Ojleska latkoska, Vesna
Preferred name
Ojleska latkoska, Vesna
Official Name
Ojleska latkoska, Vesna
Main Affiliation
Email
vojleska@feit.ukim.edu.mk
3 results
Now showing 1 - 3 of 3
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, DETECTION OF EPILEPSY USING ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM(Ss. Cyril and Methodius University in Skopje, Faculty of Electrical Engineering and Information Technologies, 2018-12-27) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Comparative Analysis of Different Heliostat Field Control Algorithms(Society for Electronics, Telecommunications, Automatics and Informatics of the Republic of Macedonia - ETAI, 2021-09); This study presents the use of various algorithms for control of a field of heliostats, through which a thermal power plant with concentrated solar energy is controlled. The design of the control algorithms consists of several steps. First, in order to obtain the mathematical model of the system, the real system is identified according to the gray box and the least-square method. The data used to identify the system is generated by step excitation on the real system, for a specific sampling period. The resulting mathematical model is used to design and simulate a continuous and discrete PID controller, Mamdani and Sugeno fuzzy logic controllers, as well as ANFIS based fuzzy logic controller. The results of the applied controllers are analyzed and compared, based on the output overshoot, the rise and settling time. It can be concluded that we got best results (least settling time and the least overshoot) when fuzzy logic controller with ANFIS was used, while in terms of speed and rise time, the best results were obtained when discrete PID control algorithm was used. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Comparing Classical Machine Learning and Deep Learning for Classification of Arrhythmia from ECG Signals(2023-11-30); Arrhythmia detection is a vital task for reducing the mortality rate of cardiovascular diseases. Electrocardiogram (ECG) is a simple and inexpensive tool that can provide valuable information about the heart’s electrical activity and detect arrhythmias. However, manual analysis of ECG signals can be time-consuming and prone to errors. Therefore, machine learning models have been proposed to automate the process and improve the accuracy and efficiency of arrhythmia detection. In this paper, we compare six machine learning models, namely ADA boosting, Gradient Boost, Random Forest, C-Support Vector (SVC), Convolutional Neural Network (CNN), and Long Short-Term Memory Network (LSTM), for arrhythmia detection using ECG data from the MIT-BIH Arrhythmia Database. We evaluate the performance of the models using various metrics, such as accuracy, precision, recall, and F1-score, on different classes of ECG beats. We also use confusion matrices to visualize the errors made by the models. We find that the CNN model is the best performing model overall, achieving accuracy of 95% and F1-score of 84.75%. SVC and LSTM were the second and third best, achieving accuracy of 94% and 93%, respectively. We also discuss the challenges of using ECG data for arrhythmia detection, such as noise, imbalance, and similarity of classes. We suggest some possible ways to overcome these challenges, such as using more advanced preprocessing and resampling techniques, or incorporating domain knowledge and expert feedback into the models.