Volume 20 – Issue 1 – EN

Enhancing STEM skills with the design of mobile robots: an experience with technical secondary school students

Authors:

De Omena, Rômulo Afonso L. V. and Da Silva, John Vitor T. and Rodrigues, Manoel Messias de O. and Filho, Maurício Freitas dos Santos and Silva, Sarah Kauane L. and Costa, Heshelley Roberta M. L. and Moraes, Débora Ruthe N. and Albuquerque, Arthur da Rocha

Abstract:

An education model with pillars on science, technology, engineering, and mathematics (STEM) is increasingly necessary to prepare our students for future jobs. A didactic tool that can engage students in STEM is robotics. A study area of robotics, mobile robotics is a rich tool that generates enthusiasm in students and involves diverse disciplines. While commercial robotic platforms for education exist, their high cost and limited customizability often pose challenges, particularly within the Brazilian public education system. This paper presents an experience with ten technical secondary school students focused on developing two distinct low-cost mobile robots: a differential drive and an omnidirectional one, sponsored by a research foundation. The primary objectives were to investigate the impact of a maker-approach environment on the enhancement of STEM skills and to provide accessible robotic platforms for future educational projects. Students, divided into pairs, worked collaboratively on various aspects of robot development, including chassis design, power supply, motor drive, data acquisition, and simulation and coding, utilizing computational tools like Tinkercad, AutoCAD, Arduino IDE, and ROS 2. This project aimed to answer how such an initiative could foster specific STEM competencies and what challenges and perceptions arise from the students’ perspective. The experience demonstrated that students not only developed STEM skills but also contributed valuable robotic platforms to the academic community. The initiative underscores the importance of foundational support in equipping the Brazilian education system to prepare students with skills vital for future professions.

+ Info



Integration of Scenario-Based Learning in CyberTOMP with FLECO Studio: Enhancing Situational Awareness Training in Cybersecurity

Authors:

Domínguez-Dorado, Manuel and Rodríguez-Pérez, Francisco J. and Cortés-Polo, David and Galeano-Brajones, Jesús and Calle-Cancho, Jesús

Abstract:

Situational awareness is crucial in cybersecurity to identify, understand, and anticipate cyber threats, and to make effective decisions during cyber crises. This study evaluates the effectiveness of a hands-on approach based on interactive scenarios using FLECO Studio software, integrated into the holistic management model CyberTOMP, compared to a traditional lecture-based approach framed within the same model. An experiment was designed with 200 participants, divided into a treatment group (70%) and a control group (30%). Both groups received training aimed at increasing their level of situational awareness in cybersecurity, with assessments conducted before and after the training. The treatment group employed the interactive scenario-based approach modeled with FLECO Studio, while the control group received traditional lecture-based training. To mitigate potential biases, preventive measures were implemented during the design and analysis of the study. The statistically analyzed results illustrated a significant improvement (up to 54%) in the situational awareness level of the treatment group, along with a strongly positive perception of effectiveness among the participants. These findings suggest that the interactive scenario-based approach, using tools embedded within a comprehensive holistic framework, significantly enhances the acquisition of situational awareness capabilities in cybersecurity compared to a traditional lecture-based approach.

+ Info



Data-Driven Learning Analytics and Artificial Intelligence in Higher Education: A Systematic Review

Authors:

González-Pérez, Laura Icela and García-Peñalvo, Francisco José and Argüelles-Cruz, Amadeo José

Abstract:

Technological change drives a constant cycle of adaptation in learning systems, especially within Engineering Education and ICT fields. The integration of Artificial Intelligence (AI) introduces both challenges and opportunities for improving educational processes. This article presents a Systematic Literature Review (SLR) of 51 peer-reviewed articles from the Web of Science and Scopus databases, covering the period from January 2021 to February 2025. The review investigates data-driven approaches combined with AI across four educational domains: learning, teaching, assessment, and academic administration. Results show that assessment is the most frequently targeted area, particularly through predictive modeling. However, there is a critical need for AI architectures that support Task-specific cognitive analysis. The limited adoption of mixed-methods research raises concerns about bias and restricts deeper pedagogical understanding. Advancing digital transformation in higher education requires aligning AI integration, data governance, and learning analytics with pedagogical models grounded in social justice and equity. The study concludes by highlighting the potential of Generative AI to enhance the interpretability of analytics and foster intelligent, inclusive educational ecosystems. These findings provide valuable guidance for decision-makers seeking to implement digital learning products through evidence-based, data-driven strategies.

+ Info



What determines Student Employability? Educational Data Mining through Machine and Deep Learning Approach

Authors:

Tariq, Rasikh and Vargas, Diego Gutiérrez and Ali, Farhan and Gonzalez-Mendoza, Miguel and Torres-Castillo, Cristina Sofia

Abstract:

Employability is vital for graduates to succeed in competitive job markets and reflects higher education institutions' effectiveness. It is essential to investigate which specific traits contribute to a higher success rate of employability, as understanding these factors can help optimize targeted interventions and improve employment outcomes. The objective of this research is to identify and analyze the key traits that influence student employability using educational data mining techniques integrated with machine learning and deep learning models while providing an explainable framework to inform targeted interventions and enhance job market readiness among graduates. Addressing gaps in existing research, this study integrates a wide range of variables and employs advanced Artificial Intelligence (AI) techniques, specifically Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), to develop a predictive framework for understanding employability over time. Using data from mock job interviews, the study applies Shapley Additive exPlanations (SHAP) values to assess the impact of traits like Self-Confidence and Ability to Present Ideas. Hyperparameter tuning through Grid Search and k-fold cross-validation is employed to optimize model performance. The LSTM model, configured with three layers, achieved an accuracy of 91.46%, and demonstrated the highest performance among the evaluated models. Its robustness was further supported by a 90.48% accuracy obtained through 3-fold cross-validation. The current findings highlight the importance of soft skills, such as Self-Confidence, Ability to Present Ideas, and General Appearance, identified by SHAP analysis as critical predictors of employability, emphasizing the need for educational institutions to actively integrate soft skills development into their curricula to ensure students are both academically prepared and professionally equipped.

+ Info