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

Search Results

Now showing 1 - 10 of 2152
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Contribution to the Quasigroup Based Error-Detecting Code
    (IEEE, 2023-07-19)
    In the last years we have developed few error-detecting codes based on quasigroups. One of them is the code which is a subject of this paper. The previous analyses of the code shows that the code has very high probability of detecting transmission errors. We have previously identified so-called best class of quasigroups of order 4, with the highest probability of detecting errors when the coding process is performed with a quasigroups of order 4. But, there is one more class of quasigroups of order 4, second-best class, whose quasigroups give approximately equal probability of undetected errors as the quasigroups from the best one. Therefore, we proceeded with the examination of the code when it uses quasigroups from this second-best class of quasigroups of order 4. In this paper we will analytically obtain the second important parameter of every error-detecting code, i.e. the number of errors that the code surely detects when for coding it uses a quasigroup from this second-best class of quasigroups of order 4. At the end we will conclude whether the quasigroups from these top two classes have overall equal ability to detect errors with this code.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Simulating the error-detecting capability of the error-detecting code
    (IEEE, 2018-05)
    Using simulations, we analyze an error-detecting code from the aspect of the number of errors that the code surely detects. In order to conclude whether and how the order of the quasigroup used for coding affects the number of errors that the code surely detects, we use quasigroups of different orders for coding. Also, we code input blocks of different lengths in order to conclude whether the number of errors that the code surely detects depends on the length of the input block, i.e., the length of the code word.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A Comparison of GEC Tools for Grammatical Error Correction in English
    (IEEE, 2025-06-02)
    Virtanen, Johanna
    ;
    Using the Building Educational Application (BEA) benchmark11https://codalab.lisn.upsaclay.fr/competitions/4057, this study compares the capabilities of Google Gemini22https://gemini.google.com/, ChatGPT33https://openai.com/chatgpt, DeepSeek44https://www.deepseek.com/en, and the builtin grammar checkers in Google Docs and Microsoft Word for grammatical error correction (GEC). These tools correct a variety of errors, some of which overlap. Based on the BEA benchmark evaluation results, Google Gemini and the Google Docs grammar checker achieve the best F0.5 scores of 60.2 and 65.86, respectively. Google Docs grammar checker is easy to use and, according to this evaluation, performs well, thus proving to be a viable option for GEC. However, standard grammar checkers are not typically designed for rewriting text to the same extent as GenAI tools; hence, it may be advisable especially for non-native speakers to combine traditional and GenAI grammar correction for the best possible results. However, it is necessary to check the grammatical corrections of LLMs, since generative AI tools suffer from hallucinations, which refers to their tendency to generate information that can be factually incorrect [1].
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    The Ability of Word Embeddings to Capture Word Similarities
    (Academy and Industry Research Collaboration Center (AIRCC), 2020-06-30)
    ;
    Kalajdjieski, Jovan
    ;
    Stojanovska, Frosina
    Distributed language representation has become the most widely used technique for language representation in various natural language processing tasks. Most of the natural language processing models that are based on deep learning techniques use already pre-trained distributed word representations, commonly called word embedding. Determining the most qualitative word embedding is of crucial importance for such models. However, selecting the appropriate word embedding is a perplexing task since the projected embedding space is not intuitive to humans.In this paper, we explore different approaches for creating distributed word representations. We perform an intrinsic evaluation of several state-of-the-art word embedding methods. Their performance on capturing word similarities is analysed with existing benchmark datasets for word pairs similarities. The research in this paper conducts a correlation analysis between ground truth word similarities and similarities obtained by different word embedding methods.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Improving the QRS detection for one-channel ECG sensor
    (SAGE Publications, 2019-11-07)
    Domazet, Ervin
    ;
    We analyzed several QRS detection algorithms in order to build a quality industrial beat detector, intended for a small, wearable, one channel electrocardiogram sensor with a sampling rate of 125 Hz, and analog-to-digital conversion of 10 bits. The research was a lengthy process that included building several hundred rules to cope with the QRS detection problems and finding an optimal threshold value for several parameters. We obtained 99.90% QRS sensitivity and 99.90% QRS positive predictive rate measured on the first channel of rescaled and resampled MIT-BIH Arrhythmia ECG database. Even more so, our solution works better than the algorithms for the original signals with a sampling rate of 360 Hz and analog-to-digital conversion of 11 bits.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A new model for cloud elastic services efficiency
    (Informa UK Limited, 2018-02-09)
    Ristov, Sasko
    ;
    Mathá, Roland
    ;
    Kimovski, Dragi
    ;
    Prodan, Radu
    ;
    The speedup measures the improvement in performance when the computational resources are being scaled. The efficiency, on the other side, provides the ratio between the achieved speedup and the number of scaled computational resources (processors). Both parameters (speedup and efficiency), which are defined according to Amdahl’s Law, provide very important information about performance of a computer system with scaled resources compared with a computer system with a single processor. However, as cloud elastic services’ load is variable, apart of the scaled resources, it is vital to analyse the load in order to determine which system is more effective and efficient. Unfortunately, both the speedup and efficiency are not sufficient enough for proper modeling of cloud elastic services, as the assumptions for both the speedup and efficiency are that the system’s resources are scaled, while the load is constant. In this paper, we extend the scaling of resources and define two additional scaled systems by (i) scaling the load and (ii) scaling both the load and resources. We introduce a model to determine the efficiency for each scaled system, which can be used to compare the efficiencies of all scaled systems, regardless if they are scaled in terms of load or resources. We have evaluated the model by using Windows Azure and the experimental results confirm the theoretical analysis. Although one can argue that web services are scalable and comply with Gustafson’s Law only, we provide a taxonomy that classifies scaled systems based on the compliance with both the Amdahl’s and Gustafson’s laws. For three different scaled systems (scaled resources R, scaled load L and combination RL), we introduce a model to determine the scaling efficiency. Our model extends the current definition of efficiency according to Amdahl’s Law, which assumes scaling the resources, and not the load.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Noninvasive Glucose Measurement Using Machine Learning and Neural Network Methods and Correlation with Heart Rate Variability
    (Wiley, 2020-01-06)
    ;
    ;
    Spasevski, Gjoko
    ;
    ;
    Diabetes is one of today’s greatest global problems, and it is only becoming bigger. Constant measuring of blood glucose level is a prerequisite for monitoring glucose blood level and establishing diabetes treatment procedures. The usual way of glucose level measuring is by an invasive procedure that requires finger pricking with the lancet and might become painful and obeying, especially if this becomes a daily routine. In this study, we analyze noninvasive glucose measurement approaches and present several classification dimensions according to different criteria: size, invasiveness, analyzed media, sensing properties, applied method, activation type, response delay, measurement duration, and access to results. We set the focus on using machine learning and neural network methods and correlation with heart rate variability and electrocardiogram, as a new research and development trend.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A Programmatic Approach for Development of the ViewHRV Service Platform with Accurate and Reliable Results
    (IEEE, 2020-09-28)
    Shaqiri, E.
    ;
    There are dozens of available packages and libraries that claim to calculate HRV. This paper aims at comparing the results from the calculation of a single array of intervals between normal beats, including the most popular open source Python HRV measurement packages available on GitHub. Furthermore, the same array was ran through the Kubios software and compared to the previous results. In order to compare the accuracy of the results, as a benchmark we used the C programs provided by Physionet. The results showed a huge difference in the results with almost all the indices, in fact the simplest measurement that of Standard Deviation of NN Intervals showed to be incorrect in Kubios and in most of the Python packages. Results like these are the reason we decided to develop our own package to calculate HRV. Finally, the goal of this paper is to present details on developing a publicly available web service platform ViewHRV with guaranteed precision obtaining accurate and reliable results.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Impact of Dew Computing on Cyber-Physical Systems and IoT
    (IEEE, 2020-09-28)
    Cyber-physical systems and IoT devices are part of today's interconnected networked world and participate in huge data exchange transfer. Owners of related devices and systems tend to use them independently of external systems and in addition, to be autonomous devices and systems that can perform their tasks without any external support. Edge computing refers to devices on the edge of the Internet, as they integrate into a more complex cyber-physical system. The concept of edge computing means that the corresponding cloud and edge servers are always connected to the edge devices and IoT. In the analyzed case, although these devices and systems can work in an integrated environment, they are rather classified into the dew computing concept, giving them an environment for autonomous performance, independent of surrounding devices and systems. This paper elaborates the underlying concept, benefits, market trends and impact of integrating the dew computing concept to the cyber-physical systems and IoT devices.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Correlating Short-Term Heart Rate Variability and Instantaneous Blood Glucose Measurements
    (IEEE, 2020-11-24)
    Vishinov, Ilija
    ;
    ;
    ;
    In this research, we aim to analyze the correlations between instantaneous blood glucose measurements and short term (30 seconds to 5 minutes) heart rate variability (HRV) parameters and check the research hypothesis that these HRV parameters indicate the ability of a patient to control the blood glucose level. Methodology: Pearson and Spearman's Rank correlations are used as methods within this paper. Although 155 patients with heart problems and arrhythmia were included in the study, only intervals between normal heartbeats were evaluated. Data: The HRV parameters correlated to the blood glucose levels are divided into time-domain (TD) HRV parameters: SDNN, SDNN Prima (SDNN-1), ASDNN, ASDNN Prima (ASDNN-1), ASDNN Secunda (ASDNN-2), ASDNN Tertia (ASDNN-3), SDANN Secunda (SDANN-2), SDANN Tertia (SDANN-3), NN50, NN50 Prima (NN50-1), pNN50, pNN50 Prima (pNN50-1), rMSSD and rMSSD Prima (rMSSD-1); and non-linear HRV parameters: SD1, SD2, SD1/SD2. Several methods were utilized to process the ECG signal strip and eliminate the ectopic beats, artifacts, lost signals, noise, and other segments that influence HRV metrics. Conclusion: We found that SD1/SD2 showed the strongest positive correlations for 5 minute ECG recordings, 45-40 minutes before ( r = 0.36) and 20-25 minutes after ( r = 0.31) the fasting glucose measurement satisfying the condition p ≤ 0.05. We conclude that short term HRV parameters can't indicate a strong linear or monotonic correlation to the blood glucose regulation ability, but can motivate further research including deep learning.