|
|
Radio Modulation Recognition Networks
Pijáčková, Kristýna ; Maršálek, Roman (referee) ; Götthans, Tomáš (advisor)
Bakalářská práce se zabývá klasifikací rádiových modulací pomocí metod hloubkového učení. V práci jsou navrženy čtyři architektury, kde tři z nich jsou tvořeny pomocí konvolučních a rekurentních neuronových sítí a čtvrtá využívá architekturu transformátorů. Při návrhu architektur byl brán v potaz výsledný počet parametrů jednotlivých sítí, který může výrazně ovlivňovat výslednou velikost sítě. Pro účely návrhu byl využit programovací jazyk Python a knihovna Keras, která umožňuje práci s neuronovými sítěmi. Výsledky práce jsou následně zhodnoceny a porovnány s výsledky sítí navržených v článcích zabývajících se tímto tématem.
|
|
|
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.
|
|
|
Classification of thorax diseases on chest X-ray images using artificial intelligence
Pijáček, Štěpán ; Mikulec, Marek (referee) ; Mezina, Anzhelika (advisor)
Tato práce se zabývá výzkumem použitelných řešení pro problém klasifikace onemocnění hrudníku na rentgenových snímcích hrudníku pomocí umělé inteligence. Pro lepší pochopení problému jsou v prvních kapitolách vysvětleny základní konvoluční neuronové sítě a jejich výhody a nevýhody. Na základě těchto prvních vysvětlení jsou vybrány dvě neuronové sítě, které rozšiřují koncept konvoluční neuronové sítě. Těmito sítěmi jsou kapslová síť a reziduální síť, obě jsou dále vysvětleny v příslušných kapitolách s jejich výhodami a nevýhodami. Reziduální síť a kapslová síť jsou poté implementovány pomocí programovacího jazyka python a frameworku TensorFlow s knihovnou Keras, obě se svými příslušnými kapitolami. Na konci práce jsou uvedeny výsledky a závěr.
|
|
|
The Use of Artificial Intelligence for Decision Making in the Firm
Volný, Miloš ; Budík, Jan (referee) ; Dostál, Petr (advisor)
This thesis is concerned with future trend prediction on capital markets on the basis of neural networks. Usage of convolutional and recurrent neural networks, Elliott wave theory and scalograms for capital market's future trend prediction is discussed. The aim of this thesis is to propose a novel approach to future trend prediction based on Elliott's wave theory. The proposed approach will be based on the principle of classification of chosen patterns from Elliott's theory by the way of convolutional neural network. To this end scalograms of the chosen Elliott patterns will be created through application of continuous wavelet transform on parts of historical time series of price for chosen stocks.
|
|
|
Typing Using Brain Signals
Wagner, Lukáš ; Malinka, Kamil (referee) ; Tinka, Jan (advisor)
This bachelor thesis focusses on the implementation of a brain-computer interface, programmed in Python language, that would enable to communicate using EEG. The thesis investigates and evaluates existing brain-computer interface technologies for this purpose. The thesis also explores the use of machine learning applied to the technology, in particular neural networks, which have proven to be one of the most accurate methods of EEG signal processing. Following that, 3 different systems are proposed and implemented, each on different paradigm of visually evoking EEG potential changes. These systems were tested with different signal classification approaches. Unfortunately, none of the systems proved to be useful in communication.
|
|
|
Text Recognition Enhanced by Writer Identity
Trněný, Matěj ; Kišš, Martin (referee) ; Kohút, Jan (advisor)
The objective of this theses was to implement a neural network for text recognition enhanced by writers identity. Adversarial learning method was selected for this purpose. Usefulness of this method was verified by experiments. This net should yield better results on data which are not similar to data contained in training data set. Accuracy of the resulting net was compared to method single-task learning and method multi-task learning. Net implementing single-task learning method has reached average character recognition error of 7, 995%, net implementing multi-task learning method has reached average error of 7, 565% and net implementing adversarial learning method has reached average error of 7, 573%. In comparison to the net implementing single-task learning multi-task learning has improvement of 5, 38% and adversarial learning has reached improvement of 5, 28%.
|
|
|
Face Liveness Detection Using a 2D Camera
Valo, Ondrej ; Drahanský, Martin (referee) ; Goldmann, Tomáš (advisor)
Facial recognition is one of the most socially accepted forms of biometric recognition. The recent availability of highly accurate and efficient face recognition algorithms leaves vulnerability to presentation attacks as a major challenge for face recognition solutions. This work deals with the explanation of the issues related to the detection of facial liveliness, which will help to understand the various possibilities of attack and their relationship to existing solutions. And the implementation of an algorithm that recognizes the liveliness of the face based on videos.
|
|
|
Person Identification and Verification Using EEG
Žitný, Roland ; Orság, Filip (referee) ; Tinka, Jan (advisor)
The aim of this work was to create a brain-computer interface that reliably identifies and verifies a person using his electroencephalographic signals. Creating a user profile and verifying it is based on processing reactions to his own face, and the face of strangers or acquaintances. Algorithms such as bandpass and noise removal using wavelet transformation are user to filter signals. The classification of reactions is performed using a convolutional neural network or linear discriminant analysis. The average accuracy of the linear discriminant analysis is 66.2 % and of the convolutional neural network is 58.7 %. The maximum achieved accuracy was with linear discriminant analysis and at 93.7 %.
|
|
|
Detection of significant events in systems baased on phase OTDR
Makówka, David ; Petyovský, Petr (referee) ; Valach, Soběslav (advisor)
This diploma thesis concerns the design, implementation and testing of a system that classifies events captured using optic fiber along a perimeter of guarded objects. A theoretical part introduces physical principles, main structures of measuring systems, methods of measuring, data format, pre-processing options and classification using convolutional neural networks. A practical part describes implementation of a software for convolutional neural networks training and testing, process of samples extraction from measured data, its annotation and conversion to format required by neural networks. Results of measured data analysis and results of achieved classification accuracy using convolutional neural networks for both post processing of measured data and for deployment of neural network into real time processing system are presented.
|
|
|
Reinforcement Learning for Bomberman Type Game
Adamčiak, Jakub ; Beran, Vítězslav (referee) ; Hradiš, Michal (advisor)
This bachelor's thesis aims to develop, implement and train reinforcement learning models for a Bomberman-type game. It is based on Bomberland environment from CoderOne. This environment was created for education and research in the field of artificial intelligence. In this thesis I tackle the settings and problems of implementing agent into the environment. I used 2 policies (MLP and CNN), 2 algorithms (PPO and A2C) and 5 setups of neural networks for feature extraction with the use of libraries stable baselines 3 and pytorch. Total training time resulted in 1207 real-world hours, 4168 computing hours and 271 milions of time steps. Although the training was not successful, this thesis shows the process of implementing a reinforcement learning model into a Gym environment.
|
guest ::
