|
|
Application of neural networks in telecommunications
Šulák, Michal ; Koula, Ivan (referee) ; Kacálek, Jan (advisor)
This Master’s Thesis consists of description of current routing protocols and routers, basic principles of neural networks and their interpretation in connection with the use for routing in data networks and telecommunications networks. In the thesis I focused on neural networks, which use energetic functions to find solution stabled states and their use for data routing. I produced the application software to test and find suitable variables for each function. This application counts the shortest path and is able to change variables to reach the best solution of stabled state of neural network. These solutions are compared with other functions that are usually used in nowadays systems for data network routing.
|
|
|
Experimentální mechanická analýza konstrukčního LSL kompozitu ze směsi plochých třísek vybraných druhů dřevin
Šulák, Michal
The diploma thesis deals with the idea of replacing spruce wood in structural elements with another alternative wood type- larch. This work compares 3 variants of experimentally manufactured LSL boards. Boards made only with larch or spruce particles were compared with board which contains a mix of spruce and larch chips in a ratio of 60:40. The effect of board composition on mechanical properties was evaluated using bending (flat- and edge-wise), internal bonding, compression and thickness swelling test. The non-destructive digital Image Correlation (DIC) method was used to evaluate the results strain fields during both bending schemes. To determine the behavior of the glued joint itself was used a modified shear strength test on three types of specimen MD/MD, SM/SM and MD/SM. In the case of bending tests were found any significant differences between the boards. Significant differences weren´t found when the compressive behaviour of the boards was tested. However, a statistically significant difference was found in the density of the tested samples for compression and for IB specimen. In both cases, the density of specimen made from spruce particles was significantly lower. When tested for internal bonding, ANOVAs did not confirm significant differences between specimen groups. A significant influence of the strand combination was found in thickness swelling and water absorption. During the lap shear test, a significantly higher strength of the glued joint was found in the MD/MD samples compared to the other groups of samples.
|
|
|
Application of neural networks in telecommunications
Šulák, Michal ; Koula, Ivan (referee) ; Kacálek, Jan (advisor)
This Master’s Thesis consists of description of current routing protocols and routers, basic principles of neural networks and their interpretation in connection with the use for routing in data networks and telecommunications networks. In the thesis I focused on neural networks, which use energetic functions to find solution stabled states and their use for data routing. I produced the application software to test and find suitable variables for each function. This application counts the shortest path and is able to change variables to reach the best solution of stabled state of neural network. These solutions are compared with other functions that are usually used in nowadays systems for data network routing.
|
guest ::
RSS feed.