|
| |
|
|
Classification of the vascular tree in fundus images
Tebenkova, Iuliia ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
Retinal image analysis plays a very important role, as human gets around 90% of environment information with the help of eyes. Automation of process of retinal image analysis promotes to improve the efficiency of retinal medical examinations. The following thesis is dedicated to automatic classification methods of retinal vascular system images obtained from a digital fundus camera. Vessel classification method using classifier on the base of neural networks, which is trained and then tested on the retinal vessel segments, is investigated and implemented. In this thesis anatomical retinal survey, properties of image data from digital fundus camera and retinal image classification methods are briefly described. The last chapter is devoted to the evaluation of efficiency of retinal vessel classification with automatic methods.
|
|
|
Age effect modeling of the unipolar transistor
Soukal, Pavel ; Kolka, Zdeněk (referee) ; Petržela, Jiří (advisor)
According to non-stopable progress in wireless communications, it is desirable to integrate the RF front-end with the baseband building blocks of communication circuits into a one chip in the recent years. The CMOS technology advances, this is the reason why it becomes attractive for system-on-a-chip implementation, but CMOS device is getting shrink, so the channel electric field increasing and the hot carrier (HCI) effect becomes more significant. If the oxide is scaled down to less than 3 nm, then there is the possibility of soft or hard oxide breakdown (S/HBD) often takes place. As a result of the oxide trapping and interface generation is the long term performance drift and related reliability problems in devices and circuits. During the scaling and increasing chip power dissipation operating temperatures for device have also is increasing. Another reliability concern is the negative bias temperature instability (NBTI) caused by the interface traps under high temperature and negative gate voltage bias are arising while the operation temperature of devices is increasing. Parameter’s extraction is a very important part of the current electronic components modeling process, as it looking for the value of the unknown parameters in mathematical model, which represents physical behavior of given electronic component. The problem of parameter extraction is that fits electronic components mathematical model to a measured data set is an ill-posed problem and its solution is inherently difficult. This diploma thesis presents the parameter extraction, optimization methodology and verifies it on a case study of a MOSFET mathematical models (LEVEL1, LEVEL2 and LEVEL3) parameter extraction. The presented nonlinear method is based on the method of the least squares, which is solved with the aid of Levenberg- Marquardt’s algorithm.
|
|
|
Recognition of music style from orchestral recording using Music Information Retrieval techniques
Jelínková, Jana ; Zvončák, Vojtěch (referee) ; Kiska, Tomáš (advisor)
As all genres of popular music, classical music consists of many different subgenres. The aim of this work is to recognize those subgenres from orchestral recordings. It is focused on the time period from the very end of 16th century to the beginning of 20th century, which means that Baroque era, Classical era and Romantic era are researched. The Music Information Retrieval (MIR) method was used to classify chosen subgenres. In the first phase of MIR method, parameters were extracted from musical recordings and were evaluated. Only the best parameters were used as input data for machine learning classifiers, to be specific: kNN (K-Nearest Neighbor), LDA (Linear Discriminant Analysis), GMM (Gaussian Mixture Models) and SVM (Support Vector Machines). In the final chapter, all the best results are summarized. According to the results, there is significant difference between the Baroque era and the other researched eras. This significant difference led to better identification of the Baroque era recordings. On the contrary, Classical era ended up to be relatively similar to Romantic era and therefore all classifiers had less success in identification of recordings from this era. The results are in line with music theory and characteristics of chosen musical eras.
|
|
|
Extraction of parameters for the research of music performance
Laborová, Anna ; Miklánek, Štěpán (referee) ; Ištvánek, Matěj (advisor)
Different music performances of the same piece may significantly differ from each other. Not only the composer and the score defines the listener’s music experience, but the music performance itself is an integral part of this experience. Four parameter classes can be used to describe a performance objectively: tempo and timing, loudness (dynamics), timbre, and pitch. Each of the individual parameters or their combination can generate a unique characteristic performance. The extraction of such objective parameters is one of the difficulties in the field of Music Performance Analysis and Music Information Retrieval. The submitted work summarizes knowledge and methods from both of the fields. The system is applied to extract data from 31 string quartet performances of 2. movement Lento of String Quartet no. 12 F major (1893) by czech romantic composer Antonín Dvořák (1841–1904).
|
|
|
Extraction of parameters for the research of music performance
Laborová, Anna ; Miklánek, Štěpán (referee) ; Ištvánek, Matěj (advisor)
Different music performances of the same piece may significantly differ from each other. Not only the composer and the score defines the listener’s music experience, but the music performance itself is an integral part of this experience. Four parameter classes can be used to describe a performance objectively: tempo and timing, loudness (dynamics), timbre, and pitch. Each of the individual parameters or their combination can generate a unique characteristic performance. The extraction of such objective parameters is one of the difficulties in the field of Music Performance Analysis and Music Information Retrieval. The submitted work summarizes knowledge and methods from both of the fields. The system is applied to extract data from 31 string quartet performances of 2. movement Lento of String Quartet no. 12 F major (1893) by czech romantic composer Antonín Dvořák (1841–1904).
|
|
|
Recognition of music style from orchestral recording using Music Information Retrieval techniques
Jelínková, Jana ; Zvončák, Vojtěch (referee) ; Kiska, Tomáš (advisor)
As all genres of popular music, classical music consists of many different subgenres. The aim of this work is to recognize those subgenres from orchestral recordings. It is focused on the time period from the very end of 16th century to the beginning of 20th century, which means that Baroque era, Classical era and Romantic era are researched. The Music Information Retrieval (MIR) method was used to classify chosen subgenres. In the first phase of MIR method, parameters were extracted from musical recordings and were evaluated. Only the best parameters were used as input data for machine learning classifiers, to be specific: kNN (K-Nearest Neighbor), LDA (Linear Discriminant Analysis), GMM (Gaussian Mixture Models) and SVM (Support Vector Machines). In the final chapter, all the best results are summarized. According to the results, there is significant difference between the Baroque era and the other researched eras. This significant difference led to better identification of the Baroque era recordings. On the contrary, Classical era ended up to be relatively similar to Romantic era and therefore all classifiers had less success in identification of recordings from this era. The results are in line with music theory and characteristics of chosen musical eras.
|
|
|
Classification of the vascular tree in fundus images
Tebenkova, Iuliia ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
Retinal image analysis plays a very important role, as human gets around 90% of environment information with the help of eyes. Automation of process of retinal image analysis promotes to improve the efficiency of retinal medical examinations. The following thesis is dedicated to automatic classification methods of retinal vascular system images obtained from a digital fundus camera. Vessel classification method using classifier on the base of neural networks, which is trained and then tested on the retinal vessel segments, is investigated and implemented. In this thesis anatomical retinal survey, properties of image data from digital fundus camera and retinal image classification methods are briefly described. The last chapter is devoted to the evaluation of efficiency of retinal vessel classification with automatic methods.
|
|
|
Age effect modeling of the unipolar transistor
Soukal, Pavel ; Kolka, Zdeněk (referee) ; Petržela, Jiří (advisor)
According to non-stopable progress in wireless communications, it is desirable to integrate the RF front-end with the baseband building blocks of communication circuits into a one chip in the recent years. The CMOS technology advances, this is the reason why it becomes attractive for system-on-a-chip implementation, but CMOS device is getting shrink, so the channel electric field increasing and the hot carrier (HCI) effect becomes more significant. If the oxide is scaled down to less than 3 nm, then there is the possibility of soft or hard oxide breakdown (S/HBD) often takes place. As a result of the oxide trapping and interface generation is the long term performance drift and related reliability problems in devices and circuits. During the scaling and increasing chip power dissipation operating temperatures for device have also is increasing. Another reliability concern is the negative bias temperature instability (NBTI) caused by the interface traps under high temperature and negative gate voltage bias are arising while the operation temperature of devices is increasing. Parameter’s extraction is a very important part of the current electronic components modeling process, as it looking for the value of the unknown parameters in mathematical model, which represents physical behavior of given electronic component. The problem of parameter extraction is that fits electronic components mathematical model to a measured data set is an ill-posed problem and its solution is inherently difficult. This diploma thesis presents the parameter extraction, optimization methodology and verifies it on a case study of a MOSFET mathematical models (LEVEL1, LEVEL2 and LEVEL3) parameter extraction. The presented nonlinear method is based on the method of the least squares, which is solved with the aid of Levenberg- Marquardt’s algorithm.
|
guest ::
