|
|
Deep Learning for Medical Image Analysis
Bíl, Tomáš ; Kodym, Oldřich (referee) ; Španěl, Michal (advisor)
The goal of this thesis is developing convolutional neural network which is able to classify if x-ray images are suitable for cephalometry analysis. Four networks were created and trained on a dataset for this purpose. Two of them are VGG type, one is based on UNet and one is Resnet. The dataset was generated from ct scan images. VGG network with four blocks has got the best results. Measured accuracy performed on test dataset is 97%.
|
|
|
Deep Learning for Medical Image Analysis
Bíl, Tomáš ; Kodym, Oldřich (referee) ; Španěl, Michal (advisor)
The goal of this thesis is developing convolutional neural network which is able to classify if x-ray images are suitable for cephalometry analysis. Four networks were created and trained on a dataset for this purpose. Two of them are VGG type, one is based on UNet and one is Resnet. The dataset was generated from ct scan images. VGG network with four blocks has got the best results. Measured accuracy performed on test dataset is 97%.
|
|
|
Staff performance and motivation in the organization (and design IT to support them)
Biľ, Tomáš ; Surynek, Alois (advisor) ; Chlapek, Dušan (referee)
Paper summarizes the importance of motivation and performance of employees in the organization. The primary goal of this paper is to propose solutions to increase motivation and thus performance. Meet this target would require the implementation of many activities, from finding present, the IS architecture, through detailed analysis of individual systems, which affect workers. Important too was the definition of where all the motivation and performance in man takes and how it can be measured. In the practical part I have done, according to gained experience, using the LMI survey questionnaire to identify weak areas of performance motivation. These results, I finally offered advice and firstly from a psychological perspective, and secondly in terms of IT and its main information system, the workers who come into contact every day and therefore has a huge impact on them. Contribution of the author of this thesis was to identify and increase motivation, through analysis and recommendations specified by the selected methodologies.
|
|
|
Optimization processes IT Help Desk department in a large enterprise
Biľ, Tomáš ; Kunstová, Renáta (advisor) ; Kapitán, Petr (referee)
The goal of this paper is the IT helpdesk process analysis and its optimization. As a part of the analysis, existing processes are described, completed tasks, existing problems, weak spots, data collecting applications and request resolving solutions are analysed. Currently there are no detailed guidelines and measures within the company as to providing IT support. The main part of this paper is to provide directions on how to optimize chosen processes and improve data collecting applications. This is achieved by simplifying forms, introducing feedback clarification and by change of approach. Furthermore, there are changes to requirement solving applications. Existing shortcomings in the companys processes -- IT helpdesk department -- are solved e.g. by using the Method " TSP - Traveling Salesman Problem" -- applied to technicians travel among individual branches.
|
guest ::
RSS feed.