Home > Search Results: Vystrčilová, Michaela
Search:
Search Tips :: Advanced Search
Search collections:
Sort by: Display results: Output format:
National Repository of Grey Literature 2 records found  Search took 0.01 seconds. 
Predikce rychlosti a absolutni rychlosti pohybu z lidských intrakraniálních EEG dat pomocí hlubokých neuronových sítí.
 Vystrčilová, Michaela ; Antolík, Ján (advisor) ; Pilát, Martin (referee)
Our brain controls the processes of the body including movement. In this thesis, we try to understand how the information about hand movement is encoded into the brain's electrical activity and how this activity can be used to predict the velocity and absolute velocity of hand movements. Using a well-established deep neural network architecture for EEG decoding - the Deep4Net - we predict hand movement velocity and absolute velocity from intracranial EEG signals. While reaching the expected performance level, we determine the influence of different frequency bands on the network's prediction. We find that modulations in the high-gamma frequency band are less informative than expected based on previous studies. We also identify two architectural modifications which lead to higher performances. 1. the removal of max-pooling layers in the architecture leads to significantly higher correlations. 2. the non-uniform receptive field of the network is a potential drawback making the network biased towards less relevant information. 1
Detailed record
Similarity methods for music recommender systems
 Vystrčilová, Michaela ; Peška, Ladislav (advisor) ; Balcar, Štěpán (referee)
Traditional music recommender systems rely on collaborative-filtering methods. This, however, puts listeners who do not enjoy mainstream songs at a disadvantage because CF systems depend on popularity patterns. Content-based recommendation methods might be useful in solving this issue. Since tag-based searches are a widespread tool to aid tra- ditional music recommendation, this paper presents content-based methods measuring similarity between songs with focus on methods utilizing song's lyrics and audio record- ings. First, we evaluated the accuracy of several approaches based on lyrics and audio information on real user playlists and found that lyrics-based methods yield competitive results to audio-based methods. Results also revealed that both categories include meth- ods that are 100 times more accurate compared to random suggestions and that they have potential for even better results. After the evaluation phase, we selected well-performing methods and implemented them in a web application aiming on recommending novel music to the users based on their content-based profile. 1
Detailed record

See also: similar author names
2 Vystrčilová, Martina
Interested in being notified about new results for this query?
Subscribe to the RSS feed.
Digital Repository :: Search :: Submit :: Personalize :: Help
Powered by Invenio v1.1.2
Maintained by admin.invenio@techlib.cz
This site is also available in the following languages:
Česky  English