Machine learning
Research conducted by the Indian Institute of Technology (IIT) Mandi has led to significant breakthroughs in industrial automation, with a focus on deep learning-based anomaly detection. The study highlights the importance of accurate anomaly detection in maintaining the reliability and robustness of automated systems. By evaluating traditional techniques and state-of-the-art
Machine learning
Research conducted at Burdur Mehmet Akif Ersoy University has resulted in a significant breakthrough in the field of artificial intelligence. The study focused on the traveling salesman problem, a notoriously difficult issue in combinatorial optimization, and proposed a new approach using the physarum-energy optimization algorithm (PEO). This population-based optimization algorithm
Machine learning
Researchers at the Technical University Darmstadt (TU Darmstadt) have conducted a study comparing model-space extrapolation methods for No-Core Shell Model calculations of ground-state energies and root-mean-square radii in lithium isotopes. The research aims to benchmark the latest machine-learning tools against conventional methods, providing insights into the reliability and accuracy of
Machine learning
A team of researchers at the Nanjing University of Aeronautics and Astronautics has developed a novel algorithm for inverse kinematics of offset wrist manipulators, which significantly improves solution accuracy and sets a robust foundation for future research in robotic control. The algorithm, known as TPEDE-IK, integrates an improved differential evolution
Machine learning
Researchers from Hohai University have proposed a robust Monte Carlo localization (RMCL) algorithm to address challenges in mobile robot localization. This approach combines an adaptive odometry motion model and adaptive relocation detection to enhance the accuracy of the particle filter model. The simulated experiments demonstrated a significant improvement in accuracy,
Machine learning
Investigations at Tsinghua University have led to the development of an innovative framework, Articubevseg, for road semantic understanding in bird's eye view (BEV) using panoramic vision systems of long combination vehicles (LCVs). The researchers aimed to address the challenges posed by the unique characteristics of LCVs, including articulation
Machine learning
Researchers at Zhejiang Science Technical University have proposed a novel Kinematic Batch Informed Trees algorithm (K-BIT*) for efficient mobile robot path planning. The algorithm addresses the limitations of existing methods, which often experience low efficiency, poor geometric smoothness, and local optima. By utilizing a variable density sampling strategy, K-BIT* can
Machine learning
A patent for a robot cleaning system that can automatically replace a mopping module has been released, providing a significant advancement in domestic cleaning robots. The system consists of a cleaning robot, a base station, and a control method. The base station is equipped with a storage module, an operating
Machine learning
Mansoura University researchers have utilized machine learning algorithms to analyze and predict annual carbon emissions from 1990 to 2023 in the top ten high-carbon emission source countries. The study employed various algorithms, including random forest and support vector machines, to forecast CO emissions based on selected features such as primary
Machine learning
Researchers at Karpagam College of Engineering have made a significant breakthrough in the detection of cyberbullying through the development of a novel deep learning method called Hybrid averaged and weighted averaged review vector Quantum long short-term memory neural based Multitask Learning with Black-winged kite Optimization (HQMLBO). This method uses a
Machine learning
Researchers at the Beijing Institute of Technology have made a significant breakthrough in controlling continuum robots, particularly cable-driven continuum robots (CDCRs), by developing a discrete elastic rod method based on discrete differential geometry. This new approach enables the accurate control of CDCRs, which is crucial for their application in various
Machine learning
Researchers at Sichuan Agricultural University have proposed a hybrid route planning algorithm that combines the Modified Golden Jackal Optimization (MGJO) algorithm and the Improved Dynamic Window Approach (IDWA) to overcome the challenges of traditional path planning algorithms in large-scale scenarios. The algorithm has been validated through real-world experiments and has
