Faculty of Computer Science and Engineering
Permanent URI for this communityhttps://repository.ukim.mk/handle/20.500.12188/5
The Faculty of Computer Science and Engineering (FCSE) within UKIM is the largest and most prestigious faculty in the field of computer science and technologies in Macedonia, and among the largest
faculties in that field in the region.
The FCSE teaching staff consists of 50 professors and 30 associates. These include many “best in field” personnel, such as the most referenced scientists in Macedonia and the most influential professors in the ICT industry in the Republic of Macedonia.
Browse
8 results
Search Results
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Processing MIMIC-III for Evaluation of Various Blood Pressure Estimation Models(2023-10); ; - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Processing MIMIC-III for Evaluation of Various Blood Pressure Estimation Models(2024); ; - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Transformer Models for Processing Biological Signal(Ss Cyril and Methodius University in Skopje, Faculty of Computer Science and Engineering, Republic of North Macedonia, 2023-07); Madevska Bogadnova, AnaThe transformer neural network architecture is a deep learning model, that has been developed recently and as such it’s potential is still being investigated. It is a powerful model due to the their self-attention mechanism that finds use in several domains, but our focus is on transformers used for biological signals processing. Various hybrid model architectures suitable for this type of task are considered in this study: the basic transformer, temporal fusion transformer, time series transformer, convolutional vision transformer and informer. A brief description of the architecture is given. The reasons why they are appropriate for processing biological signals, what makes them unique, along with their strengths and weaknesses, are discussed. Finally, a literature review is made involving actual studies that use these model types for biosignal processing. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Blood pressure class estimation using CNN-GRU model(2022); Madevska Bogdanova, AnaBlood pressure (BP) estimation can add on great value in emergency medicine, especially in case of mass casualty situations. The presented research aims to create a model for BP class estimation using electrocardiogram (ECG) and photoplethysmogram (PPG) waveforms. We focus on developing a BP classification model as a convolutional neural network (CNN) - gated recurrent unit (GRU) hybrid model, containing both CNN and GRU layers. The used dataset is the publicly available UCI Machine Learning Repository dataset. We have achieved f1 score of 0.83, 0.73 and 0.74 respectively according to the BP classes and 78% overall accuracy. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Using Cuffless Non-Invasive Methods for Blood Pressure Estimation: Description of the Selected Solutions(2022-09) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Blood pressure classification using CNN-LSTM model(2022-09); Blood pressure (BP) estimation can aid the triage process and help prioritizing and helping injured, especially in a situation of multiple casualties. The presented research aims to create a model for BP class estimation using electrocardiogram (ECG) and photoplethysmogram (PPG) waveforms. We focus on developing a BP classification model as a convolutional neural network (CNN) - gated recurrent unit (LSTM) hybrid model, containing both CNN and LSTM layers. The used dataset is the publicly available UCI Machine Learning Repository dataset. We have achieved stable AUCROC for each class - 0.89, 0.83, and 0.89 respectively and overall accuracy of 83%. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Fast Cuffless Blood Pressure Classification with ECG and PPG signals using CNN-LSTM Models in Emergency Medicine(IEEE, 2022-05-23); Cuffless blood pressure (BP) measurement is gaining a lot of attention as a promising new technology that can be embedded in a patch-like biosensor device. Electrocardiogram (ECG) and photoplethysmogram (PPG) waveforms are non-invasive by their nature - they can be recorded without sending any electrical impulses to the human body. These signals present different aspects of the cardiovascular system, thus using both of the signals for blood pressure classification seems like a viable strategy. Quick estimation of the blood pressure during the triage process in cases of natural disasters with many injured subjects, is an essential measure for following the hemostability of the injured. The main goal of this study is to develop a two-class classification model (Hypotension and Nothypotension) for fast prediction of the blood pressure category by utilizing ECG and PPG signals, in order to detect a BP sudden drop. The developed deep learning models are based on the LSTM architecture and its variants, CNN-LSTM. We also conducted three class classification model. The models were trained and tested using the data from the UCI Machine Learning Repository Cuff-Less Blood Pressure Estimation dataset with 12000 instances. The best result in the two-class model is AUROC = 0.74. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Blood pressure class estimation using CNN-GRU model(2022)