In this paper, we propose a semantic communication framework facilitated by multi-access edge computing (MEC)assisted satellite-air-ground integrated networks (SAGIN), which comprises of LEO satellites, unmanned aerial vehicles (UAVs), and macro-cell base stations (MBSs). Considering the limited wireless resources and diversified quality of service (QoS) requirements of semantic tasks, an optimization problem with the goal of minimizing system cost in terms of the task latency and energy consumption is formulated. In order to address the mixed-integer nonlinear programming (MINLP) problem, we propose an alternating optimization algorithm that tackles UAV deployment sub-problem with the successive convex approximation (SCA) method, task offloading, semantic compression, power allocation and computation resource allocation optimization with deep reinforcement learning (DRL)-based multi-agent proximal policy optimization (MAPPO) method. Simulation results demonstrate that our proposed algorithm outperformes other reinforcement learning algorithms, i.e., about 5.12%, 23.72% and 35.64% over PPO, DDPG, and A2C, respectively.

In recent years, the integration of wearable technology with emotional intelligence coaching, powered by deep reinforcement learning and artificial intelligence, has emerged as a pioneering approach to enhance mental health support for graduate students. This research addresses the significant issues of stress and burnout prevalent in the graduate student community. The study utilizes wearable technology, like the Empatica Embrace Plus, for continuous, real-time monitoring, combined with customized emotional intelligence coaching. This strategy aims to transform existing mental health support methods within academic settings, especially in engineering education, offering a dynamic and student-centered solution. This work explores the potential of artificial intelligence, especially deep reinforcement learning techniques, to improve the efficacy and impact of wearable technology in mental health support for graduate students. Firstly, the study discusses the integration of wearable technology in monitoring various physiological signals, such as electrodermal activity and heart rate variability. Next, it presents applications of emotional intelligence coaching, informed by the insights derived from wearable data and Emotional Quotient Inventory 2.0 assessments. This approach facilitates personalized and effective interventions for enhancing students' emotional regulation skills and coping mechanisms for academic stressors. Furthermore, by highlighting successful case studies and initial findings of the research, it demonstrates correlations between physiological data from wearables and emotional assessments. These findings also reveal patterns of stress and well-being linked to demographic factors among the participants. Artificial intelligence, particularly deep reinforcement learning, has shown significant promise in various fields, including mental health support and wearable technology. In recent years, researchers have begun exploring its potential in education, specifically for mental health support in engineering education. This study presents a comprehensive review of recent advancements in AI and reinforcement learning techniques applied to wearable technology for mental health support. The research explores how these techniques can analyze emotional states and stress patterns and optimize interventions for student mental health support. The study also discusses the future directions and challenges in incorporating AI-enhanced wearable technology with emotional intelligence coaching in engineering education. This research contributes to the growing body of knowledge on the potential of artificial intelligence, emotional intelligence, and wearable technology in mental health support for graduate students, particularly in engineering. The findings suggest that this integrative approach can provide more dynamic, personalized, and effective mental health support, enhancing the overall well-being and academic performance of engineering students.

This study proposes an innovative approach to improve mental health support for students in engineering using machine learning (ML) and eye-tracking technology. Leveraging cutting edge technology, this approach aims to fill a gap in the literature by providing a tool to tackle the growing mental health crisis among engineering students, furthermore, this approach provides a novel method to integrate technology-based mental health support into engineering curriculum.

This Work-In-Progress study proposes a novel approach to explore the learning behaviors of students with learning disabilities in online learning environments by investigating eye-tracking metrics and effectiveness of visual learning aids. It builds on previous research that suggests that students with learning disabilities often face difficulties in online learning environments due to the lack of visual cues and their limited ability to interact with the learning material. The use of machine learning to analyze eye-tracking data and visual learning aids can provide insights into how students with learning disability interact with online learning materials, with the goal of improving the learning outcomes as well as informing the design of constructive teaching strategies and seeking to expand this research to the online learning context.