|
|
Segmentation of Electrocardiographic Signals Using Deep Learning Methods
Hejč, Jakub ; Černý, Martin (referee) ; Halámek, Josef (referee) ; Kolářová, Jana (advisor)
The thesis deals with deep learning methods for the segmentation of surface and intracardiac electrocardiographic recording with focus on atrial activity. The theoretical part introduces current segmentation aproaches of electrocardiographic signals. Issues related to the development of deep learning models in context of standard ECG databases were also discussed. We proposed a pipeling for processing multimodal electrophysiology data from interventional procedures in order to build reliable training datasets. A deep model for segmentation of intracardiac recordings based on a modified residual architecture was proposed. A series of experiments was conducted to evaluate the effect of both model and dataset properties on segmentation quality. The annotation methodology of recordings with atrial fibrillation proved to be a crucial factor. Properties of loss function and type of data augmentation were revealed as secondary important parameters. A novel P wave segmentation method for incomplete references was proposed in the thesis. The approach was inspired by the deep contrast learning. It was modified to distinguish local segments of signals at different levels of abstraction of the extracted feature maps. Results were analyzed using standard quality metrics and post-hoc visual analysis. In some cases, a statistical comparison of experiments for different settings was performed. The results of the work showed that it is possible to use intracardiac signals for embedding a vector representation of local atrial activation into deep models.
|
|
|
Deep Learning for Image Stitching
Šilling, Petr ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
Sešívání obrázků je klíčovou technikou pro rekonstrukci objemů biologických vzorků z překrývajících se snímků z elektronové mikroskopie (EM). Současné metody zpracování snímků z EM k sešívání zpravidla využívají ručně definované příznaky, produkované například technikou SIFT. Nedávný vývoj však ukazuje, že konvoluční neuronové sítě dokáží zlepšit přesnost sešívání tím, že se naučí diskriminativní příznaky přímo z trénovacích obrázků. S ohledem na potenciál konvolučních neuronových sítí tato práce navrhuje sešívací nástroj DEMIS, který staví na pozornostní síti LoFTR pro hledání shodných příznaků mezi páry obrázků. Dále práce navrhuje novou datovou sadu generovanou dělením obrázků z EM s vysokým rozlišením na pole překrývajících se dlaždic. Výsledná datová sada je použita pro dotrénování sítě LoFTR a k vyhodnocení nástroje DEMIS. Experimenty na dané datové sadě ukazují, že nástroj je schopen nalézt přesnější shody mezi příznaky než SIFT. Navazující experimenty na obrázcích s vysokým rozlišením a malými překryvy mezi dlaždicemi dále poukazují na výrazně vyšší robustnost oproti metodě SIFT. Dosažené výsledky celkově naznačují, že hluboké učení může vést k prospěšným změnám v oblasti EM, například k umožnění menších překryvů mezi snímanými obrázky.
|
|
|
Data Analysis for Predictive Maintenance of a Robotic Arm
Žitný, Roland ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
The Mitsubishi MELFA robotic arms used in modern factories work almost without interruption and produce sensory data about their operation. Various analysis techniques can be applied to such data for predictive maintenance, which provide information on the condition and maintenance needs of such robotic arms. The proposed predictive maintenance process consists of a sensory data acquisition system using the slmpclient and mitsubishi-monitor libraries, an analysis method system with anomaly detection using a convolutional autoencoder, anomaly classification using convolutional neural networks, and data segmentation into segments of individual robot actions using hidden Markov models. Such analysis techniques provide information on the severity, type, and location of emerging faults and abnormalities in behavior, which then determine the time required to perform the required maintenance. This work presents a created chain of predictive maintenance processes, where the obtained findings provide valuable insights into the application of predictive maintenance of Mitsubishi MELFA robotic arms in an industrial environment.
|
|
|
Intracranial hemorrhage localization in axial slices of head CT images
Kopečný, Kryštof ; Chmelík, Jiří (referee) ; Nemček, Jakub (advisor)
This thesis is focused on detection of intracranial hemorrhage in CT images using both one-stage and two-stage object detectors based on convolutional neural networks. The fundamentals of intracranial hemorrhage pathology and CT imaging as well as essential insight into computer vision and object detection are listed in this work. The knowledge of these fields of studies is a starting point for the implemenation of hemorrhage detector. The use of open-source CT image datasets is also discussed. The final part of this thesis is a model evaluation on a test dataset and results examination.
|
|
|
Detection of cells in confocal microscopy images
Hubálek, Michal ; Štursa, Dominik (referee) ; Škrabánek, Pavel (advisor)
The goal of the thesis was to create an application that automatically detects healthy cardiomyocytes from images captured by a confocal microscope. The thesis was created based on the specific needs of researchers from the Slovak Academy of Sciences.The application will facilitate and increase the efficiency of their research,because until now they have to evaluate the images and search for suitable cells manually. The RetinaNet convolutional neural network is used for detection and has been implemented in a user-friendly desktop application. The application also automatically records and stores coordinates of detected cells which can be used for capturing cells in higher image quality. Another advantage of the developed application is its versatility, which allows to train detection on other data, making it applicable to other projects. The result of this work is a functional, standalone and intuitive application that is ready to be used by researchers.
|
|
|
Vehicle Counting in Still Image
Vágner, Filip ; Juránek, Roman (referee) ; Špaňhel, Jakub (advisor)
The goal of this work is to compare models of convolutional neural networks designed to count vehicles in a static image using density estimation with a focus on different sizes of objects in the scene. A total of four models were evaluated - Scale Pyramid Network, Scale-adaptive CNN, Multi-scale fusion network and CASA-Crowd. The evaluation was done on three data sets - TRANCOS, CARPK, PUCPR+. Scale Pyramid Network achieved the best results. The model reached 5.44 in the Mean Absolute Error metric and 9.95 in the GAME(3) metric on TRANCOS dataset.
|
|
|
Enhancement of image quality for security forces
Varga, Adam ; Galáž, Zoltán (referee) ; Burget, Radim (advisor)
This bachelor thesis deals with image quality enhancement for security forces. Image quality enhancement in this case means increasing the resolution of image data by using super-resolution techniques using models of deep convolutional neural networks. The thesis in its theoretical part describes the principles of the operation of this technique and in its practical part is presented the work with selected state-of-the-art models in the area of super-resolution.
|
|
|
Evolutionary Design of Image Classifier
Koči, Martin ; Bidlo, Michal (referee) ; Drahošová, Michaela (advisor)
This thesis deals with evolutionary design of image classifier with help of genetic programming, specifically with cartesian genetic programming. Thesis discribes teoretical basics of machine learing, evolutionary algorithms and genetic programming. Part of this thesis is described design of the program and its implementation. Futhermore, experiments are performed on two solved tasks for the classification of handwritten digits and the classification of cube drawings, which can be used to determine the rate of dementia in Parkinson's disease. The best designed solution for digits is with AUC of 0.95 and for cubes 0.86. Designed solutions are compared by other methods, namely convolutional neural networks (CNN) and the support vector machines (SVM). The resulting AUC for the classification of digits for both CNN and SVM is 0.99, for cubes CNN has a final AUC 0.81 and SVM 0.69. The cubes are then compared with existing solution, which resulted in AUC 0.70, so that the results of the experiments show an improvement in the method used in this thesis.
|
|
|
Algorithmic Solution for Determining the Age of a Person Based on 2D Photography Using Artificial Intelligence
Bednář, Pavel ; Goldmann, Tomáš (referee) ; Drahanský, Martin (advisor)
Automated person's age estimation from a facial image is one of the challenges in the field of artificial intelligence and machine learning. Age estimation is often a non-trivial complexity for a person, unlike other biological characteristics such as determining gender or race. Information about an individual's age is very important for certain situations. For example, when committing an offense or crime, the amount of the sentence is co-determined by age. This information can also be used in the analysis of customers of a commercial entity and the subsequent adjustment of the offer. The aim of this work is to be able to extract his age from a photograph of a human face. The algorithm consists of two modules. If the first module says that the person is under 14 years old, the image will go to the second module. Furthermore, another version of the algorithm is proposed with an added module focused on selected facial features. In all modules transformations are performed on the image and their results are averaged. Finally, the algorithm is evaluated on standard datasets for age estimation and compared with state-of-the-art methods in this area.
|
|
|
Position Control With Camera
Ficek, Dominik ; Honec, Peter (referee) ; Richter, Miloslav (advisor)
Thesis focuses on camera’s pose estimation in set world coordinate system. This coordinate system is defined by position of predefined marks. Cursor control is selected as a pose estimation feedback. Aim of this thesis is designing real time cursor control with camera methods. In theoretical part of this thesis is dedicated to explanation of basic theory of image processing, artificial intelligence in computer vision and 3D reconstruction. Following theoretical chapter is a chapter dedicated to the design of two position control with camera methods. First method defines fixed coordinate system and cursor is controlled by camera’s movement. Second method utilizes fixed camera and movable coordinate system. Further chapters are dedicated to realization of designed methods, their evaluation and comparison.
|
guest ::
