Probabilistic Models for Symmetric Object Detection in Images
Šára, Radim; Tyleček, Radim
2015 - English
Available in digital repository of ČVUT.
Probabilistic Models for Symmetric Object Detection in Images
Company Bankruptcy Models
Starý, Oldřich; Bemš, Július
2015 - English
Available in digital repository of ČVUT.
Company Bankruptcy Models
Wireless Power Transmission
Mazánek, Miloš; Pechač, Pavel; Kraček, Jan
2015 - English
Available in digital repository of ČVUT.
Wireless Power Transmission
Specific Language Impairments and Possibilities of Classification and Detection from Children's Speech
Tučková, Jana; Grill, Pavel
2015 - English
Many young children have speech disorders. My research focused on one such disorder, known as specific language impairment or developmental dysphasia. A major problem in treating this disorder is the fact that specific language impairment is detected in children at a relatively late age. For successful speech therapy, early diagnosis is critical. I present two different approaches to this issue using a very simple test that I have devised for diagnosing this disorder. In this thesis, I describe a new method for detecting specific language impairment based on the number of pronunciation errors in utterances. An advantage of this method is its simplicity; anyone can use it, including parents. The second method is based on the acoustic features of the speech signal. An advantage of this method is that it could be used to develop an automatic detection system.
Key
Available in digital repository of ČVUT.
Specific Language Impairments and Possibilities of Classification and Detection from Children's Speech
Many young children have speech disorders. My research focused on one such disorder, known as specific language impairment or developmental dysphasia. A major problem in treating this disorder is the ...
Template-based Ontology Evolution
Kouba, Zdeněk; Blaško, Miroslav
2015 - English
Available in digital repository of ČVUT.
Template-based Ontology Evolution
A Two-Way Metamodeling Approach in Web Engineering
Richta, Karel; Merunka, Vojtěch; Xhevi Qafmolla
2015 - English
This dissertation thesis introduces a new model-driven approach in Web engineering that
aims to decrease the communication gap between stakeholders during the early phases
of the project and reduce the development e ort required for the production of the nal
Web application. The approach has been applied in the domain of content-based Web
applications and is supported by related methodology and proof-of-concept tools.
While several model-driven approaches specialized in the discipline of Web engineering
have been developed in the last decade, the majority of them is outdated, or is applied
under speci c conditions in practice, usually involving a high cost of adoption. The main
reason is that most of these approaches apply the modeling part in a top-down mode,
i.e. they focus on a high-level conceptual model of the Web application upon which later
are applied transformation techniques to generate the nal components. The drawback of
such approach is two-fold. Firstly, communication between stakeholders on a high-level at
the early phases of the project is ambiguous, leading to problems and increased overhead
e ort at later phases. Secondly, transformation of an abstract model is complex and it
involves several errors and manual operations. In contrast, our proposal consists of a two-
way approach of model creation and transformation. Both technical and non-technical
stakeholders use a common low-level conceptual model to ne-tune requirements, such as
a rapid prototype of theWeb application in HTML or other form (bottom-up phase). After
several iterations, once the model is enough mature, it is used as an input for the (semi-
)automated creation of the nal application's components and its initial content (top-down
phase).
The proposed approach has been evaluated qualitatively in real-world case studies and
quantitatively through a large number of simulated projects using open-source Web appli-
cation templates. The achieved results are promising and they show potential improvement
in the practical application of model-driven techniques in the Web engineering discipline.
Available in digital repository of ČVUT.
A Two-Way Metamodeling Approach in Web Engineering
This dissertation thesis introduces a new model-driven approach in Web engineering that aims to decrease the communication gap between stakeholders during the early phases of the project and reduce ...
Determination of the Actual User´s Position in Urban Environments Using GNSS Multipath Propagation Model
Chod, Jiří; Píšová, Petra
2015 - English
Available in digital repository of ČVUT.
Determination of the Actual User´s Position in Urban Environments Using GNSS Multipath Propagation Model
Efficient Control Routing and Wavelength Assignment in Loss-Less Optical Burst Switching Networks
Boháč, Leoš; Kozák, Miloš
2015 - English
Available in digital repository of ČVUT.
Efficient Control Routing and Wavelength Assignment in Loss-Less Optical Burst Switching Networks
Model Machine Learning-based Feature Ranking and Feature Selection
Šnorek, Miroslav; Pilný, Aleš
2015 - English
This thesis introduces two novel machine learning methods of feature ranking and feature
selection. The methods build on data mining and knowledge discovery techniques.
The methods are based on arti cial neural network and evolutionary computation. The
proposed methods are designed to adapt to the problem,and thus, to provide robust and
e cient algorithms and their results in comparison to other used techniques on real world
problems. In the past, research in this eld has focused on speci c kind of problem such
as classi cation or regression. This thesis shows applicability of presented approaches for
both types of problems: classi cation and regression.
Feature ranking and feature selection play an important part of the whole knowledge
discovery process. Successful approaches often exploit some expert knowledge speci c to a
given task, which might be di cult or even impossible to transfer to a di erent task. The
main contribution of the thesis is development of techniques that do not require such an
expert input. This is achieved by integrating the construction of the data mining model
into the method.
The proposed approach not only delivers the solution, but also derives a mathematical
expression that justi es the outcome. This expression is automatically evolved during
the data mining process. In case of arti cial neural network, the expression represents a
data mining model which provides results of classi cation or regression. In case of genetic
programming, the expression represents how the attribute importance was determined and
describes a relationship between particular attributes and output variables.
The methods were experimentally evaluated on both, synthetic data, with feature importance
known in advance, and on standard real datasets. The quality of the proposed feature
selection and ranking is on par with state-of-the-art approaches, in a number of cases even
achieving the best performance. Our methods were successfully applied to di erent realworld
disciplines, including anthropology and dental medicine for prediction of age from
teeth mineralization, or modelling of oral exostoses.
Available in digital repository of ČVUT.
Model Machine Learning-based Feature Ranking and Feature Selection
This thesis introduces two novel machine learning methods of feature ranking and feature selection. The methods build on data mining and knowledge discovery techniques. The methods are based on arti ...
Improvement of Inertial Navigation System Accuracy Using Alternative Sensors
Roháč, Jan; Šipoš, Martin
2015 - English
Available in digital repository of ČVUT.
Improvement of Inertial Navigation System Accuracy Using Alternative Sensors
NRGL provides central access to information on grey literature produced in the Czech Republic in the fields of science, research and education. You can find more information about grey literature and NRGL at service web
Send your suggestions and comments to nusl@techlib.cz
Provider
Other bases