A5007872132- Online Learning and Analytics
- Imbalanced Data Classification Techniques
- Natural Language Processing Techniques
- Caching and Content Delivery
- Software System Performance and Reliability
- Open Education and E-Learning
- Mobile Learning in Education
- Semantic Web and Ontologies
- Educational Technology and Assessment
- IPv6, Mobility, Handover, Networks, Security
- Sustainable Agricultural Systems Analysis
- Service-Oriented Architecture and Web Services
- Mobile and Web Applications
- Topic Modeling
- Advanced Image and Video Retrieval Techniques
- Data Visualization and Analytics
- Sentiment Analysis and Opinion Mining
- Geographic Information Systems Studies
- Misinformation and Its Impacts
- Web and Library Services
- Text and Document Classification Technologies
- Machine Learning and Data Classification
- Augmented Reality Applications
- Food Supply Chain Traceability
- Nuclear Structure and Function
Polytechnic University of Timişoara
2010-2024
Dilated cardiomyopathy (DCM) represents a group of disorders affecting the structure and function heart muscle, leading to high risk failure sudden cardiac death (SCD). DCM frequently involves an underlying genetic etiology. Genetic testing is valuable for stratification, treatment decisions, family screening. Romanian population data on etiology are lacking. We aimed investigate causes among adult patients at tertiary referral centers across country. Clinical investigations were performed...
Educational Data Mining (EDM) techniques offer unique opportunities to discover knowledge from data generated in educational environments. These can assist tutors and researchers predict future trends behavior of students. This study examines the possibility only using traditional, already available, course report data, over years by tutors, apply EDM techniques. Based on five algorithms two cross-validation methods we developed evaluated classification models our experiments identify one...
The educational ontology we presented in this paper is used to model web-based e-learning systems for higher education. Our main objective was create domain play an important role representing education concepts and assist specialized systems. We have stressed the need developing models that meet expectations of community with regards adaptation efficiency by employing ontologies Semantic Web techniques.
Predicting student failure is an important task that can empower educators to counteract the factors affect performance. In this paper, a part of bigger problem predicting addressed: students do not complete their assignment tasks. For solving problem, real data collected by our university’s educational platform was used. Because consisted one three possible classes (multi-class classification), appropriate algorithms and methods were selected. Several experiments carried out find best...
For indexing an image databases there are used many features. In this paper features like histograms for the color components, stochastic moments, few parameters of co-occurrences matrix and Gabor filters decomposition. Using all them we obtain good performance in field content-based retrieval. There some speed problems because search process. Here, I present algorithm retrieval, which use a supervised tree increasing. The area applications is very wide: multimedia documents, transaction...
Misinformation poses a significant challenge in the digital age, requiring robust methods to detect fake news. This study investigates effectiveness of using Back Translation (BT) augmentation, specifically transformer-based models, improve news detection Romanian. Using data set extracted from Factual.ro, research finds that BT-augmented models show better accuracy, precision, recall, F1 score, and AUC compared those original set. Additionally, mBART for BT augmentation with French as...
Extraction of information relays heavily on the user. The correct extraction is very important especially in an eLearning environment. We can ensure distribution data (contact information, calendar events, and locations) by encapsulating that formats rely automated agents for processing. In this paper, we propose a model republishing user contact from Moodle hCard vCard formats, also QR codes mobile tagging. This application be extended future to regarding events (vcalendar, hcalendard,...
Abstract The techniques and tools developed for geodetic determinations have made it possible, over the past half century, to carry out measurements using global navigation satellite systems. As accuracy precision of positioning solutions, such as Fast Static RTK, improve through technological advances, more applications will become available that can provide users with information time, autonomously verify integrity transmitted data, ensure sufficient their intended purposes. In our study...
The increased usage of information technologies in educational tasks resulted high volume data, exploited to build analytical systems that can provide practical insight the learning process. In this paper, we propose a method running social network analysis on multiple data sources (academic years, communication tools). To achieve this, collected describe interactions were converted into common format by employing prior developed semantic web ontology. Using mapping language relational set...
The present work considers the possibility of using Moodle course logs and student performance indicators within Database Systems to apply K-Means clustering algorithm. Clusters students are identified explained partition with similar study behaviours performance. Moreover, understanding five groups emerged in cluster analysis allowed us identify a that contains 86% at risk not completing activity. One important aspect differentiates our from other works is use data collected over long...
This paper describes the results of piloting an online - mobile phone environment -ViCaDiS Virtual Campus for Digital Students, as a co-operation between 6 universities from European Union to develop common learning enhanced with web 2.0 tools supporting international at academic level. ViCaDiS facilitates shift Institutional Learning Environments towards Personal Environments. students are young adults who have grown up digital technologies integrated everyday feature their lives. It...
Microformats are small standards used to make big steps towards the internet of future - Semantic Web. Three microformats (hCard, hCalendar and hAudio) have been implemented into educational portal by Distance Learning Center's students from "Politehnica" University Timisoara. This paper presents different methods test viability this experiment in a particular learning context (technical university, distance students, background so on).
The creation of agricultural clusters is one the methods by which farmers can increase their competitiveness and generate economic growth. Machine learning help to decide are best form in an area. aim paper examine possibility using clustering on platform. This platform under development, currently there no real data available for training purposes. Therefore, we constructed a set integrating multiple sources. was be as similar possible characteristics final proposed consists 4480 records 60...