Refine
Year of publication
Document Type
- Master's Thesis (66)
- Bachelor Thesis (29)
- Study Thesis (13)
- Conference Proceeding (8)
- Article (reviewed) (6)
- Book (1)
- Other (1)
Conference Type
- Konferenzartikel (4)
- Konferenzband (4)
Language
- English (124) (remove)
Is part of the Bibliography
- no (124) (remove)
Keywords
- COVID-19 (13)
- Government Measures (13)
- Corona (9)
- Crisis (8)
- IT-Sicherheit (8)
- Export (7)
- Maschinelles Lernen (5)
- Deep learning (4)
- Communication Systems (3)
- Computersicherheit (3)
Institute
- Fakultät Medien (M) (ab 22.04.2021) (31)
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (28)
- Fakultät Wirtschaft (W) (24)
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (16)
- Fakultät Elektrotechnik und Informationstechnik (E+I) (bis 03/2019) (15)
- IfTI - Institute for Trade and Innovation (13)
- Fakultät Medien und Informationswesen (M+I) (bis 21.04.2021) (11)
- ivESK - Institut für verlässliche Embedded Systems und Kommunikationselektronik (4)
- INES - Institut für nachhaltige Energiesysteme (2)
- IUAS - Institute for Unmanned Aerial Systems (1)
Open Access
- Closed (52)
- Closed Access (41)
- Open Access (31)
- Diamond (5)
- Gold (1)
Much of the research in the field of audio-based machine learning has focused on recreating human speech via feature extraction and imitation, known as deepfakes. The current state of affairs has prompted a look into other areas, such as the recognition of recording devices, and potentially speakers, by only analysing sound files. Segregation and feature extraction are at the core of this approach.
This research focuses on determining whether a recorded sound can reveal the recording device with which it was captured. Each specific microphone manufacturer and model, among other characteristics and imperfections, can have subtle but compounding effects on the results, whether it be differences in noise, or the recording tempo and sensitivity of the microphone while recording. By studying these slight perturbations, it was found to be possible to distinguish between microphones based on the sounds they recorded.
After the recording, pre-processing, and feature extraction phases we completed, the prepared data was fed into several different machine learning algorithms, with results ranging from 70% to 100% accuracy, showing Multi-Layer Perceptron and Logistic Regression to be the most effective for this type of task.
This was further extended to be able to tell the difference between two microphones of the same make and model. Achieving the identification of identical models of a microphone suggests that the small deviations in their manufacturing process are enough of a factor to uniquely distinguish them and potentially target individuals using them. This however does not take into account any form of compression applied to the sound files, as that may alter or degrade some or most of the distinguishing features that are necessary for this experiment.
Building on top of prior research in the area, such as by Das et al. in in which different acoustic features were explored and assessed on their ability to be used to uniquely fingerprint smartphones, more concrete results along with the methodology by which they were achieved are published in this project’s publicly accessible code repository.
Total Cost of Ownership (TCO) is a key tool to have a complete understanding of the costs associated with an investment, as it allows to analyze not only the initial acquisition costs, but also the long-term costs related to operation, maintenance, depreciation, and other factors. In the context of the cement industry, TCO is especially important due to the complexity of the production processes and the wide variety of components and machinery involved in the process.
For this reason, a TCO analysis for the cement industry has been conducted in this study, with the objective of showing the different components of the cost of production. This analysis will allow the reader to gain knowledge about these costs, in the industrial model will be to make informed decisions on the adoption of technologies and practices that will allow them to reduce costs in the long run and improve their operational efficiency.
In particular, this study pursues to give visibility to technologies and practices that enable the reduction of carbon emissions in cement production, thus contributing to the sustainability of industry and the protection of the environment. By being at the forefront of sustainability issues, the cement industry can contribute to the achievement of environmentally friendly technologies and enable the development of people and industry.
The Oxyfuel technology has been selected as a carbon capture solution for the cement industry due to its practical application, low costs, and practical adaptation to non-capture processes. The adoption of this technology allows for a significant reduction in CO2 emissions, which is a crucial factor in achieving sustainability in the cement manufacturing process.
Carbon capture storage technologies represent a high investment, although these technologies increase the cost of production, the application of Oxyfuel technology is one of the most economically viable as the cheapest technology per capture according to the comparison. However, this price increase is a technical advantage as the carbon capture efficiency of this technology reaches 90%. This level of efficiency leads to a decrease in taxes for the generation of CO2 emissions, making the cement manufacturing process sustainable.
Schluckspecht project
(2022)
The objective of this thesis is the conceptual design of a battery management system for the first prototype of the UWC (University of the Western Cape) Modular Battery System. The battery system is a lithium-ion battery that aims to be used in renewable energy systems and for niche electric vehicles such as golf carts.
The concept that is introduced in this thesis comprises the parameter monitoring, the safety management and has its main focus on an accurate state of charge estimation.
Another battery system that was already implemented is used as base for the parameter monitoring and the safety management for the new battery management system. In contrast to that, the concept for the state of charge estimation must be developed completely.
Different methods for the state of charge estimation which are based on the measured voltage, current and temperature are discussed, evaluated and the chosen method is conceived in this thesis. The method used for the state of charge estimation is different for the time when the battery is active than when it is inactive. During charge and discharge Coulomb counting is used and when the cell is inactive voltage versus state of charge lookup tables are used to update the estimation.
To have an accurate estimation when the cell is inactive only for a short time, a model of the voltage relaxation is used to predict the voltage when the cells are in equilibrium. This allows the algorithm to reset the state of charge that is estimated by Coulomb counting – which tends to have a growing error over time – frequently.
To evaluate the accuracy of the voltage prediction, cell tests were executed where the voltage relaxation was sampled. The recursive least square method to predict the end voltage was tested with a MATLAB programme. With the help of voltage versus state of charge lookup tables it was possible to determine the state of charge accuracy with the accuracy of the voltage prediction.
To date, many experiments have been performed to study how the internal geometrical shapes of the annular liquid seal can reduce internal leakage and increase pump efficiency. These can be time-consuming and expensive as all rotordynamic coefficients must be determined in each case.
Nowadays, accurate simulation methods to calculate rotordynamic coefficients of annular seals are still rare. Therefore, new numerical methods must be designed and validated for annular seals.
The present study aims to contribute to this labour by providing a summary of the available test rig and seals dimensions and experimental results obtained in the following experiments:
− Kaneko, S et al., Experimental Study on Static and Dynamic Characteristics of Liquid Annular Convergent-Tapered Seals with Honeycomb Roughness Pattern (2003) [1] − J. Alex Moreland, Influence of pre-swirl and eccentricity in smooth stator/grooved rotor liquid annular seals, static and rotordynamic characteristics (2016) [2]
A 3D CAD simulation with Siemens NX Software of the test rig used in J. Alex Moreland’s experiment has been made. The following annular liquid seals have also been 3D modelled, as well as their fluid volume:
− Smooth Annular Liquid Seal (SS/GR) (J. Alex Moreland experiment)
− Grooved Annular Liquid Seal (GS/SR)
− Round-Hole Pattern Annular Liquid Seal (𝐻𝑑=2 mm) (GS/SR)
− Straight Honeycomb Annular Liquid Seal (GS/SR)
− Convergent Honeycomb Annular Liquid Seal (No. 3) (GS/SR)
− Smooth Annular Liquid Seal (SS/SR) (S. Kaneko experiment)
In the case of the seals used in S. Kaneko’s experiments, the test rig has been adapted to each seal, defining interpart expressions which can be easily modified.
Afterwards, it has been done a CFD simulation of the Smooth Annular Liquid Seal using Ansys CFX Software. To do so, the fluid volume geometry has been simplified to do a first approximation. Results have been compared for an eccentricity 𝜀0=0.00 for the following ranges of rotor speeds and differential of pressure:
− Δ𝑃= 2.07, 4.14, 6.21, and 8.27 bar,
− 𝜔= 2, 4, 6 and 8 krpm.
Even results obtained have the same trend as the one proportionated by the literature, they cannot be validated as the error is above 5%. It is also observed that as the pressure drop increases, the relative error decreases considerably.
The COVID-19 pandemic has led to an economic downturn in the Slovak Republic. To bridge corporate liquidity problems the Slovakian Government has introduced several support measures. The investigation discusses the effectiveness of the measures imposed. Based on theoretical foundations, the research question is empirically examined by using a qualitative expert survey. As the automotive industry plays a leading role in Slovakia, the research conducted is oriented towards the financing phases, a typical automotive exporter is undergoing. As a result of the research, bridging loans and government grants were identified as the most important measures. Additionally, tendencies towards political recommendations for action were identified. The research explored, that the Slovakian Government should focus on meeting the short-term liquidity needs, boosting exports and promoting innovation as well as considering a support package for the automotive industry.
How can manufacturers or service companies provide better services with connected products, without having acquired a powerful IT infrastructure nor the competences for software development?
Today companies can appeal to a relocated-IT-infrastructure provider, which is called Cloud.
Consequently, they do not have to manage and take care of the safety/security aspect, the updates and the breakdown of the infrastructure internally, as those are all managed by the provider.
It is possible to outsource the development of the software of the connected product to an external company. However, the question now is how fast this company can juggle from one Cloud to another in order to fulfil their clients wishes?
neverMind offers a solution based on a multi-protocols-platform linking the different connected products to a multitude of Clouds without having to redesign the whole communication stack/building block for each change in the Cloud-solution. This is the object of my thesis.
The development follows the V-Model, the first steps to understand the complexity of the project were the realisation of the product technical and architectural specifications. The last step before the Implementation was to design in details the progress and the process of every parts of the platform.
The outcome of the requirements analysis led me to divide the project in two parts:
• a “General Interface” acting as a gateway between the Client-application and “Cloud-modules”
• the “Cloud-modules” themselves.
So far, the specifications are drown up; the General Interface and a client example are coded, as well as a first Cloud-module template.
The objective of this thesis is the quantification and qualification of neonicotinoid insecticides using thin-layer chromatography (TLC). Neonicotinoids are a relatively new form of pesticides, which have been proven to be extremely lethal to the honey bee, Apis mellifera. In this paper six forms of neonicotinoid insecticides (i.e. Acetamiprid, Thiacloprid, Imidacloprid, Clothianidin, Thaimethoxam, and Nitenpyram) are analysed. The initial steps are to first find a suitable mobile phase eluent, followed by the search for a reagent causing a luminescence effect of the neonicotinoids on a TLC plate. Subsequently, a calibration method is then used to find the detection limit of this TLC experiment. The aim is, therefore, to achieve a standard method of quantifying and qualifying neonicotinoids via TLC. Whilst a suitable mobile phase has been established, an optimal fluorescent reagent has yet to be found and more research on the subject must be carried out.
In the field of network security, the detection of intrusions is an important task to prevent and analyse attacks.
In recent years, an increasing number of works have been published on this subject, which perform this detection based on machine learning techniques.
Thereby not only the well-studied detection of intrusions, but also the real-time capability must be considered.
This thesis addresses the real-time functionality of machine learning based network intrusion detection.
For this purpose we introduce the network feature generator library PyNetFlowGen, which is designed to allow real-time processing of network data.
This library generates 83 statistical features based on reassembled data flows.
The introduced performant Cython implementation allows processing individual packets within 4.58 microseconds.
Based on the generated features, machine learning models were examined with regard to their runtime and real-time capabilities.
The selected Decision-Tree-Classifier model created in Python was further optimised by transpiling it into C-Code, what reduced the prediction time of a single sample to 3.96 microseconds on average.
Based on the feature generator and the machine learning model, an basic IDS system was implemented, which allows a data throughput between 63.7 Mbit/s and 2.5 Gbit/s.
The identification of vulnerabilities is an important element of the software development process to ensure the security of software. Vulnerability identification based on the source code is a well studied field. To find vulnerabilities on the basis of a binary executable without the corresponding source code is more challenging. Recent research has shown how such detection can be performed statically and thus runtime efficiently by using deep learning methods for certain types of vulnerabilities.
This thesis aims to examine to what extent this identification can be applied sufficiently for a variety of vulnerabilities. Therefore, a supervised deep learning approach using recurrent neural networks for the application of vulnerability detection based on binary executables is used. For this purpose, a dataset with 50,651 samples of 23 different vulnerabilities in the form of a standardised LLVM Intermediate Representation was prepared. The vectorised features of a Word2Vec model were then used to train different variations of three basic architectures of recurrent neural networks (GRU, LSTM, SRNN). For this purpose, a binary classification was trained for the presence of an arbitrary vulnerability, and a multi-class model was trained for the identification of the exact vulnerability, which achieved an out-of-sample accuracy of 88% and 77%, respectively. Differences in the detection of different vulnerabilities were also observed, with non-vulnerable samples being detected with a particularly high precision of over 98%. Thus, the methodology presented allows an accurate detection of vulnerabilities, as well as a strong limitation of the analysis scope for further analysis steps.