This paper proposes a secure and distributed system for lung disease diagnosis, specifically COVID-19 and Pneumonia, using a hybrid federated learning-enabled ensemble model. It combines established CNN architectures with the SWIN Transformer to enhance diagnostic accuracy and ensure patient data privacy through federated learning.

This paper introduces FR-GESTURE, a novel RGBD dataset for gesture-based control of Unmanned Ground Vehicles (UGVs) by First Responders (FRs). It defines 12 specific gestures inspired by existing FR signals and tactical hand signals, collected to facilitate more intuitive human-robot interaction in disaster scenarios.

The paper presents a community vision for integrating Artificial Intelligence across the entire experimental lifecycle in particle physics to accelerate discovery. It outlines grand challenges and proposes a national-scale collaboration to enable transformative breakthroughs and secure U.S. leadership in AI-powered fundamental science.

This paper introduces a practical framework for benchmarking and optimizing AI models on ARM Cortex processors in embedded systems. It focuses on balancing energy efficiency, accuracy, and resource utilization, demonstrating how optimal processor and model selections depend on an application's inference cycle time.

This paper presents a vision for self-driving particle accelerators that operate autonomously with minimal human intervention. It proposes future facilities be designed through AI co-design, where AI jointly optimizes accelerator components and science applications from inception to maximize performance and enable autonomous operation.