The latest advances in industry have been accomplished within the 4th Industrial Revolution, mostly noted as Industrie 4.0. This industrial revolution is boosted by the application of Internet of Things (IoT) technologies into the industrial contexts, also known as Industrial Internet of Things (IIoT), which is being supported by the implementation of Cyber-Physical Production Systems (CPPS). In this context, most of the existing work concentrates on developing IIoT models and CPPS architectures, laking the identification of validation requirements of these platforms. By rushing into releasing state-of-the-art IIoT applications, developers usually forget to implement methodologies to validate these applications. In this paper, we propose a list of requirements for IIoT platform validation, based on its architecture, as well as in requirements established by the industrial reality. A CPPS case study is presented, in order to illustrate some of these requisites and how validation of these type of system could be achieved.

This paper presents a Systematic Literature Review (SLR) of Artificial Intelligence (AI)-powered Learning Analytics Dashboards (LADs), focusing on their applications, underlying techniques, and research gaps. A PRISMA-guided search across four major databases identified 21 relevant studies published between 2013 and 2024. The review shows that most AI-powered LADs are used for predicting academic performance, supporting self-regulated learning, and providing teacher-facing insights. Machine learning approaches such as decision trees, ensemble methods (AdaBoost, CatBoost), and Bayesian models are the most frequently employed, with ensemble methods often yielding stronger predictive performance. However, the literature highlights recurring limitations, including small-scale evaluations, limited causal evidence linking predictions to interventions, and weak deployment in real classroom contexts. Ethical considerations, particularly data privacy, bias, and explainability, are also insufficiently addressed. The review concludes by outlining open challenges and proposing directions for future research on scalable, explainable, and ethically grounded AI-powered LADs.

Designing and developing distributed cyber-physical production systems (CPPS) is a time-consuming, complex, and error-prone process. These systems are typically heterogeneous, i.e., they consist of multiple components implemented with different languages and development tools. One of the main problems nowadays in CPPS implementation is enabling security mechanisms by design while reducing the complexity and increasing the system’s maintainability. Adopting the IEC 61499 standard is an excellent approach to tackle these challenges by enabling the design, deployment, and management of CPPS in a model-based engineering methodology. We propose a method for CPPS design based on the IEC 61499 standard. The method allows designers to embed a bio-inspired anomaly-based host intrusion detection system (A-HIDS) in Edge devices. This A-HIDS is based on the incremental Dendritic Cell Algorithm (iDCA) and can analyze OPC UA network data exchanged between the Edge devices and detect attacks that target the CPPS’ Edge layer. This study’s findings have practical implications on the industrial security community by making novel contributions to the intrusion detection problem in CPPS considering immune-inspired solutions, and cost-effective security by design system implementation. According to the experimental data, the proposed solution can dramatically reduce design and code complexity while improving application maintainability and successfully detecting network attacks without negatively impacting the performance of the CPPS Edge devices.

Artificial Intelligence (AI) technologies are reshaping educational environments, particularly through Intelligent Tutoring Systems (ITS) that enable personalized instruction and real-time adaptability. This Systematic Literature Review (SLR) explores the application of AI-powered ITS in engineering education, a field where learners often struggle with abstract and technically complex content. Guided by the PRISMA methodology, the review analyzes 46 peer-reviewed studies featuring components such as Natural Language Processing (NLP), adaptive learning pathways, real-time feedback, and learner progress tracking. Unlike prior reviews that emphasize general pedagogical frameworks, this work offers three key contributions: a focused synthesis of AI-based ITS solutions tailored to engineering education; a novel analysis of underexplored feature combinations, such as the integration of teacher-facing analytics with student-facing personalization; and the identification of research gaps in dual-user support for both learners and instructors. These findings provide actionable insights for researchers and developers aiming to design next-generation ITS platforms that are pedagogically robust, technically scalable, and aligned with the discipline-specific demands of engineering education.

Introduction: This study explores the shift toward predictive maintenance through real-time data analytics to minimize machine downtime and improve machinery insights in industrial environments. Predictive maintenance aims to enable proactive interventions by predicting failures, enhancing operational efficiency.Methods: The research was conducted in three stages. First, BA Glass equipment was sensorized using OPC Router and PowerStudio SCADA to facilitate real-time data extraction. A predictive maintenance algorithm was then developed in Python to analyze sensor data, predict failures, and trigger alarms. Finally, various forecasting models, including Linear and Polynomial Regression, Simple and Double Exponential Smoothing, ARIMA, and Prophet, were evaluated using a combination of blocked cross-validation and rolling window methodologies. The algorithm calculated performance metrics such as MSE, RMSE, and MAE for different parameter configurations and training sizes.Results: A comparative analysis between wired and wireless sensors concluded that wireless sensors, although more expensive, were more practical and interchangeable in the factory setting. The results from the evaluation of prediction models showed that the Double Exponential Smoothing (DES) model with an additive damped trend and linear models performed best for datasets with daily seasonality and gradual oscillations. For datasets with stable trends and higher frequency oscillations, ARIMA and Prophet models proved to be more accurate.Discussion: These findings suggest that the choice of sensors and prediction models can significantly impact the effectiveness of predictive maintenance systems. Wireless sensors offer long-term benefits in terms of flexibility and practicality, while the DES model and ARIMA/Prophet models are optimal depending on the dataset characteristics. This research highlights the value of real-time data analytics and predictive models in industrial environments for reducing downtime and improving decision-making.