Continuous monitoring of Hearth Rate (HR) based on photoplethysmography (PPG) sensors is an essential capability of nearly all wrist-worn devices. However, arm movements lead to the creation of Motion Artifacts (MA), affecting the accuracy of HR tracking using PPG sensors. This problem is commonly tackled by exploiting the recorded accelerometer data to correlate them with the PPG signal and eventually clean it. Thus, automatic fusion techniques based on Deep Learning (DL) algorithms have been proposed, but they are considered too large and complex to be deployed on wearable devices. The current work presents a novel and lightweight DL architecture, PULSE, improving sensor fusion by applying a multi-head cross-attention layer to the extracted temporal features. Moreover, we propose a relation-based knowledge distillation mechanism to pass PULSE's knowledge to a student network that uses modality-wise convolutions to replace the attention module and mimic the teacher's performance with 5× fewer parameters. The teacher and student are evaluated on two datasets: a) PPG-DaLiA the most extensive available dataset, with PULSE achieving close performance to the best state-of-the-art model, and b) WESAD with PULSE reducing the mean absolute error by 22.6%. The student model is further compressed using post-training quantization and deployed on two commercial-off-the-shelf microcontrollers, demonstrating its suitability for real-time execution, having a close-to-state-of-the-art MAE of 4.81 BPM (+0.40 BPM) on the PPG-DaLiA, but a 10.9× lower memory footprint of 37.9 kB, and consuming 45.9× lower energy (0.577 mJ).

Human-like social robots (or humanoids) such as Softbank's NAO6, have been proven valuable assistants, able to advance State-of-the-Art of Technology in Education and Learning (TEL) as they are quite impressive “clones” of human behavior, and due to their relatable form, are often perceived as superior social companions. The rise of accessible Large Language Models and cloud computing, could transform robots like NAO6- a rather obsolete robot with quite low computing capacity (Pentium CPU, 2–4 GB RAM)- into a capable social agent, able to adopt A.I. behavior. In the current paper, we present a solution to enrich Softbank NAO6with A.I. capacity, in order to act as an LLM vessel. Specifically, we managed to connect an augmented AI chatbot to NAO6by deploying corresponding Python APIs. In our showcase, a NAO6acts as the ancient Greek Philosopher Plato that “guides the one who seeks wisdom” based on his theory. Our solution has been evaluated in real crowded settings as a proof-of-concept. Next steps involve to evaluate our solution in school classrooms.

The widespread use of social networks has brought to the fore a very important issue, the reliability of the information circulating within them. This paper presents the developed technologies referring to the visualization of data coming from social media involving the parameter of trustworthiness, and demonstrates the solution of H2020 EUNOMIA project. In particular, EUNOMIA's Digital Observatory is comprised of two tools drawing data from a REST API structure that returns the data in JSON format. A tool provides visualizations about the post's sentiment accompanied by their votes of trustworthiness and a second tool that depicts the most shared posts illustrating their trustworthiness according to their votes in an interactive way that permits user to define the level of trustworthiness.

In this paper, we present a series of tasks that can be combined in a scavenger hunt game, in order to provide a practical training on networking and information security. In combination with a theoretical approach in several security principles, this hands-on experience can be used in a course on network and information security.

Privacy and confidentiality in communication with a public entity, especially when this communication is about issues related to security (i.e. reporting criminal activity), is paramount. The guarantees that the reporting system can provide to end users directly contribute to the overall success of the system while of utmost importance, that can greatly influence whether the system is used or not is too maintain a sense of security that will increarse the user's trust. In this paper, we present an architecture for ensuring privacy and confidentiality in incident reporting taking primarily, under consideration the large number of mobile devices that can be used in creating these reports. The proposed solution consists of two servers and uses identity cloaking and message encryption of the data exchanged.