A5015701338- ECG Monitoring and Analysis
- Statistical Methods and Inference
- Phonocardiography and Auscultation Techniques
- Advanced Statistical Methods and Models
- EEG and Brain-Computer Interfaces
- Human Motion and Animation
- Cardiac electrophysiology and arrhythmias
- Context-Aware Activity Recognition Systems
- Electrostatic Discharge in Electronics
- Gaussian Processes and Bayesian Inference
- Forecasting Techniques and Applications
- IoT and Edge/Fog Computing
- Digital Transformation in Industry
- Neural Networks and Applications
University of Pavol Jozef Šafárik
2020-2022
Czech Academy of Sciences, Institute of Computer Science
2021
Within PhysioNet/Computing in Cardiology Challenge 2021, we developed a two-phase method of automatic ECG recording classification. In the first phase, pre-trained model on large training set with our proposed mapping original labels to SNOMED codes, using threevalued labels. To solve multilabel binary classification task, used deep convolutional neural network, which is 1D variant popular ResNet50 network. second performed fine-tuning for metric and conditions. Our team CeZIS took 6 <sup...
Objective.Within the PhysioNet/Computing in Cardiology Challenge 2021, we focused on design of a machine learning algorithm to identify cardiac abnormalities from electrocardiogram recordings (ECGs) with various number leads and assess diagnostic potential reduced-lead ECGs compared standard 12-lead ECGs.Approach.In our solution, developed model based deep convolutional neural network, which is 1D variant popular ResNet50 network. This base was pre-trained large training set proposed mapping...
As part of the George B. Moody PhysioNet Challenge 2022, we developed a computational approach to identify abnormal cardiac function from phonocardiograms that combines deep learning and traditional machine methods.We adopted supervised contrastive convolutional neural network obtain an embedding phonocardiogram slice onto unit hypersphere in low-dimensional space.Thus, applied obtained latent factors classify patients using Random Forest model.The murmur detection classifier created by our...
A growing interest in promoting and supporting the use of artificial intelligence systems is observed all major market sectors worldwide, as well public sector. The development Slovakia an important key for innovations field healthcare, digitalization industry, agriculture, but also other Slovak economy. Extending implementation activities within National Project IT Academy – Education 21st Century by area Artificial Intelligence was order to provide educational training possibilities...