Marian Bucos

@upt.ro

Communications Department / Faculty of Electronics, Telecommunications, and Informational Technologies
Politehnica University Timisoara

Marian Bucos


                           Download Compact PDF  
https://researchid.co/marianbucos

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Science, Artificial Intelligence, Information Systems, Electrical and Electronic Engineering
23

Scopus Publications

340

Scholar Citations

9

Scholar h-index

9

Scholar i10-index

Scopus Publications

  • A Multimodal Deep Learning Approach for Analyzing Content Preferences on TikTok Across European Technical Universities Using Media Information Processing System
    Dragoş-Florin Sburlan, Marian Bucos
    Electronics Switzerland, 2026
    Social media platforms have become primary communication channels for technical European universities. However, the extent to which global platform algorithms homogenize individual preferences across cultures remains underexplored. Although the current literature offers insights into the topic, none of the works consider the cross-national and multimodal nature of the phenomenon. In the current paper, we introduce the Media Information Processing System (MIPS), a privacy-preserving multimodal deep learning (DL) framework that incorporates large language models (LLMs), computer vision (CV), and knowledge graphs. We analyze data from 15,520 public videos shared by 2359 followers of six top technical universities from Romania, Germany, Italy, and Russia. The results of the study suggest that the degree of homogeneity of the followers’ interest profiles is markedly high. Statistical profiling of the data indicates that the interest profiles of the followers from different countries are positively correlated with a high degree of strength (mean Pearson r = 0.96; p > 0.90). Consensus clustering of the data reveals the existence of stable clusters of themes with high stability scores (>0.75), such as “Human Interaction Dynamics”. The results of the study contradict the traditional theory of regional cultural differentiation. Instead, the results suggest the existence of a new “digital student persona” that is characteristic of the academic lifestyle of students from different countries.
  • Proactive Proctoring: A Critical Analysis of Machine Learning Architectures and Custom Temporal Data Sets for Moodle Fraud Detection
    Andrei-Nicolae Vacariu, Marian Bucos, Marius Otesteanu, Bogdan Dragulescu
    Applied Sciences Switzerland, 2026
    This paper examines the use of Machine Learning (ML) approaches in maintaining academic integrity using the information provided in the Moodle system logs. The paper focuses on data set construction, handling the issue of class imbalance, and the assessment of the performance of different ML models in uncovering academic fraud. Twelve different data sets were created by using the concept of temporal windows (e.g., one-day and three-day windows) during the feature extraction stage from the Moodle system logs. The manual labeling of the data sets was done based on a predefined set of rules that outline the fraudulent activities. The issue of class imbalance was treated using eleven different resampling approaches, such as SMOTE, ADASYN, Tomek Links, and NearMiss. We evaluated six classification algorithms, thus resulting in a total of 792 experiments based on the interactions between the data sets, resampling methods, and classification algorithms. The results from the experiment show that the Random Forest and AdaBoost models performed the best in the experiment. Furthermore, we observed a trade-off between fraud detection rates and model precision based on the temporal windows and resampling methods. The shortest temporal windows and hybrid undersampling approaches resulted in the maximum recall value in this study and could identify the greatest number of at-risk students. On the other hand, the longest temporal windows and hybrid oversampling approaches with data cleaning resulted in the best results in terms of F1-Score and Cohen’s Kappa statistics. The results provide conclusive evidence that the models can identify fraud; however, they should be used as predictive models for the improvement of proctoring approaches, such as random selection for verification or seating arrangement strategies, instead of judgment models.
  • An Architecture of a Web Application for Deploying Machine Learning Models in Healthcare Domain
    Mihai-Eronim-Octavian Ursan, Cătălin Daniel Căleanu, Marian Bucos
    2024 16th International Symposium on Electronics and Telecommunications Isetc 2024 Conference Proceedings, 2024
    An important gap exists between advanced Deep Learning (DL) models developed for medical imaging and their insitu implementation in clinical environments. Our research proposes a scalable software architecture for a web-based computer-aided diagnosis (CAD) application that bridges the gap between research and production. The main goals are: (1) creating an intuitive interface for non-technical users and, (2) designating a feedback mechanism to enhance the Machine Learning (ML) models with medical expertise. The architecture assumes a microservices approach, containerization, and current web technologies to enable seamless deployment and user-friendliness. Key components include ONNX-based model conversion for cross- platform compatibility, asynchronous processing based on FastAPI, and a modular data handling system using PostgreSQL. Our proof-of-concept (PoC) shows the system's feasibility by deploying it on the Google Cloud Platform (GCP) and getting initial feedback from clinicians. Early findings indicate potential improvements in model usability and stakeholder engagement. Future actions will involve implementing continuous integration and delivery pipelines to improve system resilience and scalability.
  • Automated Detection of AI-Generated Text Using LLM Embedding-Driven ML Models
    Andrei-Nicolae Vacariu, Marian Bucos, Marius Otesteanu, Bogdan Dragulescu
    2024 16th International Symposium on Electronics and Telecommunications Isetc 2024 Conference Proceedings, 2024
    Large Language Models (LLM) have proved their ability in tasks once thought to be exclusive to humans, such as text sumarization, completion, question answering, and others. Although LLMs were present for some time, OpenAI's ChatGPT introduced them to a broader audience. Despite their ability to assist humans in various tasks, some concerns arise, as there is a big probability of misuse in areas such as fake news, plagiarism, and propaganda. Previous studies have shown that humans are unable to accurately detect generated text, which motivates the need for automated detectors. In this work, we explore whether machine learning models can distinguish between text written by humans and generated text when using embeddings as input. We process a publicly available data set, Human ChatGPT Comparison Corpus (HC3). The data set contains question-answer pairs in various domains, including open-domain, financial, medical, legal, and psychological areas. We are using Llama3, an open-source large language model, to generate the embeddings. We then evaluate the performance of four machine learning (ML) models in detecting text generated by ChatGPT with the text embeddings used as input. The ML models are the Support Vector Classifier, Naive Bayes, the K-Nearest Neighbors Classifier, and a neural network. The results show that relatively simple models can identify the generated text. SVC demonstrated the best results with an F1-score of 99.95%.
  • Natural language processing with transformers: a review
    Georgiana Tucudean, Marian Bucos, Bogdan Dragulescu, Catalin Daniel Caleanu
    Peerj Computer Science, 2024
    Natural language processing (NLP) tasks can be addressed with several deep learning architectures, and many different approaches have proven to be efficient. This study aims to briefly summarize the use cases for NLP tasks along with the main architectures. This research presents transformer-based solutions for NLP tasks such as Bidirectional Encoder Representations from Transformers (BERT), and Generative Pre-Training (GPT) architectures. To achieve that, we conducted a step-by-step process in the review strategy: identify the recent studies that include Transformers, apply filters to extract the most consistent studies, identify and define inclusion and exclusion criteria, assess the strategy proposed in each study, and finally discuss the methods and architectures presented in the resulting articles. These steps facilitated the systematic summarization and comparative analysis of NLP applications based on Transformer architectures. The primary focus is the current state of the NLP domain, particularly regarding its applications, language models, and data set types. The results provide insights into the challenges encountered in this research domain.
  • Enhancing Fake News Detection in Romanian Using Transformer-Based Back Translation Augmentation
    Marian Bucos, Bogdan Drăgulescu
    Applied Sciences Switzerland, 2023
    Misinformation poses a significant challenge in the digital age, requiring robust methods to detect fake news. This study investigates the effectiveness of using Back Translation (BT) augmentation, specifically transformer-based models, to improve fake news detection in Romanian. Using a data set extracted from Factual.ro, the research finds that BT-augmented models show better accuracy, precision, recall, F1 score, and AUC compared to those using the original data set. Additionally, using mBART for BT augmentation with French as a target language improved the model’s performance compared to Google Translate. The Extra Trees Classifier and the Random Forest Classifier performed the best among the models tested. The findings suggest that the use of BT augmentation with transformer-based models, such as mBART, has the potential to enhance fake news detection. More research is needed to evaluate the effects in other languages.
  • Text Data Augmentation Techniques for Fake News Detection in the Romanian Language
    Marian Bucos, Georgiana Țucudean
    Applied Sciences Switzerland, 2023
    This paper aims to investigate the use of a Romanian data source, different classifiers, and text data augmentation techniques to implement a fake news detection system. The paper focusses on text data augmentation techniques to improve the efficiency of fake news detection tasks. This study provides two approaches for fake news detection based on content and context features found in the Factual.ro data set. For this purpose, we implemented two data augmentation techniques, Back Translation (BT) and Easy Data Augmentation (EDA), to improve the performance of the models. The results indicate that the implementation of the BT and EDA techniques successfully improved the performance of the classifiers used in our study. The results of our content-based approach show that an Extra Trees Classifier model is the most effective, whether data augmentation is used or not, as it produced the highest accuracy, precision, F1 score, and Kappa. The Random Forest Classifier with BT yielded the best results of the context-based experiment overall, with the highest accuracy, recall, F1 score, and Kappa. Furthermore, we found that BT and EDA led to an increase in the AUC scores of all models in both content-based and context-based data sets.
  • The Use of Data Augmentation as a Technique for Improving Fake News Detection in the Romanian Language
    Georgiana Tucudean, Marian Bucos
    2022 15th International Symposium on Electronics and Telecommunications Isetc 2022 Conference Proceedings, 2022
    Anomalies and fake data can be identified by applying supervised learning algorithms to news sources. These techniques can help reduce the negative impact of fake news on consumers. Fake news is a widespread problem around the world and is also gaining momentum in Romania. For the detection of fake news in Romanian, we investigate methods to construct a Romanian data set and apply algorithms that offer the highest performance. To improve performance, we use a data augmentation technique called back translation in conjunction with the Support Vector Machine classifier.
  • Predictive Analytics Models for Student Admission to Master Programs in Romania
    Mihai Ursan, Marian Bucos
    2022 15th International Symposium on Electronics and Telecommunications Isetc 2022 Conference Proceedings, 2022
    This study examines the student admission process at Politehnica University Timisoara's Faculty of Electronics, Telecommunications, and Information Technologies for master's engineering programs. The focus of the study is the student's admission prediction into the mainstream programs offered by our faculty. The programs in this category are the most successful and stable. Most of the features we use have been geared toward the options of future degree programs students may choose to pursue. In these experiments, we used several evaluation methods, including stratified cross-validation and evaluation of unseen data chunks that were not used for training. The Gradient Boost Classifier performs the best of the six models. Among the conclusions drawn is that secondary options do not provide relevant information for predictive models. We implemented the experiments using a low-code framework; as a result, the predictive analysis pipeline was largely automated.
  • Grouping farmers using agglomerative clustering on data generated from statistics
    Georgiana Simion, Catalin Daniel Caleanu, Marian Bucos, Bogdan Dragulescu
    2022 15th International Symposium on Electronics and Telecommunications Isetc 2022 Conference Proceedings, 2022
    The creation of agricultural clusters is one of the methods by which farmers can increase their competitiveness and generate economic growth. Machine learning can help to decide which are the best clusters to form in an area. The aim of the paper is to examine the possibility of using clustering on an agricultural platform. This platform is under development, and currently there are no real data available for training purposes. Therefore, we constructed a data set by integrating multiple data sources. This was constructed to be as similar as possible to the characteristics of the data available in the final platform. The proposed data set consists of 4480 records and 60 features, ranging from geographical location to crop yield. Next, the experimental part proposes a scenario for grouping the farmers based on geographic proximity and crop yield.
  • Student cluster analysis based on Moodle data and academic performance indicators
    Marian Bucos, Bogdan Dragulescu
    2020 14th International Symposium on Electronics and Telecommunications Isetc 2020 Conference Proceedings, 2020
  • Hyperparameter Tuning Using Automated Methods to Improve Models for Predicting Student Success
    Bogdan Drăgulescu, Marian Bucos
    Communications in Computer and Information Science, 2020
  • Predicting student success using data generated in traditional educational environments
    TEM Journal, 2018
  • CVLA: Integrating multiple analytics techniques in a custom moodle report
    Bogdan Drăgulescu, Marian Bucos, Radu Vasiu
    Communications in Computer and Information Science, 2015
  • Social network analysis on educational data set in RDF format
    Bogdan Dragulescu, Marian Bucos, Radu Vasiu
    Journal of Computing and Information Technology, 2015
  • A semantic web approach for automated test generation
    Proceedings of the Iadis International Conference Www Internet 2012 Icwi 2012, 2012
  • Piloting a multi-regional master programme in eActivities
    Radu Vasiu, Diana Andone, Andrei Ternauciuc, Marian Bucos
    Saci 2012 7th IEEE International Symposium on Applied Computational Intelligence and Informatics Proceedings, 2012
  • Using hCard and vCard for improving usability in Moodle
    B. Dragulescu, I. Ermalai, M. Bucos, M. Mocofan
    Saci 2011 6th IEEE International Symposium on Applied Computational Intelligence and Informatics Proceedings, 2011
  • Supervised tree content based search algorithm for multimedia image databases
    M. Mocofan, I. Ermalai, M. Bucos, M. Onita, B. Dragulescu
    Saci 2011 6th IEEE International Symposium on Applied Computational Intelligence and Informatics Proceedings, 2011
  • Designing a semantic web ontology for e-learning in higher education
    Marian Bucos, Bogdan Dragulescu, Marius Veltan
    2010 9th International Symposium on Electronics and Telecommunications Isetc 10 Conference Proceedings, 2010
  • Multimedia interfaces in the control process of smart buildings using 3D scenes, flash animations and relational databases
    M. Mocofan, R. Vasiu, M. Bucos, M. Ionita, I. Ermalai
    11th International Conference on Optimization of Electrical and Electronic Equipment Optim 2008, 2008
  • Approaches to life long learning by using online tools
    Iadis International Conference on Cognition and Exploratory Learning in Digital Age Celda 2006, 2006
  • Is it eLearning a viable solution in Romania?
    R. Vasiu, N. Robu, D. Andone, M. Bucos
    Proceedings 5th IEEE International Conference on Advanced Learning Technologies Icalt 2005, 2005

RECENT SCHOLAR PUBLICATIONS

  • A Multimodal Deep Learning Approach for Analyzing Content Preferences on TikTok Across European Technical Universities Using Media Information Processing System
    DF Sburlan, M Bucos
    Electronics 15 (6), 1288 , 2026
    2026
    Citations: 1
  • Proactive Proctoring: A Critical Analysis of Machine Learning Architectures and Custom Temporal Data Sets for Moodle Fraud Detection
    AN Vacariu, M Bucos, M Otesteanu, B Dragulescu
    Applied Sciences 16 (5), 2381 , 2026
    2026
  • Programare în Python
    M Bucos, B Drăgulescu
    Timişoara: Editura Politehnica , 2025
    2025
  • An Architecture of a Web Application for Deploying Machine Learning Models in Healthcare Domain
    MEO Ursan, CD Caleanu, M Bucos
    2024 International Symposium on Electronics and Telecommunications (ISETC) , 2024
    2024
    Citations: 3
  • Automated Detection of AI-Generated Text Using LLM Embedding-Driven ML Models
    AN Vacariu, M Bucos, M Otesteanu, B Drăgulescu
    2024 International Symposium on Electronics and Telecommunications (ISETC) , 2024
    2024
    Citations: 1
  • Natural Language Processing with Transformers: A Review
    G Tucudean, M Bucos, B Dragulescu, C Caleanu
    PeerJ Computer Science 10 , 2024
    2024
    Citations: 59
  • Enhancing Fake News Detection in Romanian Using Transformer-Based Back Translation Augmentation
    M Bucos, B Dragulescu
    Applied Sciences 13 (24), 13207 , 2023
    2023
    Citations: 9
  • Text Data Augmentation Techniques for Fake News Detection in the Romanian Language
    M Bucos, G Țucudean
    Applied Sciences 13 (13), 7389 , 2023
    2023
    Citations: 20
  • Predictive Analytics Models for Student Admission to Master Programs in Romania
    M Ursan, M Bucos
    2022 International Symposium on Electronics and Telecommunications (ISETC), 1-4 , 2022
    2022
    Citations: 7
  • The Use of Data Augmentation as a Technique for Improving Fake News Detection in the Romanian Language
    G Ţucudean, M Bucos
    2022 International Symposium on Electronics and Telecommunications (ISETC), 1-4 , 2022
    2022
    Citations: 3
  • Grouping Farmers Using Agglomerative Clustering on Data Generated from Statistics
    G Simion, CD Căleanu, M Bucos, B Dragulescu
    2022 International Symposium on Electronics and Telecommunications (ISETC), 1-4 , 2022
    2022
    Citations: 2
  • Student Cluster Analysis Based on Moodle Data and Academic Performance Indicators
    M Bucos, B Drăgulescu
    2020 International Symposium on Electronics and Telecommunications (ISETC), 1-4 , 2020
    2020
    Citations: 13
  • Hyperparameter Tuning Using Automated Methods to Improve Models for Predicting Student Success
    B Drăgulescu, M Bucos
    Information and Software Technologies 1283, 309-320 , 2020
    2020
    Citations: 8
  • Predicting Student Success Using Data Generated in Traditional Educational Environments
    M Bucos, B Drăgulescu
    TEM Journal 7 (3), 617 , 2018
    2018
    Citations: 56
  • Social Network Analysis on Educational Data Set in RDF Format
    B Dragulescu, M Bucos, R Vasiu
    Journal of computing and information technology 23 (3), 269-281 , 2015
    2015
    Citations: 7
  • Predicting Assignment Submissions in a Multi-Class Classification Problem
    B Drăgulescu, M Bucos, R Vasiu
    TEM Journal 4 (3), 244-254 , 2015
    2015
    Citations: 19
  • CVLA: Integrating Multiple Analytics Techniques in a Custom Moodle Report
    B Drăgulescu, M Bucos, R Vasiu
    Information and Software Technologies 538, 115-126 , 2015
    2015
    Citations: 15
  • Piloting a Multi-Regional Master Programme in eActivities
    R Vasiu, D Andone, A Ternauciuc, M Bucos
    2012 7th IEEE International Symposium on Applied Computational Intelligence … , 2012
    2012
    Citations: 2
  • A Semantic Web Approach for Automated Test Generation
    B Dragulescu, M Bucos, R Vasiu
    Proceedings of the IADIS International Conference WWW/Internet 2012, ICWI … , 2012
    2012
  • Metadata Methods for Improving Usability in Moodle
    B Dragulescu, I Ermalai, M Bucos, R Vasiu
    International Journal of Web Engineering 1 (1), 6-10 , 2012
    2012
    Citations: 15

MOST CITED SCHOLAR PUBLICATIONS

  • Natural Language Processing with Transformers: A Review
    G Tucudean, M Bucos, B Dragulescu, C Caleanu
    PeerJ Computer Science 10 , 2024
    2024
    Citations: 59
  • Predicting Student Success Using Data Generated in Traditional Educational Environments
    M Bucos, B Drăgulescu
    TEM Journal 7 (3), 617 , 2018
    2018
    Citations: 56
  • Designing a Semantic Web Ontology for E-Learning in Higher Education
    M Bucos, B Dragulescu, M Veltan
    2010 9th International Symposium on Electronics and Telecommunications, 415-418 , 2010
    2010
    Citations: 31
  • Text Data Augmentation Techniques for Fake News Detection in the Romanian Language
    M Bucos, G Țucudean
    Applied Sciences 13 (13), 7389 , 2023
    2023
    Citations: 20
  • Predicting Assignment Submissions in a Multi-Class Classification Problem
    B Drăgulescu, M Bucos, R Vasiu
    TEM Journal 4 (3), 244-254 , 2015
    2015
    Citations: 19
  • Supervised Tree Content Based Search Algorithm for Multimedia Image Databases
    M Mocofan, I Ermalai, M Bucos, M Onita, B Dragulescu
    2011 6th IEEE International Symposium on Applied Computational Intelligence … , 2011
    2011
    Citations: 19
  • CVLA: Integrating Multiple Analytics Techniques in a Custom Moodle Report
    B Drăgulescu, M Bucos, R Vasiu
    Information and Software Technologies 538, 115-126 , 2015
    2015
    Citations: 15
  • Metadata Methods for Improving Usability in Moodle
    B Dragulescu, I Ermalai, M Bucos, R Vasiu
    International Journal of Web Engineering 1 (1), 6-10 , 2012
    2012
    Citations: 15
  • Student Cluster Analysis Based on Moodle Data and Academic Performance Indicators
    M Bucos, B Drăgulescu
    2020 International Symposium on Electronics and Telecommunications (ISETC), 1-4 , 2020
    2020
    Citations: 13
  • Enhancing Fake News Detection in Romanian Using Transformer-Based Back Translation Augmentation
    M Bucos, B Dragulescu
    Applied Sciences 13 (24), 13207 , 2023
    2023
    Citations: 9
  • Developing Virtual Labs at Politehnica University of Timisoara
    M Bucos, B Dragulescu, A Ternauciuc
    Interactive Conference on Computer Aided Learning , 2008
    2008
    Citations: 9
  • Hyperparameter Tuning Using Automated Methods to Improve Models for Predicting Student Success
    B Drăgulescu, M Bucos
    Information and Software Technologies 1283, 309-320 , 2020
    2020
    Citations: 8
  • Predictive Analytics Models for Student Admission to Master Programs in Romania
    M Ursan, M Bucos
    2022 International Symposium on Electronics and Telecommunications (ISETC), 1-4 , 2022
    2022
    Citations: 7
  • Social Network Analysis on Educational Data Set in RDF Format
    B Dragulescu, M Bucos, R Vasiu
    Journal of computing and information technology 23 (3), 269-281 , 2015
    2015
    Citations: 7
  • Using hCard and vCard for Improving Usability in Moodle
    B Dragulescu, I Ermalai, M Bucos, M Mocofan
    6th IEEE International Symposium on Applied Computational Intelligence and … , 2011
    2011
    Citations: 7
  • Is It eLearning a Viable Solution in Romania?
    R Vasiu, N Robu, D Andone, M Bucos
    5th IEEE International Conference on Advanced Learning Technologies, ICALT … , 2005
    2005
    Citations: 7
  • Integration of eLearning in Romanian Technical Universities
    R Vasiu, N Robu, D Andone, M Bucos, M Onita
    EdMedia+ Innovate Learning, 121-126 , 2006
    2006
    Citations: 6
  • The Development of the Politehnica University of Timisoara Distance Learning Web Portal
    R Vasiu, M Bucos, D Andone
    IT, Knowledge, Education, Cooperation and Collaboration , 2004
    2004
    Citations: 6
  • Streaming Technologies in Education and Entertainment Environment
    M Onita, M Bucos, I Ermalai, S Petan, CI Toma
    3rd International Conference Elearning and Software for Education (ELSE … , 2007
    2007
    Citations: 4
  • An Architecture of a Web Application for Deploying Machine Learning Models in Healthcare Domain
    MEO Ursan, CD Caleanu, M Bucos
    2024 International Symposium on Electronics and Telecommunications (ISETC) , 2024
    2024
    Citations: 3