|
|
Webmining
Ljubopytnov, Vladimír ; Pokorný, Jaroslav (advisor) ; Húsek, Dušan (referee)
This thesis focuses on mapping latest knowledge in the area of web mining with emphasis on document clustering. Most attention is given to the DOC projective clustering algorithm, a modification is presented for data with weighted dimensions. Algorithm is used for web search engine result clustering. Also, a clustering package with Google interface and phrase evaluation tool is implemented.
|
|
|
Clusters of closely related documents
Diviš, Jiří ; Holub, Martin (advisor) ; Húsek, Dušan (referee)
This thesis focuses on automatic searching for clusters of topically similar texts in large text collection. We introduce an algorithm for nding the clusters and a method of optimizing its parameters using machine learning techniques. The algorithm is implemented and experimentaly evaluated. For evaluation we use a manually annotated collection of Czech documents, which contains a set of sample clusters chosen and tagged by a human annotator, and a huge collection of newspaper arcticles. Experiments show that the output of our algorithm ful ls our expectation and gives clusters of topically similar texts.
|
|
|
Assessment of Independent EEG Components Obtained by Different Methods for BCI Based on Motor Imagery
Húsek, Dušan ; Frolov, A. A. ; Kerechanin, J. V. ; Bobrov, P.D.
Eight methods of decomposition of a multichannel EEG signal are compared in terms of their ability to identify the most physiologically significant components. The criterion for the meaningfulness of a method is its ability to reduce mutual information between components; to create components that can be attributed to the activity of dipoles located in the cerebral cortex; find components that are provided by other methods and for this case; and at the same time, these components should most contribute to the accuracy of the BCI based on imaginary movement. Independent component analysis methods AMICA, RUNICA and FASTICA outperform others in the first three criteria and are second only to the Common Spatial Patterns method in the fourth criterion. The components created by all methods for 386 experimental sessions of 27 subjects were combined into more than 100 clusters containing more than 10 elements. Additionally, the components of the 12 largest clusters were analyzed. They have proven to be of great importance in controlling BCI, their origins can be modeled using dipoles in the brain, and they have been detected by several degradation methods. Five of the 12 selected components have been identified and described in our previous articles. Even if the physiological and functional origins of the rest of identified components’ are to be the subject of further research, we have shown that their physiological nature is at least highly probable.\n
|
|
|
Visual Images Segmentation based on Uniform Textures Extraction
Goltsev, A. ; Gritsenko, V. ; Húsek, Dušan
A new effective procedure for partial texture segmentation of visual images is proposed. The procedure segments any input image into a number of non-overlapping homogeneous ne-grained texture areas. The main advantages of the proposed procedure are as follows. It is completely unsupervised, that is, it processes the input image without any prior knowledge of either the type of textures or the number of texture segments in the image. In addition, the procedure segments arbitrary images of all types. This means that no changes to the procedure parameters are required to switch from one image type to another. Another major advantage of the procedure is that in most cases it extracts the uniform ne-grained texture segments present in the image, just as humans do. This result is supported by series of experiments that demonstrate the ability of the procedure to delineate uniform ne-grained texture segments over a wide range of images. At a minimum, image processing according to the proposed technique leads to a signficant reduction in the uncertainty of the internal structure of the analyzed image.
|
|
|
Webmining
Ljubopytnov, Vladimír ; Húsek, Dušan (referee) ; Pokorný, Jaroslav (advisor)
This thesis focuses on mapping latest knowledge in the area of web mining with emphasis on document clustering. Most attention is given to the DOC projective clustering algorithm, a modification is presented for data with weighted dimensions. Algorithm is used for web search engine result clustering. Also, a clustering package with Google interface and phrase evaluation tool is implemented.
|
|
|
Clusters of closely related documents
Diviš, Jiří ; Húsek, Dušan (referee) ; Holub, Martin (advisor)
This thesis focuses on automatic searching for clusters of topically similar texts in large text collection. We introduce an algorithm for nding the clusters and a method of optimizing its parameters using machine learning techniques. The algorithm is implemented and experimentaly evaluated. For evaluation we use a manually annotated collection of Czech documents, which contains a set of sample clusters chosen and tagged by a human annotator, and a huge collection of newspaper arcticles. Experiments show that the output of our algorithm ful ls our expectation and gives clusters of topically similar texts.
|
|
| |
|
|
Biologicky inspirované modely založené na prototypech a aplikace gompertzovské dynamiky ve shlukové analýze
Pastorek, Lukáš ; Řezanková, Hana (advisor) ; Húsek, Dušan (referee) ; Nánásiová, Oľga (referee)
The thesis deals with the analysis of the clustering and mapping techniques derived from the principles of the neural and statistical learning and growth theory. The selected branch of the unsupervised bio-inspired prototype-based models is described in terms of the proposed logical framework, which highlights the continuity of these methods with the classical "pure" statistical methods. Moreover, as those methods are broadly understood as the "black boxes" with the unpredictable, unclear and especially hidden behavior, the examples of the spatial computational and organizational patterns in two-dimensional space are provided. Additionally, this thesis presents the novel concept based on the non-linear, non-Gaussian Gompertzian function, which has been widely used as the universal law in dynamic growth models, but has not yet been applied in the field of computational intelligence. The essence of Gompertzian dynamics is mathematically analyzed and a novel simple version of the Gompertzian normalized function is introduced. Furthermore, the function was modified for use in the field of artificial intelligence and neural implications were discussed. Additionally, the novel neural networks were proposed and derived from the topological principles of Kohonen's self-organizing maps and neural gas algorithm. The Gompertzian networks were evaluated using several indicators for various generated and real datasets. Gompertzian neural networks with fixed grid and integrated neighborhood ranking principle generally show lower mean squared errors than the original SOM algorithms. Likewise, the unconstrained Gompertzian networks have demonstrated overall low error rates comparable to neural gas algorithm, more stable and lower error solutions than the k- means sequential procedure. In conclusion, the Gompertzian function has been shown to be a viable concept and an effective computational tool for multidimensional data analysis.
|
|
|
Source localization for EEG patterns relevant to motor imagery BCI control
Bobrov, P. ; Frolov, A. ; Húsek, Dušan ; Tintěra, J.
This work concerns spatial localization of sources of EEG patterns the most specific for control of the motor imagery based BCI. In our previous work we have shown that performance of Bayesian BCI classifier can be drastically improved by extraction of the most relevant independent components of the EEG signal. This paper presents the results of spatial localization of electrical brain activity sources which activity is reflected by the extracted components. The localization was performed by solving the inverse problem in EEG source localization, using individual finite-element head models. The sources were located in central sulcus (Brodmann area 3a), in the superior regions of post- and precentral gyri, and supplementary motor cortex.
|
|
| |
guest ::
RSS feed.