Refine
Document Type
- Master's Thesis (10)
- Bachelor Thesis (8)
- Diploma Thesis (1)
Year of publication
- 2018 (19) (remove)
Language
- English (19) (remove)
Keywords
- Unternehmen (3)
- Vektorquantisierung (2)
- Algorithmus (1)
- Ausländer (1)
- Bruchmechanik (1)
- Bruchzähigkeit (1)
- Cluster-Analyse (1)
- Datenbank (1)
- Deutschland (1)
- Forschung (1)
In the following study we evaluated capabilities of how a simple autoencoder can be used to trainGeneralized Learning Vector Quantization classifier. Specifically, we proved that the bottlenecks of an autoencoder serve as an "information filter" which tries to best represent the desired output in that particular layer in the statistical sense of mutual information.
Autoencoder model was trained for purely unsupervised task and leveraged the advantages by learning feature representations. As a result, the model got the significant value of the accuracy. Implementation and tuning of the model was carried out using Tensor Flow [1].
An extra study has been dedicated to improve traditional GLVQ algorithm taken from sklearn-lvg [2] using the bottleneck from an autoencoder.
The study has revealed potential of bottlenecks of an autoencoder as pre-processing tool in improving the accuracy of GLVQ. Specifically, the model was capable to identify 75% improvements of accuracy in GLVQ comparing to original one, which has about 62%. Consequently, the research exposed the need for further improvement of the model in the present problem case.
Community acquired pneumonia (CAP) is a very common, yet infectious and sometimes lethal disease. Therefor, this disease is connected to high costs of diagnosis and treatment. To actually reduce the costs for health care in this matter, diagnosis and treatment must get cheaper to conduct with no loss in predictive accuracy. One effective way in doing so would be the identification of easy detectable and highly specific transcriptomic markers, which would reduce the amount of work required for laboratory tests by possibly enhanced diagnosis capability.
Transcriptomic whole blood data, derived from the PROGRESS study was combined with several documented features like age, smoking status or the SOFA score. The analysis pipeline included processing by self organizing maps for dimensionality and noise reduction, as well as diffusion pseudotime (DPT). Pseudotime enabled modelling a disease run of CAP, where each sample represented a state/time in the modelled run. Both methods combined resulted in a proposed disease run of CAP, described by 1476 marker genes. The additional conduction of a geneset analysis also provided information about the immune related functions of these marker genes.
In this work, we discuss the key role that “conflict minerals” (Gold, Coltan, Cobalt, Tin, Tungsten) play in global supply chains and high-technology industries, and the issues surrounding their extraction and trade in origin
countries, particularly in the African Congo Basin and the Great Lakes Region. We discuss ongoing international efforts to combat violence, child labour and human rights violations at mineral extraction areas, particularly in the Democratic Republic of the Congo (DRC), where very large mineral reserves have been discovered. We present the OECD Due Diligence Guidance for Responsible Supply Chains of Minerals from Conflict-Affected and High-Risk Areas, and the
GOTS MineralTrace mineral proof-of-origin and trade chain certification solution developed by ibes AG in Germany, which automates and simplifies the implementation of the OECD Guidance. We discuss a pilot project in DRC involving the GOTS GoldTrace application, based on the MineralTrace platform. We point out MineralTrace’s benefits and its limitations. We analyse possible solutions to said limitations, including an analysis of blockchain-based transactional information exchange and record keeping systems, and finally we propose a new MineralTrace Application Programming Interface (API) that solves current limitations, introduces configuration flexibility for client applications, introduces workflow flexibility to adapt MineralTrace to any country or region, and simplifies data export functionality.
Soft Learning Vector Quantisation (SLVQ) andRobust Soft Learning Vector Quantisation (RSLVQ) are supervised data classification methods, that have been applied successfully to real world classification problems. The performance of SLVQ and RSLVQ, however, reduces, when they are applied tomore complicated classification problems. In this thesis, we have introducedmodi-fications to SLVQand RSLVQ, in order to havemore capable versions of them. A few possibilities to modify SLVQ and RSLVQ are considered, some of them are not successful enough and they have been included for the sake of completeness. The fruits of the thesis are plenty, including Tangent Soft Learning Vector Quantisation-Strong (TSLVQ-S), together with its more stable version Tangent Robust Soft Learning Vector Quantisation-Strong (TRSLVQ-S), Attraction Soft Learning Vector Quantisation (ASLVQ) and Grassmannian Soft Learning Vector Quantisation (GSLVQ).
DropConnect (the generalization of Dropout) is a very simple regularization technique that was introduced a few years ago and has become extremely popular because of its simplicity and effectiveness. In this thesis, a suitable architecture for applying DropConnect to Learning Vector Quantization networks is proposed along with a reference implementation and experimental results. Inmany classification tasks, the uncertainty of themodel is a vital piece of information for experts. Methods to extract the uncertainty and stability using DropConnect are also proposed and the corresponding experimental results are documented.
The subject of the following paper is the mental well-being of employees at their work and how the leader can improve this well-being using positive psychology. The paper is compilatory in nature because it uses research and literature of experts to analyse how employee mental well-being can be further stimulated. The expert literature is used to present tools, but also to demonstrate the effectiveness of these tools through real-life case studies and evidence. The paper wishes to inform persons, leaders, and entire organizations how positive psychology can be beneficial to organizational members’ well-being in the long term. Using a compilation of positive psychology literature and reallife case studies’ analysis, the informative purpose of the thesis can be achieved.
This thesis work is focusing on the optimization and improvement of IP network and IP transit operations and strategy as well as service offerings. Therefore, this thesis tries to give suggestions at different areas of engineering, business, strategy and operational contexts. This thesis is written in English, as this topic itself is mainly handled in English language too. The first part will try to identify and evaluate methods which are helpful to improve the practical work which will be focused in the second part of this work.
Internationalization and business expansion appear to be the most challenging processes in business conduction today. Every step of the foreign market entry process and overseas operations establishment is full of obvious risks and hidden pitfalls. Theoretical background, multiplied with the vital practice, is playing the key role in such a complicated business process; such information can be used as a guideline by further market entrants and players. At present, Germany with its well-developed engineering industry represents a broad space for research of internationalization process in its different forms, as well as can show both successful and negative results of foreign market entries.
Object detection and classification is active field of research inmachine learning and computervision. Depending on the application there are different limitations to adjust to, but also possibilities to take advantage of. In my thesis, We focus on classification and detection of video sequence during night-time and the proposed method is robust since it does use image thresholding [8] which is commonly use in other methods and the thesis uses histograms of oriented gradients (HOG) [37] as features and support vector machine (SVM) [74] as classifier. It is of great importance that the extracted features from the images should be robust and distinct enough to help the classifier distinguish between high-beam and a low-beam. The classifier is part of the object detection which predicts whether or not a testing image matches one group or the other. In our case that is predicting whether or not an image belongs to high or low-beam sequence.