Machine learning
Researchers from Shandong University have made significant discoveries regarding the development of artificial intelligence (AI) technology, which is poised to bring about a transformative change in library knowledge services. As AI technology continues to advance, its potential to enhance the intelligent transformation of library knowledge services and support the innovation
Machine learning
Research at Southwest University has made significant advancements in the field of agricultural robots, with a focus on automatic fruit identification and harvesting. A team of researchers has designed a human-robot collaborative picking robot that utilizes somatosensory interactive servo control. The robot system consists of four main parts: picking execution
Machine learning
Researchers from Beijing University of Technology have developed a physics-informed and data-driven framework, dubbed PHOENIX, which enables proactive real-time detection and prediction of welding instability in robotic manufacturing scenarios. This significant advancement in robotics has far-reaching implications for the manufacturing industry, allowing for more efficient and autonomous production processes. The
Machine learning
Researchers from the University of Hassan 2 Casablanca have conducted a detailed analysis of land cover changes in the Fez province of Morocco, utilizing machine learning and deep learning techniques to generate high-resolution land cover maps. This study, spanning from 2014 to 2022, aimed to identify the most suitable algorithm
Machine learning
Researchers at the School of Advanced Engineering in India have conducted a study to explore the impact of dust accumulation on photovoltaic (PV) system power output using artificial neural networks (ANN) and machine learning (ML) based modeling approaches. The study utilized a 60 W PV module under controlled laboratory conditions
Machine learning
Research conducted by Universiti Teknologi PETRONAS has demonstrated the potential of machine learning algorithms in predicting gas sorption capacity in heterogeneous porous materials, with a focus on shale gas. The study utilized extreme gradient boosting (XGBoost) and artificial neural networks (ANN) optimized with artificial bee colony (ABC) and particle swarm
Machine learning
Researchers at the University of Bonn have presented a novel methodology to harmonize attributions in machine learning, improving transparency and trust in computer vision applications. This innovative approach addresses the challenge of different attribution methods producing conflicting outcomes, particularly when dealing with remote sensing imagery. The researchers demonstrate that their
Machine learning
A recent study conducted by researchers at Ruhr-University Bochum has made significant contributions to the field of power electronics by proposing a novel regression-based neural network approach for estimating capacitors' lifetime in modular multilevel converters (MMC). The researchers developed a method that can accurately predict capacitance degradation without requiring
Machine learning
Researchers from Sapienza University of Rome have introduced a novel approach for pricing health insurance coverage using neural networks. The study, published in the journal Risks, focuses on modeling the frequency and severity of correlated medical claims. Unlike traditional regression models, the proposed approach uses negative multinomial neural networks and
Machine learning
Investigations into fluid dynamics have led researchers to develop a machine learning framework for enhanced computational efficiency and accuracy. A team from the University of Laval, in collaboration with other institutions, has successfully simulated viscoplastic fluid flows in channels with asymmetric superhydrophobic walls. Their research utilized computational fluid dynamics simulations
Machine learning
Researchers from the Technical University of Darmstadt have found that generative AI models, despite their impressive results, are susceptible to degenerated and biased human behavior. These models, which rely on large datasets scraped from the internet, can perpetuate and even amplify existing biases. To address this issue, the researchers have
Machine learning
Research on robot-assisted feeding systems for individuals with motor impairments has shown significant technological progress, but widespread adoption remains limited due to challenges related to adaptability, safety, and cost. A recent study from Shanghai Polytechnic University investigated recent advancements in robot-assisted feeding, highlighting key technical and usability challenges, and outlining
