Machine learning
Researchers at the Nanjing Institute of Technology have successfully developed a hardness prediction model for high-entropy borides (HEBs) using the gradient boosting algorithm. This breakthrough has significant implications for fields such as aerospace and energy chemistry. The model achieved a high R2 of 0.876 on the test set, with
Machine learning
Scientists at the National University of Singapore have made groundbreaking advancements in controlling fluid mechanics systems, particularly in the area of reinforcement learning. By leveraging the intrinsic symmetry of a flow system, researchers have developed a novel approach to training machine learning algorithms for fluid mechanics applications. This research, supported
Machine learning
Vietnamese scientists have successfully developed a remote sensing and artificial intelligence (AI)-based system to monitor water quality in Hao! Long Bay, a UNESCO World Natural Heritage site, and the adjacent Ca a La Y=c estuary. Led by VA(c) Anh Tuan from the Vietnam National Space Centre, the
Machine learning
Experts from the Space and Exploration Technology Group at the University of Glasgow are supporting Craft Prospect Ltd on a new contract from the European Space Agency to prototype and demonstrate machine learning algorithms for motion planning in orbital space missions. The project, 'Robust real-time constrained optimal control using
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 has found that maize-soybean intercropping is a sustainable farming practice that optimizes resource use efficiency and improves yield potential. A new study proposes a Fuzzy-Optimized Hybrid Ensemble Model (FOHEM) to improve yield prediction in these systems. The model integrates stacked ensemble machine learning algorithms with a fuzzy inference system
Artificial intelligence
Researchers from Shahid Beheshti University, Tehran, Iran, have utilized machine learning algorithms to create more accurate models for predicting the habitat suitability of Salvia leriifolia, an endangered herb found in Khorasan Razavi, Iran. The study aimed to identify key environmental and anthropogenic variables that influence the herb's habitat,
Artificial intelligence
Recent research has shed light on the complex factors that influence academic performance among primary school students in Somaliland. Investigators analyzed data from 20,638 students who took the 2022-2023 national primary examination, using a combination of machine learning algorithms and traditional regression methods. The study found that proficiency in
Machine learning
A recent research study led by Polina Lemenkova from the Alma Mater Studiorum-University of Bologna has shed new light on the use of machine learning algorithms for processing remote sensing data, particularly in land cover mapping. By utilizing a six-year dataset from 2018 to 2024, the research team demonstrated the
Artificial intelligence
New research out of Cairo University proposes a data-driven multiphase virtual flow meter (DD-MVFM) that estimates oil, gas, and water flow rates and provides real-time monitoring, with predictive capabilities and high accuracy. This innovation has the potential to significantly reduce operating costs, lower CO2 emissions, and simplify the infrastructure for
