Latest

Artificial neural networks

Breakthrough in Malicious Network Traffic Detection: A Novel Model Achieves High Accuracy

Researchers from Jiangsu University have developed a novel model, BiRNN-SA, for detecting malicious network traffic with unprecedented accuracy. This deep learning model integrates Bidirectional Recurrent Neural Networks (BiRNNs) with a Self-Attention (SA) mechanism to address the growing complexity of cyber threats. The model has been evaluated on four benchmark datasets,

Automotive industry

Data-Driven State of Health for Lithium-ion Batteries: Feature Engineering, Estimation Approaches, and Future Directions

Research published in Batteries & Supercaps by a team of scientists from Anhui University reveals a comprehensive exposition of data-driven methodologies for estimating the state of health of lithium-ion batteries. The study aims to ensure the safe and efficient operation of electric vehicles by identifying key factors influencing battery state

Differential equations

Novel Framework for Data-Driven Identification of Piecewise Dynamical Systems

Researchers at the Chongqing University of Posts and Telecommunications have developed a novel framework for data-driven identification of piecewise dynamical systems. This approach, known as Sparse Identification Neural Ordinary Differential Equations (SI-NODEs), leverages neural ordinary differential equations (NODEs) to extract localized information and identify points of imperfect fit in piecewise