Machine learning
A groundbreaking study published in Scientific Reports has used machine learning algorithms to identify key predictors of fertility preferences among reproductive-aged women in Somalia. The research, conducted by investigators at the Federal University Birnin Kebbi, utilized data from the 2020 Somalia Demographic and Health Survey (SDHS) to analyze the relationship
Machine learning
North Carolina Agricultural and Technical State University College of Engineering assistant professor Olusola Odeyomi, Ph.D., has been awarded the National Science Foundation's (NSF) Faculty Early Career Development (CAREER) award, one of the agency's most prestigious honors for early-career faculty. Odeyomi's research focuses on
Machine learning
TE Connectivity Solutions GmbH has been granted a patent for its innovative system that allows mobile robots to autonomously take an elevator, enhancing their mobility and safety. This achievement comes after the inventors filed the patent on March 13, 2020, and it was published online on August 12, 2025. The
Machine learning
Researchers from Stanford University have developed a custom robotic end-effector, known as SLIM, designed to operate in cluttered and confined spaces. The system addresses the limitations of traditional robotic manipulators by introducing a bidirectional hand and an integrated 2-axis wrist. Funded by the NSF Graduate Fellowships and the Toyota Research
Machine learning
Research published in IEEE Access by the University of Piraeus has introduced LYRICEL, a framework that combines Knowledge Graph (KG) representation learning, Large Language Models (LLMs), and machine learning for reliable and explainable cross-cultural lyric analysis. The framework's core component, Sequential Language Model Integration (SLMI), enhances the interpretability
Machine learning
Researchers at the University of Portsmouth have proposed a novel framework, FedLLMGuard, to address the rising security challenges in 5G networks. This framework integrates Federated Learning (FL) with Large Language Models (LLMs) for real-time, privacy-preserving, and adaptive anomaly detection. FedLLMGuard has been evaluated against traditional Machine learning-based Intrusion Detection Systems
Machine learning
Research from the University of Texas MD Anderson Cancer Center has shed light on the potential of machine translation in patient-centered care. The study focuses on the ability to rapidly and inexpensively create accurate translations of English language patient-reported outcome measures (PROMs) to facilitate global uptake. The researchers explored the
Machine learning
Research conducted at the Poznan Supercomputing and Networking Center has resulted in significant advancements in machine learning optimization techniques. The study focused on model optimization methods, parallelization strategies for image recognition, and the impact of different performance techniques on large language model (LLM) tuning processes. Key Takeaways: * Researchers from the
Machine learning
Developed by researchers at Ibaraki University in Japan, a new transformable wheel mechanism called the dual legged-wheel (DLW) system has been designed to enable commercial vehicles to transport a wide range of weights over paved roads. The DLW system consists of two tri-legged structures coaxially connected through an elastic mechanism,
Machine learning
Research conducted by the Huazhong University of Science and Technology has led to the development of a new method for addressing the issue of LiDAR scan distortions caused by high-speed ground robots moving on unstructured terrains. The study, published in IEEE Robotics and Automation Letters, introduces post-undistortion uncertainty to improve
Machine learning
Researchers from Nanjing University in China have developed an artificial intelligence (AI) model that can diagnose acute coronary syndrome (ACS) and predict future risk within defined timeframes. The study, published in eClinicalMedicine, used a multicentre cohort study in China between January 2012 and December 2021 to develop and validate the
Machine learning
Researchers at Hengshui University have made significant findings in the field of artificial intelligence, proposing a deep learning-based algorithm to improve creative efficiency and precision in image processing for visual communication design. The algorithm, designed to optimize image processing workflows, has demonstrated excellent scalability, robust support for personalized design, and
