Machine learning
A team of researchers at the University of Ulsan in South Korea has made a breakthrough in simulating high-temperature proton exchange membrane fuel cells (PEMFCs) using a novel deep learning approach. The study aimed to address the high computational cost and data generation challenges in PEMFC simulations by introducing a
Machine learning
Researchers at Galgotias University have unveiled a novel Quantum-Inspired Hybrid Reinforcement Learning and Multi-Objective Optimization Framework (QHRMOF) designed to optimize task scheduling, dynamic load balancing, and server consolidation while minimizing power consumption and enhancing system performance. The framework integrates quantum-inspired evolutionary algorithms, hybrid deep reinforcement learning, and multi-objective optimization techniques
Machine learning
Researchers at the University of Hong Kong have developed an explainable machine learning framework to understand the relationship between urban morphology and building energy consumption in Dongguan, China. The study integrates large-scale smart meter records with 3D building footprints to construct high-resolution datasets, demonstrating superior predictive performance over comparative methods.
Machine learning
A recent study employing machine learning techniques has analyzed hourly electricity consumption for 125 households participating in the People Demand Response (DR) program, a Peak Time Rebate (PTR) initiative in Korea, and found varying effects of DR interventions across different household clusters. The research also discovered learning effects over time
Machine learning
A study published in the Journal of Surgical Research has demonstrated the efficacy of a machine learning algorithm-based tumor-stroma ratio in stratifying the prognosis of intrahepatic cholangiocarcinoma (iCCA) patients after radical surgery. The research, conducted by a team of scientists from Sun Yat-Sen University, aimed to quantify tumor components and
Machine learning
Researchers from Capital Medical University have made a significant breakthrough in the diagnosis of asymptomatic tuberculosis (TB) by identifying plasma biomarkers that can accurately discriminate between asymptomatic TB, latent TB infection, and healthy controls. The study, published in the Journal of Proteome Research, employed the Olink Proximity Extension Assay to
Machine learning
Molecular property prediction is a crucial application of machine learning, but its reliability can be hampered by various error sources, including regions of the chemical space with large property differences and a lack of representation of test molecules in the training data. Researchers at Sanofi-Aventis Deutschland GmbH have analyzed the
Artificial intelligence
Research conducted by Amrita Vishwa Vidyapeetham has led to the development of a new hybrid generative adversarial network called ProWGAN, which simplifies image production for video games, virtual reality, and motion pictures. This model combines ProGAN and WGAN approaches to automate landscape synthesis, reducing manual work, lowering production time, and
Machine learning
A team of researchers from the Polytechnic University of Valencia has made significant breakthroughs in using machine learning to efficiently remove dyes from wastewater. The study utilized Cedarlea odorata L. as a bioadsorbent material to treat industrial-scale wastewater contaminated with methylene blue and safranin, which can have detrimental effects on
Machine learning
A recent study at Kongju National University has made significant breakthroughs in accurately recording the colors of cultural heritage objects using digital photography and machine learning algorithms. The research aimed to reproduce colors that closely match those of the object, enabling precise documentation and analysis for conservation, restoration, and research
Machine learning
Graph-Patchformer, a novel deep learning framework, has been proposed to revolutionize multivariate time series forecasting. This breakthrough methodology, developed by researchers at the Beijing University of Technology, leverages structural encodings to capture inter-series relationships and temporal variations within multivariate time series. By employing a patch interaction transformer with adaptive graph
Artificial intelligence
Medical school admissions committees rely on personal statements to evaluate applicants' values, motivations, and experiences. However, with the rise of artificial intelligence (AI), a new study suggests that AI-generated personal statements may become a concern for maintaining credibility in medical school admissions. Researchers from Nemours Children's Hospital
