|
|
DNA Sequence Classification
Heczková, Petra ; Burgetová, Ivana (referee) ; Martínek, Tomáš (advisor)
The work deals with DNA sequence classification. The first part summarizes information about existing methods a their characteristics. In the second part there are description of implementation and experiments. Average sensitivity of method was 65% and specificity 92%.
|
|
| |
|
|
Development of modern acoustic features quantifying hypokinetic dysarthria
Kowolowski, Alexander ; Zvončák, Vojtěch (referee) ; Galáž, Zoltán (advisor)
This work deals with designing and testing of new acoustic features for analysis of dysprosodic speech occurring in hypokinetic dysarthria patients. 41 new features for dysprosody quantification (describing melody, loudness, rhythm and pace) are presented and tested in this work. New features can be divided into 7 groups. Inside the groups, features vary by the used statistical values. First four groups are based on absolute differences and cumulative sums of fundamental frequency and short-time energy of the signal. Fifth group contains features based on multiples of this fundamental frequency and short-time energy combined into one global intonation feature. Sixth group contains global time features, which are made of divisions between conventional rhythm and pace features. Last group contains global features for quantification of whole dysprosody, made of divisions between global intonation and global time features. All features were tested on Czech Parkinsonian speech database PARCZ. First, kernel density estimation was made and plotted for all features. Then correlation analysis with medicinal metadata was made, first for all the features, then for global features only. Next classification and regression analysis were made, using classification and regression trees algorithm (CART). This analysis was first made for all the features separately, then for all the data at once and eventually a sequential floating feature selection was made, to find out the best fitting combination of features for the current matter. Even though none of the features emerged as a universal best, there were a few features, that were appearing as one of the best repeatedly and also there was a trend that there was a bigger drop between the best and the second best feature, marking it as a much better feature for the given matter, than the rest of the tested. Results are included in the conclusion together with the discussion.
|
|
|
A Classification Methods for Retinal Nerve Fibre Layer Analysis
Zapletal, Petr ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
This thesis is deal with classification for retinal nerve fibre layer. Texture features from six texture analysis methods are used for classification. All methods calculate feature vector from inputs images. This feature vector is characterized for every cluster (class). Classification is realized by three supervised learning algorithms and one unsupervised learning algorithm. The first testing algorithm is called Ho-Kashyap. The next is Bayess classifier NDDF (Normal Density Discriminant Function). The third is the Nearest Neighbor algorithm k-NN and the last tested classifier is algorithm K-means, which belongs to clustering. For better compactness of this thesis, three methods for selection of training patterns in supervised learning algorithms are implemented. The methods are based on Repeated Random Subsampling Cross Validation, K-Fold Cross Validation and Leave One Out Cross Validation algorithms. All algorithms are quantitatively compared in the sense of classication error evaluation.
|
|
|
Semantic Similarity of Articles
Veselovský, Martin ; Otrusina, Lubomír (referee) ; Kouřil, Jan (advisor)
This bachelor's thesis deals with modelling of structure of semantic relationships among articles in English language. There are introduced existing methods of articles representation and computation of similarity. The base method is vector space model, which represents document as vector of words. There are given weights of importance to these words using TF-IDF method. Next, there are described advanced methods of modelling, Latent semantic analysis (LSA) and Latent Dirichlet allocation (LDA). This thesis also deals with articles, which are semantically annotated, while weights of annotation words are computed by Stochastic Gradient Descent method. Evaluation of results takes place on the prepared test corpus of documents to which there is reference similarity evaluation.
|
|
|
Image search using similarity measures
Harvánek, Martin ; Mašek, Jan (referee) ; Burget, Radim (advisor)
There are these methods implemented: circular sectors, color moments, color coherence vector and Gabor filters, they are based on low-level image features. These methods were evaluated after their optimal parameters were found. The finding of optimal parameters of methods is done by measuring of classification accuracy of learning operators and usage of operator cross validation on images in program RapidMiner. Implemented methods are evaluated on these image categories - ancient, beach, bus, dinousaur, elephant, flower, food, horse, mountain and natives, based on total average precision. The classification accuracy result is increased by 8 % by implemented modification (HSB color space + statistical function median) of original method circular sectors. The combination of methods color moments, circular sectors and Gabor filters with weighted ratio gives the best total average precision at 70,48 % and is the best method among all implemented methods.
|
|
|
Development of modern acoustic features quantifying hypokinetic dysarthria
Kowolowski, Alexander ; Zvončák, Vojtěch (referee) ; Galáž, Zoltán (advisor)
This work deals with designing and testing of new acoustic features for analysis of dysprosodic speech occurring in hypokinetic dysarthria patients. 41 new features for dysprosody quantification (describing melody, loudness, rhythm and pace) are presented and tested in this work. New features can be divided into 7 groups. Inside the groups, features vary by the used statistical values. First four groups are based on absolute differences and cumulative sums of fundamental frequency and short-time energy of the signal. Fifth group contains features based on multiples of this fundamental frequency and short-time energy combined into one global intonation feature. Sixth group contains global time features, which are made of divisions between conventional rhythm and pace features. Last group contains global features for quantification of whole dysprosody, made of divisions between global intonation and global time features. All features were tested on Czech Parkinsonian speech database PARCZ. First, kernel density estimation was made and plotted for all features. Then correlation analysis with medicinal metadata was made, first for all the features, then for global features only. Next classification and regression analysis were made, using classification and regression trees algorithm (CART). This analysis was first made for all the features separately, then for all the data at once and eventually a sequential floating feature selection was made, to find out the best fitting combination of features for the current matter. Even though none of the features emerged as a universal best, there were a few features, that were appearing as one of the best repeatedly and also there was a trend that there was a bigger drop between the best and the second best feature, marking it as a much better feature for the given matter, than the rest of the tested. Results are included in the conclusion together with the discussion.
|
|
|
DNA Sequence Classification
Heczková, Petra ; Burgetová, Ivana (referee) ; Martínek, Tomáš (advisor)
The work deals with DNA sequence classification. The first part summarizes information about existing methods a their characteristics. In the second part there are description of implementation and experiments. Average sensitivity of method was 65% and specificity 92%.
|
|
|
Semantic Similarity of Articles
Veselovský, Martin ; Otrusina, Lubomír (referee) ; Kouřil, Jan (advisor)
This bachelor's thesis deals with modelling of structure of semantic relationships among articles in English language. There are introduced existing methods of articles representation and computation of similarity. The base method is vector space model, which represents document as vector of words. There are given weights of importance to these words using TF-IDF method. Next, there are described advanced methods of modelling, Latent semantic analysis (LSA) and Latent Dirichlet allocation (LDA). This thesis also deals with articles, which are semantically annotated, while weights of annotation words are computed by Stochastic Gradient Descent method. Evaluation of results takes place on the prepared test corpus of documents to which there is reference similarity evaluation.
|
|
|
Image search using similarity measures
Harvánek, Martin ; Mašek, Jan (referee) ; Burget, Radim (advisor)
There are these methods implemented: circular sectors, color moments, color coherence vector and Gabor filters, they are based on low-level image features. These methods were evaluated after their optimal parameters were found. The finding of optimal parameters of methods is done by measuring of classification accuracy of learning operators and usage of operator cross validation on images in program RapidMiner. Implemented methods are evaluated on these image categories - ancient, beach, bus, dinousaur, elephant, flower, food, horse, mountain and natives, based on total average precision. The classification accuracy result is increased by 8 % by implemented modification (HSB color space + statistical function median) of original method circular sectors. The combination of methods color moments, circular sectors and Gabor filters with weighted ratio gives the best total average precision at 70,48 % and is the best method among all implemented methods.
|
guest ::
