Online learning environments such as e-learning platforms are often used to encourage collaborative activities amongst students. In this context, group work is often used to improve the learning outcomes. Group formation is often performed randomly since university courses can be composed of a large number of students. While random formation saves time and resources, the student heterogeneity in terms of learning capabilities is not guaranteed. Although advanced e-learning platforms such as Moodle are widely used, they lack plugins that allow the automatic formation of heterogeneous groups of students. This work proposes a novel intelligent plugin for Moodle that allows the creation of heterogeneous groups by using Machine Learning. This intelligent application can be used in order to improve the students’ performance in collaborative activities. Our machine learning approach first uses clustering algorithms on Moodle data to identify homogeneous groups that are composed of students having similar behavior. Heterogeneous groups are then created by combining students selected from different homogeneous groups. To this end, a novel algorithm and the corresponding software, which allow the creation of heterogeneous groups, have been developed. We have implemented our approach by realizing a Moodle plugin where teachers can create heterogeneous groups.

A key strategic objective of the University courses is the promotion and development of new and innovative teaching activities, also through the e-learning environment, with the aim of providing students with direct involvement in the learning process. Collaborative activities represent important and effective teaching methodologies that allow the improvements of learning outcomes through active learning. Furthermore, they can allow the development of soft skills because they enable learners to work together and practice critical reflection and conflict negotiation. Recently, online learning environments are being used to design and deliver assignments based on student work groups. Indeed, the development of digital technologies allows the organization of these online activities in a flexible way for both students and teachers. The goal of this work is to develop successful collaborative activities for undergraduate students to ensure the improvement of knowledge and soft skills on a specific topic. One of the fundamental factors that influence the success of collaborative learning is the students’ group formation, which consists in the realization of heterogeneous groups in terms of cognitive resources, characteristics, and behaviors, composed by four or five students. However, the correct implementation of groups requires careful profiling of each student’s behavior which can be difficult for the teacher to detect. In this work an intelligent software, developed using Artificial Intelligence algorithms, was used to assist the teacher in the realization of heterogeneous groups of students. It is composed of a Machine Learning model, consisting in clustering techniques applied to Moodle learning analytics performed to return clusters that identifies different students’ profiles, and a specific algorithm that automatically organizes the groups, ensuring the heterogeneity including at least one student from each cluster. At the end of the execution the software returns the list of the heterogeneous groups to the teacher. The software was applied to assignments that required working group within a specific online course for university students, using a Moodle e-learning platform. The quantitative analysis demonstrated the effectiveness of the numerical method for group composition proposed in this work to ensure successful collaborative activities, confirmed also by the perceptions of the students on the course.

The Advanced Message Queuing Protocol (AMQP) is a widely used communication standard in IoT systems due to its robust and reliable message delivery capabilities. However, its increasing adoption has made it a target for various cyber threats, including Distributed Denial of Service (DDoS), Man-in-the-Middle (MitM), and brute force attacks. This study presents a comprehensive analysis of AMQP-specific vulnerabilities and introduces a statistical model for the detection and classification of malicious activities in IoT networks. Leveraging a custom-designed IoT testbed, realistic attack scenarios were simulated, and a dataset encompassing normal, malicious, and mixed traffic was generated. Unique attack signatures were identified and validated through repeated experiments, forming the foundation of a signature-based detection mechanism tailored for AMQP networks. The proposed model demonstrated high accuracy in detecting and classifying attack-specific traffic while maintaining a low false positive rate for benign traffic. Notable results include effective detection of RST packets in DDoS scenarios, precise classification of MitM attack patterns, and identification of brute force attempts on AMQP systems. This research highlights the efficacy of signature-based approaches in enhancing IoT security and offers a benchmark for future machine learning-driven detection systems. By addressing AMQP-specific challenges, the study contributes to the development of resilient and secure IoT ecosystems.

The use of hybrid educational environments, especially after COVID-19 pandemic, has intensified leading to new pedagogic challenges as the integration of biometric sensors into learning processes. Instructors must adapt their methods so that teaching and its quality are not negatively affected. The aim of this study is to enhance the understanding of students’ learning experiences by analysing biometric data during different learning activities. This paper focuses on the use of an Internet of Things (IoT) device, to collect Galvanic Skin Response (GSR) and Heart rate (HR) levels, in addition to biometric data. The quantitative analysis of the collected data shows a correlation between the data extracted that allow us to detect changes on students’ emotions. Subsequently the data analysis is used by instructors to provide formative feedback to enhance student learning, benefiting learners in terms of self-directed learning and motivation which can help them to improve their performance. The paper illustrates a case study of a hybrid learning university learning activity adopted in undergraduate programmes.

Collaborative learning has been widely acknowledged as a successful teaching method within the education field, with research indicating its positive impact on student outcomes. During the COVID-19 pandemic, when all courses transitioned online due to lockdown measures, many universities employed learning management systems to facilitate continued group work among students. However, forming effective student groups remained challenging, particularly given the large number of enrolled students. To address this issue, this study proposes the application of an artificial intelligence (machine learning) solution to automatically group students based on their behaviours and interactions within an e-learning environment. This paper explores the potential of machine learning (ML) algorithms in assisting educators to create heterogeneous groups, considering various student attributes, such as behaviour and performance, to optimise collaborative learning outcomes. Students’ performance within a module was compared using a wiki activity that employed group work over the course of two academic years. In the first experiment, groups were formed randomly, while in the second experiment, students with similar behaviours were firstly identified using a clustering algorithm and then organised by an additional algorithm into heterogeneous groups. The results demonstrate the efficacy of the machine learning solution compared to the random approach in assisting educators with group formation for a collaborative activity such as the wiki, confirmed by a comparative analysis showing an improvement in student performance and satisfaction. This research contributes to the advancement of online education through the creation of more effective group dynamics using machine learning algorithms, thereby improving overall student learning.