Srdjan Sladojevic

Prof. Srdjan Sladojevic

University of Novi Sad Faculty of Technical Sciences

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 July 2019 in Symmetry
Verified
Journal Article
Open access
PDF file
MAMarko Arsenovic
Marko Arsenovic
MKMirjana Karanovic
Mirjana Karanovic
Srdjan SladojevicSrdjan Sladojevic
Srdjan Sladojevic
Andras AnderlaAndras Anderla
Andras Anderla
DSDarko Stefanovic
Darko Stefanovic
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 discussed in this paper. Furthermore, a new dataset containing 79,265 images was introduced with the aim to become the largest dataset containing leaf images. Images were taken in various weather conditions, at different angles, and daylight hours with an inconsistent background mimicking practical situations. Two approaches were used to augment the number of images in the dataset: traditional augmentation methods and state-of-the-art style generative adversarial networks. Several experiments were conducted to test the impact of training in a controlled environment and usage in real-life situations to accurately identify plant diseases in a complex background and in various conditions including the detection of multiple diseases in a single leaf. Finally, a novel two-stage architecture of a neural network was proposed for plant disease classification focused on a real environment. The trained model achieved an accuracy of 93.67%.

28 March 2024 in Journal of Sensors
Verified
Journal Article
Open access
PDF file
Srdjan SladojevicSrdjan Sladojevic
Srdjan Sladojevic
MAMarko Arsenovic
Marko Arsenovic
Danilo NikolićDanilo Nikolić
Danilo Nikolić
Andras AnderlaAndras Anderla
Andras Anderla
DSDarko Stefanovic
Darko Stefanovic
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 to point out the main obstacles in the field and propose solutions. Furthermore, the paper presents the development of an Android smartphone-based real-time monitoring system that utilizes an external analog sensor board to acquire and evaluate physical measurements. The proposed system is calibrated for CO gas measurements, and it is compared with a commercial gas analyzer instrument. Results imply that the developed system is capable of detecting concentration levels in the air and that the accuracy is within the range of the industrial device’s accuracy.

15 December 2022 in International Journal of Simulation Modelling
Verified
Journal Article
Closed access
Branislav StevanovBranislav Stevanov
Branislav Stevanov
Nemanja SremcevNemanja Sremcev
Nemanja Sremcev
MLM. Lazarevic
M. Lazarevic
Andras AnderlaAndras Anderla
Andras Anderla
Srdjan SladojevicSrdjan Sladojevic
Srdjan Sladojevic
PVPredrag Vidicki
Predrag Vidicki

20 January 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
ISIvan Secerov
Ivan Secerov
Srdjan PopovSrdjan Popov
Srdjan Popov
Srdjan SladojevicSrdjan Sladojevic
Srdjan Sladojevic
DMDragana Milin
Dragana Milin
LLLazar Lazić
Lazar Lazić
Stevan SavićStevan Savić
Stevan Savić
An urban environment defines a specific micro-climate which directly affects the quality of life in urbanized areas and often has a negative impact on urban populations. Phenomena like urban heat and surface heat islands are direct products of an urban lifestyle. Urban meteorological networks (UMNs) are a tool that can help to better understand and analyze the current situation and make the right decisions about future urban development. Deployed to monitor and record different objects and their states inside urban areas, UMNs build a long-term meteorological data time series database. The most commonly used systems for achieving this goal include wireless sensor networks (WSNs). This paper presents a combined experience in deploying three different WSN systems. During seven years of research in this field, the authors have recognized the importance of data reliability in data acquisition. More importantly, due to the lack of research addressing the reliability of the data received from WSNs by the core segment of the server (processes used in receiving, validating, parsing, and storing data into a database instance), the received data are used in scientific studies without questioning their reliability. To determine the possibility of shifting information provided by the data measured from sensor networks before it is stored in a desired form of database, this paper proposes a highly reliable socket server model. The model is built with high reliability and performance in mind and it includes three major processes, which use a combination of signals and control messages to pass information about their states. A case study is performed using high-end hardware, running a Linux operating system stressed to its limits. Repetition testing revealed inconsistency in the information provided by the operating system to the application layer, which could lead to the loss of information about short-term and rarely occurring monitored objects. The results lead to the conclusion that there is a clear need for a higher level of data reliability in the process of data acquisition by UMNs. The proposed socket server should fill this gap within the server’s core segment.

17 March 2014 in The Scientific World Journal
Verified
Journal Article
Open access
PDF file
MSMiroslava Sladojevic
Miroslava Sladojevic
Srdjan SladojevicSrdjan Sladojevic
Srdjan Sladojevic
DCDubravko Culibrk
Dubravko Culibrk
STSnezana Tadic
Snezana Tadic
RJRobert Jung
Robert Jung
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 December 2008 to December 2011 was used to develop a risk model based on echocardiographic parameters using the binary logistic regression. This model was independently evaluated in validation cohort prospectively (954 patients admitted during 2012). In-hospital mortality in derivation cohort was 7.73%, and 6.28% in validation cohort. Developed model has been designed with 4 independent echocardiographic predictors of in-hospital mortality: left ventricular ejection fraction (LVEF RR=0.892; 95%CI=0.854–0.932,P<0.0005), aortic leaflet separation diameter (AOvs RR=0.131; 95%CI=0.027–0.627,P=0.011), right ventricle diameter (RV RR=2.675; 95%CI=1.109–6.448,P=0.028) and right ventricle systolic pressure (RVSP RR=1.036; 95%CI=1.000–1.074,P=0.048). Model has good prognostic accuracy (AUROC=0.84) and it retains good (AUROC=0.78) when testing on the validation cohort. Risks for in-hospital mortality after PCI in ACS patients using echocardiographic measurements could be accurately predicted in contemporary practice. Incorporation of such developed model should facilitate research, clinical decisions, and optimizing treatment strategy in selected high risk ACS patients.

1 January 2025 in Open Computer Science
Verified
Journal Article
Open access
PDF file
DGDejana Gladić
Dejana Gladić
JPJelena Petrovački
Jelena Petrovački
Srdjan SladojevicSrdjan Sladojevic
Srdjan Sladojevic
MAMarko Arsenovic
Marko Arsenovic
SRSonja Ristic
Sonja Ristic
The Internet of Things (IoT) encompasses a network of interconnected devices that collect, analyze, and exchange vast amounts of data. However, this connectivity creates opportunities for various types of cyberattacks, making IoT systems vulnerable and potentially leading to the compromise of sensitive information. Therefore, developing effective intrusion detection system (IDS) is one of the key challenges in IoT network security. The aim of this study is to develop a machine learning (ML) model for network traffic classification and attack detection in IoT environments. Through a comparative analysis of different algorithms, the study seeks to identify the model with the best performance, which could serve as a foundation for efficient IDS solutions tailored to the specific characteristics of IoT networks. The RT-IoT2022 dataset was used for experimental analysis, providing realistic framework for testing ML models, including k-nearest neighbors, Random Forest, XGBoost, multilayer perceptron, and various 1D convolutional neural network architectures. The study examines preprocessing techniques, focusing on dimensionality reduction (principal component analysis, variance inflation factor, Pearson’s test), outlier detection (interquartile range, Z -score, Isolation Forest), and transformation methods (Box–Cox, RobustScaler, Winsorization). Based on the results of the experiment, the most effective model and preprocessing technique were proposed.