Refine
Year of publication
- 2020 (105) (remove)
Document type
- Article (peer-reviewed) (68)
- Bachelor Thesis (14)
- Contribution to a Periodical (7)
- Master's Thesis (5)
- Other (5)
- Report (3)
- Working Paper (3)
Has full text
- Yes (105) (remove)
Keywords
- Electrical impedance tomography (5)
- Bone mineral density (4)
- Exercise (4)
- Umfrage (4)
- Germany (3)
- ARDS (2)
- COVID-19 (2)
- Electrical impedance tomopraphy (2)
- Hygiene (2)
- Inertial measurement unit (2)
Adding evidence of the effects of treatments into relevant Wikipedia pages: a randomised trial
(2020)
Prostate segmentation is an essential part of brachytherapy treatment planning, in order to perform the procedure with required accuracy. Nowadays, segmentation of the prostate is still carried out manually during the planning steps, therefore it is a process that can be tedious, time-consuming and prone to inter-observer error. Much effort has been made in development of an computer-based algorithm that can perform prostate segmentation automatically, but only with appearance of deep learning methods, more promising algorithms emerged. So far, convolutional neural networks demonstrated excellent results in fully automatic prostate segmentation. Development of such an algorithm and training an efficient deep learning model is a challenging task, and requires a lot of optimizations. The objective of this study is development and evaluation of an algorithm for image processing based on deep learning methods that can perform fully automatic segmentation of the prostate gland in transrectal ultrasound images. Additionally, we made an overview of the development process, along with challenges and their solutions and demonstrated an algorithm implemented using Python and Tensorflow library, consisted of preprocessing, augmentation, training and validation, postprocessing and validation steps, which is able to successfully carry out fully automatic prostate segmentation with expert level of accuracy. Finally, we presented our implementation of fully convolutional neural network model and results that are encouraging to continue with model improvements and potential clinical application.
Die Biografie- und Erinnerungspflege stellt eine Behandlungsform für die unheilbare Demenzerkrankung dar. Hierbei wird versucht durch Aktivitäten, welche einen Bezug zu der Vergangenheit des Menschen mit Demenz haben, Erinnerungen auszulösen. Dies hilft der an Demenz erkrankten Person ihr Identitätsgefühl zu festigen.
Im Rahmen dieser Bachelorarbeit wurde eine innovative Anwendung entwickelt, welche interaktive und multimediale Bilder für die Biografie- und Erinnerungspflege bereitstellt. Mit diesen Bildern kann der Mensch mit Demenz interagieren, indem er auf einzelne Objekte drückt und daraufhin ein thematisch passendes Medium präsentiert wird. Die interaktiven Bilder werden automatisch, mittels Machine Learning, erstellt. Des Weiteren wurde ein Recommender System implementiert, welches basierend auf den Präferenzen des Menschen mit Demenz, Inhalte für eine Biografie- und Erinnerungspflegesitzung vorschlägt.
Funding is the key to success for a start-up. Since start-ups are often operating in innovative industries, they rarely receive loans from traditional debt lenders such as banks. However, start-ups do have the option of acquiring money for company growth through equity financing. One possibility for this is venture capital. In this scope, Germany is significantly behind the United States of America due to various aspects. This problem shows the relevance of the topic and justifies the critical examination of this subject. This work aims to analyze the German venture capital market, its development over the last 20 years, its advantages on the one hand and its disadvantages on the other hand as well as its future perspectives. Beyond that, the differences between the German and the American venture capital market and its success factors are presented. To answer all research questions, a broad literature review in combi-nation with several conducted expert interviews, which are evaluated on the principle of the qualitative content analysis according to Mayring, is applied. The results of the analysis indicate that there are mainly three fields that are crucial for a successful venture capital market: Political actions, attitudes of the society, and the economic situation. Within these fields, some aspects of Germany are considered worse than in the U.S. In the United States of America politics often intervenes to create better conditions for investments via venture capital. Besides, the risk affinity of society in the U.S. is a major advantage compared to the risk-averse society in Germany. This is complemented by a pronounced start-up mentality in the U.S. and the positive attitude of society towards the failure of a new start-up. In Germany, the opposite can be found in both aspects. Nevertheless, the German venture capital market has developed positively in recent years and has some advantages, such as a wide range of government grants for start-ups and the opportunity for investors to earn high returns on the initial investment. All experts that were interviewed are very confident that venture capital in Germany will continue to develop positively. They identified the reasons for this evolution in an increasing number of start-ups and better skills among the founders, which increases a start-ups' chances of success. For this reason, the experts forecast rising yield expectations, as well as an increasing number of venture capital providers, and venture capital takers. This research also indicates that the volumes of venture capital funds will rise, and the COVID-19-pandemic will accelerate the development of venture capital in Germany. The results of the research clearly show that despite some weaknesses, the German venture capital market has been on a good path for several years, and that there is a high probability that the growth will continue in the future.