Srdjan Sladojevic

University of Novi Sad · Department of Industrial Engineering and Engineering Management

Cardiovascular diseases are the main cause of death across the globe. Therefore, it is critical to detect them at an early stage, while an electrocardiogram (ECG) presents a widely used tool for making diagnosis. There is a large number of ECG devices on the market, with different features that suit a wide range of users, but simultaneously it pose...

The aim of this paper is to investigate the effectiveness of combining mobile technologies and sensors to detect harmful particles in the air and address the problem of air pollution caused by traffic and exhaust emissions. The paper contains a systematic literature review of information technology research related to pollution detection in order t...

Additive Manufacturing (AM) has made a giant leap across numerous fields and industries, enabling the manufacturing of complex components in layer-by-layer form customized to the needs of the customer. This paper aims to outline current trends, review present issues and opportunities, and classify different AM techniques and their fields of applica...

Due to the constant progress of technology and the growing need for digitalization of various processes, the development of Information Systems, their implementation and the need to measure these systems is constantly growing. The situation caused by the Covid-19 virus has forced all educational institutions to replace their previous traditional wa...

In this paper, a possible solution for the architecture of the remote employee monitoring system is proposed. Development of such a system is particularly interesting at a time of the Covid-19 virus pandemic, when many employees work from home. Today's monitoring systems are mainly based on time tracking and screen monitoring features, without in-d...

In the last decade, data processing of vehicle license plates became a common subject of research with numerous methodologies proposed to address the problem. The license plate recognition technology converts image data from a camera into a character format that can be further processed and manipulated in a database in a specific application area....

The COVID-19 pandemic has a destructive effect on health on the population worldwide. Due to that, the crucial step in the fight against it is to control the spread of the disease while screening the broad number of suspected cases for appropriate quarantine and treatment as priority. Nonetheless, the capacity and quality of laboratory testing is a...

In this paper a novel approach based on deep learning methodology for automated arrhythmia detection is proposed. Over 50 million people are at risk of having cardiovascular diseases around the globe and thus making it one of the most serious health problems at the present time. Based on that, automatic detection and classification of cardiac arrhy...

With today's highly automated business environment and exponential growth of diverse data, new research domains are being established. An example is process mining, a discipline that emerged in the last decade and has process-centric view on data science. Process mining uses real event data in the form of event logs, generated usually from extracte...

Plant diseases cause great damage in agriculture, resulting in significant yield losses. The recent expansion of deep learning methods has found its application in plant disease detection, offering a robust tool with highly accurate results. The current limitations and shortcomings of existing plant disease detection models are presented and discus...

Recently, many researchers have been inspired by the success of deep learning in computer vision to improve the performance of detection systems for plant diseases. Unfortunately, most of these studies did not leverage recent deep architectures and were based essentially on AlexNet, GoogleNet or similar architectures. Moreover, the research did not...

Recently, many researchers inspired from the success of deep learning in computer vision to improve the performance of plant diseases detection systems. Unfortunately, most of these studies did not leverage the recent deep architectures and based essentially on AlexNet, GoogleNet or similar architectures. Moreover, the deep learning visualization m...

Up to now, eye tracking technologies have been used for different purposes in various industries, from medical to gaming. Eye tracking methods could include predicting fixations, gaze mapping or movement classification. Recent advances in deep learning techniques provide possibilities for solving many computer vision tasks with high accuracy. Autho...

Coronary artery disease (CAD) is one of the most common causes of death. This paper presents a study on the applicability of open-source data mining tools for the development of medical risk scores and their regional character for CAD detection. The presented methodology is based on the performance evaluation of diverse data mining techniques on we...

During the last decade, rapid growth of the social media usage and the Internet in general led to the drastic expansion of the publicly available data. This gives the great opportunity for research and analysis in many fields of machine learning and data science. Even though this data is open to use, often it is distributed over the various sources...

In the interest of recent accomplishments in the development of deep convolutional neural networks (CNNs) for face detection and recognition tasks, a new deep learning based face recognition attendance system is proposed in this paper. The entire process of developing a face recognition model is described in detail. This model is composed of severa...

Corresponding to the raising importance of data mining in today's highly competitive business environment, the number of available data mining tools continues to grow. Consequently, competition between data mining software developers increases as well and the choice of the most suitable tool becomes increasingly difficult. Therefore, comparison of...

Optical character recognition (OCR) represents one of well-studied areas of computer vision and machine learning. Due to the complexity of the problem there is always room for improvement. Usually, there are specialized solutions for certain types of character recognition tasks in many areas of industry: banking, legal, government, education and et...

Information system engineering is a complex discipline which involves learning different skills, from both technical and organizational point of view. At the Faculty of Technical Sciences, Novi Sad, the initial information system engineering study program has been changed with the goal of improving knowledge quality of future engineers. The reforme...

Customer churn modeling has received a lot of attention lately, as there are indications that a large share of corporate profit comes from the existing customer base. Businesses are therefore very interested in identifying customers who are likely to churn and often undertake Data Mining projects to help them with that. In this paper we explore som...

This paper presents the results of a study of the effects of integer (fixed-point) arithmetic implementation on classification accuracy of a popular open-source people detection system based on Histogram of Oriented Gradients. It is investigated how the system performance deviates from the reference algorithm performance as integer arithmetic is in...

Doing business in the era of modern technologies faces numerous challenges, so it is required that all of the employees are analytic, well organized, that they manage their time in a proper way and always have all of the important information at the right time. They are responsible for doing a number of different tasks on a daily basis, and meeting...

Medical imaging is invaluable when it comes to gaining insight into the human body. As is well known, medical images need to deal with artefacts. This article presents a modern procedure for metal artifact reduction in computed tomography, which relies on additional information extracted from corresponding magnetic resonance images. We conducted a...

An increasingly growing amount of publicly available data opens countless possibilities for research and analysis in the field of data science. Data mining enables us to summarize large amounts of data in a manner that allows discovery of hidden patterns in collected data. Based on those patterns it is possible to generate predictive models and imp...

In the recent period, fast ICT expansion and rapid appearance of new technologies raised the importance of fast and accurate planning and deployment of emerging communication technologies, especially wireless ones. In this paper is analyzed possible usage of Lee propagation model for planning, design and management of networks based on LoRa 868MHz...

The latest generation of convolutional neural networks (CNNs) has achieved impressive results in the field of image classification. This paper is concerned with a new approach to the development of plant disease recognition model, based on leaf image classification, by the use of deep convolutional networks. Novel way of training and the methodolog...

The burden of chronic disease and associated disability present a major threat to financial sustainability of healthcare delivery systems. The need for cost-effective early diagnosis and disease prevention is evident driving the development of personalized home health solutions. The proposed solution presents an easy to use ECG monitoring system. T...

Pervasiveness of mobile devices and ubiquitous broadband Internet access have laid foundations for video content to be consumed increasingly on smart phones or tablets. As over 85% of the global con- sumer traffic by 2016 is estimated to be generated by streaming video content, video quality as perceived by end-users of such devices is be- coming a...

Background/aim: The lack of effective therapy for advanced stages of melanoma emphasizes the importance of preventive measures and screenings of population at risk. Identifying individuals at high risk should allow targeted screenings and follow-up involving those who would benefit most. The aim of this study was to identify most significant facto...

In this paper we investigate the design of DASH stream-switching solution suitable for mobile cellular video streaming consumers. Our goal is to design a solution that reduces the amount of downloaded content while adhering to user preferences regarding received video quality. We firstly present a graphical (trellis-like) representation of a stream...

Different ways have been used to stratify risk in acute coronary syndrome (ACS) patients. The aim of the study was to examine the usefulness of echocardiographic parameters as predictors of in-hospital outcome in patients with ACS after percutaneous coronary intervention (PCI). A data of 2030 patients with diagnosis of ACS hospitalized from Decembe...

Arterial hypertension represents the most common non-communicable disease of our time. The prevalence of hypertension varies according to gender and age criteria, but also depends on the geographical, ethnic and racial factors and has the character of an epidemic [1]. Among the adult population, arterial hypertension is considered as one of leading...

H.264 is one of the first video coding standard incorporating coding formats with a bit-depth of above 8 bits. This paper presents the results of compression comparison tests for the H.264 “High 422” profile, between 10-bit and 8-bit sample depths. The simulations were run on five 720p and 1080i high definition sequences. PSNR and SSIM metrics were...

In the modern world, where multimedia is predicted to form 86% of traffic transmitted over the telecommunication networks in the near future, content providers are looking to shift towards Quality of Experience, rather than Quality of Service in multimedia delivery. Thus, no-reference image quality assessment and the related video quality assessmen...

Purpose: The aim of the study was to evaluate the innovative approach of using Data Mining techniques for developing an in-hospital mortality prediction model for patients presented with ST-segment elevation myocardial infarction (STEMI) submitted to primary percutaneous coronary intervention (pPCI). Methods: A set of patient-related data obtained...

While a fairly large number of databases exist that provide impaired video sequences designed for the development and evaluation of Quality of Experience (QoE) approaches, the impairments due to transmission errors resulting in packet loss in these databases are based on simulation of small number of scenarios and not representative of real transmi...

3D reconstruction takes important place in medicine. Obtained models can help doctors in better visualization of human organs and make it easier and more accurate to diagnose and prescribe therapy for the patient. Magnetic Resonance Imaging (MRI) produces two dimensional images that represent different cross-sections of the appropriate part of the...

Visual attention deployment mechanisms allow the Human Visual System to cope with an overwhelming amount of visual data by dedicating most of the processing power to objects of interest. The ability to automatically detect areas of the visual scene that will be attended to by humans is of interest for a large number of applications, from video codi...

The paper presents a study focused on the problem of predicting the churn of telecommunication-service users. The transition of customers (users) to competitors is a significant business problem in areas with poor market differentiation of products and services, which is particularly evident in the market of telecommunication services. The paper ev...