|
|
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.
|
|
|
Utilization of Convolution Neural Network Based Road Detection in Mobile Robot Localization
Krejsa, Jiří ; Věchet, Stanislav
Mobile robot on-road navigation requires fusion of both global and local sensory information with an emphasis on the road detection processing. The paper deals with the road detection based on convolution neural networks (CNN) using commonly available tools such as TensorFlow and Keras. The road is defined by its linear boundaries. Network output is formed by the road definition together with classification parameters and serves as a local sensor in Kalman filter based localization. CNN based road detection is currently capable to successfully detect about 90% of images.
|
|
|
Detection of Traffic Signs and Lights
Chocholatý, Tomáš ; Bartl, Vojtěch (referee) ; Herout, Adam (advisor)
The thesis focuses on traffic sign detection and traffic lights detection in view with utilization convolution neural network. The goal is create suitable detector for detection and classification traffic sign in real traffic. For training of convolution neural network were created appropriate datasets, that contains synthetic and real dataset. For synthetic dataset was create generator, that can simulated different deformation of traffic signs. Evaluation is done by own program for quantitative evaluation. The detection rate successfully detected signs is 89\% over own test dataset. The results allow to find out importance of representation real or synthetic dataset in training dataset and influence individual deformations synthetic dataset for final detection quality.
|
|
|
Head Pose Estimation in an Image by a Neural Network
Rybnikár, Lukáš ; Goldmann, Tomáš (referee) ; Orság, Filip (advisor)
Artificial neural networks are not a novelty, but their recent rise in popularity is noticeable as well as their gain of attention from the masses. This bachelor thesis focuses on the head pose estimation in an image using the convolution neural networks. The fields of use of neural networks are vast and during last years strong enough hardware has been developed to allow us to train these networks under commonly accessible conditions. In theoretical part there are neural networks introduced with an explanation of what they are, how they work, how they are divided followed by a detailed description of convolutional neural networks. In the practical part the necessary tools used for development needed to perform experiments, such as determining appropriate configuration for neural network and optimization to get the best results possible, are described.
|
|
|
Hybrid Deep Question Answering
Aghaebrahimian, Ahmad ; Holub, Martin (advisor) ; Kordik, Pavel (referee) ; Pecina, Pavel (referee)
Title: Hybrid Deep Question Answering Author: Ahmad Aghaebrahimian Institute: Institute of Formal and Applied Linguistics Supervisor: RNDr. Martin Holub, Ph.D., Institute of Formal and Applied Lin- guistics Abstract: As one of the oldest tasks of Natural Language Processing, Question Answering is one of the most exciting and challenging research areas with lots of scientific and commercial applications. Question Answering as a discipline in the conjunction of computer science, statistics, linguistics, and cognitive science is concerned with building systems that automatically retrieve answers to ques- tions posed by humans in a natural language. This doctoral dissertation presents the author's research carried out in this discipline. It highlights his studies and research toward a hybrid Question Answering system consisting of two engines for Question Answering over structured and unstructured data. The structured engine comprises a state-of-the-art Question Answering system based on knowl- edge graphs. The unstructured engine consists of a state-of-the-art sentence-level Question Answering system and a word-level Question Answering system with results near to human performance. This work introduces a new Question An- swering dataset for answering word- and sentence-level questions as well. Start- ing from a...
|
|
|
Neuroevolution Principles and Applications
Herec, Jan ; Strnadel, Josef (referee) ; Bidlo, Michal (advisor)
The theoretical part of this work deals with evolutionary algorithms (EA), neural networks (NN) and their synthesis in the form of neuroevolution. From a practical point of view, the aim of the work is to show the application of neuroevolution on two different tasks. The first task is the evolutionary design of the convolutional neural network (CNN) architecture that would be able to classify handwritten digits (from the MNIST dataset) with a high accurancy. The second task is the evolutionary optimization of neurocontroller for a simulated Falcon 9 rocket landing. Both tasks are computationally demanding and therefore have been solved on a supercomputer. As a part of the first task, it was possible to design such architectures which, when properly trained, achieve an accuracy of 99.49%. It turned out that it is possible to automate the design of high-quality architectures with the use of neuroevolution. Within the second task, the neuro-controller weights have been optimized so that, for defined initial conditions, the model of the Falcon booster can successfully land. Neuroevolution succeeded in both tasks.
|
|
|
Using advanced segmentation methods for images from TEM microscopes
Mocko, Štefan ; Chmelík, Jiří (referee) ; Potočňák, Tomáš (advisor)
Tato magisterská práce se zabývá využitím konvolučních neuronových sítí pro segmentační účely v oblasti transmisní elektronové mikroskopie. Také popisuje zvolenou topologii neuronové sítě - U-NET, použíté augmentační techniky a programové prostředí. Firma Thermo Fisher Scientific (dříve FEI Czech Republic s.r.o) poskytla obrazová data pro účely této práce. Získané segmentační výsledky jsou prezentovány ve formě křivek (ROC, PRC) a ve formě numerických hodnot (ARI, DSC, Chybová matice). Zvolená UNET topologie dosáhla excelentních výsledků v oblasti pixelové segmentace. S největší pravděpodobností, budou tyto výsledky sloužit jako odrazový můstek pro interní firemní výzkum.
|
|
|
Captcha Code Recognition
Pazderka, Radek ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
This bachelor thesis is dedicated to design and implementation of application , which's purpose is to recognize text CAPTCHA codes . It describes image processing algorithms , segmentation algorithms and character classification . Two different aproaches were used for classification . Convolution neural network LeNet and histogram classificator , which uses Pearson's correlation coefficient . Chosen classificators were tested on different CAPTCHA codes while finding out the success rate of recognition .
|
|
|
Word2vec Models with Added Context Information
Šůstek, Martin ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
This thesis is concerned with the explanation of the word2vec models. Even though word2vec was introduced recently (2013), many researchers have already tried to extend, understand or at least use the model because it provides surprisingly rich semantic information. This information is encoded in N-dim vector representation and can be recall by performing some operations over the algebra. As an addition, I suggest a model modifications in order to obtain different word representation. To achieve that, I use public picture datasets. This thesis also includes parts dedicated to word2vec extension based on convolution neural network.
|
|
|
Trainable image segmentation using deep neural networks
Majtán, Martin ; Burget, Radim (referee) ; Harár, Pavol (advisor)
Diploma thesis is aimed to trainable image segmentation using deep neural networks. In the paper is explained the principle of digital image processing and image segmentation. In the paper is also explained the principle of artificial neural network, model of artificial neuron, training and activation of artificial neural network. In practical part of the paper is created an algorithm of sliding window to generate sub-images from image from magnetic rezonance. Generated sub-images are used to train, test and validate of the model of neural network. In practical part of the paper si created the model of the artificial neural network, which is used to trainable image segmentation. Model of the neural network is created using the Deeplearning4j library and it is optimized to parallel training using Spark library.
|
guest ::
