|
|
Command Classification from EMG Using Neural Network
Zauška, Ján ; Šůstek, Martin (referee) ; Szőke, Igor (advisor)
This work deals with classification of 15 commands (short words), from small dataset recorded by sEMG electrodes placed on face and neck of speaker. Two types of speech are differentiated in recordings - audible speech, what is classic speech and silent speech, hence speech, in which sound output is suppressed. This work describes EMG signal processing, feature extraction, classifier design and classification results. The convolutional neural network architecture was used as a classifier. There are a lot of experiments in this work that compare the classification accuracy of silent and audible speech.
|
|
|
Sleep scoring using artificial neural networks
Vašíčková, Zuzana ; Mézl, Martin (referee) ; Králík, Martin (advisor)
Hlavným cieľom semestrálnej práce je vytvorenie umelej neurónovej siete, ktorá bude schopná roztriediť spánok do spánkových epoch. Na začiatku je uvedené zhrnutie informácií o spánku a spánkových epochách. V ďalších kapitolách sa nachádza dôkladnejší prehľad metod na spracovávanie signálov a na klasifikáciu. Po zhrnutí teoretických znalostí potrebných na uskutočnenie praktickej časti práce boli na základe tohto rozboru vypočítané zo signálov potrebné znaky. Tieto znaky boli podrobené štatistickej analýze a na jej základe boli vybrané niektoré znaky, ktoré boli vhodné ako vstup do neurónovej siete, ktorá je po naučení schopná triediť spánkové epochy do príslušných fáz.
|
|
|
Text Layout Analysis in Historical Documents
Palacková, Bianca ; Hradiš, Michal (referee) ; Kodym, Oldřich (advisor)
The goal of this thesis is to design and implement algorithm for text layout analysis in historical documents. Neural network was used to solve this problem, specifically architecture Faster-RCNN. Dataset of 6 135 images with historical newspaper was used for training and testing. For purpose of the thesis four models of neural networks were trained: model for detection of words, headings, text regions and model for words detection based on position in line. Outputs from these models were processed in order to determine text layout in input image. A modified F-score metric was used for the evaluation. Based on this metric, the algorithm reached an accuracy almost 80 %.
|
|
|
Playing Gomoku with Neural Networks
Bako, Matúš ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The goal of this thesis is to create an artificial intelligence for playing Gomoku. While conventional methods usually use state space search combined with predefined rules, this artificial intelligence uses state space search and learned neural networks. A strategic network computes probability distribution for given a board state and a value network determines outcome of the game from a given board state. I trained multiple architectures of neural networks with different number of convolutional layers and different sizes of convolution kernels. Experiments show, that it is problematic to end a game without using the value network or search algorithm, but the strategic network can be used as a heuristic for choosing next move. Despite using relatively small dataset, created artificial intelligence is capable of beating weaker programs from Gomocup competition.
|
|
|
Weapon Detection in an Image
Debnár, Pavol ; Drahanský, Martin (referee) ; Dvořák, Michal (advisor)
This thesis is focused on the topic of firearms detection in images. In the theoretic section, the explanation of the term firearm is covered, along with the definition of the most prevalent firearm categories. Then the concept of image noise and the ways it can hinder image detection is covered, along with ways of reducing it. Next, algorithms of image detection are introduced - first those which operate on the basis of neural nets - such as Convolutional Neural Nets and Single Shot Multibox Detection. The next section discusses classic algorithms of object detection such as HOG+SVM and SURF. After that, information on the used libraries and software is provided. The experimental part covers the designed algorithm and database. For detection, the HOG+SVM, SURF and SSD algorithms were used. All the algorithms are tested on the database and, if possible, on video. A final evaluation is provided, along with possible future development options.
|
|
|
Intelligent Manager of Fantasy Premier League Game
Vasilišin, Maroš ; Burgetová, Ivana (referee) ; Hynek, Jiří (advisor)
Hra Fantasy Premier League poskytuje miliónom hráčov po celom svete možnosť stať sa na chvíľu manažérom svojho vlastného klubu. Výsledky a bodové ohodnotenie v hre závisia na správnom predvídaní, ako sa budú hráči chovať v skutočných futbalových zápasoch. Ak by pri tomto rozhodovaní pomáhal software na predikciu a analýzu budúcich výkonov hráčov, výsledky v hre sa môžu rapídne zlepšiť. Táto diplomová práca sa zaoberá návrhom a implementáciou predikčného modelu, ktorý využíva neurónové siete na predikcie časových radov počas celej sezóny v hre. Boli použité metódy na spracovanie dát o hráčoch a kluboch za posledné 4 sezóny. Výkonnosť a presnosť predikčných metód boli testované na dátach z poslednej sezóny Premier League a predikcie algoritmu sa vo väčšine prípadov blížili realite. Ak by sa užívateľ držal predikčného modelu v hre stopercentne, získal by väčší počet bodov ako bežný hráč, ktorý žiadny predikčný model nepoužíva.
|
|
|
Playing Gomoku with Neural Networks
Slávka, Michal ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
Táto práca sa zaoberá použitím algoritmu AlphaZero pre hru Gomoku. AlphaZero je založený na spätnoväzbnom učení a k trénovaniu nemusia byť využité žiadne existujúce datasety. Trénovanie prebieha iba na hrách algoritmu samého so sebou. AlphaZero používa algoritmus na prehľadávanie stromu, pre zlepšenie stratégie. Na vylepšnej stratégii sa následne trénuje neurónová sieť. Tento prístup bol úspešný v hrách proti existujúcim algoritmom. Generovanie trénovacích dát vysokej kvality si vyžaduje veľa výpočetne náročných iterácií trénovania a generovania dát. Experimenty ukázali, že každou iteráciou sa algoritmus zlepšuje, čo naznačuje, že je ešte miesto na zlepšenie, ale množstvo iterácií nedostačovalo na to, aby bol poriadne natrénovaný.
|
|
|
Multi-Modal Text Recognition
Kabáč, Michal ; Herout, Adam (referee) ; Kišš, Martin (advisor)
The aim of this thesis is to describe and create a method for correcting text recognizer outputs using speech recognition. The thesis presents an overview of current methods for text and speech recognition using neural networks. It also presents a few existing methods of connecting the outputs of two modalities. Within the thesis, several approaches for the correction of recognizers, which are based on algorithms or neural networks, are designed and implemented. An algorithm based on the principle of searching the outputs of recognizers using levenshtain alignment was proven to be the best approach. It scans the outputs, if the uncertainty of the text recognizer character is less than the pre-selected limit. As part of the work, an annotation server was created for the text transcripts, which was used to collect recordings for the evaluation of experiments.
|
|
|
Classification Framework
Koroncziová, Dominika ; Otrusina, Lubomír (referee) ; Kouřil, Jan (advisor)
The goal of this work is the design and implementation of a machine learning software, based on the RapidMiner library. The finished application integrates the most commonly used algorithms and processes implemented in RapidMiner into an easily usable program. The application contains a simple command line interface, as well as a graphic interface to simplify selection of multiple parameters. The program also provides a tool to create standalone programs, that can be used for classification with a pre-trained model. On top of the original requirements the possibility to work with textual data from Wikipedia was also implemented, providing a tool for downloading and preprocessing of the data in order to use them as training input. This text focuses on the specifics of the algorithms and classifiers used and on their features and uses, and describes the design and implementation of the system. As part of this work, several tests were run in order to validate the efficiency and functionality of the program. The test results are included at the end of the thesis.
|
|
|
Plot Analysis from Book Summaries and User Reviews
Rúček, Peter ; Dočekal, Martin (referee) ; Smrž, Pavel (advisor)
The aim of this work is to create a system for analysis and classification of plot keywords from summarized storylines and user reviews in English. The chosen problem is solved using a transformer-based machine learning technique. The created solution also implements data downloading and a dataset of user reviews and information about books was created, exceeding 23 million reviews and 900 thousand information about books. The system can predict what plot keywords the data contains.
|
guest ::
