|
|
COVID-19 disease classification based on analysis of chest X-rays
Šteflík, Dominik ; Kiac, Martin (referee) ; Myška, Vojtěch (advisor)
This diploma thesis addresses the development and evaluation of artificial intelligence algorithms for classifying COVID-19 disease from chest X-ray images. Given the severity and impact of the COVID-19 pandemic on the global population, the ability to rapidly and accurately diagnose diseases from radiographic images has become critical. This study synthesizes current advancements in image processing and deep learning to evaluate the application of several novel classification methods in practice. Using a dataset obtained from a Czech medical environment, these methods are analyzed and validated in order to examine their effectiveness and accuracy in real life scenarios. The methods chosen for this study, COVID-Net, DarkCovidNet, and CoroNet, were selected due to their availability, widespread use and proven effectiveness in the field. The core of the thesis is the design of a convolutional neural network tailored to extract and learn from the subtle features present in X-ray images indicative of COVID-19. This initiative confronted significant challenges posed by variable acquisition parameters of X-ray images, which can substantially affect diagnostic accuracy. The uniformity of these parameters is crucial for reliable analysis, underscoring the importance of rigorous preprocessing techniques. In response, advanced normalization, contrast adjustment, and augmentation procedures were implemented to standardize the input data. The convolutional network itself employs a series of convolutional, pooling, and fully connected layers, optimized to handle the nuanced variations present in medical imaging data. Notably, the network architecture incorporates an attention mechanism, implemented through a Squeeze-and-Excitation block, to dynamically adjust the importance of different channels in the input image. By integrating these elements, the network model is trained to focus on significant features within the X-ray images, allowing it to distinguish subtle indicators of COVID-19 effectively. Furthermore, this work discusses the potential of integrating these AI-driven diagnostic tools into existing healthcare infrastructures to enhance early detection and treatment of COVID-19. The findings indicate that leveraging artificial intelligence in medical imaging can substantially aid in managing and controlling disease outbreaks, ultimately contributing to better health outcomes.
|
|
|
Named Entity Recognition Exploiting Sub Word Information
Dobrovodský, Patrik ; Egorova, Ekaterina (referee) ; Kesiraju, Santosh (advisor)
Cieľom tejto bakalárskej práce je zhotovenie systému rozpoznania názvoslovnej entity zhotovenej na základe modelu, ktorý bol nedávno považovaný za jeden z najmodernejších a popri tom skúma aký vplyv majú podslovné informácie na nahradenie slov mimo slovnej zásoby. Vytvorený systém vedľa anglického jazyka podporuje aj dva Indo-Európske jazyky konkrétne nemčinu a maďarčinu. Bakalárska práca predstavuje systém využívajúci hlboké učenie pre rozpoznávanie názvoslovných entít, ktorý používa predtrénované a samotrénované slovné vnorenia, zriedkavé vnorenia a charakterové vnorenia vyzdvihnuté konvolučnou neurónovou sieťou. Tieto vnorenia najprv spracujeme sekvenčnou (dlhodobá-krátkodobá pamäť) a potom charakteristickou (podmienené náhodné pole) metódou. Cieľom je dosiahnuť podobnú F1-mieru akú má inšpiračný model s možnosťou porovnania s ostatnými modernými systémami. Výsledkom našej práce je systém, ktorý na anglickej testovacej sade CoNLL 2003 dosiahol 90.98%-né F1-mieru používajúci predtrénované vnorenia a približuje sa k inšpiračnej práci s hodnotou 91.26%. V prípade ďalších jazykov používajúcich samotrénované slovné vnorenia dosiahol systém na testovacej sade WikiAnn pre nemčinu 89.34%-nú a pre maďarčinu 93.04%-nú F1-mieru.
|
|
|
Basics of Pedestrians Detection in Image by Machine Learning
Lučanský, Peter ; Klečka, Jan (referee) ; Horák, Karel (advisor)
Táto Bakalárska práce sa zaoberá významnou problematikou v oblasti počítačového videnia, ktorou je detekcia osôb/chodcov v obraze, za pomoci metod strojového učenia, spolu s jej možným využitím, vývojom a vysvetlením princípov. Taktiež sa zaoberá testovaním dnes najlepšieho dostupného algoritmu, pričom sa porovnávajú faktory ktoré vplívajú na kvalitu jeho činnosti. Na začiatku je problematika stručne popísaná, potom sa prejde k podrobným popisom dosiahnutých pokrokov. V nasledujúcej časti sú popísané dostupné datasety, ktoré by sa dali použiť pri tréningu detekčného algoritmu. V poslednom rade sú vykonané trénovacie procesy za rozličných podmienok, pričom sú jednotlivé výsledky porovnávané.
|
|
|
Using machine learning for quality control in industrial applications
Gaško, Viktor ; Dobrovský, Ladislav (referee) ; Parák, Roman (advisor)
Goal of this bachelor´s thesis is to get acquainted with issue of quality control in industrial applications with focus on deep learning. For this and similar issues was created several libraries which have a purpose of simplifying these issues. Main task is to create program for quality control with help of programming language Python and framework Tensorflow. This program will be comprised of three neural network, from which one will identify the approximate position of the part, second its color, and third will check the correctness of its production.
|
|
|
Mobile Application Using Deep Convolutional Neural Networks
Poliak, Sebastián ; Herout, Adam (referee) ; Sochor, Jakub (advisor)
This thesis describes a process of creating a mobile application using deep convolutional neural networks. The process starts with proposal of the main idea, followed by product and technical design, implementation and evaluation. The thesis also explores the technical background of image recognition, and chooses the most suitable options for the purpose of the application. These are object detection and multi-label classification, which are both implemented, evaluated and compared. The resulting application tries to bring value from both user and technical point of view.
|
|
|
Neural Network Implementation without Multiplication
Slouka, Lukáš ; Baskar, Murali Karthick (referee) ; Szőke, Igor (advisor)
The subject of this thesis is neural network acceleration with the goal of reducing the number of floating point multiplications. The theoretical part of the thesis surveys current trends and methods used in the field of neural network acceleration. However, the focus is on the binarization techniques which allow replacing multiplications with logical operators. The theoretical base is put into practice in two ways. First is the GPU implementation of crucial binary operators in the Tensorflow framework with a performance benchmark. Second is an application of these operators in simple image classifier. Results are certainly encouraging. Implemented operators achieve speed-up by a factor of 2.5 when compared to highly optimized cuBLAS operators. The last chapter compares accuracies achieved by binarized models and their full-precision counterparts on various architectures.
|
|
|
Face Recognition with Acceleration on the Neural Compute Stick
Horník, Matej ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
This bachelor thesis deals with current techniques for recognizing people by face. Convolutional neural networks are currently used for face recognition. In this work, convolutional neural networks will be described and also the architectures of convolutional networks used for face recognition will be compared. The goal will be to create a built-in system that will consist of a camera, a computing unit and a Neural Compute Stick accelerator. The system will recognize people by face with a freely available algorithm.
|
|
|
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.
|
|
|
Determination of Gun Type and Position in Image Scene
Kolcún, Róbert ; Goldmann, Tomáš (referee) ; Drahanský, Martin (advisor)
The main goal of this work is to design an approach for classifying guns into two categories, with short and long weapons, and determining a position of guns in the image scene. This problem was solved using the classical approach as K-Nearest-Neighbour and SVM classification and using convolutional neural networks. In this work was made a comparison of these approaches with a resulting accuracy up to 90%. With the results of this work, it is possible to choose a right approach to this problem.
|
|
|
Object Detection in the Laser Scans Using Convolutional Neural Networks
Zelenák, Michal ; Kodym, Oldřich (referee) ; Veľas, Martin (advisor)
This work is focused on road segmentation in laser scans, using a convolutional neural network. To achieve this goal, which will find application in the field of road maintenance, convolutional neural networks have been used for their flexibility and speed. The work brings implementation and modifications of the existing method, which solves the problem by using a fully connected convolutional neural network. Used modifications include, for example using of various parameters for the loss function, the use of a different number of classes in the network model and dataset. The effect of the modification was experimentally verified and the accuracy of 96.12%, and the value for F-measure 95.02% were achieved.
|
guest ::
