Using extensive databases and known algorithms to predict short-term energy consumption comprises most computational solutions based on artificial intelligence today. State-of-the-art approaches validate their prediction models in offline environments that disregard automation, quality monitoring, and retraining challenges present in online scenarios. The existing demand response initiatives lack personalization, thus not engaging consumers. Obtaining specific and valuable recommendations is difficult for most digital platforms due to their solution pattern: extensive database, specialized algorithms, and using profiles with similar aspects. The challenges and present personalization tactics have been researched by adopting a digital twin model. This study creates a different approach by adding structural topology to build a new category of recommendation platform using the digital twin model with real-time data collected by IoT sensors to improve machine learning methods. A residential study case with 31 IoT smart meter and smart plug devices with 19-month data (measurements performed each second) validated Digital Twin MLOps architecture for personalized demand response suggestions based on online short-term energy consumption prediction.

Project-based learning (PBL) is an active learning methodology focused on developing both soft and hard skills by solving real-world problems. In PBL, teachers act as facilitators while students take charge of their own learning. While the practice of this methodology in computing education has been growing in recent years, it still poses some challenges that need to be addressed. Integrating Scrum and Agile methodologies into PBL can be a valuable addition when teaching computing subjects to students. Therefore, this paper presents a case study of a successful implementation of PBL with Scrum, applying Agile values and principles to teach Artificial Intelligence to undergraduate students. This study contributes to the limited research on Scrum in education, as well as helps bridge the research gap in AI teaching and learning. The case study involved 30 students from an undergraduate computing program, divided into five groups, who successfully developed five different Machine Learning (ML) models to tackle the challenging real-life problem of breast cancer prediction for the Cancer Institute of the State of São Paulo. The findings of the study indicate that the students effectively utilized Scrum and Agile methodologies throughout the process and expressed satisfaction with the approach. Additionally, they developed problem-solving abilities, critical thinking and communication skills, teamwork capabilities, and gained experience in working with real-life situations and problems. The study also demonstrates that the proposed technique aligns with the foundations of the PBL approach in computing education discussed in previous literature. It serves as a valuable resource for future research on PBL implementation, by comparing similarities and differences with existing literature and discussing the strategies employed to address implementation challenges.

Practical knowledge is essential for engineering education. With the COVID-19 pandemic, new challenges have arisen for remote practical learning (e.g., collaborations/experimentations with real equipment when face-to-face offerings are not possible). In this context, LabEAD is a remote lab project that aims to provide practical knowledge learning opportunities for Brazilian engineering students. This article describes how engineering project management methods consisting of application domains, requirement identification, technical solution specification, implementation, and delivery phases, were applied to the development of an Internet of Things (IoT) remote lab architecture. The distributed computing environment allows integration between students’ smartphones and IoT devices deployed in campus labs and in student residences. The code is open-source for facilitated replication and reuse, and the remote lab was built in six months to enable six experiments for the digital electronics lab during the COVID-19 pandemic, covering all the experiments of the original face-to-face offering. More than 70% of the 32 students preferred remote labs over simulations, and only 2 were not approved in the digital electronics course offered remotely.Student perceptions collected by questionnaires showed that they could successfully specify, develop, and present their projects using the remote lab infrastructure in four weeks.

Virtual assistants, deployed on smartphone and smart speaker devices, enable hands-free financial transactions by voice commands. Even though these voice transactions are frictionless for end users, they are susceptible to typical attacks to authentication protocols (e.g., replay). Using traditional knowledge-based or possession-based authentication with additional invasive interactions raises users concerns regarding security and usefulness. State-of-the-art schemes for trusted devices with physical unclonable functions (PUF) have complex enrollment processes. We propose a scheme based on a challenge response protocol with a trusted Internet of Things (IoT) autonomous device for hands-free scenarios (i.e., with no additional user interaction), integrated with smart home behavior for continuous authentication. The protocol was validated with automatic formal security analysis. A proof of concept with websockets presented an average response time of 383 ms for mutual authentication using a 6-message protocol with a simple enrollment process. We performed hands-free activity recognition of a specific user, based on smart home testbed data from a 2-month period, obtaining an accuracy of 97% and a recall of 81%. Given the data minimization privacy principle, we could reduce the total number of smart home events time series from 7 to 5. When compared with existing invasive solutions, our non-invasive mechanism contributes to the efforts to enhance the usability of financial institutions’ virtual assistants, while maintaining security and privacy.

The globalization of the hardware supply chain reduces costs but increases security challenges with the potential insertion of hardware trojans by third parties. Traditional detection methods face scalability limitations by relying solely on simple examples (e.g., AES). Although open-source hardware promotes transparency, it does not guarantee security. In this research, Natural Language Processing (NLP) and Machine Learning (ML) techniques were applied to identify hardware trojans in complex designs (e.g., RISC-V). Using data from existing benchmarks (ISCAS85-89, TrustHub) and synthetic data generated with Large Language Models (LLM); a dataset of 3,808 instances was used in this research. The approach using TF-IDF and Decision Tree achieved 97.26% accuracy with this dataset, surpassing the state of the art. The use of LLMs with prompt optimization achieved a recall of 99%, minimizing false negatives. A novel framework integrating NLP, ML, and LLMs was developed to enhance the security of open-source hardware.

Contribution: This article describes one approach to foster technical skills (Digital Electronics) and professional skills (critical thinking, problem solving, communication, and collaboration) for Computer Engineering students in a fully remote way. Background: Engineering competencies development requires practical activities. Besides the technical skills, professional skills such as communication are necessary in the workplace. Intended Outcomes: When compared to face-to-face offering, the fully remote course must have no statistically relevant differences in terms of student performance. The course must also support the enhancement of professional skills (e.g., collaboration). Application Design: This study presents a comparison of the face-to-face (one year) and the fully remote (two years) Digital Electronics lab offerings. A course organization framework is proposed with two blocks: 1) controlled experiments and 2) projects in groups of two students. The study investigates how Project-Based Learning and Peer Assessment are perceived by students in the fully remote offering. A total of 110 students participated in the years 2019 (face-to-face), 2020, and 2021 (fully remote). Findings: Students in the second remote course offering (2021) presented a higher performance in their projects than face-to-face students (2019). Besides the student performance and technical skills development, it was observed that problem solving and collaboration, professional skills could be enhanced according to the students’ perceptions. However, the same did not occur for critical thinking or communication professional skills even with the Peer Assessment and project pitches. The main concern is the high workload for students.