Dejan Ljubobratović

Mr. Dejan Ljubobratović

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
3 August 2022 in Sensors
Verified
Journal Article
Open access
PDF file
DLDejan Ljubobratović
Dejan Ljubobratović
MVMarko Vuković
Marko Vuković
Marija Brkic BakaricMarija Brkic Bakaric
Marija Brkic Bakaric
Tomislav JemrićTomislav Jemrić
Tomislav Jemrić
Maja MateticMaja Matetic
Maja Matetic
To date, many machine learning models have been used for peach maturity prediction using non-destructive data, but no performance comparison of the models on these datasets has been conducted. In this study, eight machine learning models were trained on a dataset containing data from 180 ‘Suncrest’ peaches. Before the models were trained, the dataset was subjected to dimensionality reduction using the least absolute shrinkage and selection operator (LASSO) regularization, and 8 input variables (out of 29) were chosen. At the same time, a subgroup consisting of the peach ground color measurements was singled out by dividing the set of variables into three subgroups and by using group LASSO regularization. This type of variable subgroup selection provided valuable information on the contribution of specific groups of peach traits to the maturity prediction. The area under the receiver operating characteristic curve (AUC) values of the selected models were compared, and the artificial neural network (ANN) model achieved the best performance, with an average AUC of 0.782. The second-best machine learning model was linear discriminant analysis with an AUC of 0.766, followed by logistic regression, gradient boosting machine, random forest, support vector machines, a classification and regression trees model, and k-nearest neighbors. Although the primary parameter used to determine the performance of the model was AUC, accuracy, F1 score, and kappa served as control parameters and ultimately confirmed the obtained results. By outperforming other models, ANN proved to be the most accurate model for peach maturity prediction on the given dataset.

14 December 2021 in Electronics
Verified
Journal Article
Open access
PDF file
DLDejan Ljubobratović
Dejan Ljubobratović
MVMarko Vuković
Marko Vuković
Marija Brkic BakaricMarija Brkic Bakaric
Marija Brkic Bakaric
Tomislav JemrićTomislav Jemrić
Tomislav Jemrić
Maja MateticMaja Matetic
Maja Matetic
Peaches (Prunus persica (L.) Batsch) are a popular fruit in Europe and Croatia. Maturity at harvest has a crucial influence on peach fruit quality, storage life, and consequently consumer acceptance. The main goal of this study is to develop a machine learning model that will detect the most important features for predicting peach maturity by first training models and then using the importance ratings of these models to detect nonlinear (and linear) relationships. Thus, the most important peach features at a given stage of its ripening could be revealed. To date, this method has not been used for this purpose, and at the same time, it has the potential to be applied to other similar peach varieties. A total of 33 fruit features are measured on the harvested peaches, and three imbalanced datasets are created using firmness thresholds of 1.84, 3.57, and 4.59 kg·cm−2. These datasets are balanced using the SMOTE and ROSE techniques, and the Random Forest machine learning model is trained on them. Permutation Feature Importance (PFI), Variable Importance (VI), and LIME interpretability methods are used to detect variables that most influence predictions in the given machine learning models. PFI shows that the h° and a* ground color parameters, COL ground color index, SSC/TA, and TA inner quality parameters are among the top ten most contributing variables in all three models. Meanwhile, VI shows that this is the case for the a* ground color parameter, COL and CCL ground color indexes, and the SSC/TA inner quality parameter. The fruit flesh ratio is highly positioned (among the top three according to PFI) in two models, but it is not even among the top ten in the third.

1 January 2020 in The future of information science
Verified
Conference Paper
Open access
PDF file
DLDejan Ljubobratović
Dejan Ljubobratović
Maja MateticMaja Matetic
Maja Matetic
This is the seventh publication in the series of biennial international conferences, The Future of Information Sciences (INFuture) organised by the Department of Information and Communication Sciences, Faculty of Humanities and Social Sciences, University of Zagreb. Since its beginnings twelve years ago, the INFuture conference has been providing a platform for discussing both theoretical and practical issues in information organization and information integration through the explorations of how developments in information and communication technology influence the future of the field of information sciences. Education and research in information sciences and its interdisciplinary scope and application is of particular interest to this conference which is aimed at researchers and professionals from the broad field of information and communication sciences and related professions. The title of this year's conference is INFuture2019: Knowledge in the Digital Age. The conference explores the influence the information and communication sciences have on the society as a whole.The INFuture2019 conference consists of 26 papers from 58 authors from nine countries -Austria, Croatia, Germany, Netherlands, Norway, Slovenia, South Korea, Sweden and United States.

17 June 2025 in Agronomy
Verified
Journal Article
Open access
PDF file
MVMarko Vuković
Marko Vuković
DLDejan Ljubobratović
Dejan Ljubobratović
Maja MateticMaja Matetic
Maja Matetic
Marija Brkic BakaricMarija Brkic Bakaric
Marija Brkic Bakaric
Slaven JurićSlaven Jurić
Slaven Jurić
Tomislav JemrićTomislav Jemrić
Tomislav Jemrić
The main goal of this study was to investigate and better understand the evolution of the main non-destructive and destructive quality parameters of peach ‘Redhaven’ during ripening process. This study was conducted from 8 to 21 July 2023, during which peaches ‘Redhaven’ were harvested each second day from a commercial orchard located in Novaki Bistranjski. Maturity categories were defined according to different firmness thresholds: maturity for long-distance chain stores (H1), maturity for medium-distance chain stores (H2), maturity below the defined maximum firmness in order to preserve optimal quality traits (H3), ready to buy (H4), ready to eat (H5), and overripe (H6). The chlorophyll absorbance index was the non-destructive parameter that was mostly distinguished between maturity categories (r = 0.78 with firmness), followed by a* and h° ground colour parameters. During the first three maturity categories (H1–H3), firmness had a notably smaller correlation with titratable acidity and the ratio of total soluble solids and titratable acidity, which is not the case for a* and h° ground colour parameters, chlorophyll absorbance index, and the share of additional colour. During the last three maturity categories (H4–H6), non-destructive parameters are not reliable for maturity prediction. When ground colour parameters are measured near petiole insertion, mostly smaller segregation between maturity categories is obtained compared to when measured at the rest of the fruit. Total polyphenol and flavonoid content in peach juice notably corelated only in the last two maturity categories with L* ground colour parameter.

13 December 2025 in Computers
Verified
Journal Article
Open access
PDF file
DLDejan Ljubobratović
Dejan Ljubobratović
MVMarko Vuković
Marko Vuković
Marija Brkic BakaricMarija Brkic Bakaric
Marija Brkic Bakaric
Tomislav JemrićTomislav Jemrić
Tomislav Jemrić
Maja MateticMaja Matetic
Maja Matetic
Peach maturity at harvest is a critical factor influencing fruit quality and postharvest life. Traditional destructive methods for maturity assessment, although effective, compromise fruit integrity and are unsuitable for practical implementation in modern production. This study presents a machine learning approach for non-destructive peach maturity prediction using tabular data collected from 701 ‘Redhaven’ peaches. Three neural network models suitable for small tabular datasets (TabNet, SAINT, and NODE) were applied and evaluated using classification metrics, including accuracy, F1-score, and AUC. The models demonstrated consistently strong performance across several feature configurations, with TabNet achieving the highest accuracy when all non-destructive measurements were available, while TabNet provided the most robust and practical performance on the comprehensive non-destructive subset and in optimized minimal-feature settings. These findings indicate that non-destructive sensing methods, particularly when combined with modern neural architectures, can reliably predict maturity and offer potential for real-time, automated fruit selection after harvest. The integration of such models into autonomous harvesting systems, for instance, through drone-based platforms equipped with appropriate sensors, could significantly improve efficiency and fruit quality management in horticultural peach production.