|
|
Bearing diagnostics using machine learning
Zonygová, Kristýna ; Marada, Tomáš (referee) ; Zuth, Daniel (advisor)
The Master's thesis deals with the use of artificial intelligence methods in order to classify bearing failures. The SVC (Support Vector Classification), KNN (K-Nearest Neighbors Classifier), RFC (Random Forest Classifier) and CNN (Convolutional Neural Network) classification methods are described and tested on ball-bearing vibration signals from two different datasets. All methods achieve quite well accuracy (from 94.1 % to 99.8 %). Scripts in the Python programming environment that use libraries with free-licenses are also included. They provide the possibility of training classification methods (SVC, KNN, RFC or CNN) on your own data, or the use of already trained models.
|
|
|
Lossless Video Compression
Polák, Michael Adam ; Polok, Lukáš (referee) ; Bařina, David (advisor)
This thesis is describing methods of lossless video compression. It also contains the description and formulas for conversions of color models suitable for lossless compression. The last theoretical part describes context compression and entropy coding with emphasis on arithmetic coding. Following the arithmetic coder is the description and details about the implemented video codec. This codec is then tested and compared with the currently used FFV1 and Huffyuv codecs. The result of this thesis is that adding the number of contexts improves the compression ratio although it does not outperform the compression ratio of FFV1, the compression ratio of Huffuyv was always outperformed.
|
|
|
Predicting the therapeutic response to cognitive behavioral therapy in patients with pharmacoresistant obsessive-compulsive disorder.
Vyskočilová, Jana ; Šípek, Jiří (advisor) ; Šivicová, Gabriela (referee)
I chose the theme of obsessive-compulsive disorder as a topic of my thesis. The main reason was that it is a disorder I have worked as a therapist in individual or group therapy frequently. Also I have participated in several studies as evaluator in Psychiatric Centre, and I collected data from dozens of patients. In the first part the thesis deals with the symptoms, clinical picture, prevalence, aetiology and treatment of OCD. Thesis is focuses on behavioural and cognitive models of the disorder in detail, because the treatment used in the present group of patients was CBT. Various models of cognitive behavioural therapy I discuss in more detail, because they allow different views of what happens to the patient and how to change it. The practical part has two parts. The first deals with the effectiveness of group cognitive behavioral approach for OCD patients, who use antidepressants but were resistant to previous treatment and were attended a daycare center at the Prague Psychiatric Center. The second part of the thesis deals with finding a predictor of successful cognitive behavioral therapy in these patients. The aim was to determine whether certain demographic or clinical factors that we evaluated before treatment may predict success outcome. The result is the finding that severity of the...
|
|
|
Bearing diagnostics using machine learning
Zonygová, Kristýna ; Marada, Tomáš (referee) ; Zuth, Daniel (advisor)
The Master's thesis deals with the use of artificial intelligence methods in order to classify bearing failures. The SVC (Support Vector Classification), KNN (K-Nearest Neighbors Classifier), RFC (Random Forest Classifier) and CNN (Convolutional Neural Network) classification methods are described and tested on ball-bearing vibration signals from two different datasets. All methods achieve quite well accuracy (from 94.1 % to 99.8 %). Scripts in the Python programming environment that use libraries with free-licenses are also included. They provide the possibility of training classification methods (SVC, KNN, RFC or CNN) on your own data, or the use of already trained models.
|
|
|
More time or more money? Predictors of the length of working hours in the European Union
Lehmann, Štěpánka ; Vlček, Josef (advisor) ; Havlík, Radomír (referee) ; Kuchař, Pavel (referee)
Štěpánka Lehmann: More time or more money? Predictors of the length of working hours in the European Union Dissertation thesis Abstract Present empirical study analyses important predictors of the length of working hours. It aims at integrating existing conceptions via an approach that would synthetize findings on the influence of different factors of the length of working hours at various levels into a consistent and complex model. For these purposes it uses explorative analytical methods applied on data from the European Working Conditions Survey (EWCS). The thesis is based on two assumptions. First, it is more appropriate to study the length of working hours on the basis of its distribution than based on the average number of working hours. Second, the specific working hours are being established simultaneously at four different levels, the mechanisms of which need to be understood: at the national, sectoral and professional, establishment and household levels. The analysis performed revealed the most important predictors of the length of working hours and their mutual ties. The integration of predictors that are effective at the individual levels resulted in a model which reflects the identified relevant factors when analysing patterns of the length of working hours. The complexity of the working time...
|
|
|
Lossless Video Compression
Polák, Michael Adam ; Polok, Lukáš (referee) ; Bařina, David (advisor)
This thesis is describing methods of lossless video compression. It also contains the description and formulas for conversions of color models suitable for lossless compression. The last theoretical part describes context compression and entropy coding with emphasis on arithmetic coding. Following the arithmetic coder is the description and details about the implemented video codec. This codec is then tested and compared with the currently used FFV1 and Huffyuv codecs. The result of this thesis is that adding the number of contexts improves the compression ratio although it does not outperform the compression ratio of FFV1, the compression ratio of Huffuyv was always outperformed.
|
|
|
More time or more money? Predictors of the length of working hours in the European Union
Lehmann, Štěpánka ; Vlček, Josef (advisor) ; Havlík, Radomír (referee) ; Kuchař, Pavel (referee)
Štěpánka Lehmann: More time or more money? Predictors of the length of working hours in the European Union Dissertation thesis Abstract Present empirical study analyses important predictors of the length of working hours. It aims at integrating existing conceptions via an approach that would synthetize findings on the influence of different factors of the length of working hours at various levels into a consistent and complex model. For these purposes it uses explorative analytical methods applied on data from the European Working Conditions Survey (EWCS). The thesis is based on two assumptions. First, it is more appropriate to study the length of working hours on the basis of its distribution than based on the average number of working hours. Second, the specific working hours are being established simultaneously at four different levels, the mechanisms of which need to be understood: at the national, sectoral and professional, establishment and household levels. The analysis performed revealed the most important predictors of the length of working hours and their mutual ties. The integration of predictors that are effective at the individual levels resulted in a model which reflects the identified relevant factors when analysing patterns of the length of working hours. The complexity of the working time...
|
|
|
Predicting the therapeutic response to cognitive behavioral therapy in patients with pharmacoresistant obsessive-compulsive disorder.
Vyskočilová, Jana ; Šípek, Jiří (advisor) ; Šivicová, Gabriela (referee)
I chose the theme of obsessive-compulsive disorder as a topic of my thesis. The main reason was that it is a disorder I have worked as a therapist in individual or group therapy frequently. Also I have participated in several studies as evaluator in Psychiatric Centre, and I collected data from dozens of patients. In the first part the thesis deals with the symptoms, clinical picture, prevalence, aetiology and treatment of OCD. Thesis is focuses on behavioural and cognitive models of the disorder in detail, because the treatment used in the present group of patients was CBT. Various models of cognitive behavioural therapy I discuss in more detail, because they allow different views of what happens to the patient and how to change it. The practical part has two parts. The first deals with the effectiveness of group cognitive behavioral approach for OCD patients, who use antidepressants but were resistant to previous treatment and were attended a daycare center at the Prague Psychiatric Center. The second part of the thesis deals with finding a predictor of successful cognitive behavioral therapy in these patients. The aim was to determine whether certain demographic or clinical factors that we evaluated before treatment may predict success outcome. The result is the finding that severity of the...
|
|
|
Ideal and non-ideal predictors in estimation of Bellman function
Zeman, Jan
The paper considers estimation of Bellman function using revision of the past decisions. The original approach is further extended by employing predictions coming from an imperfect predictor. The resulting algorithm speeds up the convergence of Bellman function estimation and improves the results quality. The potential of the approach is demonstrated on a futures market data.
|
|
|
Psychological predictors and correlates of subjectively assessed health problems: a longitudinal perspective
Slezáčková, Alena ; Millová, Katarína ; Blatný, Marek ; Jelínek, Martin
The study examines the psychological correlates of health problems in people of middle age and their predictors in adolescence. The sample consisted of 74 participants (32 men and 42 woman aged from 41 to 44 years) who participate in the longitudinal study running from 1961. An analysis of data obtained using the methods EPI, SOC, NEO, TCI, Logo-test and Health questionnaire revealed that the most significant predictor of health problems in adulthood is extraversion at age 16. We found in middle age connections between psychosomatic problems and the degree of extraversion, neuroticism, Sense of Coherence and self-directedness. Specific health problems (pain, shortness of breath) in middle age are also connected to the degree of existential frustration and self-directedness. The results of this study highlight the importance of studying the psychological correlates and predictors of health status of individuals in adulthood.
|
guest ::
