Nonverbal communication is essential for effective oral presentations, shaping audience engagement and conveying confidence beyond spoken words. Multimodal Learning Analytics (MmLA) research has advanced the automatic detection of presenters’ behaviors—such as posture, gestures, and eye contact—but continues to explore how to provide actionable feedback that fosters reflection and skill development. Recent advances in Generative Artificial Intelligence (GenAI) offer new opportunities to automate the analysis of nonverbal cues and generate narrative evaluations that go beyond raw metrics. This study investigates the integration of a Learning Analytics Dashboard (LAD) with a Large Language Model (LLM) to deliver both numerical and narrative feedback across five dimensions of nonverbal communication: body posture, eye contact, hand gestures, facial expression, and use of space. Twenty-two undergraduate students participated in the study, receiving numerical feedback through a LAD and narrative feedback from either a human expert or an LLM. Findings revealed no significant differences in students’ perceptions of human- and LLM-generated feedback, while also highlighting the potential of LLM-based feedback to support reflection despite certain technical limitations. These results suggest that LLMs can meaningfully enhance learning analytics dashboards by delivering actionable, human-like feedback that supports the development of nonverbal communication skills.

Recent advancements in machine learning (ML) have paved the way for new research paths across various disciplines. Nevertheless, students in the global south often have limited exposure to these breakthroughs and may not actively pursue opportunities in these emerging fields. This paper presents a case study of a training workshop that aimed to involve students from diverse undergraduate programs to actively engage in research opportunities utilizing ML skills in other application domains. To do so, we present empirical quantitative findings based on the participation of 24 undergraduate students from 10 distinct programs in workshops designed to introduce them to ML concepts and applications, as well as the research process and methodologies. We hypothesized that this kind of workshop would lead to a higher intention to do research, along with positive improvements in their assessment of self-efficacy, focusing on perceived behavioral control (PBC), behavioral beliefs (BB), and subjective norms (SN). The workshop led to an improvement in students' PBC in self-efficacy beliefs over their perceived ability, especially in the development of research and ML skills. These findings provide valuable insights and set a clear course for future initiatives, with the aim of further encouraging students' involvement and confidence in computing research initiatives.

Modern communication technologies are expected to be available in the future Smart Grids to enable the control of equipments over the whole power grid. In this paper, we consider such networked control approach to address failures that may occur at any location of the grid, due to attacks or unit malfunction, and provide a wide-scale solution that prevent the failure impacts from spreading over a large area. Different from literature work that focuses on modifying power equations under the standard constraints of the power system, we estimate the impact of controlling different nodes on topological areas of the grid based on social metrics, which are derived from the graph capturing both the topological and electrical properties of the power grid. We propose a failure control algorithm for topological containment of failures in smart grid. Our algorithm also takes careful consideration of the impact the planned control has on the grid to avoid the possibly involuntary failure extension. We show that social metrics can efficiently trade off between the topological and electrical characteristics revealed by the power grid graph representation. We evaluate the performance against networked control strategies that only use power models to determine the actions to be performed at power nodes. Our results show that the proposed control scheme can effectively contain failures within their original location range.

Phasor Measurement Units (PMUs) provide high precision data at high sampling rates to support Smart Grid applications. Power Line Outage detection mechanisms can enhance the grid reliability by assisting power operators in taking proper control actions. Despite the potential provided by PMUs, there are very limited efforts on exploiting data available to more effectively detect outages. Conventional outage detection schemes are mostly designed based on simplified power models, and the limited work on detection with data either assume all the measurement samples are available or ignore the missing entries. Their performance suffers in the complex grid conditions in the presence of missing data. In this paper, we design a detection mechanism considering unreliable data, in the form of missing data samples. Detection is performed through the grouping of nodes according to their data availability and their learned detection capabilities. To enable the robust detection of power line outages, we propose learning outage characteristics for each individual node instead of specific single line outage scenarios. Our results show that the outages detected are highly consistent with the evaluated failures under different scenarios, with high accuracy and low false positive rates. Moreover, the detection application is resilient to unreliable data, and can properly differentiate data problems from physical power line failures.

Efficient power line monitoring is essential for reliable operation of the Smart Grid. A Power Line Monitoring Network (PLMN) based on wireless sensor nodes can provide the necessary infrastructure to deliver data from the extension of the power grid to one or several control centers. However, the restricted physical topology of the power lines constrains the data paths, and has a great impact on the reporting performance. We discuss the features of power-lines and their impact on the performance of monitoring and transmissions. We present a comprehensive design to guide efficient and flexible relay selection in PLMNs to ensure reliable and energy efficient transmissions while taking into account the restricted topology of power-lines. Specifically, our design applies probabilistic power control along with flexible transmission scheduling to combat the poor channel conditions around power line while maintaining the energy level of transmission nodes. We evaluate the impact of different channel conditions, non-uniform topologies for a power line corridor and the effect of reporting events. Our performance results demonstrate that our data forwarding scheme can well control the energy consumption and delay while ensuring reliability and extended lifetime.