National Repository of Grey Literature 13 records found  1 - 10next  jump to record: Search took 0.00 seconds. 
Graph Convolutional Neural Networks For Sentiment Analysis
Myska, Vojtech
Commonly used approaches based on deep learning for sentiment analysis task operating over data in Euclidean space. In contrast with them, this paper presents, a novel approach for sentiment analysis task based on a graph convolutional neural networks (GCNs) operating with data in Non-Euclidean space. Text data processed by the approach have to be converted to a graph structure. Our GCNs models have been trained on 25 000 data samples and evaluated 5 000 samples. The Yelp data set has been used. The experiment is focused on polarity sentiment analysis task. Nevertheless, a relatively small training data set has been used, our best model achieved 86.12% accuracy.
Interactive web presentation of audiovisual works
Paulech, Matúš ; Myška, Vojtěch (referee) ; Sikora, Pavel (advisor)
The bachelor thesis contains a presentation of audiovisual works processed by a calibrator based on neural networks (deep learning and artificial intelligence). The work deals with uploading video files to a web application and then playing them on a website. Data, that have been processed by neural networks, are added to the videos. This data is divided according to the classification into given tags, in which it is written what is currently in the image of video. These tags can be used to classify videos, and these classifications are also displayed in real time during video playback.
Image data segmentation using deep neural networks
Hrdý, Martin ; Myška, Vojtěch (referee) ; Kiac, Martin (advisor)
The main aim of this master’s thesis is to get acquainted with the theory of the current segmentation methods, that use deep learning. Segmentation neural network that will be capable of segmenting individual instances of the objects will be proposed and created based on theoretical knowledge. The main focus of the segmentation neural network will be segmentation of electronic components from printed circuit boards.
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.
Object detection in video using neural networks
Mikulský, Petr ; Sikora, Pavel (referee) ; Myška, Vojtěch (advisor)
This diploma thesis deals with the detection of moving objects in a video recording using neural networks. The aim of the thesis was to detect road users in video recordings. Pre-trained YOLOv5 object detection model was used for a practical part of the thesis. As part of the solution, an own dataset of traffic road video recordings was created and annotated with following classes: a car, a bus, a van, a motorcycle, a truck and a trailer truck. Final version of this dataset comprise 5404 frames and 6467 annotated objects in total. After training, the YOLOv5 model achieved 0.995 mAP, 0.995 precision and 0.986 recall on the dataset. All steps leading to the final form of the dataset are described in the conclusion chapter.
Object detection in video using neural networks and Android application
Mikulec, Vojtěch ; Kiac, Martin (referee) ; Myška, Vojtěch (advisor)
This master’s thesis deals with the implementation of functional solution for classifying road users using mobile device with Android operating system. The goal is to create Android application which classifies vehicles in real time using rear-facing camera and saves timestamps of classification. Testing is performed mostly with own, diversely modificated dataset. Five models are trained and their performance is measured in dependence on hardware. The best classification performance is from pretrained MobileNet model where transfer learning with 6 classes of own dataset is used – 62,33 %. The results are summarized and a method for faster and more accurate traffic analysis is proposed.
Language-Independent Text Classifier Based On Recurrent Neural Networks
Myska, Vojtech
This paper deals with a proposal of language independent text classifiers based on recurrent neural networks. They work at a character level thus they do not require any text preprocessing. The classifiers have been trained and evaluated on a multilingual data set that is privately collected from film review databases. It contains Czech (Slovak), English, German and Spanish language subset. The resulting accuracy of the proposed language independent classifiers base on the recurrent neural networks in polarity sentiment analysis task is 78.55%.
Interactive Searching in Online Archive of Visual and Audiovisual Artworks
Kuře, Dominik ; Myška, Vojtěch (referee) ; Schimmel, Jiří (advisor)
This bachelor thesis focuses on development of a web application, which serves as an archive for videos. Each video has a certain amount of keywords. The application uses an already created database and a preinstalled server on which the videos are uploaded. The database was given to the author by his supervisor. Searching through the archive can be done by inputting an expression into a search bar or through a variation of filters that are based on information about each video. The results and the database as a whole are graphically represented by charts, which change their form based on given data. Videos can be played in a video player and a list of similar videos is generated. The list is based on keywords which the videos have in common. The main technologies used in the application are Node.js, React and MariaDB. A good amount of libraries are used for this application, allowing JavaScript to be the primary programming language in all phases of development. The text of this bachelor thesis can be dividen in two parts - theoretical and practical. The first part describes all the technologies and libraries used in the application. An in depth approach was taken especially on those parts of each library which are actually being used in the practical. Apart from the necessary technologies, the reader will be also introduced to libraries and systems which help a programmer with his work such as automatic formatting of code and it's backup, saving different versions of the code or adding static datatypes into JavaScript through TypeScript. The theoretical part should give the reader a summary of how browser applications work and communicate with each other. In the practical part an entire application will be built from scratch. The application will connect four different servers - front-end, back-end, database server and a server storing the videos - and allow them to communicate accordingly. The bachelor thesis also contains information about using different controllers for manipulating the browser.
Creation of Bluetooth data logger for recording and processing of measured data
Vaverka, Jan ; Myška, Vojtěch (referee) ; Dejdar, Petr (advisor)
The first part of the theses deals with dataloggers and their use in today's world. The second part is dedicated to microcontrollers which are used as a control unit for dataloggers. Individual peripheral devices MCU and their communication interfaces have been described. The next part deals with Bluetooth Low Energy which is used for data broadcasting to the user. Based on the acquired knowledge the microcontroller and sensors were selected. A datalogger was constructed and programmed from selected components, which will measure the properties of ferment during fruit fermentation. Finally, a mobile application was created to download data from the datalogger and then display the data in charts.
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.

National Repository of Grey Literature : 13 records found   1 - 10next  jump to record:
See also: similar author names
4 Myska, Vojtech
1 Myška, Vladan
Interested in being notified about new results for this query?
Subscribe to the RSS feed.