Machine learning
Researchers from the Dalian University of Technology have shed new light on the synergy between metaheuristic algorithms and machine learning, revealing their high effectiveness in delivering high-quality solutions across diverse fields. This breakthrough has sparked interest in the potential applications of their integration, particularly in real-world applications such as autonomous
Machine learning
During the COVID-19 lockdown in the United Kingdom, parents of babies under 12 months turned to online groups for support, entertainment, and connection. A qualitative study conducted by researchers at the University of Stirling found that while online groups were a lifeline for some parents, they also presented challenges, such
Machine learning
Researchers from the National University of Defense Technology have made significant progress in overcoming the challenges of occlusion in UAV-based object detection. By leveraging the versatility of unmanned aerial vehicles (UAVs), they have developed an active object detection (AOD) method that enables autonomous path planning for target identification. To facilitate
Machine learning
Research published in the IEEE Robotics and Automation Letters has highlighted the promising potential of vision-based soft sensors in robotics and automation. The study, led by Nhan Huu Nguyen and his team from the Japan Advanced Institute of Science and Technology, reveals that these sensors can achieve multiple perceptual capabilities
Machine learning
A team of researchers from North Dakota State University has made significant strides in developing a novel artificial intelligence (AI) model for enhancing diabetes management with privacy-preserving edge AI. According to the study, the increasing prevalence of diabetes necessitates innovative glucose prediction methods that prioritize patient privacy. The researchers introduced
Machine learning
Researchers from Sejong University have conducted an in-depth analysis of the intersection of distributed machine learning and the metaverse, highlighting several potential benefits and significant privacy concerns. The study, published in the May 2025 issue of ICT Express, emphasizes the need for privacy-preserving measures in the development of metaverse applications.
Machine learning
Research conducted at the Royal Melbourne Institute of Technology - RMIT University has revealed a novel framework that leverages the Zero Trust model to identify and counter external threats in Federated Learning (FL) networks. The study proposes a framework strengthened by the Zero Trust model to identify external free riders
Machine learning
Research in India has led to the development of an optimized image compression model for medical imaging. The model, which utilizes Improved Huffman encoding and a new algorithm named Snake Updated BES Optimization (SU-BESO), has been shown to be effective in reducing the excess data in images and allowing for
Machine learning
Researchers from Beijing Information Science and Technology University have developed a novel federated learning framework, dubbed FedCGP, to address the challenges of data heterogeneity in medical image segmentation. This framework integrates personalization and clustering to preserve patient data privacy while achieving state-of-the-art performance in segmentation tasks. By dynamically adjusting the
Machine learning
Researchers at Zhejiang Normal University in Jinhua, People's Republic of China, have developed a system for intelligent diagnosis based on dynamic ultrasound that utilizes machine learning and image processing technologies. This system is designed to improve the speed and accuracy of ultrasound video diagnostics, providing reliable diagnostic assistance
Machine learning
Tsutaoka, Takuya, a patent inventor from Kanagawa, Japan, has filed a patent for an image processing device, method, and program that can accurately select normal images for machine learning without human intervention. According to the patent, the invention relates to an image processing device, an image processing method, and a
Machine learning
Researchers at MIT have developed a machine learning-based adaptive control algorithm for autonomous drones to minimize deviation from their intended trajectory in the face of unpredictable forces like gusty winds. The new technique does not require prior knowledge of the structure of disturbances and can learn all it needs to
