Machine learning
Researchers at COMSATS University Islamabad have utilized machine learning algorithms to model Quantitative Structure Property Relationship, a crucial task in forecasting the physiochemical characteristics of drugs. By applying machine learning, the team was able to predict the effectiveness and properties of potential drugs, supporting the search for new therapeutic compounds.
Machine learning
Researchers at the University Center have proposed a new solution for automating and scaling up the accuracy of glass classification using machine learning and deep learning algorithms. According to the study, traditional practices for glass classification are time-consuming and non-scalable, and the use of AI-based methods can revolutionize the process
Machine learning
Researchers at Xi'an Shiyou University have published a new study on pipeline leakage detection technology that integrates machine learning algorithms with Dempster-Shafer (DS) evidence theory. The study proposes a pipeline leakage detection technology that effectively combines multiple machine learning algorithms to enhance the accuracy and precision of leakage
Machine learning
Research conducted at the University of Tehran has investigated the efficiency of photocatalytic reactions in degrading pollutants, which is crucial for environmental remediation, including wastewater treatment. The study focused on designing optimal photocatalysts using machine learning techniques, incorporating both experimental and molecular structural features. The results demonstrated the effectiveness of
Machine learning
A team of researchers from Shenzhen University has successfully applied artificial intelligence to improve the accuracy of virtual screening in drug discovery. By leveraging machine learning techniques, the study, funded by the Shenzhen Science And Technology Innovation Program and the Guangdong Provincial Natural Science Foundation, aimed to enhance the performance
Machine learning
Research at the Michael Okpara University of Agriculture has led to a breakthrough in using sawdust ash as a sustainable material for road construction. According to the study, sawdust ash can be hazardous to the environment unless incinerated, which then turns it into a pozzolanic material. By combining sawdust ash
Machine learning
Researchers from the Chinese Academy of Sciences have developed a new method for constructing potential energy surfaces (PESs) using a combination of fundamental invariant-neural network (FI-NN) and force field approaches. This Delta-machine learning framework has been shown to be highly effective in precision and efficiency. The new method, which has
Machine learning
Researchers at the Swiss Federal Institute of Technology have made a groundbreaking discovery in the field of robotics and automation, introducing a method to simultaneously actuate and localize a tethered magnetic device using a single electromagnetic navigation system. This pioneering work has the potential to revolutionize minimally invasive surgical procedures,
Machine learning
Researchers from Stanford University have introduced DexForce, a novel approach to collecting dexterous manipulation demonstrations that leverages contact forces measured during kinesthetic demonstrations to compute force-informed actions for policy learning. This groundbreaking research aims to address the challenges of collecting high-quality demonstrations for contact-rich tasks, which are essential for advanced
Machine learning
Research from the University of Siena has led to the development of a lightweight, three-degrees-of-freedom exoskeleton powered by Twisted String Actuators (TSAs) for wrist rehabilitation. This innovative device, specifically designed to support flexion/extension, radial/ulnar deviation, and pronation/supination movements, has been shown to effectively achieve the desired wrist
Machine learning
Researchers from the University of Paris Saclay have developed a new method for estimating 6D camera pose distribution from a single RGB image. This innovative approach, called Corr2Distrib, utilizes local correspondences to recover all valid poses, even in the presence of visual ambiguities. The method has been shown to outperform
Machine learning
The National Institute for Public Health and the Environment in Bilthoven, Netherlands has conducted groundbreaking research on the application of artificial intelligence (AI) in healthcare-associated infection surveillance. The study found that AI-based methods have been applied less frequently in automated surveillance and more frequently for early prediction, particularly for sepsis.
