Machine learning
Researchers at Deakin University have conducted a comprehensive study on the latest advancements in terrain classification methods for off-road perception, highlighting the importance of efficient terrain classification for the safe and efficient operation of autonomous vehicles. The study explores the use of sensor modalities and techniques that leverage both appearance
Machine learning
A new research study proposes an efficient path planning method for mobile robots in dynamic environments, using an improved twin delayed deep deterministic policy gradient (TD3) algorithm. This method, named PL-TD3, integrates prioritized experience replay and long short-term memory neural networks, enhancing both sample efficiency and the ability to handle
Machine learning
The inventors Mochizuki, Kenki, Ninomiya, Takeyuki, and Sotobayashi have developed a novel robot design that enables downsizing of the arm. Patent application 20250162136 was filed on November 19, 2024, and posted on May 22, 2025. The design features a first arm, a second arm, and a first motor housed in
Machine learning
Researchers at the University of Vaasa have presented a comprehensive study on civil service ethics in Germany, focusing on the institutionalization and management of ethics at the federal level. The study, published in the Central European Public Administration Review, provides a unique EU-wide dataset and challenges the assumption that traditional
Machine learning
Research conducted at Peking University People's Hospital in Beijing, People's Republic of China, has developed and validated a machine learning model using XGBoost to predict in-hospital mortality in cancer patients with acute pulmonary embolism (APE). The study analyzed a retrospective cohort of 448 cancer patients with
Machine learning
Researchers at the Third Xiangya Hospital of Central South University have made a significant breakthrough in predicting sepsis-associated liver injury (SALI) using machine learning techniques. The study, published in the Journal of Medical Internet Research, aimed to develop an explainable machine learning model that could predict the occurrence of liver
Machine learning
Researchers from the Dhirubhai Ambani Institute of Information and Communication Technology in Gujarat, India, have published a report on the potential of big data analytics in personalized cardiovascular healthcare. The study highlights the importance of leveraging large datasets to understand disease mechanisms, improve patient care, and reduce the burden of
Machine learning
Scientists at Peking University Third Hospital in Beijing, China have made a significant breakthrough in the field of personalized medicine by developing a machine learning model that can predict neurological recovery in spinal cord injury patients. The model, which uses a combination of clinical, radiomics, and laboratory data, has been
Johns Hopkins University
Researchers at Johns Hopkins University have discovered a method to accelerate the exploration process in Reinforcement Learning (RL), which significantly affects sample efficiency. This breakthrough could have profound implications for the development of more efficient and effective machine learning models. A study published in the Proceedings of the International Florida
Machine learning
A new report from researchers at the First Affiliated Hospital of Anhui Medical University sheds light on the complex interplay between cell death and non-alcoholic steatohepatitis (NASH) progression. The study, which was published in the journal Lipids in Health and Disease, reveals that dysregulated programmed cell death pathways are mechanistically
Machine learning
Research conducted by a team of scientists from Stevens Institute of Technology has made a significant breakthrough in the development of a new snow parameter retrieval (SPR) algorithm for the Global Change Observation Mission-Climate/Second Generation Global Imager (GCOM-C/SGLI) instrument. The algorithm, which combines accurate radiative transfer model (RTM)
Machine learning
Cancer genomics analysis is a complex task, and researchers have long struggled with identifying structural variations and copy number aberrations in long-read DNA sequencing data. To overcome this challenge, researchers at the European Bioinformatics Institute (EMBL-EBI) and Genomics England developed SAVANA, a machine learning algorithm that accurately identifies cancer-specific structural
