Refine
Document type
- Article (peer-reviewed) (1)
- Bachelor Thesis (1)
- Master's Thesis (1)
Language
- English (3)
Keywords
- Segmentation (3) (remove)
Course of studies
This bachelor thesis is designed to develop a segmented sales approach using the target costing method. Herby it is important to note that this thesis is a practical one, on behalf of a German high-tech company. The assignment was to create feasible action points, which will later assist during the company's sales approach improvements.
The theoretical part of this thesis deals with the basics of product segmentation, process analysis and sales channel analysis. Afterwards, the theoretical background for the sales cost analysis, target costing method and sales scenarios is elaborated. The aim was to define major elements later applied in this thesis.
The second part of this thesis applies the theoretical knowledge established in the first chapter to the situation at the company. The results of the project show an importance to focus on one specific product, due to a high level of competition. Currently, the sales scenario consists of the direct and the indirect sales channel. As a consequence, sales costs are very high. The third chapter gives recommendations for each chapter. Results show the need for simplicity and less reporting as well as one maintained document archive system. The third part shows the importance of establishing an online channel. Furthermore, it is advised to establish one strategy for the sales channels and to communicate this to coordinate different sales channels effectively. The fourth and fifth parts deal with the sales cost and target costing recommendations, highlighting marketing and HR costs as the main cost driver. One solution to reduce the sales cost is to establish the online channel, saving travel costs and to reevaluate marketing activities. That way, the target of limiting the sales cost to 15% of the revenue could be met.
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.