Ivan Jokic

Dr. Ivan Jokic

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
22 April 2025 in AlfaTech
Verified
Journal Article
Open access
PDF file
IJIvan Jokic
Ivan Jokic
Vlado DelićVlado Delić
Vlado Delić
Zoran PerićZoran Perić
Zoran Perić
This paper presents an implementation of automatic speaker recognition utilizing feature vectors composed of 21 mel-frequency cepstral coefficients (MFCCs) as part of an IoT-driven solution for enhancing security and optimization in smart cities. Experiments are conducted on the Solo portion of the CHAINS database, containing 33 unique sentences pronounced by each of 36 speakers. Results indicate that recognition accuracy varies with the training and testing datasets and improves with longer test recordings. A comparative analysis of MFCC calculation methods reveals that accuracy is generally higher when a sigmoidal square of amplitude characteristic is applied to frequency-selective ranges, rather than an exponential approach. Models are developed for each speaker’s recordings, represented by a covariance matrix of feature vectors, and applying a sigmoid function to the model elements yields a 5% increase in recognition accuracy in most cases. These findings highlight the potential for MFCC-based speaker recognition as a scalable, data-driven IoT tool for security, public safety, and resource optimization in the context of smart cities.

27 February 2026 in Electronics
Verified
Journal Article
Open access
PDF file
SJStevan Dragutin Jokic
Stevan Dragutin Jokic
IJIvan Jokic
Ivan Jokic
Nenad GligoricNenad Gligoric
Nenad Gligoric
AKAneta Kartali
Aneta Kartali
OMOctavian Machidon
Octavian Machidon
The development of reliable smartphone-based methods for vascular assessment is limited by the scarcity of large-scale, high-quality, real-world photoplethysmography (PPG) datasets. This work introduces two openly reusable smartphone camera-based PPG datasets curated from over one million unconstrained recordings, designed to support vascular morphology analysis and vascular aging research. The first dataset comprises approximately 5000 high-fidelity PPG heartbeat templates labeled into four morphological classes based on dicrotic notch characteristics, enabling assessment of arterial waveform structure beyond chronological age. The second dataset contains about 10,000 demographically balanced PPG samples curated for chronological age regression using rigorous subject-level balancing and correlation-based quality control. A standardized processing pipeline is presented, including beat alignment, ensemble averaging, and objective signal acceptance criteria to ensure morphological stability. To validate dataset utility, multiple machine learning models were benchmarked using raw signals, second derivatives, and compact Gaussian representations, achieving classification accuracy up to 90.08% and age prediction error below 10 years. By prioritizing real-world data quality, transparency, and reuse, this work provides a robust foundation for scalable, interpretable, and reproducible research in smartphone-based vascular assessment.

1 January 2025
Verified
Conference Paper
Closed access
IJIvan Jokic
Ivan Jokic
SJStevan Dragutin Jokic
Stevan Dragutin Jokic
One procedure for automatic speaker recognition based on use of 21 mel-frequency cepstral coefficients as speaker features and covariance matrix as speaker model is tested in this paper. Tests are conducted on the Solo part of the CHAINS speech database which contains 37 recordings for each of 36 speakers. Each speech recording is represented by appropriate matrix of feature vectors. Modeling of recording of speaker is done by covariance matrix of matrix of feature vectors. Results of recognition accuracy are compared for two cases, when on elements of speaker model is applied sigmoid function and when it is not. Tests are done in five stages. Application of sigmoid function on elements of covariance matrices results in most of tests in significantly increasing of recognition accuracy. Achieved mean recognition accuracy for all done tests when sigmoid function is not applied is 87,84% and when sigmoid function is applied is 94,64%.

1 January 2025
Verified
Conference Paper
Closed access
SJStevan Dragutin Jokic
Stevan Dragutin Jokic
IJIvan Jokic
Ivan Jokic
BGBranislav Gerazov
Branislav Gerazov
Nenad GligoricNenad Gligoric
Nenad Gligoric
AKAna Vladimir Kovacevic
Ana Vladimir Kovacevic
The growing emphasis on personalized healthcare within the paradigm of smart cities highlights the need for innovative, accessible solutions that enable early detection and continuous monitoring of cardiovascular health. In this study, we propose an advanced methodology for assessing blood vessel elasticity, expressed as the vascular „biological age,“ through the analysis of Photoplethysmography (PPG) signals acquired via the widely adopted mobile application „ECG for Everybody,“ which boasts over 150,000 downloads and a database of nearly 3 million recordings. Our approach introduces the concept of a dominant PPG beat, derived by averaging PPG signals across the entire recording. This averaged waveform serves as a robust representation of vascular characteristics, enabling precise assessment of blood vessel elasticity. By analyzing the shape and temporal dynamics of this dominant beat, we estimate vascular health parameters and determine the biological age of blood vessels. The analysis leverages a deep neural network trained on a diverse dataset collected from real-world users of the „ECG for Everybody“ application, as well as multiple signal processing techniques. This neural model correlates the morphological features of the averaged PPG beat with vascular elasticity, providing an innovative and noninvasive method for assessing cardiovascular health. Initial experimental results validate the efficacy of the proposed approach in accurately estimating vascular biological age. By integrating advanced PPG signal processing and machine learning techniques within a user-friendly mobile application, this work represents a significant step toward accessible, real-time healthcare solutions tailored for smart city environments.

1 January 2025
Verified
Conference Paper
Closed access
ZRZlatko Radovanović
Zlatko Radovanović
SJStevan Dragutin Jokic
Stevan Dragutin Jokic
IJIvan Jokic
Ivan Jokic
BGBranislav Gerazov
Branislav Gerazov
AKAna Vladimir Kovacevic
Ana Vladimir Kovacevic
Nenad GligoricNenad Gligoric
Nenad Gligoric
Biomedical signals or biosignals are spatial, temporal or spatio-temporal records of a biological phenomenon. Biosignals contain information that is of great importance for understanding the specific physiological mechanisms of biological phenomena or the systems from which they originate. Signals provide important information about the internal state of organs, response to external stimuli, general state, general state of health and the state of various other parameters and are an indispensable part of modern medical diagnostic practice. The signal that arises as a result of the device’s action on the organism, the subject of this paper, is the signal obtained by the photoplethysmography (PPG) method. Certain artificial intelligence methods were used to analyze the PPG signal. In this paper, analysis using wavelet transformation will be used, and a special focus will be on the selection of wavelets (wavelets) that will be used for the purpose of machine learning.

1 January 2025 in Facta universitatis - series: Electronics and Energetics
Verified
Journal Article
Open access
IJIvan Jokic
Ivan Jokic
SJStevan Dragutin Jokic
Stevan Dragutin Jokic
Vlado DelićVlado Delić
Vlado Delić
Zoran PerićZoran Perić
Zoran Perić
The efficiency of the proposed automatic speaker recognizer is evaluated using two speech databases. The feature vector consists of 21 mel-frequency cepstral coefficients (MFCCs), along with up to three additional features derived from the amplitude spectrum. The additional features are calculated based on the logarithm of the energy around the appropriate local maximum in the spectrum, the frequency of that maximum, and the logarithm of the energy of the maximum component in the spectrum across all frames of the observed signal. The speaker identification procedure for a closed set of speakers is tested on the Solo section of the CHAINS database and a speech database with expressed emotions, developed within the S-ADAPT project. The achieved maximum mean recognition accuracies are 97.11%, on the CHAINS database, using a feature vector of 21 MFCCs and two additional features, and 98.65% on neutral speech, as well as 98.72% on the entire database, for the S-ADAPT database, using a feature vector of 21 MFCCs.