|
|
Modern anorganic foundry binder systems
Kolařík, Martin ; Rusín, Karel (referee) ; Cupák, Petr (advisor)
This bachelor thesis deals with newly developed inorganic binder systems. These are mainly developed for their ecological advantages. However, some of the discussed binder systems have better technological properties. Inorganic binder systems are described herein, both on the basis of alkaline silicates and on the basis of inorganic salts. Attention is also paid to bentonite, which is still the most commonly used binder in the world. It turns out that these binder systems will be important for the future of the foundry industry.
|
|
|
Multiclass segmentation of 3D medical data using deep learning
Slunský, Tomáš ; Uher, Václav (referee) ; Kolařík, Martin (advisor)
Master's thesis deals with multiclass image segmentation using convolutional neural networks. The theoretical part of the Master's thesis focuses on image segmentation. There are basics principles of neural networks and image segmentation with more types of approaches. In practical part the Unet architecture is choosen and is described for image segmentation more. U-net was applied for medicine dataset. There is processing procedure which is more described for image proccesing of three-dimmensional data. There are also methods for data preproccessing which were applied for image multiclass segmentation. Final part of current master's thesis evaluates results.
|
|
|
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.
|
|
| |
|
|
Segmentation of multiple sclerosis lesions using deep neural networks
Sasko, Dominik ; Myška, Vojtěch (referee) ; Kolařík, Martin (advisor)
Hlavným zámerom tejto diplomovej práce bola automatická segmentácia lézií sklerózy multiplex na snímkoch MRI. V rámci práce boli otestované najnovšie metódy segmentácie s využitím hlbokých neurónových sietí a porovnané prístupy inicializácie váh sietí pomocou preneseného učenia (transfer learning) a samoriadeného učenia (self-supervised learning). Samotný problém automatickej segmentácie lézií sklerózy multiplex je veľmi náročný, a to primárne kvôli vysokej nevyváženosti datasetu (skeny mozgov zvyčajne obsahujú len malé množstvo poškodeného tkaniva). Ďalšou výzvou je manuálna anotácia týchto lézií, nakoľko dvaja rozdielni doktori môžu označiť iné časti mozgu ako poškodené a hodnota Dice Coefficient týchto anotácií je približne 0,86. Možnosť zjednodušenia procesu anotovania lézií automatizáciou by mohlo zlepšiť výpočet množstva lézií, čo by mohlo viesť k zlepšeniu diagnostiky individuálnych pacientov. Našim cieľom bolo navrhnutie dvoch techník využívajúcich transfer learning na predtrénovanie váh, ktoré by neskôr mohli zlepšiť výsledky terajších segmentačných modelov. Teoretická časť opisuje rozdelenie umelej inteligencie, strojového učenia a hlbokých neurónových sietí a ich využitie pri segmentácii obrazu. Následne je popísaná skleróza multiplex, jej typy, symptómy, diagnostika a liečba. Praktická časť začína predspracovaním dát. Najprv boli skeny mozgu upravené na rovnaké rozlíšenie s rovnakou veľkosťou voxelu. Dôvodom tejto úpravy bolo využitie troch odlišných datasetov, v ktorých boli skeny vytvárané rozličnými prístrojmi od rôznych výrobcov. Jeden dataset taktiež obsahoval lebku, a tak bolo nutné jej odstránenie pomocou nástroju FSL pre ponechanie samotného mozgu pacienta. Využívali sme 3D skeny (FLAIR, T1 a T2 modality), ktoré boli postupne rozdelené na individuálne 2D rezy a použité na vstup neurónovej siete s enkodér-dekodér architektúrou. Dataset na trénovanie obsahoval 6720 rezov s rozlíšením 192 x 192 pixelov (po odstránení rezov, ktorých maska neobsahovala žiadnu hodnotu). Využitá loss funkcia bola Combo loss (kombinácia Dice Loss s upravenou Cross-Entropy). Prvá metóda sa zameriavala na využitie predtrénovaných váh z ImageNet datasetu na enkodér U-Net architektúry so zamknutými váhami enkodéra, resp. bez zamknutia a následného porovnania s náhodnou inicializáciou váh. V tomto prípade sme použili len FLAIR modalitu. Transfer learning dokázalo zvýšiť sledovanú metriku z hodnoty približne 0,4 na 0,6. Rozdiel medzi zamknutými a nezamknutými váhami enkodéru sa pohyboval okolo 0,02. Druhá navrhnutá technika používala self-supervised kontext enkodér s Generative Adversarial Networks (GAN) na predtrénovanie váh. Táto sieť využívala všetky tri spomenuté modality aj s prázdnymi rezmi masiek (spolu 23040 obrázkov). Úlohou GAN siete bolo dotvoriť sken mozgu, ktorý bol prekrytý čiernou maskou v tvare šachovnice. Takto naučené váhy boli následne načítané do enkodéru na aplikáciu na náš segmentačný problém. Tento experiment nevykazoval lepšie výsledky, s hodnotou DSC 0,29 a 0,09 (nezamknuté a zamknuté váhy enkodéru). Prudké zníženie metriky mohlo byť spôsobené použitím predtrénovaných váh na vzdialených problémoch (segmentácia a self-supervised kontext enkodér), ako aj zložitosť úlohy kvôli nevyváženému datasetu.
|
|
|
Denoise Pre-Training For Segmentation Neural Networks
Kolarik, Martin
This paper proposes a method for pre-training segmentation neural networks on small datasets using unlabelled training data with added noise. The pre-training process helps the network with initial better weights settings for the training itself and also augments the training dataset when dealing with small labelled datasets especially in medical imaging. The experiment comparing results of pre-trained and not pre-trained networks on MRI brain segmentation task has shown that the denoise pre-training helps the network with faster training convergence without overfitting and achieving better results in all compared metrics even on very small datasets.
|
|
|
Email spam filtering using artificial intelligence
Safonov, Yehor ; Uher, Václav (referee) ; Kolařík, Martin (advisor)
In the modern world, email communication defines itself as the most used technology for exchanging messages between users. It is based on three pillars which contribute to the popularity and stimulate its rapid growth. These pillars are represented by free availability, efficiency and intuitiveness during exchange of information. All of them constitute a significant advantage in the provision of communication services. On the other hand, the growing popularity of email technologies poses considerable security risks and transforms them into an universal tool for spreading unsolicited content. Potential attacks may be aimed at either a specific endpoints or whole computer infrastructures. Despite achieving high accuracy during spam filtering, traditional techniques do not often catch up to rapid growth and evolution of spam techniques. These approaches are affected by overfitting issues, converging into a poor local minimum, inefficiency in highdimensional data processing and have long-term maintainability issues. One of the main goals of this master's thesis is to develop and train deep neural networks using the latest machine learning techniques for successfully solving text-based spam classification problem belonging to the Natural Language Processing (NLP) domain. From a theoretical point of view, the master's thesis is focused on the e-mail communication area with an emphasis on spam filtering. Next parts of the thesis bring attention to the domain of machine learning and artificial neural networks, discuss principles of their operations and basic properties. The theoretical part also covers possible ways of applying described techniques to the area of text analysis and solving NLP. One of the key aspects of the study lies in a detailed comparison of current machine learning methods, their specifics and accuracy when applied to spam filtering. At the beginning of the practical part, focus will be placed on the e-mail dataset processing. This phase was divided into five stages with the motivation of maintaining key features of the raw data and increasing the final quality of the dataset. The created dataset was used for training, testing and validation of types of the chosen deep neural networks. Selected models ULMFiT, BERT and XLNet have been successfully implemented. The master's thesis includes a description of the final data adaptation, neural networks learning process, their testing and validation. In the end of the work, the implemented models are compared using a confusion matrix and possible improvements and concise conclusion are also outlined.
|
|
|
A tool for generating a random configuration of a cyber arena
Matisko, Maroš ; Kolařík, Martin (referee) ; Uher, Václav (advisor)
The master's thesis is focused on the design and implementation of a tool for generating configuration named Ansible. The result of using this tool is generated configuration, which contains random values chosen according to specified parameters and it was deployed on a virtual testing infrastructure. The theoretical part describes approaches of network automation in the process of deploying and configuration of network devices called Infrastructure as code. It also describes programme Ansible, which will be using the output of the implemented tool. The practical part of the thesis is focused on designing the functionality and internal structure of the tool, implementation of the tool and testing implemented tool as well as generated configuration.
|
|
|
Image segmentation methods with limited data sets
Horečný, Peter ; Kolařík, Martin (referee) ; Burget, Radim (advisor)
The goal of this thesis was to propose an image segmentation method, which is capable of effective segmentation process with small datasets. Recently published ODE neural network was used for this method, because its features should provide better generalization in case of tasks with only small datasets available. The proposed ODE-UNet network was created by combining UNet architecture with ODE neural network, while using benefits of both networks. ODE-UNet reached following results on ISBI dataset: Rand: 0,950272 and Info: 0,978061. These results are better than the ones received from UNet model, which was also tested in this thesis, but it has been proven that state of the art can not be outperformed using ODE neural networks. However, the advantages of ODE neural network over tested UNet architecture and other methods were confirmed, and there is still a room for improvement by extending this method.
|
|
|
Image segmentation using graph neural networks
Boszorád, Matej ; Kolařík, Martin (referee) ; Myška, Vojtěch (advisor)
This diploma thesis describes and implements the design of a graph neural network usedfor 2D segmentation of neural structure. The first chapter of the thesis briefly introduces the problem of segmentation. In this chapter, segmentation techniques are divided according to the principles of the methods they use. Each type of technique contains the essence of this category as well as a description of one representative. The second chapter of the diploma thesis explains graph neural networks (GNN for short). Here, the thesis divides graph neural networks in general and describes recurrent graph neural networks(RGNN for short) and graph autoencoders, that can be used for image segmentation, in more detail. The specific image segmentation solution is based on the message passing method in RGNN, which can replace convolution masks in convolutional neural networks.RGNN also provides a simpler multilayer perceptron topology. The second type of graph neural networks characterised in the thesis are graph autoencoders, which use various methods for better encoding of graph vertices into Euclidean space. The last part ofthe diploma thesis deals with the analysis of the problem, the proposal of its specific solution and the evaluation of results. The purpose of the practical part of the work was the implementation of GNN for image data segmentation. The advantage of using neural networks is the ability to solve different types of segmentation by changing training data. RGNN with messaging passing and node2vec were used as implementation GNNf or segmentation problem. RGNN training was performed on graphics cards provided bythe school and Google Colaboratory. Learning RGNN using node2vec was very memory intensive and therefore it was necessary to train on a processor with an operating memory larger than 12GB. As part of the RGNN optimization, learning was tested using various loss functions, changing topology and learning parameters. A tree structure method was developed to use node2vec to improve segmentation, but the results did not confirman improvement for a small number of iterations. The best outcomes of the practical implementation were evaluated by comparing the tested data with the convolutional neural network U-Net. It is possible to state comparable results to the U-Net network, but further testing is needed to compare these neural networks. The result of the thesisis the use of RGNN as a modern solution to the problem of image segmentation and providing a foundation for further research.
|
guest ::
