Marko Barjaktarovic

Dr. Marko Barjaktarovic

orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
15 March 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
MAMilica Badza Atanasijevic
Milica Badza Atanasijevic
MBMarko Barjaktarovic
Marko Barjaktarovic
The classification of brain tumors is performed by biopsy, which is not usually conducted before definitive brain surgery. The improvement of technology and machine learning can help radiologists in tumor diagnostics without invasive measures. A machine-learning algorithm that has achieved substantial results in image segmentation and classification is the convolutional neural network (CNN). We present a new CNN architecture for brain tumor classification of three tumor types. The developed network is simpler than already-existing pre-trained networks, and it was tested on T1-weighted contrast-enhanced magnetic resonance images. The performance of the network was evaluated using four approaches: combinations of two 10-fold cross-validation methods and two databases. The generalization capability of the network was tested with one of the 10-fold methods, subject-wise cross-validation, and the improvement was tested by using an augmented image database. The best result for the 10-fold cross-validation method was obtained for the record-wise cross-validation for the augmented data set, and, in that case, the accuracy was 96.56%. With good generalization capability and good execution speed, the new developed CNN architecture could be used as an effective decision-support tool for radiologists in medical diagnostics.

1 November 2018
Verified
Conference Paper
Closed access
AKAneta Kartali
Aneta Kartali
MRMilos Roglic
Milos Roglic
MBMarko Barjaktarovic
Marko Barjaktarovic
MDMilica Duric-Jovicic
Milica Duric-Jovicic
MJMilica M. Jankovic
Milica M. Jankovic
Emotion recognition has application in various fields such as medicine (rehabilitation, therapy, counseling, etc.), e-learning, entertainment, emotion monitoring, marketing, law. Different algorithms for emotion recognition include feature extraction and classification based on physiological signals, facial expressions, body movements. In this paper, we present a comparison of five different approaches for real-time emotion recognition of four basic emotions (happiness, sadness, anger and fear) from facial images. We have compared three deep-learning approaches based on convolutional neural networks (CNN) and two conventional approaches for classification of Histogram of Oriented Gradients (HOG) features: 1) AlexNet CNN, 2) commercial Affdex CNN solution, 3) custom made FER-CNN, 4) Support Vector Machine (SVM) of HOG features, 5) Multilayer Perceptron (MLP) artificial neural network of HOG features. The result of real-time testing of five different algorithms on the group of eight volunteers is presented.

13 March 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
MBMarko Barjaktarovic
Marko Barjaktarovic
MSMassimo Santoni
Massimo Santoni
LBLorenzo Bruzzone
Lorenzo Bruzzone
With the rapid increase of the world population, climate changes, and the slow expansion of cultivated areas, only precision agriculture (PA) can provide enough food or resources. PA requires flexible instruments for measuring the spectral signatures of the crops to understand their conditions. Unfortunately, the high initial costs of multispectral cameras reduce the implementation of PA in small farms, which constitute a large portion of arable land in Europe and contribute with social bonds, local know-how, and cultural legacy. With the objective to speed up the use of multispectral imaging, in this paper, we present a novel low-cost imaging device consisting of a multispectral camera with nine bands and a thermal imager, which price is several times lower than commercially available ones. This paper describes the design and the calibration of the imaging device based on the off-the-shelf components: Raspberry Pi, dedicated quad camera kit, thermal core, and multi-band optical filters. The spectral reconstruction accuracy has a high average R2 score of 0.986. Finally, images from multiple sensors are aligned using phase-only correlation and dense optical flow, providing a method that can be implemented on all platforms. The presented solution is open source, permitting one to modify and expand the capabilities of the described device and adapt to specific needs. Moreover, the device is flexible as the thermal camera can be removed to reduce the total system cost if its usage is not required. Even if its primary application is PA, the proposed solution can be used for other applications.

10 May 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
MAMilica Badza Atanasijevic
Milica Badza Atanasijevic
MBMarko Barjaktarovic
Marko Barjaktarovic
The use of machine learning algorithms and modern technologies for automatic segmentation of brain tissue increases in everyday clinical diagnostics. One of the most commonly used machine learning algorithms for image processing is convolutional neural networks. We present a new convolutional neural autoencoder for brain tumor segmentation based on semantic segmentation. The developed architecture is small, and it is tested on the largest online image database. The dataset consists of 3064 T1-weighted contrast-enhanced magnetic resonance images. The proposed architecture’s performance is tested using a combination of two different data division methods, and two different evaluation methods, and by training the network with the original and augmented dataset. Using one of these data division methods, the network’s generalization ability in medical diagnostics was also tested. The best results were obtained for record-wise data division, training the network with the augmented dataset. The average accuracy classification of pixels is 99.23% and 99.28% for 5-fold cross-validation and one test, respectively, and the average dice coefficient is 71.68% and 72.87%. Considering the achieved performance results, execution speed, and subject generalization ability, the developed network has great potential for being a decision support system in everyday clinical practice.

1 November 2016
Verified
Conference Paper
Closed access
NJNovica Jankovic
Novica Jankovic
MBMarko Barjaktarovic
Marko Barjaktarovic
MJMilica M. Jankovic
Milica M. Jankovic
Djordje CantrakDjordje Cantrak
Djordje Cantrak
Particle image velocimetry (PIV) is an optical, laser based, measurement of fluid velocity and its 2D/3D visualisation. We have presented a new approach in low-cost PIV design using: 1) fast industrial camera, 2) laser pointer, with cylindrical lens for continual fluid flow illumination, 3) acquisition software developed in house, 4) OpenPIV analysis software. Velocity was measured in the glass jar where swirl flow was generated by magnetic stirrer. In this pilot study, results obtained by calibration device based on Laser Doppler anemometry and our PIV results are in good agreement.

2 November 2023 in Circuits, Systems, and Signal Processing
Verified
Journal Article
Closed access
PDF file
ZŠZoran Šarić
Zoran Šarić
MSMisko Zoran Subotic
Misko Zoran Subotic
RBRužica Bilibajkić
Ružica Bilibajkić
MBMarko Barjaktarovic
Marko Barjaktarovic
JSJasmina Stojanovic
Jasmina Stojanovic