We present AR-TMT, an AR adaptation of the Trail Making Test designed to evaluate how different types of distractors affect user attention in the AR environment. Built on the Magic Leap 2, AR-TMT captures gaze behavior as users perform a cognitively demanding visual search task under two distraction conditions: bottom-up (visually salient) and top-down (semantically misleading). The system visualizes gaze patterns and performance, revealing distinct attentional responses to the two distraction types. This demo could give insights on cognitive security in XR by offering a empirical findings of visual attention vulnerabilities with regard to distraction types and informing the design of distraction-aware, cognitively resilient AR systems.

Despite the growing use of AR in safety-critical domains, the field lacks a systematic understanding of how different types of distraction affect user behavior in AR environments. To address this gap, we present AR-TMT, an AR adaptation of the Trail Making Test that spatially renders targets for sequential selection on the Magic Leap 2. We implemented distractions in three categories: top-down, bottom-up, and spatial distraction based on Wolfe’s Guided Search model, and captured performance, gaze, motor behavior, and subjective load measures to analyze user attention and behavior. A user study with 34 participants revealed that top-down distraction degraded performance through semantic interference, while bottom-up distraction disrupted initial attentional engagement. Spatial distraction destabilized gaze behavior, leading to more scattered and less structured visual scanning patterns. We also found that performance was correlated with attention control (R2 =.20–.35) under object-based distraction conditions, where distractors possessed task-relevant features. The study offers insights into distraction mechanisms and their impact on users, providing opportunities for generalization to ecologically relevant AR tasks while underscoring the need to address the unique demands of AR environments.

Split learning (SL) is a promising distributed learning framework that enables to utilize the huge data and parallel computing resources of mobile devices. SL is built upon a model-split architecture, wherein a server stores an upper model segment that is shared by different mobile clients storing its lower model segments. Without exchanging raw data, SL achieves high accuracy and fast convergence by only uploading smashed data from clients and downloading global gradients from the server. Nonetheless, the original implementation of SL sequentially serves multiple clients, incurring high latency with many clients. A parallel implementation of SL has great potential in reducing latency, yet existing parallel SL algorithms resort to compromising scalability and/or convergence speed. Motivated by this, the goal of this article is to develop a scalable parallel SL algorithm with fast convergence and low latency. As a first step, we identify that the fundamental bottleneck of existing parallel SL comes from the model-split and parallel computing architectures, under which the server-client model updates are often imbalanced, and the client models are prone to detach from the server’s model. To fix this problem, by carefully integrating local parallelism, federated learning, and mixup augmentation techniques, we propose a novel parallel SL framework, coined LocFedMix-SL. Simulation results corroborate that LocFedMix-SL achieves improved scalability, convergence speed, and latency, compared to sequential SL as well as the state-of-the-art parallel SL algorithms such as SplitFed and LocSplitFed.

With recent deployments of the fifth generation (5G) network and advances in unmanned aerial vehicles, diverse airborne missions that provide high resolution aerial imagery in real-time are possible. However, a reliable inference of 3D cellular coverage is required to provide seamless imagery. As a part of intercontinental 5G testbed activities within Korea-EU 5G Project (PriMO-5G), we construct 3D 5G coverage map manually, to present insights regarding 3D coverage and how to construct its map efficiently. We then devise algorithms for constructing 3D coverage map simultaneously with real-time airborne missions in a cost-effective manner.