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

Search Results

Now showing 1 - 10 of 18

Some of the metrics are blocked by your
consent settings
Design of a Non-invasive ECG-based Glucose Measurement System
(IEEE, 2020-09-28)
;
Guseva, E.
;
Poposka, L.
Diabetic patients have to pay for each glucose reading with a blood drop and a small fortune. In addition, routine finger pricking is troublesome for diabetic patients because it can lead to scarring. It is no surprise then that the idea that glucose measurement can be done cheaply and in a non-invasive way surpasses the wildest dreams of diabetic patients. The goal of this paper is to present the design of a new technology solution for non-invasive glucose measurement based on processing the electrocardiogram obtained via a light easy-to-wear ECG monitor. We present details on how to develop a service that tracks glucose levels based on real-time ECG monitoring, and using sophisticated machine learning and related technologies. Our initial analysis shows that no similar solution is present on the market today, although several research initiatives are ongoing.
Some of the metrics are blocked by your
consent settings
Detection of Uninterpretable ECG Signal Segments
(IEEE, 2020-09-28)
Krluku, E. Ajdaraga
;
Remote diagnosis represents one of the fundamental reasons for the introduction of telemedicine services. Specialized wearable health monitoring devices collect large amounts of data, which are transmitted to cloud collection centers for further monitoring and interpretation. However, the presence of noise corrupts the ECG signals, especially in wearable sensors, due to physical activities and movements. This significantly decreases the diagnosis accuracy and performance. Therefore, timely noise detection and identification of uninterpretable ECG segments are crucial for wearable devices.In this paper, we present results from our research to detect noisy segments in ECG signals without a goal to eliminate them and improve the QRS detection, but to detect where QRS detection would be impossible and avoid detection and interpretation mistakes. Our work includes two algorithms and multiple related variables that add to the success of the proposed algorithms. Finally, we achieved high performance for detecting signals where the signal to noise ratio is lower than 6 dB, with sensitivity and a positive predictive rate of over 90%.
Some of the metrics are blocked by your
consent settings
Optimal Filter Length to Identify Uninterpretable Electrocardiograms
(IEEE, 2020-11-24)
Krluku, Era Ajdaraga
;
The ubiquity of wearable health monitors has drastically improved the quality of life for end-users whose wellbeing relies on continuous monitoring. The main challenge with telemedicine services lies in the quality of the data that the system receives from the user. Therefore, it is paramount that the telehealth processing system has a way to check and identify corrupted data so that it can be corrected or excluded from further processing. The Simple Differential Filter (SDF) aims to solve the challenge of artifact detection in ECG signals. In this paper, we research the optimal value for filter length. This parameter is significant not only because of its implications on performance and accuracy, but memory management in big data systems as well.
Some of the metrics are blocked by your
consent settings
A Method to Detect Ventricular Fibrillation in Electrocardiograms
(IEEE, 2021-09-27)
Temelkov, G.
;
The objective of this research is to create an algorithm for automatic detection of ventricular fibrillation in electrocardiogram records customized for wearable single-channel sensors. Our approach is based on observing and examining sequences of ventricular fibrillation in their frequency-domain. The research, design, and validation process, along with comprehensive annotations, is carried out on Physionet reference databases. We use a sliding window approach and apply the Fast Fourier Transform to convert the data from the time domain to the frequency domain. Our approach is based on the determination of frequency peaks, calculation of energy around the peak, and its ratio to the overall spectra. The evaluation of detection performance classification results by applying the digital signal processing algorithms with machine learning methods classify ventricular arrhythmia episodes with F1 score of 0.77 and accuracy of 0.92.
Some of the metrics are blocked by your
consent settings
TPC-H Benchmark Q3, Q6 and Q12 Sequential, OpenMP Parallel and CUDA Parallel Implementation
(IEEE, 2021-09-27)
Mitrovski, Jovan
;
Djinevski, Leonid
;
;
Arsenovski, Sime
In the last decade or two, parallel computing has solved a myriad of problems when it comes to speeding up the problem-solving process. To deliver the necessary acceleration of their product, application developers have turned to CUDA-powered GPU parallel processing. One of the many uses of the well-known NVIDIA parallel computing platform CUDA is to enhance the performance of problems whose root comes from speeding up database queries. The fundamental focus of this paper is evaluating the performance of different parallelizing techniques using the TPC-H benchmark. This is achieved by parallelizing the ‘SELECT’ queries that the benchmark offers using the Open Multi-Processing (OpenMP) API (Q3, Q6, and Q12 in particular), then parallel on the GPU using the previously mentioned CUDA platform. Lastly, comparing the GPU's performance with both sequential instruction execution and parallel instruction execution on a CPU. This implementation resulted in speedup ratios ranging from 2 to 4 when analyzing the CPU-parallel code and ranging from 10 up to 558 when analyzing the GPU - parallel code.
Some of the metrics are blocked by your
consent settings
The ECGview Tool for Time and Frequency Domain ECG Visualization and Signal Generation
(IEEE, 2020-11-24)
Temelkov, Goran
;
Spasovska, Ana
;
We developed the ECGview tool that enables visual inspection of ECG signals in their time and frequency domain and integrates a generator of artificial ECG signals upon given specified input parameters. The tool's goal is to offer better understanding and ease of analysis in understanding different anomalies to create better algorithms. The tool can be accessed through an UI interface as a standard web application or by an API interface for other applications that require these types of processing.
Some of the metrics are blocked by your
consent settings
Deep Learning Method to Estimate Glucose Level from Heart Rate Variability
(IEEE, 2020-11-24)
Shaqiri, Ervin
;
Recently, there have been efforts by different researchers in implementing some Machine Learning (ML) and Deep Learning (DL) techniques in designing a model that will predict Glucose based solely on Heart Rate Variability parameters. However, each study uses an in-house dataset and thus the results differ from the rest. The aim of this paper is to explore the predictive capabilities of DL techniques in designing a model to predict glucose regulation from Heart Rate Variability. The clinical study was conducted on a dataset of 155 patients with long-term Electrocardiogram measurements. The best results are achieved with an architecture of three hidden layers (32, 256, and 64 neurons, respectively) with an Adam optimizer alongside a learning rate of 0.001 coupled by a Binary Cross entropy loss function. Furthermore, the Z score outlier removal method proved to lead to a higher accuracy value, whilst the IQR outlier removal method proved to lead to a higher Fl score value.
Some of the metrics are blocked by your
consent settings
A New ML-based AFIB Detector
(IEEE, 2021-11-23)
Tudjarski, Stojancho
;
Ignjatov, Tomislav
;
Objectives: This paper aims to develop a model for detecting Atrial Fibrillation (AFIB) in a single-channel electrocardiogram.Methodology: The applied Machine Learning methods are XGBoost and Random Forest. Training and testing split was realized by splitting the patients 70% for training and 30% for testing. Features included annotations for heartbeats, intervals between neighboring heartbeats, Shannon entropy, and Fluctuation index by designing a moving window with predefined length.Data: Standard ECG benchmarks were used for training and testing from MIT-BIH Arrhythmia [1] and MIT-BIH Atrial Fibrillation[2] datasets.Conclusion: Experiments were done with different window sizes and different hyperparameters. The best results were achieved from the 41 Beat window, with XGBoost achieving the best performance of 99% with an F1 score of 99%.
Some of the metrics are blocked by your
consent settings
Detection of Premature Heartbeats
(IEEE, 2022-05-23)
Premature heartbeats are those that appear earlier than the regular ones due to contractions not originating from the Sinus Atrial Node, out of the normal heart rhythm. Although one might think this is a trivial task to detect, the distribution of premature heartbeats in the benchmark electrocardiograms shows it is not the case. We aim at finding the optimal method to detect premature heartbeats, threshold value and context level for temporal based approach. Methodology: Several methods are specified to calculate the relation of the premature heartbeat to a set of several previous instances and conduct experiments to present which averaging method (arithmetic, geometric and harmonic mean) delivers the best solution. Then, we calculate the deviation ratio to the average of these beats that affect the prematurity condition. Particularly, the goal is to find an average AV G of previous k beat-to-beat intervals RR, such that the ratio between the difference dRR of the analyzed RR and AV G versus AV G is more than a specific threshold T hr. Data: The comprehensive MIT-BIH Arrhythmia Electrocardiogram benchmark database is used in our evaluation. The analysis is conducted on the array of beat-to-beat intervals for the heartbeats preceding the premature one. Conclusion: The results show that the optimal method is based on the arithmetic mean AM We found that the larger k, the better performance is achieved. A sufficient performance with F1 score over 85% is achieved for k = 5 and T hr = 15%.
Some of the metrics are blocked by your
consent settings
Detecting Ventricular Beats with Machine Learning Models
(IEEE, 2022-05-23)
Tudjarski, Stojancho
;
Stankovski, Aleksandar
;
This paper aims at modeling a classifier of Ventricular heartbeats by experimenting with the most advanced classic binary classifiers in different scenarios for feature engineering. Methodology: The results were acquired based on experimenting with XGBoost and Random Forest algorithms, as two of the most advanced classifiers not based on neural networks. Although the annotated ECG data sets contain records with several heartbeat classes, we focus on a model that would distinguish V from others (Non-V heartbeats). Considering that we are dealing with a highly imbalanced data set, we applied the SMOTE algorithm for data enrichment to provide a better-balanced data set for training the model. To acquire better results, we added new calculated features, with and without feature selection. For feature selection, we used the Fisher Selector algorithm. Data: We used MIT-BIH Arrhythmia benchmark database, with train/test split according to the patient-oriented splitting approach that separates the original dataset into two subsets with approximately equal sizes and distribution of heartbeat types. Conclusion: The best results are achieved with XGBoost algorithm with original feature set. We achieved precision of 91.36%, recall of 88.31% and F1 score of 89.81%. Results showed that oversampling does not provide significantly better overall model performance. Still, we would recommend this approach since in practice, when dealing with imbalanced data sets, this leads to more robust models that perform better with data outside the training and test sets, such as when the model is used in production.

Faculty of Computer Science and Engineering

Browse

Filters

Settings

Sort By

Results per page

Search Results