Sylvio Barbon Junior

About Me

Hi, I'm Sylvio Barbon Junior, a researcher and professor working at the intersection of Artificial Intelligence ( University of Trieste, Italy), Process Mining, and Data Science. My academic and professional journey has been shaped by curiosity about how data can reveal insights into complex processes and support better decision-making. Over the years, I have been involved in projects that span both academia and industry, ranging from methodological research to applied solutions that address practical challenges. I particularly enjoy collaborating in multidisciplinary environments, where diverse perspectives often lead to innovative outcomes. Teaching and mentoring are also central to my work, as I value the opportunity to support students and colleagues in developing their skills and pursuing their own research paths. What drives me most is the chance to connect theory with practice—whether by developing models, analyzing data, or building tools that have tangible impact. Through this balance of research, teaching, and applied projects, I aim to contribute to advancing knowledge while also creating value beyond the academic setting.

Current Projects

Contact

Email: sylvio.barbonjunior@units.it

GitHub: github.com/sbarbonjr

LinkedIn: linkedin.com/in/barbon

Publications

Show/Hide Publications (2018–2025)

2025

  • de Souza Schiaber, P. et al. Analyzing fatigue in dynamic exercise through electromyography signals. Biomedical Signal Processing and Control, 99, 106864, Elsevier, 2025.
  • von Zuben, T.W. et al. Machine learning predictions of methanol/ethanol electrooxidation potentials. Electrochimica Acta, 509, 145285, 2025.
  • Moraes, I.A. de et al. Assessment of oleogel stability over storage. 2025.
  • Moraes, I.A. de et al. Explainable AI for microscopy/spectroscopy in oleogel stability. Journal of Food Engineering, 394, 112515, Elsevier, 2025.
  • Moraes, I.A. et al. Predicting oleogel properties using spectroscopy + ML. Food Research Int., 207, 116044, Elsevier, 2025.
  • Moraes, I.A. de et al. Physicochemical and structural analysis of oleogels. 2025.
  • Moraes, I.A. et al. Authentication of coriander oil with spectroscopy & e-nose. Food Chemistry, 483, 144196, Elsevier, 2025.
  • Arrighi, L. et al. Explainable AI techniques for interpretation of food datasets: a review. arXiv:2504.10527, 2025.
  • Lopes, J.F. et al. Online Meta-Recommendation of CUSUM Hyperparameters. Sensors, 25(9):2787, MDPI, 2025.
  • Ceschin, M. et al. Extending Decision Predicate Graphs for Isolation Forest explanation. arXiv:2505.04019, 2025.
  • Guido, R.C., Barbon Junior, S. Beyond accuracy: Explainable AI in biomedical voice tech. Computers in Biology and Medicine, 110240, Elsevier, 2025.
  • Soares, J.M.L. et al. Predicting glycerol electrochemical oxidation potentials with ML. J. Braz. Chem. Soc., 36(8), e–20250090, 2025.
  • Berti, M. et al. Meta-learning for variational autoencoder hyperparameter tuning. J. Universal Computer Science, 31(7):668, 2025.

2024

  • Ceravolo, P. et al. Tuning ML to Address Process Mining Requirements. IEEE Access, 12, 24583–24595, 2024.
  • Silva, R.P. et al. Unsupervised tuning for drift detectors. IEEE Access, 12, 54256–54271, 2024.
  • Grigore, I.M. et al. Automated Trace Clustering Pipeline Synthesis. Information, 15(4):241, 2024.
  • Oyamada, R.S. et al. Enhancing Predictive Process Monitoring with Time Features. CAiSE, 71–86, Springer, 2024.
  • Junior, S.B. et al. Are LLMs the New Interface for Data Pipelines?. BiDEDE@SIGMOD, ACM, 2024.
  • Oyamada, R.S. et al. CoSMo: Conditioned Process Simulation Models. BPM, 328–344, 2024.
  • da Silva, M.C. et al. Benchmarking AutoML Clustering Frameworks. AutoML Conf., 2024.
  • de Moraes, I.A. et al. Interpreting carambola maturity with computer vision. Food Research Int., 192, 114836, 2024.
  • Junior, S.B. et al. Data-Driven Methods for Soccer Analysis. Springer AI in Sports, 233, 2024.
  • da Silva Ferreira, M.V. et al. XAI for dragon fruit classification. Scientia Horticulturae, 338, 113605, 2024.
  • Vecchi, L.P. et al. Tuning Hypothesis Creation for Hate Speech Detection. BRACIS, 253–268, 2024.
  • Arrighi, L. et al. Decision Predicate Graphs in Tree Ensembles. World Conf. on XAI, 311–332, 2024.
  • de Souza, R.A. et al. Forecasting Malware Incident Rates. AINA, 226–237, 2024.
  • da Silva Pereira, E. et al. Portable NIR spectrometer for mastitis detection. Food Control, 163, 110527, 2024.
  • da Silva, M.C. et al. Problem-oriented AutoML in Clustering. arXiv:2409.16218, 2024.
  • Sakurai, G.Y. et al. A Self-Tuning Ensemble for Drift Detection. ENIAC, 811–822, 2024.

2023

  • Oyamada, R.S. et al. Meta-learning framework for graph similarity search. Information Systems, 112, 102123, 2023.
  • Martins, V.E. et al. Meta-learning for tuning active learning in streams. Pattern Recognition, 138, 109359, 2023.
  • Silva, M.C. et al. Using Process Mining to Reduce Fraud. FinTech, 2(1):120–137, 2023.
  • Vitor, A.L.O. et al. Induction motor fault diagnosis with ML. Expert Systems with Applications, 224, 119998, 2023.
  • Sakurai, G.Y. et al. Benchmarking Drift Detector Algorithms. Future Internet, 15(5):169, 2023.
  • Junior, S.B. et al. Multiple voice disorders: multi-label approaches. Speech Communication, 152, 102952, 2023.
  • Abonizio, H.Q. et al. CoronaAI: chatbot against disinformation. Int. J. Med. Informatics, 177, 105134, 2023.
  • Tavares, G.M. et al. Anomaly detection with encoding techniques. CSIS, 20(3):1207–1233, 2023.
  • Tavares, G.M. et al. Trace encoding in process mining: survey. Eng. Apps. of AI, 126, 107028, 2023.
  • Arrighi, L. et al. Explainable Automated Anomaly Recognition. World Conf. on XAI, 420–432, 2023.
  • de Castro Silva, V. et al. Explainable Time Series Tree. IEEE Access, 11, 120845–120856, 2023.

2022

  • Aguiar, G.J. et al. Using meta-learning for multi-target regression. Information Sciences, 584, 665–684, 2022.
  • Scaranti, G.F. et al. Unsupervised anomaly detection in SDN. Expert Systems with Applications, 191, 116225, 2022.
  • Barbon Junior, S. et al. Sport action mining: dribbling recognition in soccer. Multimedia Tools & Applications, 81(3):4341–4364, 2022.
  • Tavares, G.M. et al. Automating process discovery with meta-learning. CoopIS, 205–222, Springer, 2022.
  • Tavares, G.M. et al. Selecting optimal trace clustering pipelines with meta-learning. BRACIS, 150–164, 2022.
  • Alberghini, G. et al. Adaptive ensembles for drifting data streams. Neurocomputing, 481, 228–248, 2022.
  • Lopes, J.F. et al. Deep computer vision system for cocoa classification. Multimedia Tools & Applications, 81(28):41059–41077, 2022.

2021

  • Santana, E.J. et al. Improved soil prediction with multi-target stacked models. Chemometrics & Intelligent Lab. Systems, 104231, 2021.
  • Oliveira, M.M. et al. Classification of fermented cocoa beans. J. Food Composition & Analysis, 97, 103771, 2021.
  • Zarpelão, B. et al. Blockchain for agrifood traceability. Food Authentication & Traceability, 279–302, 2021.
  • Barbon Junior, S. et al. Using meta-learning to recommend process discovery methods. arXiv:2103.12874, 2021.
  • Vertuam Neto, R. et al. Online clustering for anomaly detection. SBIS, 2021.
  • Azzini, A. et al. Advances in Data Management in the Big Data Era. Springer, 99–126, 2021.
  • Peres, L.M. et al. Meta-recommendation of pork quality standards. Biosystems Eng., 210, 13–19, 2021.
  • Tavares, G.M., Barbon, S.B. Encoding via meta-learning for anomaly detection. ADBIS, 157–168, 2021.
  • Barbon, S.B. et al. Selecting optimal trace clustering pipelines with AutoML. arXiv:2109.00635, 2021.
  • Abonizio, H.Q. et al. Text data augmentation for sentiment analysis. IEEE Trans. AI, 3(5):657–668, 2021.
  • Santana, E.J. et al. Adversarial examples in regression forecasting. Information, 12(10):394, 2021.
  • Silva, R.P. et al. Time series segmentation via stationarity analysis. Sensors, 21(21):7333, 2021.
  • Caetano, F.G. et al. Football player dominant regions model. Scientific Reports, 11:18209, 2021.

2020

  • Junior, S.B. et al. Multi-target prediction of wheat flour quality. Information Processing in Agriculture, 7(2):342–354, 2020.
  • Lopes, J.F. et al. Dual Stage Image Analysis for ham defects. Biosystems Eng., 191:129–144, 2020.
  • Campos, G.F.C. et al. Robust CV system for meat segmentation. ELCVIA, 19(1):15–27, 2020.
  • Lopes, J.F. et al. Evaluating trade-offs for data stream classification. IEEE Trans. Net. & Serv. Mgmt, 17(2):1013–1025, 2020.
  • Abonizio, H.Q. et al. Language-independent fake news detection. Future Internet, 12(5):87, 2020.
  • Scaranti, G.F. et al. AI systems + fuzzy logic for SDN attacks. IEEE Access, 8:100172–100184, 2020.
  • Ceravolo, P. et al. Evaluation goals for online process mining. IEEE TSC, 15(4):2473–2489, 2020.
  • Junior, S.B. et al. Anomaly Detection on Event Logs with Few Labels. ICPM, 161–168, IEEE, 2020.
  • Mastelini, S.M. et al. DSTARS: Deep Structure for regressor stacking. Applied Soft Computing, 106215, 2020.
  • Queiroz, H. et al. Pre-trained data augmentation for text classification. BRACIS, 551–565, 2020.
  • Santana, E.J. et al. Photovoltaic generation forecast under adversarial attacks. BRACIS, 634–649, 2020.
  • Martins, V.E. et al. Active learning embedded in incremental decision trees. BRACIS, 367–381, 2020.
  • Junior, S.B. et al. Evaluating Trace Encoding Methods in Process Mining. DataMod, 174, Springer, 2020.
  • Oyamada, R.S. et al. Proximity graph auto-configuration via meta-learning. ADBIS, 93–107, 2020.

2019

  • Mastelini, S.M. et al. Multi-output tree chaining for multi-target regression. J. Signal Processing Systems, 91(2):191–215, 2019.
  • Kato, T. et al. White striping degree assessment in chicken. Asian-Australasian J. Animal Sciences, 32(7):1015, 2019.
  • Geronimo, B.C. et al. CV + NIR for wooden breast classification. Infrared Physics & Technology, 96:303–310, 2019.
  • Campos, G.F.C. et al. ML hyperparameter selection for CLAHE. EURASIP JIVP, 2019(1):59.
  • Nolasco, I.M. et al. Comparison of rapid techniques for ground meat classification. Biosystems Eng., 183:151–159, 2019.
  • Turrisi, V.G. et al. Evaluating trade-offs in stream classification. GPC, 3–17, Springer, 2019.
  • Costa, V.G. et al. Mobile botnets detection with ML. Int. J. Security & Networks, 14(2):103–118, 2019.
  • Lopes, J.F. et al. Barley flour classification with CV. Sensors, 19(13):2953, 2019.
  • Tavares, G.M. et al. Synthetic event streams. IEEE Dataport, 2019.
  • Tavares, G.M. et al. Overlapping Analytic Stages in Online Process Mining. SCC, 167–175, IEEE, 2019.
  • Aguiar, G.J. et al. Meta-learning for multi-target regression. BRACIS, 377–382, 2019.
  • Bezerra, V.H. et al. IoTDS: one-class detection of botnets. Sensors, 19(14):3188, 2019.
  • Omori, N.J. et al. Comparing drift detection with process mining tools. SBIS, 2019.

2018

  • Paula, R.S. et al. Multispectral system for meat quality evaluation. Computers and Electronics in Agriculture, 146:465–472, 2018.
  • Bezerra, V.H. et al. IoTDS: Internet of Things dataset for DDoS attacks. IEEE Dataport, 2018.
  • de Lima, F.G. et al. Sports video segmentation for highlights. Multimedia Tools & Applications, 77(10):12133–12152, 2018.
  • dos Santos, J.L. et al. Multispectral chicken meat classification. Infrared Physics & Technology, 92:341–350, 2018.
  • Oliveira, M.M. et al. Chicken meat quality classification with spectral techniques. Food Research Int., 108:245–249, 2018.
  • Simoes, J.M. et al. Quality control in poultry meat production. Food Analytical Methods, 11(6):1648–1659, 2018.