|
Gpon Attacks And Errors Classification
Tomašov, Adrián
This paper focuses on various types of attacks and errors in an activation process of Gigabitcapablepassive optical networks. The process sends messages via Physical Layer Operation Administrationand Maintenance header field inside the transmitted frame. An exemplar network communicationis captured by a special hardware-accelerated network interface card capable of processing opticalsignals from passive optical networks. The captured data is filtered of irrelevant parts and messagesand correctly formatted into a suitable shape for a neural network. The filtered data is divided intosmall sequences called time windows and analyzed using a recurrent neural network-based on Gatedrecurrent unit cells. A new neural network model is designed to classify sequences into several categories:additional message, missing message, error inside (noisy) message, and message order error.All of these categories represent a certain type of attack or error. The proposed model can distinguishmessage sequences into these categories with high accuracy resulting in revealing a possible attackeror drift from protocol recommendation.
|
|
Using artificial intelligence to monitor the state of the machine
Popara, Nikola ; Bražina, Jakub (referee) ; Kovář, Jiří (advisor)
This thesis is focus on monitoring state of machine parts that are under the most stress. Type of artificial intelligence used in this work is recurrent neural network and its modifications. Chosen type of neural network was used because of the sequential character of used data. This thesis is solving three problems. In first problem algorithm is trying to determine state of mill tool wear using recurrent neural network. Used method for monitoring state is indirect. Second Problem was focused on detecting fault of a bearing and classifying it to specific category. In third problem RNN is used to predict RUL of monitored bearing.
|
|
Adaptation of Neural Networks to Target Writer
Sekula, Jakub ; Hradiš, Michal (referee) ; Kohút, Jan (advisor)
This bachelor's thesis deals with the adaptation of neural networks to a specific writer with an aim to improve recognition of handwritten text of this specific writer. The method that I use is fast, requires small training dataset and uses regularization, which tries to keep the distribution of regularized weights in adaptation network similar to the one in the original network. I tested this method on dataset of printed text called IMPACT and dataset of handwritten text. When testing on dataset of handwritten text I was able to improve recognition on two diaries with pre adaptation recognition error rate of 10,82 % and 1,82 % to 8,48 % and 0,77 % with a small number of adaptation iterations and using small amount of training lines. When testing on IMPACT dataset I was able to improve recognition error rate from 32,88 % to 5,30 %.
|
|
Convolutional Networks for Handwriting Recognition
Sladký, Jan ; Kišš, Martin (referee) ; Hradiš, Michal (advisor)
This thesis deals with handwriting recognition using convolutional neural networks. From the current methods, a network model was chosen to consist of convolutional and recurrent neural networks with the Connectist Temporal Classification. The Vertical Attention Module, which selects the relevant information in each column corresponding to the text in the figure was subsequently implemented in such a model. Then, this module was compared with other possibilities of vertical aggregation between convolutional and recurrent networks. The experiments took place on a data set containing over 80,000 lines of text from Czech letters from the 20th century. The results show that the Vertical Attention Module almost always achieves the best results on all used types of convolution networks. The resulting network achieved the best result with 8,9% of the character error rate. The contribution of this work is a neural network with a newly introduced element that can recognize lines of text.
|
|
Neural Network for Autocomplete in the Browser
Kubík, Ján Jakub ; Zemčík, Pavel (referee) ; Kolář, Martin (advisor)
The goal of this thesis is to create and train a neural network and use it in a web browser for English text sequence prediction during writing of text by the user. The intention is to simplify the writing of frequent phrases. The problem is solved by employing a recurrent neural network that is able to predict output text based on the text input. Trained neural network is then used in a Google Chrome extension. By normalized ouput of the neural network, text choosing by sampling decoding algorithm and connecting, the extension is able to generate English word sequences, which are shown to the user as suggested text. The neural network is optimized by selecting the right loss function, and a suitable number of recurrent layers, neurons in the layers, and training epochs. The thesis contributes to enhancing the everyday user experience of writing on the Internet by using a neural network for English word sequence autocomplete in the browser.
|
|
Algorithmic Accompaniment Composition
Vinš, Jakub ; Hradiš, Michal (referee) ; Kolář, Martin (advisor)
This thesis deals with problems of computer music, especially with generating accompaniment to an existing song in MIDI format by means of artificial neural networks. Existing methods of algorithmic music composition are presented in the beginning. Followed by problems and their solutions connected with the conversion of MIDI files to matrices, which are suitable as an input for neural network and their inverse transformation. Subsequently are proposed, created, optimized and evaluated models which generate saxophone and piano accompaniment by means of feedforward and recurrent neural network. At the end model generates accompaniment to my own song as a form of a test.
|
|
Automatic tagging of musical compositions using machine learning methods
Semela, René ; Galáž, Zoltán (referee) ; Kiska, Tomáš (advisor)
One of the many challenges of machine learning are systems for automatic tagging of music, the complexity of this issue in particular. These systems can be practically used in the content analysis of music or the sorting of music libraries. This thesis deals with the design, training, testing, and evaluation of artificial neural network architectures for automatic tagging of music. In the beginning, attention is paid to the setting of the theoretical foundation of this field. In the practical part of this thesis, 8 architectures of neural networks are designed (4 fully convolutional and 4 convolutional recurrent). These architectures are then trained using the MagnaTagATune Dataset and mel spectrogram. After training, these architectures are tested and evaluated. The best results are achieved by the four-layer convolutional recurrent neural network (CRNN4) with the ROC-AUC = 0.9046 ± 0.0016. As the next step of the practical part of this thesis, a completely new Last.fm Dataset 2020 is created. This dataset uses Last.fm and Spotify API for data acquisition and contains 100 tags and 122877 tracks. The most successful architectures are then trained, tested, and evaluated on this new dataset. The best results on this dataset are achieved by the six-layer fully convolutional neural network (FCNN6) with the ROC-AUC = 0.8590 ± 0.0011. Finally, a simple application is introduced as a concluding point of this thesis. This application is designed for testing individual neural network architectures on a user-inserted audio file. Overall results of this thesis are similar to other papers on the same topic, but this thesis brings several new findings and innovations. In terms of innovations, a significant reduction in the complexity of individual neural network architectures is achieved while maintaining similar results.
|
|
Advanced classification of cardiac arrhythmias in ECG
Sláma, Štěpán ; Hejč, Jakub (referee) ; Ronzhina, Marina (advisor)
This work focuses on a theoretical explanation of heart rhythm disorders and the possibility of their automatic detection using deep learning networks. For the purposes of this work, a total of 6884 10-second ECG recordings with measured eight leads were used. Those recordings were divided into 5 groups according to heart rhythm into a group of records with atrial fibrillation, sinus rhythms, supraventricular rhythms, ventricular rhythms, and the last group consisted of the others records. Individual groups were unbalanced represented and more than 85 % of the total number of data are sinus rhythm group records. The used classification methods served effectively as a record detector of the largest group and the most effective of all was a procedure consisting of a 2D convolutional neural network into which data entered in the form of scalalograms (classification procedure number 3). It achieved results of precision of 91%, recall of 96% and F1-score values of 0.93. On the contrary, when classifying all groups at the same time, there were no such quality results for all groups. The most efficient procedure seems to be a variant composed of PCA on eight input signals with the gain of one output signal, which becomes the input of a 1D convolutional neural network (classification procedure number 5). This procedure achieved the following F1-score values: 1) group of records with atrial fibrillation 0.54, 2) group of sinus rhythms 0.91, 3) group of supraventricular rhythms 0.65, 4) group of ventricular rhythms 0.68, 5) others records 0.65.
|
|
Image based smoke and fire detection
Ďuriš, Denis ; Burda, Karel (referee) ; Přinosil, Jiří (advisor)
This diploma thesis deals with the detection of fire and smoke from the image signal. The approach of this work uses a combination of convolutional and recurrent neural network. Machine learning models created in this work contain inception modules and blocks of long short-term memory. The research part describes selected models of machine learning used in solving the problem of fire detection in static and dynamic image data. As part of the solution, a data set containing videos and still images used to train the designed neural networks was created. The results of this approach are evaluated in conclusion.
|
|
Convolutional Networks for Historic Text Recognition
Vešelíny, Peter ; Kolář, Martin (referee) ; Kišš, Martin (advisor)
This thesis deals with text line recognition of historical documents. Historical texts dating back to the 17th - 19th centuries are written in fraktur typeface. The character recognition problem is solved using neural network architecture called sequence-to-sequence . This architecture is based on encoder-decoder model and contains attention mechanism. In this thesis a dataset, from texts originated from German archiv called Deutsches Textarchiv , was created. This archive contains 3 897 different German books that have available transcripts and corresponding images of pages. The created dataset was used to train and experiment with the proposed neural network. During the experiments, several convolutional models, hyperparameters and the effects of positional embedding were investigated. The final tool can recognize characters with accuracy 99,63 %. The contribution of this work is the~mentioned dataset and neural network, which can be used to recognize historical documents.
|