|
|
2 + 1 Roads
Kosňovský, Michal ; Apeltauer, Tomáš (referee) ; Kocourek,, Jiří (referee) ; Radimský, Michal (advisor)
This dissertation addresses the possibility of using the 2+1 road arrangement in the Czech Republic. Given that there is no such 2+1 segment in the Czech Republic, it was necessary to find sections with similar characteristics, evaluate and measure the rate of accidents as well as sectional velocity. The accident rate was evaluated on 72 sections and based on this research the optimal length of 2+1 arrangement road sections was determined. Digital image analysis and license plate recognition was used to evaluate the sectional velocity. Eight selected sections was subjected to the additional sectional velocity measurement, which showed improvement in passenger vehicles travel time. Traffic model microsimulations were performed after the data analysis. 2+1 arrangement roads are suitable solution for increasing travel speeds on sections where building of four-lane road is not economically viable.
|
|
|
Detection of malignant melanoma in histological sample using deep neural networks
Frey, Adam ; Lokoč, Jakub (advisor) ; Straka, Milan (referee)
The aim of this thesis is to create a classification method for detection of ma- lignant melanoma in high-resolution digital images. Deep convolutional neural networks were used for this task. At first, a short overview of malignant melanoma and ways to detect it is presented. Deep convolutional neural networks are also introduced with a special attention given to models used further in this work. Several ways to generate samples from the provided histological images are discussed, and several experiments are evaluated to decide how to maximize the accuracy of employed classification methods. The thesis then focuses on several neural network structures used for image classification and their possible utiliza- tion for the given task. The emphasis is laid on the transfer learning, a method used for modifying already trained models for different tasks. This method is then used for training several classifiers. Further on, several methods for the visualization of model results are discussed with some of them implemented. The experiments show promising results on par with other studies dealing with similar problems. Several possibilities for further development are listed in the conclusion.
|
|
|
2 + 1 Roads
Kosňovský, Michal ; Apeltauer, Tomáš (referee) ; Kocourek,, Jiří (referee) ; Radimský, Michal (advisor)
This dissertation addresses the possibility of using the 2+1 road arrangement in the Czech Republic. Given that there is no such 2+1 segment in the Czech Republic, it was necessary to find sections with similar characteristics, evaluate and measure the rate of accidents as well as sectional velocity. The accident rate was evaluated on 72 sections and based on this research the optimal length of 2+1 arrangement road sections was determined. Digital image analysis and license plate recognition was used to evaluate the sectional velocity. Eight selected sections was subjected to the additional sectional velocity measurement, which showed improvement in passenger vehicles travel time. Traffic model microsimulations were performed after the data analysis. 2+1 arrangement roads are suitable solution for increasing travel speeds on sections where building of four-lane road is not economically viable.
|
guest ::
