|
|
Deployment of deep learning-based anomaly detection systems: challenges and solutions
Ježek, Štěpán ; Burget, Radim
Visual anomaly detection systems play an important role in various domains, including surveillance, industrial quality control, and medical imaging. However, the deployment of such systems presents significant challenges due to a wide range of possible scene setups with varying number of devices and high computational requirements of deep learning algorithms. This research paper investigates the challenges encountered during the deployment of visual anomaly detection systems for industrial applications and proposes solutions to address them effectively. We present a model use case scenario from real-world manufacturing quality control and propose an efficient distributed system for deployment of the defect detection methods in manufacturing facilities. The proposed solution aims to provide a general framework for deploying visual defect detection algorithms base on deep neural networks and their high computational requirements. Additionally, the paper addresses challenges related the whole process of automated quality control, which can be performed with varying number of camera devices and it mostly requires interaction with other factory services or workers themselves. We believe the presented framework can contribute to more widespread use of deep learning-based defect detection systems, which may provide valuable feedback for further research and development.
|
|
|
Implementation of a deep learning model for segmentation of multiple myeloma in CT data
Gálík, Pavel ; Nohel, Michal
This paper deals with the implementation of a deep learning model for spinal tumor segmentation of multiple myeloma patients in CT data. Deep learning is becoming an important part of developing computer-aided detection and diagnosis systems. In this study, a database of 25 patients who were imaged on spectral CT and for whom different parametric images (conventional CT, virtual monoenergetic images, calcium suppression images) were reconstructed, was used. Three convolutional neural network models based on the nnU-Net framework for lytic lesion segmentation were trained on the selected data. The results were evaluated on a test database and the trained models were compared.
|
|
|
Deep prior audio compression
Švento, Michal ; Balušík, Peter
Audio compression is still an up-to-date topic because the demand for big data streams is rapidly increasing. Deep learning has brought up new algorithms that decrease bitrates with good perception quality. The novel approach in generative artificial intelligence is to produce new data from prior stored in network parameters, called a deep prior. The deep audio prior framework shows its success in various tasks such as inpainting, declipping, and bandwidth extension, but it has not been tested for compression. In this paper, we test this method with a prebuilt network for inpainting. Our idea of compression is based on reducing the number of time-frequency coefficients in the spectrogram while allowing the reconstruction of the original signal with high quality.
|
|
|
Graph Neural Networks in Epilepsy Surgery
Hrtonová, Valentina ; Filipenská, Marina ; Klimeš, Petr
Epilepsy surgery presents a viable treatment option for patients with drug-resistant epilepsy, necessitating precise localization of the epileptogenic zone (EZ) for optimal outcomes. As the limitations of currently used localization methods lead to a seizure-free postsurgical outcome only in about 60% of cases, this study introduces a novel approach to EZ localization by leveraging Graph Neural Networks (GNNs) for the analysis of interictal stereoelectroencephalography (SEEG) data. A GraphSAGE-based model for identifying resected seizure-onset zone (SOZ) electrode contacts was applied to a clinical dataset comprising 17 patients from two institutions. This study uniquely focuses on the use of interictal SEEG recordings, aiming to streamline the presurgical monitoring process and minimize risks and costs associated with prolonged SEEG monitoring. Through this innovative approach, the GNN model demonstrated promising results, achieving an Area Under the Receiver Operating Characteristic (AUROC) score of 0.830 and an Area Under the Precision-Recall Curve (AUPRC) of 0.432. These outcomes along with the potential of GNNs in leveraging the patient-specific electrode placement highlight their potential in enhancing the accuracy of EZ localization in drug-resistant epilepsy patients.
|
|
|
Degree of protein structure disorder in prokaryotic and eukaryotic organisms
Nováková, Zuzana ; Vondrášek, Jiří (advisor) ; Feidakis, Christos (referee)
The structure-function paradigm of protein biology has been fundamentally changed in the last three decades by the discovery of intrinsically disordered proteins (IDPs) and regions (IDRs). These proteins have been identified as critical components in various cellular processes, including signaling, protein-protein interactions, and regulation. While it is apparent that IDPs/IDRs are vital in the function of living organisms, the study of their structure has posed a great challenge. Despite recent advancements in NMR spectroscopy and deep learning algorithms for protein structure prediction, IDPs/IDRs remain a relatively unnkown territory, with significant gaps in knowledge about their behavior and function in living systems. Although IDPs are present in all life forms, their abundance reveals a correlation between organismal complexity and degree of protein disorder. Prokaryotic organisms exhibit a much lower prevalence of IDPs than eukaryotic. Notably, a substantial degree of disorder is observed in unicellular parasitic protists, implying, that IDPs are fundamental in pathogenesis and the progression of diseases like malaria and toxoplasmosis. In humans, malfunctions in IDPs are linked to many conditions, including neurodegenerative diseases such as Parkinsons's, Alzheimer's as well as various...
|
|
|
Methods for Realtime Voice Deepfakes Creation
Alakaev, Kambulat ; Pleško, Filip (referee) ; Malinka, Kamil (advisor)
Tato práce zkoumá možnosti generování hlasových deepfake v reálném čase pomocí nástrojů s otevřeným zdrojovým kódem. Experimenty bylo zjištěno, že rychlost generování hlasových deepfakes je ovlivněna výpočetním výkonem zařízení, na kterých jsou nástroje pro tvorbu řeči spuštěny. Byl identifikován model hlubokého učení, který je schopen generovat řeč téměř v reálném čase. Omezení nástroje obsahujícího tento model však bránila kontinuálnímu zadávání vstupních dat pro generování v reálném čase. K řešení tohoto problému byl vyvinut program, který tato omezení překonává. Kvalita generovaných deepfakes byla hodnocena jak pomocí modelů pro detekci hlasových deepfake, tak pomocí online průzkumů na lidech. Výsledky ukázaly, že zatímco model dokázal oklamat detekční modely, nebyl úspěšný při oklamání lidí. Tento výzkum upozorňuje na dostupnost nástrojů pro syntézu hlasu s otevřeným zdrojovým kódem a na možnost jejich zneužití jednotlivci k podvodným účelům.
|
|
|
Detecting Presentation Attacks Using Face Spoofing
Homola, Tomáš ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
Face detection is one of the most important and widespread methods of verifying a person's identity. However, this method also raises concerns about privacy and security. It is important to be aware of the dangers it brings and constantly develop the necessary means to protect against them. This thesis aims to explain the issue of face spoofing, the threat that arises from a successful attacker's attempt at spoofing, and the detection of these spoofs using algorithms.
|
|
|
A Reduced Neural Network for Classifying the Presence of People in an Image
Stanček, Rastislav ; Rydlo, Štěpán (referee) ; Goldmann, Tomáš (advisor)
Táto práca sa zameriava na tému počítačového videnia, presnejšie, na binárnu klasifikáciu prítomnosti ľudí v obrazových dátach. Cieľom tejto práce je vytvoriť redukovanú neurónovú sieť s využitím metódy knowledge distillation. Klasifikácia a detekcia objektov je výpočtovo náročná operácia. Študentský model vytvorený pomocou knowledge distillation vykazuje ekvivalentnú presnosť, pričom je menší a má vyššiu inferenčnú rýchlosť v porovnaní s učiteľským modelom. Takýto model môže byť interdisciplinárne všestranný a to predovšetkým na koncových zariadeniach, ktoré majú relatívne slabé výpočtové schopnosti.
|
|
|
System for Recognizing Disinformation in Web Environment
Večerka, Lukáš ; Žádník, Martin (referee) ; Strnadel, Josef (advisor)
This work deals with the design, implementation, and verification of a system for automatic recognition of disinformation on the web. It addresses the issue of disinformation spread in the online environment and its impact on society. It focuses on training several Czech transformer language models for disinformation recognition and further automatic extraction of content from Czech online newspapers and their analysis using text classification and natural language processing through deep learning methods. The results of these analyses are then presented in a web user interface with the aim of providing a platform for verifying articles, authors, and sources. The interface could be used for data annotation by experts for continuous improvement of language models.
|
|
| |
guest ::
