National Repository of Grey Literature 125 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Chest X-ray Image Analysis using Convolutional Vision Transformer
Mezina, Anzhelika ; Burget, Radim
In recent years, computer techniques for clinical imageanalysis have been improved significantly, especially becauseof the pandemic situation. Most recent approaches are focusedon the detection of viral pneumonia or COVID-19 diseases.However, there is less attention to common pulmonary diseases,such as fibrosis, infiltration and others. This paper introduces theneural network, which is aimed to detect 14 pulmonary diseases.This model is composed of two branches: global, which is theInceptionNetV3, and local, which consists of Inception modulesand a modified Vision Transformer. Additionally, the AsymmetricLoss function was utilized to deal with the problem of multilabelclassification. The proposed model has achieved an AUC of 0.8012and an accuracy of 0.7429, which outperforms the well-knownclassification models.
X-ray image analysis to remove disturbing artifacts for security applications
Schiller, Vojtěch ; Mezina, Anzhelika (referee) ; Burget, Radim (advisor)
This work deals with the issue of the decomposition of a composite X-ray image, on which both key informational and noise components are present simultaneously. The goal is to remove the present disturbing artifacts as repeating phenomena in the background using deep learning techniques while emphasizing the precise preservation of the informational components contained in the image. To achieve this, the convolutional neural network U-Net and its improved versions, which dominate especially in image segmentation, were used. Competitive models achieving excellent results at image-denoising tasks were also trained and compared. This work proposes a novel method, which was compared with the most modern architectures on the same dataset, and which, in the results, objectively and subjectively significantly surpassed all of them.
Super resolution in the image to ensure improved monitoring of secured areas
Rosa, Martin ; Mezina, Anzhelika (referee) ; Burget, Radim (advisor)
The point of this bachelor thesis was to compare models of super-resolution with the application on resolving human faces. A brief review of the technologies of super-resolution was created and five models were trained and compared. The focus was on the area of super-resolution that could be helpful with identifying people from CCTV cameras. Used technologies were therefore chose based on their perceptual quality and ability to identify the person in the output image. This thesis has shown the effectivity of the compared models using objective and subjective metrics. The results were compared in a survey (106 respondents). Survey has shown the advantage of using wavelet-transform in the area of the super-resolution of human faces.
Robocode - secured platform for evaluation of students' projects
Peňáz, Vladimír ; Ježek, Štěpán (referee) ; Burget, Radim (advisor)
This bachelor's thesis focuses on the design and implementation of a secure testing platform based on the game Robocode, which is used for evaluating student projects in the MSC-PDA subject. The project utilizes principles of machine learning and addresses a problem in the complexity class EXPSPACE. Evaluating the quality of results in this complexity class is challenging, and currently, there is no suitable environment available for these purposes. The objective of this thesis is to create a secure environment that allows students to compete on a game server with minimal risk of damaging the teacher's computer and ensures superuser privileges. Students will connect their trained models to the game server, where they will receive complete information about the battlefield, based on which they generate instructions for their tanks. In this way, the model will have the same information about the battle as a manually playing human. Based on the final score, it will be possible to evaluate which model performed the best. The platform is implemented in Java and works with models implemented in Python.
Research of the new augmentation methods for online handwriting
Sigmund, Jan ; Burget, Radim (referee) ; Zvončák, Vojtěch (advisor)
Graphomotor difficulties of school-aged children are characterised by problems in handwriting and drawing and can lead to developmental dysgraphia. Timely clinical diagnosis is critical to provide preventive care. In practice however, it is not feasible on day-to-day basis due to the need for expert staff and the prevalence of difficulties up to 30\%. Machine learning models can serve as an accessible objective tool for evaluating graphomotor functioning. In most cases there is not enough data collected, which results in poor classification performance. Therefore, this thesis focuses on data augmentation of online handwriting. Generating artificial samples is based on recombination of intrinsic mode functions, obtained by empirical mode decomposition. IMFs of health controls, numbering 72, and with graphomotor difficulties, 94 children in total, are calculated. The decomposition is performed specifically on X and Y coordinate time series. IMFs of the same indices of different subjects are randomly interchanged, thus producing a new signal. Then, the graphomotor features of the original and artificial time series are extracted. Only the spatial ones related to the coordinates are selected. Finally, the correlations of the features of the two databases will be analyzed and compared.
Artificial Intelligence for Video Sonification
Dobrocký, Filip ; Burget, Radim (referee) ; Říha, Kamil (advisor)
This thesis deals with the topic of video sonification – the transformation of image into sound. It aims to use state-of-the-art techniques of computer vision based on artificial intelligence to create a system capable of algorithmic sound creation applicable in the art context. The focus is put on the fields of sound art, algorithmic composition and generative music. The thesis includes an implementation of a modular sonification system which utilizes the modern object detector YOLOv7 along with a multiple object tracking algorithm (implemented in the library Norfair), built using the programming language Python. The fundementals of the system lie in systematic assignment of sound objects to objects tracked in the video. The sound creation relies on the SuperCollider platform using the Python API Supriya, incorporating various methods of sound synthesis along with a programmatically created sound database.
Detection of objects and tracking the route of movement of traffic participants for the needs of intelligent transport nodes
Vymazal, Tomáš ; Kiac, Martin (referee) ; Burget, Radim (advisor)
The master‘s thesis is focused on the object detection. The aim of this thesis is to desine an experiment to assess the detection models YOLOv5, YOLOR, Scaled-YOLOv4 and EfficientDet and to compare their properties (detection speed, memory requirements, accuracy and certainty of detection). For this purpose a custom data set is created to investigate these parameters. The study shows that the YOLOv5 network is performd as the best solution. Deep SORT is used for object tracking which is important for the subsequent extraction of training data from video footage for object movement prediction. The added value is the design of the prediction algorithm which is based on a polynomial regression model.
Forensic analysis of handwriting for the Czech environment using artificial intelligence
Stejskal, Jan ; Přinosil, Jiří (referee) ; Burget, Radim (advisor)
The analysis of handwriting is an important area of research in modern science. However, it is a very complex process because handwritten text can take on various forms. The use of artificial intelligence for analyzing and identifying text from different authors is nothing new in the world. Research in this area is, however, slightly lagging behind in the Czech environment. For this reason, several convolutional network architectures were proposed and compared in this work in an effort to find the most suitable structure for solving this problem. Of all the trained and tested models, the model based on the ResNet18 architecture achieved the highest accuracy, with a success rate of 92.2 % on a self-made database of 1328 samples with a resolution of 750x256. This result suggests that with a sufficiently large and high-quality database, the problem can be solved even in the Czech environment with its more complicated character set.
Battery life analysis for IoT modules
Nikolic, Predrag ; Štůsek, Martin (referee) ; Burget, Radim (advisor)
The main gol of the bakalar thesis is to measure battery lifetime for IoT modules. The teoretical part describes the characteristics of IoT communication modules and battery sources designed for these devices. The practical part contains a program for calculating the battery source life on the IoT module. Current consumption has to be tested by oscilloscope. Measured data is used for recalculation of the actual current consumption. The second practical part of the thises deals with battery source simulation in the working environment. This simulation is used to approximate all the parameters of the environment that directly or indirectly affect the life of the battery source.
Automatic quality control of painted metal parts production using neural networks
Ježek, Štěpán ; Kolařík, Martin (referee) ; Burget, Radim (advisor)
This thesis is focused on the problem of visual quality control during painted metal parts fabrication. The main problem of the thesis is the design of automatic quality control method based on modern artificial intelligence and computer vision techniques. Quality control is an important part of a large number of industrial production processes, in which it is necessary to ensure compliance with a number of quality requirements for manufactured products. Until now, quality control is carried out mainly by specialized staff, who are subject to a number of expertise requirements. Currently known methods of visual quality control based on artificial intelligence are characterized by high demands on the size of the training data set and low tolerance for a significant change in position and rotation of the inspected objects relative to the scanning device. As a result of these shortcomings, the use of automated visual quality control in many current industrial applications is impossible. The main contribution of this thesis is the design of a new method for quality control, which shows a strong ability to function reliably even in cases where the above mentioned phenomena of change in position, rotation of objects and lack of training data occur during manufacturing. The accuracy of the method proposed in this thesis is experimentally verified on a data set based on the issue of quality control of painted metal parts. According to the measurement results of defect detection accuracy, the proposed method outperformed other, currently known methods by 10, 25 % using the AUROC metric.

National Repository of Grey Literature : 125 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.