|
|
Filtering of Texts Extracted from PDF, OCR or Web
Žigárdi, Tomáš ; Plchot, Oldřich (referee) ; Szőke, Igor (advisor)
This bachelor thesis describes normalization of texts created by conversion of other formats and creation of pronunciation dictionaries. They are important in speech processing process. Mistakes caused by conversion and original solution of this problem are analyzed. Design and implementation of normalization steps and pronunciation dictionaries is shown. Results are compared with results of original solution of this problem.
|
|
|
Classification of Small Noncoding RNAs
Žigárdi, Tomáš ; Martínek, Tomáš (referee) ; Vogel, Ivan (advisor)
This masters's thesis contains description of designed and implemented tool for classification of plant microRNA without genome. Properties of mature and star sequences in microRNA duplexes are used. Implemented method is based on clustering of RNA sequences (with CD-HIT) to mainly reduce their count. Selected representants from each clusters are classified using support vector machine. Performance of classification is more than 96% (based on cross-validation method using the training data).
|
|
|
Filtering of Texts Extracted from PDF, OCR or Web
Žigárdi, Tomáš ; Plchot, Oldřich (referee) ; Szőke, Igor (advisor)
This bachelor thesis describes normalization of texts created by conversion of other formats and creation of pronunciation dictionaries. They are important in speech processing process. Mistakes caused by conversion and original solution of this problem are analyzed. Design and implementation of normalization steps and pronunciation dictionaries is shown. Results are compared with results of original solution of this problem.
|
|
|
Classification of Small Noncoding RNAs
Žigárdi, Tomáš ; Martínek, Tomáš (referee) ; Vogel, Ivan (advisor)
This masters's thesis contains description of designed and implemented tool for classification of plant microRNA without genome. Properties of mature and star sequences in microRNA duplexes are used. Implemented method is based on clustering of RNA sequences (with CD-HIT) to mainly reduce their count. Selected representants from each clusters are classified using support vector machine. Performance of classification is more than 96% (based on cross-validation method using the training data).
|
guest ::
