevated cycle paths are identified as effective solutions to enhance safety and support eco-friendly transportation. By adhering to established guidelines and prioritizing safety, this research contributes to creating a secure and sustainable urban transportation network.
The book is the first of four volumes on data science and artificial intelligence. This first volume covers fundamentals of data science: an introduction to Python programming, software libraries for data management, techniques for working with big data. It contains many exercises and projects with real-world data.
Since Carbon emissions are soaring all over the atmosphere, the world suffers from significant problems daily. It has become apparent that reliance on single occupancy vehicle transportation is unsustainable, expensive, and primarily harmful to humankind. Rural areas are frequently abandoned while expanding
transportation infrastructure as urbanisation grows. In rural areas, a lack of adequate and inexpensive transportation options leads to seclusion and restricted access to products, facilities, and job opportunities.
This study explores the potential of alternative transportation methods to improve mobility in rural areas. The objectives of the research are to expand knowledge on sustainable alternative transportation in rural regions and to offer practical solutions for enhancing accessibility and mobility for rural residents.
The study employed a mixed-method approach, including a literature review, a survey, and interviews with participants in two rural regions, Mosel and Oberrothenbach. The findings suggest that the transportation challenges faced by rural inhabitants can be effectively and sustainably addressed through walking and by using alternative transportation modes, such as cycling and public transit. This thesis provides a range of ideas and strategies to improve regulations, programs, and infrastructure related to alternative transportation modes in rural areas. This study dives into the characteristics and requirements
of these places using a combination of quantitative and qualitative surveys done in representative two rural regions to recommend successful alternative transportation solutions of On-Demand Transport Services and Electric or Trolley bus Services for daily commutes. The findings underline the need for flexible, multimodal, and on-demand transit choices, as well as the need for community participation and technology integration.
Natural varnishes have been used for centuries by musical instrument makers to protect the instruments for climatic, aesthetic and acoustic reasons. The effects of varnishes on the protection of the wood surface, as well as their aesthetic parameters, are easier to verify and compare visually, but the comparison of their acoustic effects has always been challenging and debated.
In fact, varnish layers have a small effect on the vibration properties of wood. For example, the effect of a decrease or increase in humidity on the vibration properties of wood is sometimes equal to the effect of several layers of varnish. Because of this small amount of effect, measuring this effect is also difficult and challenging.
Our strategy in this study is to obtain the clearest possible results by comparing the effect of only two types of oil varnishes with completely opposite elastomechanical properties and increasing the number of samples varnished.
The samples were measured before and after each varnish layer using conventional methods for measuring vibration properties, and the average results of the same samples were discussed and analyzed.
Overall, the amber varnish obviously has a more negative effect on the vibration properties of the violin plates compared to the colophony varnish.
The Jupyter ecosystem with JupyterHub and JupyterLab as its most prominent members is the de-facto standard for teaching Python programming and also for research in machine learning and data science. Although the Jupyter project is well documented, there are lots of settings and situations requiring deep knowledge of the internal workings of Jupyter, Linux and related software tools. This report describes three problems and possible solutions arising when installing and configuring a Jupyter-based teaching environment. These three problems are the installation and setup of the autograding tool nbgrader, the interplay between JupyterHub and Linux PAM, and providing access to WebDAV resources for users of JupyterHub.
Natural Language Processing (NLP) is a wide area in computer science and software engineering that finds its application not only in such fields as machine learning or artificial intelligence, but also has very quickly become a very popular solution to various questions and issues raised in the academic field. Those issues include information classification, text analysis, performing a so-called “smart search”, information grouping, providing feedback to academic papers, and many more. The application designed and implemented for this thesis targets solving a similar problem, which is described in details below.
The faculty of Physical Engineering and Informatics at the Westsächsische Hochschule Zwickau uses a software tool called “Quest”. The “Quest” serves as an online platform that enables students to ask questions regarding the module material introduced by the teaching professors. The professors can use these questions in order to keep track of the topics rising the most amount of uncertainty, as well as to clarify those questions during the lectures. Since the modules repeat over time, similar or identical questions are frequently asked by students.
The current functionality of the “Quest” tool, however, does not provide grouping or clustering questions with a similar content into one category. The reason why this is important is because in the future phases of the improvement of the functionality of the “Quest”, professors want to be able to link similar questions with a learning material or online resources that the students can benefit from. This, however, is only possible when each incoming question is labeled with a certain category, and all previously inputted questions associated with this category become visible through the UI of the tool. That would allow students to review the questions referring to the same category that were previously asked by others, as well as to get access to the study materials or resources associated with that category.
The functionality described above would significantly improve the study process and therefore a solution to this problem is needed. One way to solve this issue would be to perform a manual classification of existing questions into associated categories, which given the large size of the question database would be quite time- and effort-consuming. Another option would be to build an application that would be able to analyze the existing dataset of questions and, with the help of the NLP techniques, classify new questions asked by students and identify the similar ones from an existing database.
The tool implemented for the above-mentioned purposes aims to serve as text analytics and classification application that would be able to find and categorize similar text and questions provided by students and/or professors at the Westsächsische Hochschule Zwickau.
This bachelor thesis demonstrates the process of building a software tool using certain NLP techniques, such as tokenization, model training, categorization, NER (Named Entity Recognition), and POS (Parts of Speech tagging), which are defined and described in Chapter 2: “Literature Overview”. The relevance of these techniques in terms of the classification tool built in the context of this thesis is discussed in the section “Selection of NLP tools and techniques” of the “Methodology” chapter.
The aim of this thesis is to describe the methods and software tools used to develop a restful API for text classification, as well as to compare and analyze the effectiveness of two common NLP classifiers – the Naïve Bayes and Logistic Regression (Entropy Model) algorithms.