Refine
Document Type
- Bachelor Thesis (66)
- Master's Thesis (54)
- Conference Proceeding (25)
- Diploma Thesis (12)
Year of publication
Language
- English (157) (remove)
Keywords
- Blockchain (12)
- Maschinelles Lernen (6)
- Unternehmen (6)
- Ethereum (4)
- Algorithmus (3)
- Bioinformatik (3)
- Bitcoin (3)
- Kundenmanagement (3)
- Proteine (3)
- Softwareentwicklung (3)
Institute
- Angewandte Computer‐ und Biowissenschaften (42)
- 03 Mathematik / Naturwissenschaften / Informatik (28)
- 06 Medien (28)
- Wirtschaftsingenieurwesen (17)
- 01 Elektro- und Informationstechnik (7)
- 04 Wirtschaftswissenschaften (4)
- 02 Maschinenbau (2)
- Sonstige (2)
- 05 Soziale Arbeit (1)
- Ingenieurwissenschaften (1)
This master thesis covers the topics of Customer relationships formation in the IT-outsourcing market on the example of “ABC” company. Most works related to the topic IT outsourcing cover the problems of implementation of IT services and the process of providing them to the customers and mostly all the issues are covered from the perspec-tive of consumers. Thus, problems and results of outsourcing providers of IT services remain almost uncovered. This master thesis is to reveal the specific features of IT out-sourcing business in Belarus and to develop an approach to the formation and construc-tion of a system of relationships between the company and its clients as a source of competitiveness increase.
At a global level, different studies disclose that transport systems are responsible for 25% of CO2 emissions. In the context of sustainable mobility, one of the challenges in the short term is associated with the research and improvement of alternative fuels, which should allow a fast decrease in the generation of greenhouse gases due to sustainable transport means. In this sense, green hydrogen can play a fundamental role. Green hydrogen is the basis for producing synthetic fuels, which can replace oil and its derivatives. Synthetic fuels or e-fuel are hydrocarbons produced from carbon dioxide (CO2) and green hydrogen (H2) as the only raw materials. H2 or efuel could be used in many sectors (manufacturing, residential, transportation, mining and other industries). In this study, different applications of hydrogen are evaluated by techno-economic analysis. The main variable that affects the production of hydrogen and its derivatives is the cost of electricity. Considering the renewable energy potential of Chile, it is feasible to develop in Chile the green hydrogen production as an energy vector, which would be technically and economically viable, together with the environmental benefits
In this paper, we designed, implemented, and tested a special surveillance camera system based on a combination of classical image processing algorithms. The system’s sub-objective consists of tracking experimental vehicles driving on a defined trajectories (Rail) in real time. Furthermore, it analyzes the scene to collect additional vehicles & rail-related information. The system then uses the gathered data to reach its main objective which confines oneself in independently predicting vehicles collision. Consequently, we propose a hybrid method of detecting and tracking ATLAS-vehicles efficiently. To detect the vehicle at the beginning of the video, periodically every n-frame, and in the case where the tracked vehicle has been lost, we used Histogram Back-Projection. By contrast, Kernelized correlation filter is used to track the detected vehicles. Combining these two methods provides one of the best trade-offs between accuracy and speed even on a single processing core. The proposed method achieves the best performance compared with three different approaches on a custom dataset.
Standard assembly time is an important piece of data in product development that is used to compare different product variants or manufacturing variants. In the presented approach, standard time is created with the use of a decision tree regarding standard manual and machine-manual operations, taking into consideration product characteristics and typical tools, equipment and layout. The analysed features include, among others: information determined during product development, such as product structure, parts characteristics (e.g. weight, size), connection type, as well as the information determined during assembly planning: tools (e.g. hand screw driver, power screw driver, pliers), equipment (e.g. press, heater), workstation layout (e.g. distance, way of feeding). The object-attribute-value (OAV) framework was applied for the assembly characteristic. An example of the decision tree application to predict standard assembly time was presented for a mechanical subassembly. The case study was dedicated to standard time prediction for a bearing assembly. The presented approach is particularly important for the enterprises which offer customized products.
Sensor fusion is an important and crucial topic in many industrial applications. One of the challenging problems is to find an appropriate sensor combination for the dedicated application or to weight their information adequately. In our contribution, we focus on the application of the sensor fusion concept together with the reference to the distance-based learning for object classification purposes. The developed machine learning model has a bi-functional architecture, which learns on the one side the discrimination of the data regarding their classes and, on the other side, the importance of the single signals, i.e., the contribution of each sensor to the decision. We show that the resulting bi-functional model is interpretative, sparse, and simple to integrate in many standard artificial neural networks.
Learning Vector Quantization (LVQ) methods have been popular choices of classification models ever since its introduction by T. Kohonen in the 90s. These days, LVQ is combined with Deep Learning methods to provide powerful yet interpretable machine-learning solutions to some of the most challenging computational problems.
However, techniques to model recurrent relationships in the data using prototype methods still remain quite unsophisticated. In particular, we are not aware of any modification of LVQ that allows the input data to have different lengths. Needless to say, such data is abundant in today's digital world and demands new processing techniques to extract useful information. In this paper, we propose the use of the Siamese architecture to not only model recurrent relationships within the prototypes but also the ability to handle prototypes of various dimensions simultaneously.
Prototype-based Vector Quantization is one of the key methods in data processing like data compression or interpretable classification learning. Prototype vectors serve as references for data and data classes. The data are given as vectors representing objects by numerical features. Famous approaches are the Neural Gas Vector Quantizer (NGVQ) for data compression and Learning Vector Quantizers (LVQ) for classification tasks. Frequently, training of those models is time consuming. In the contribution we discuss modifications of these algorithms adopting ideas from quantum computing. The aim for this is a least twofold: First quantum computing provides ideas for enormous speedup making use of quantum mechanical systems and inherent parallelization.
Second, considering data and prototype vectors in terms of quantum systems, implicit data processing is performed, which frequently results in better data separation. We will highlight respective ideas and difficulties when equipping vector quantizers with quantum computing features.
Marker-based systems can digitally record human movements in detail. Using the digital biomechanical human model Dynamicus, which was developed by the Institut für Mechatronik, it is possible to model joint angles and their velocities such accurately that it can be used to improve motion analysis in competitive sports or for ergonomic evaluation of motion sequences. In this paper, we use interpretable machine learning techniques to analyze the gait. Here, the focus is on the classification between foot touchdown and drop-off during normal walking. The motion data for training the model is labeled using force plates. We analyze how we could apply our machine learning models directly on new motion data recorded in a different scenario compared to the initial training, more precise on a treadmill. We use the properties of the interpretable model
to detect drift and to transfer our model if necessary.
This article aims to explain mathematically, why the so called double descent observed by Belkin et al., Reconciling modern machine-learning practice and the classical bias-variance trade-off, PNAS 116(32) (2019), p. 15849-15854, occurs on the way from the classical approximation regime of machine learning to the modern interpolation regime. We argue that this phenomenon may be explained by a decomposition of mean squared error plus complexity into bias, variance and an unavoidable irreducible error inherent to the problem. Further, in case of normally distributed output errors, we apply this decomposition to explain, why LASSO provides reliable predictors avoiding overfitting.
We use machine learning for the selection and classification of single–molecule trajectories to replace commonly used user–dependent sorting algorithms. Measured fluorescence time series of labelled single molecules need to be sorted into ’good molecules’ and ’bad’ molecules before further kinetic and thermodynamic analysis.
Currently, processing, sorting and analysis of the data is mainly done with the help of laboratory specific programs.
Although there are freely available programs for processing smFRET data, they do not offer ’molecular sorting’ or it is purely empirical. Only recently, new approaches came up to solve this problem by means of machine learning. Here, we describe a sound terminology for molecular sorting of smFRET data and present an efficient workflow for manual annotation followed by the training of the ML algorithm. Descriptive statistics of our generated dataset are provided and will serve as the basis for supervised ML-based molecular sorting algorithms yet to be developed.
