TY - THES A1 - Dogotari, Marcel T1 - Hardware Design and RF Performance Evaluation of a Long Range 2.4 GHz Radio Module N2 - Low–power, long–range wireless solutions are needed for transmission of environmental and industrial monitoring data from remote, battery–driven sensors. Chirp spread spectrum (CSS) modulation techniques are able to meet these requirements. A CSS–based radio module was designed to operate in the 2.4 GHz frequency band, whose advantages are worldwide availability, lack of duty–cycle restrictions and a broad spectrum. The module’s power consumption is satisfactory, but its range has to be improved. The accuracy of time-of-flight (ToF) distance estimation, an extra feature of the module, has not been evaluated. Impedance matching, transmission lines and printed circuit board design are among the practical aspects discussed, while ToF ranging and orthogonality of CSS signals are considered from a theoretical point of view. KW - Long–range radio module KW - Printed circuit board design KW - Transmission lines and impedance matching KW - Chirp spread spectrum KW - Time-of-flight ranging Y1 - 2017 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:1383-opus4-2158 ER - TY - THES A1 - Lam, Hoi Ying T1 - Radar Signal Distortion caused by Directional Vibration of a 24 GHz FMCW System N2 - This thesis is an initial attempt to investigate the influence of mechanical vibrations on the 24 GHz FMCW radar developed by IMST GmbH and develop a simple vibration compensation model for the human tracking algorithm. The project objectives are to determine the radar signal distortion caused by vibrations theoretically, conduct simulations to evaluate the effects of vibrations on the human tracking process, and develop a basic model to compensate the disturbing vibrations. The single radar pulse simulations conclude that when the radar is vibrating at a low frequency, the signal would not be distorted if the change of phase of the intermediate frequency is less than half a resolution cell. While the results from the multiple radar pulses simulations reveal that factors like the SNR value, vibrating amplitude and the target’s velocity would influence the human tracking process. The higher the SNR value, vibrating amplitude and target’s velocity, the more the detected ghost targets when there is only one target presence. A signal demodulation method is then proposed which indicate the possibility in reducing the disturbance caused by the vibrations. KW - FMCW Radar KW - Vibration KW - Human Tracking KW - Simulation KW - Compensation Y1 - 2016 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:1383-opus4-2164 ER - TY - THES A1 - Prüm, Moritz T1 - Automated Hyperspectral Field Scanner for Vegetation Monitoring N2 - Vegetation monitoring is an important tool in a variety of fields, e.g. precision agriculture and plants’ phenotyping. The system design of existing non-invasive ground based systems is usually not open-source. Therefore, these systems cannot be reliably modified and thus are not suitable to advanced applications, such as prototyping of new sensors. This thesis describes the development of a ground based hyperspectral monitoring system for use in plant science and sensor testing. A well-documented and automated working prototype has been developed and initial tests show promising results. Further work in system modularity and redundancy is needed. KW - Embedded systems KW - Hyperspectral imaging KW - Low-power design KW - System integration KW - Vegetation monitoring Y1 - 2017 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:1383-opus4-2247 ER - TY - THES A1 - Shrestha, Manjil T1 - Development of a Language Model for Medical Domain N2 - Language models are widely used as a representation of written language in various machine learning tasks, with the most commonly used model being Bidirectional Encoder Representations from Transformers (BERT). It was shown that the prediction quality strongly benefits from language model pre-training on domain-specific data. The publicly available models, though are always trained on Wikipedia, news or legal data, thereby missing the domain specific knowledge about medical terms. In this thesis, we will train a BERT language model on medical data and compare performance with domain-unspecific language models. The dataset used for this purpose is the Non-technical Summaries - International Statistical Classification of Diseases (NTS-ICD) task of classification of animal experiment descriptions into International Statistical Classification of Diseases (ICD) categories. KW - Mult-label classification KW - ICD-10 Codes KW - Fine-tuning KW - German BERT NTS classification KW - Transfer learning Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:1383-opus4-7405 ER - TY - THES A1 - Dai, Chenke T1 - Testing the Influence of Platinum Load on Performance of Fuel Cells Using Impedance Spectroscopy and Current Voltage Measurement N2 - Increasing Platinum catalyst loading in proton exchange membrane fuel cell is supposed to increase the performance and lifetime. However, Platinum is an extremely expensive material. Therefore, increasing loading could contribute to the price significantly. The aim of this work is to measure the proton exchange membrane fuel cell performance under three different catalyst loading on cathode and determine the optimum loading for performance in these three tested loading levels. The tested cathodic loadings are 0.3 mg/cm2, 0.6 mg/cm2 and 0.9 mg/cm2. By applying two methods: current-voltage measurement and electrochemical impedance spectroscopy, the open circuit voltages, polarization, power output and impedance were recorded. From the experiment, it is found that the internal resistance decreased with increasing Platinum loadings on the cathode. The simulation results indicate this change is mostly contributed by decreasing cathodic resistance. With increasing cathodic Platinum loading, the cathodic resistance decreases. It is also found during experiments, the polarization, open circuit voltage and power performance first increased and then stayed at same level. These indicators showed best performance at 0.6 mg/cm2 cathodic loading level. Combined with simulation results, the large impedance value of constant phase element in equivalent model for 0.9 mg/cm2 loading is considered as the reason why the power performance stop improving. Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:1383-opus4-7730 ER - TY - THES A1 - Navid, Sina T1 - Real-Time Web Application for Decision Support in Groundwater Management N2 - Groundwater is an essential resource that is used for a wide range of purposes all over the world, and retaining this important natural asset demands that it be managed and utilized sustainably. Despite the fact that groundwater is frequently abundant and widely utilized, it is difficult and costly to precisely estimate water levels when compared to surface water systems. Groundwater managers require improved digital tools to understand the system state of the aquifers they seek to interact with sustainably (e.g., accessing real-time updates on the state of the water table to check whether pumping operation is achieving or violating a desired drawdown target.) Here we propose a workflow for a pilot region that (a) temporally interpolates irregularly, manually-measured water levels in a real observation network using data from neighboring sensor-equipped observation, using a multiple linear regression approach to reduce complexity. The resulting interpolated time series are then used in conjunction with the sensor data to come up with (b) spatial interpolations of the groundwater field over time using inversed distance weighting (IDW) at any given point in time. From that, spatial estimates of the groundwater field can be transformed into maps of deviation from drawdown targets. We visualize these targets and their temporal evolution for groundwater managers in real-time on a web application. The web application displays these maps together with operational data (e.g., extraction rates) and meteorological data (recent and forecasted precipitation rates). It serves as a foundational tool for groundwater management when making control decisions to save energy in climate change mitigation and to reduce costs. KW - Groundwater KW - Web application KW - Plotly Dash KW - Data Engineering KW - Data visualizing Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:1383-opus4-17550 ER - TY - THES A1 - Ghosh, Anup Kumar T1 - Analyzing individual chickens' life data to predict egg and growth performance N2 - The 2022 ban on killing male chicks, implemented in Germany and France, tackled ethical problems within egg-laying hen farming. Because of this policy, alternative poultry production methods were created to better meet animal welfare guidelines. To meet this challenge, the University of Bonn launched research into dual-purpose chickens, specifically the British Ixworth breed. Integrating male and female chicken farming offers a new, innovative solution to ethical and sustainability issues in traditional farming by combining egg and meat production. The importance of this research for revolutionizing poultry farming cannot be overstated (Becker et al., 2023). A University of Bonn research team is studying this alternative farming method to determine its productivity and viability. To meet industry needs while prioritizing animal welfare, they evaluate dual-purpose chicken potential by analysing egg (number and weight) and meat (weight) yields. This thesis has four sections, exploring different facets of dual-purpose chickens across four generations via diverse statistical and machine learning methods. First, it examines existing research on various facets of analysing and forecasting individual chicken egg and growth data. It further explores Becker et al.’s 2023 study, “The British Ixworth: individual growth and egg production of a purebred dual-purpose chicken.” Moreover, the linear regression, SVR, KNN, and decision tree models were applied to this data for advanced analysis and prediction. The thesis’s second part details the methodology, including requirements analysis and dataset preparation. This thesis's third section details how data from four generations of chicken life were analysed to predict future egg production and individual chicken growth. Across generations, individual chickens' average body weight and egg weight all showed an increase in the results. Predictions from linear regression and decision tree models show an increase in individual chickens' growth across generations to come. Egg production forecasts were better with the KNN model. This research will use advanced statistical methods and machine learning to model and assess the generational performance of dual-purpose chickens. These tools will forecast future egg and meat production, thus giving key insights to enhance breeding programs. This research aims to optimize dual-purpose chicken production for growth and egg-laying performance. The researchers eagerly anticipate the results, which will help to shape their future poultry farming projects. KW - Dual-purpose chickens KW - British Ixworth KW - Poultry farming KW - Machine learning KW - Statistical analysis KW - Predictive modeling KW - Linear regression KW - K-nearest neighbors (KNN) KW - Support Vector KW - Regression (SVR) KW - Decision tree KW - Sustainable agriculture KW - Generational analysis KW - Chicken growth prediction KW - Egg-laying performance KW - Alternative poultry production Y1 - 2025 ER -