Machine learning
Researchers at Hong Kong Polytechnic University have made a breakthrough in using artificial intelligence to improve the precision glass thermoforming process. By developing a surrogate model based on a dimensionless back-propagation neural network (BPNN), they have been able to accurately predict forming errors and compensate for them in mold design.
Machine learning
A new study by researchers from Tongji University proposes a robust physical indicator for identifying leaks in urban water pipelines, grounded in the physical background of leakage noise sources. The research aims to improve the accuracy of leakage detection methods, which currently rely heavily on data-driven features. The study conducted
Machine learning
Sony Group Corporation has patented an innovative elastic unit that aims to improve the performance of linear actuators in robot devices. According to the patent filed on October 10, 2019, and published on August 19, 2025, the elastic unit is designed to enhance the controllability and maintainability of linear actuators.
Machine learning
Researchers from the Universidad Nacional del Altiplano have successfully developed artificial neural network (ANN) models to predict pH and titratable acidity in yogurt fermentation using CIELAB color parameters. The study, funded by the Consejo Nacional De Ciencia, TecnologiA E InnovacioN Tecnologica, aimed to improve process control in industrial yogurt production
Machine learning
Researchers at Marwadi University have developed a method to optimize the placement and sizing of distributed generations (DGs) and shunt capacitors in power distribution networks. By utilizing renewable energy resources, such as photovoltaic cells and wind turbines, the study aims to ensure a specific level of reliability in power distribution
Machine learning
Research conducted at the Communication University of China has led to significant advancements in artificial intelligence, particularly in the field of image dehazing. Image dehazing is a crucial approach for enhancing image quality captured under foggy or hazy conditions. Despite existing methods achieving certain success, they often rely on deep
Machine learning
Researchers have made a significant breakthrough in predicting the likelihood of children with Autism Spectrum Disorder (ASD) developing echoic verbal behavior using machine learning strategies. By analyzing 143 case records of children assessed with the Verbal Behavior-Milestones Assessment and Placement Profile (VB-MAPP), a multilayer perceptron (MLP) model achieved 100% accuracy
Machine learning
Researchers from Minia University have developed an advanced engine misfire diagnosis system using artificial neural networks (ANNs). The innovative approach combines vibration and acoustic emission (AE) signals to improve detection accuracy. By integrating multiple sensors and employing Bayesian Optimization techniques, the ANN model achieved an impressive 94.11% accuracy in
Machine learning
Researchers at the University of Management and Technology in Lahore, Pakistan, have developed a comprehensive approach to detecting toxic content on social media, particularly in under-resourced languages like Urdu. The study aims to address the significant challenge of misused social media, which can lead to abuse and hate. The researchers
Machine learning
Samsung Electronics Co. Ltd. has recently filed a patent for a wafer type sensor and a wafer alignment method. This patent, filed on December 14, 2022, and published online on August 19, 2025, describes a novel approach to wafer alignment technology. The inventors, Jin Woo Choi, Youn Ho Kim, Byung
Machine learning
A team of researchers at the University of Colorado Boulder has developed a novel machine learning-based framework for the dynamic security assessment of power systems. The framework, which employs semi-supervised multi-task learning and conditional masked encoders, has been shown to produce accurate and reliable assessments of system stability. The research,
Machine learning
A team of researchers at Nazarbayev University has developed an innovative fracture network model using artificial intelligence and geostatistical methods. The study aims to enhance the understanding of subsurface fracture characterization by combining geostatistical methods such as sequential indicators and Gaussian simulations with machine learning algorithms. Funded by Nazarbayev University
