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

Settings

Has files: NoSubject: search.filters.subject.Machine Learning

Search Results

Now showing 1 - 4 of 4
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Influence of the Yu T-norm on Vaguely Quantified Rough Set Measure Algorithm Accuracy
    (IEEE, 2022-11-16)
    ;
    ;
    This study aims to understand the impact of the Yu T-norm on the Vaguely Quantified Rough Set measurement algorithm, which combines the fuzzy and rough set theories. The algorithm uses both theories and concepts such as lower and higher approximations that integrate numerous features like T-norms, fuzzy tolerance relationship metrics, implicators, ambiguous quantifiers etc. to improve the process of real-world datasets to obtain more accurate models. The investigation process focusses on the experimental evaluation of Yu T-norm models obtained on various real-world datasets. The adjusted p-value is obtained using the insights generated by the AUC-ROC metric from the experimental assessment and a two-step approach for estimating the statistical significance. The results show that the k-parameter in Yu T-norm has impact on model performance and that the five fuzzy tolerance metrics that are studied also have impact on the model's accuracy on unseen data for the Yu T-norm. Therefore, we can conclude that a specific configuration of the k-parameter for the Yu T-norm can directly influence the overfitting of the final model.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Methodology for food prices forecasting
    (IEEE, 2023-12-15)
    Peshevski, Dimitar
    ;
    Todorovska, Ana
    ;
    Trajkovikj, Filip
    ;
    Hristov, Nikola
    ;
    Trajanoska, Milena
    Fluctuations in food prices play a pivotal role in maintaining economic equilibrium and influencing the very fabric of our everyday lives. This paper presents a comprehensive framework for modeling and analyzing food price trends in 12 select European countries, spanning from January 2013 to January 2023, utilizing advanced state-of-the-art Machine Learning techniques. To achieve this objective, historical price data and technical indicators are incorporated into the proposed XGBoost model alongside a baseline model. The model results are assessed using various measures, and a benchmark is established. Notably, the average achieved R2 for predicting food prices within the time frame from January 2020 to January 2022 is 0.85 and 0.64 from January 2021 to January 2023. The findings reveal the efficacy of the proposed model, providing valuable insights into food price forecasting model interpretability and laying the groundwork for further research, including exploration into areas such as food fraud, food sustainability, and other pertinent topics in food economics.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Blood Oxygen Saturation Estimation Using PPG Signals from the MIMIC-III Database
    (Springer, Cham, 2025-04-23)
    Petrovikj, Nenad
    ;
    Mishkovska, Bojana
    ;
    ;
    Madevska Bogdanova, Ana
    Photoplethysmogram (PPG) signals are pivotal in cardiovascular monitoring, offering real-time insights into heart rate and oxygen saturation (SpO2). This study explores the creation of deep learning and machine learning models - specifically Convolutional Neural Networks (CNNs), Bidirectional Long Short-Term Memory (BiLSTM) networks, Recurrent Neural Networks (RNNs), and Random Forest Regressors (RFRs)-to estimate SpO2 levels from single-channel PPG data. Another point is developing algorithms for using the data sourced from the PhysioNet MIMIC-III database. The patients used for training and testing are distinct, ensuring no overlap between the datasets and enabling rigorous model evaluation. A comprehensive analyses reveal that LSTM-based model achieve significant accuracy in SpO2 estimation, with R-squared value reaching up to 0.59. Specifically, the LSTM model demonstrated an MAE of 1.26, MSE of 3.11 and RMSE of 1.76. These results demonstrate the potential of machine learning techniques in advancing clinical monitoring and decision-making processes within critical care environments, thereby enhancing patient care outcomes.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Machine learning based SpO2 prediction from PPG signal's characteristics features
    (IEEE, 2022-06-22)
    ;
    Mitrova, Hristina
    ;
    Madevska Bogdanova, Ana
    ;
    Lehocki, Fedor
    Continuous monitoring of blood oxygen saturation level (SpO2) during the second triage in the high casualty event and determining the hemostability of a patient/victim until arrival to a medical facility, is essential in emergency situations. Using a SmartPatch device attached to a victim's chest that contains a Photoplethysmogram Waveforms (PPG) sensor, one can obtain the SpO2 parameter. Our interest in the process of the SmartPatch prototype development is to investigate the monitoring of a blood oxygen saturation level by using the embedded PPG sensor. We explore acquiring the Sp02 by extracting the set of features from the PPG signal utilizing two Python toolkits, HeartPy and Neurokit, in order to model the Machine learning predictors, using multiple regressors. The PPG signal is preprocessed by various filtering techniques to remove low/high frequency noise. The model was trained and tested using the clinical data collected from 52 subjects with SpO2 levels varying from 83 – 100%. The best experimental results - MAE (1.45), MSE (3.85), RMSE (1.96) and RMSLE (0.02) scores are achieved with the Random Forest regressor in the experiment with 7 features extracted from the both toolkits.