Data mining
Scientists at the Department of Agrometeorology in India have successfully integrated disease severity with real-time meteorological variables and advanced machine learning techniques to provide valuable predictive insights for assessing disease severity in wheat. The study emphasizes the potential of machine learning models, particularly artificial neural networks (ANN), in predicting wheat
Data mining
Researchers from Wuhan University have published a study on machine learning-based satellite temperature data estimation, leveraging big data sources to improve the accuracy of long-term air temperature data. The study aims to estimate daily average, maximum, and minimum temperatures at a resolution of 5 km for the Chinese region during
Data mining
Researchers from Recep Tayyip Erdogan University in Rize, Turkey, have made a significant breakthrough in the field of machine learning. The team developed four predictive models using Multivariate Adaptive Regression Splines, K-Nearest Neighbors, Support Vector Regression, and Artificial Neural Networks to forecast the concentrations of phosphorus, potassium, calcium, and magnesium
Machine learning
A new study presented at the 129th annual meeting of the American Academy of Ophthalmology has shown that a machine learning algorithm significantly outperformed human graders at diagnosing glaucoma, with an accuracy rate of 88-90% compared to 79-81% for human graders. The study suggests that AI-powered screening could be a
Machine learning
A recent study published in the World Journal of Gastrointestinal Surgery has demonstrated the effectiveness of machine learning algorithms in predicting the occurrence of parastomal hernia (PSH) in patients undergoing preventive ostomy after rectal cancer resection. Researchers from Tongji Hospital, Huazhong University of Science and Technology, conducted a retrospective analysis
Artificial intelligence
Research conducted by the State Key Laboratory of Satellite Ocean Environment Dynamics, in collaboration with the Second Institute of Oceanography, has demonstrated the effectiveness of machine learning models in predicting deep-sea near-seabed currents. The study, published in Remote Sensing, utilized data from the Western Pacific M2 block to train four
Machine learning
Researchers at the School of Computing, Lincoln Institute of Higher Education in Sydney, Australia, have made a groundbreaking discovery in the field of artificial intelligence (AI). Their study demonstrates how AI can fundamentally transform college curricula by providing data-driven personalization, enhancing student outcomes, and aligning educational programs with evolving workforce
Machine learning
Research from Taipei National University of the Arts has utilized machine learning algorithms to predict the dynamic yield stress (DYS) and plastic viscosity (PV) of recycled coarse aggregate concrete (RCAC) mixtures. The study leverages a database of 380 RCAC mixtures, incorporating 11 input features, and analyzed using six machine learning
Artificial intelligence
Researchers from Southwest Jiaotong University in China have made a significant advancement in artificial intelligence, proposing a multi-satellite fusion method for near-surface soil moisture retrieval using heterogeneous ensemble machine learning models. This innovative approach combines three base learners, Back Propagation Neural Network (BPNN), Random Forest (RF), and Support Vector Machine
Machine learning
Researchers at the University of Sassari, Italy, have assessed the effectiveness of machine learning algorithms in predicting road accidents in Switzerland, utilizing open-access data and environmental and socio-economic factors. The study employed three different algorithms - Logistic Regression Model (LRM), Random Forest with Ranger (RF), and Artificial Neural Network (ANN)
Artificial intelligence
Researchers at the University of Patras have explored the potential of quantum machine learning and deep learning, proposing a comprehensive understanding of the fundamentals of these algorithms is crucial for enhancing time efficiency and reducing algorithmic complexity. The study investigated the integration of classical machine learning with quantum information processing,
Artificial intelligence
Researchers at the State Key Laboratory have made significant strides in using machine learning to analyze sediment provenance, a challenging task in geology. The team leveraged the eXtreme Gradient Boosting (XGBoost) algorithm, improving the accuracy of predicting sediment sources by 10-20% compared to conventional methods. The study focused on detrital
