Machine learning
A team of researchers at Federal University Lavras has developed a novel lightweight Network Intrusion Detection System (NIDS) specifically designed for Vehicular Ad Hoc Networks (VANETs). The system, named LightBioptimum, leverages a bio-inspired optimization technique, Ant Colony Optimization, and a Tree-based Convolutional Neural Network (Tree-CNN) to efficiently select features and
Machine learning
Investigations into the application of machine learning in gas sensing have led to breakthroughs in the detection of hydrogen gas at room temperature. Researchers from South Korea have developed a method that utilizes UV light to reduce the sensing temperature down to room temperature, eliminating the need for micro-heaters and
Machine learning
A new research study conducted by researchers at the European Organization for Nuclear Research (CERN) has developed a machine learning-based anomaly detection system for CMSWEB services, a critical component of CMS infrastructure supporting over two dozen web services. The system employs deep learning techniques to enhance service performance and reliability
Machine learning
Researchers from the University of Tokyo have developed a novel method for tracking mooring lines of Floating Offshore Wind Turbines (FOWTs) using an Autonomous Underwater Vehicle (AUV) equipped with a tilt-controlled Multibeam Imaging Sonar (MBS). This approach enables the AUV to estimate the 3D positions of mooring lines and safely
Machine learning
Researchers at Chitkara University in Himachal Pradesh, India, have developed an AI-powered system to predict rainfall using the MapReduce framework and convolutional long short-term memory (ConvLSTM) method. The innovative system, which combines adaptive salp-stochastic-gradient-descent-based ConvLSTM (adaptive S-SGD-based ConvLSTM), has demonstrated high prediction accuracy, achieving minimal values for Mean Square Error
Machine learning
Research published by the University of Valencia has led to significant advancements in sensor research, particularly in the area of industrial surface defect detection. The study, conducted by Azeddine Mjahad and Alfredo Rosado-Munoz, employed classical Machine Learning (ML) algorithms and deep learning architectures to evaluate the effectiveness of statistical parameters
Artificial intelligence
Researchers from Polytechnic University Milan have conducted a study on the use of robots for play-based learning and social connection. The study highlights the benefits of play-oriented robots for individuals with cognitive or physical impairments, and provides a comprehensive framework for designing play-oriented robots and activities. According to the researchers,
Machine learning
Fresh data on robotics and artificial intelligence are presented in a new report from Delft University of Technology. According to the research, locomotion over granular terrain poses significant challenges for autonomous robotic systems, particularly in coastal regions characterized by loose, shifting sands. To optimize the locomotion on these challenging terrains,
Machine learning
A new patent has been granted to Semes Co. Ltd. for a carriage robot and tower lift design specifically tailored for semiconductor manufacturing. This innovative design addresses the challenges of transporting multiple containers of varying sizes in a vertical direction, without compromising transport efficiency. The patented invention provides a solution
Artificial intelligence
Artificial intelligence has taken a significant leap forward with the development of a scalable machine learning solution for the ATLAS detector. Researchers from the University of Washington have created a tool called AthenaTriton that integrates the NVIDIA Triton Inference Server with the ATLAS software framework, Athena. This innovative solution enables
Actors
Researchers have made a breakthrough in reinforcement learning by introducing a new dynamic approach, dubbed Dynamic Reinforcement Learning (DRL), which aims to improve the flexible balancing between exploration and exploitation in complex systems. The study, published in the journal Neural Networks, highlights the limitations of traditional stochastic selection methods in
Atoms
Researchers at Tsinghua University have made a significant breakthrough in the field of artificial intelligence, particularly in quantum information processing. The study, published in the npj Quantum Information journal, explores the application of SU(d)-symmetric random unitaries in diverse contexts, including information scrambling, covariant quantum error correcting random codes,
