首页|New Computational Intelligence Findings from Northeastern University Described ( Dual-scale Attributed Graph Transformer for Extracting Spatial-temporal Features With Applications In Quality Index Prediction)
New Computational Intelligence Findings from Northeastern University Described ( Dual-scale Attributed Graph Transformer for Extracting Spatial-temporal Features With Applications In Quality Index Prediction)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Fresh data on Machine Learning - Compu tational Intelligence are presented in a new report. According to news reporting originating in Shenyang, People’s Republic of China, by NewsRx journalists, res earch stated, “This paper presents a novel deep learning architecture, the Dual- scale Attribute Graph Transformer (DAGT), for extracting spatial-temporal featur es from attributed graph data. DAGT addresses the challenge of inconsistent samp ling periods in industrial data streams by utilizing two key modules: 1) Dual-Sc ale Spatial-temporal Graph Convolution Network (DSGCN): This module captures bot h spatial and temporal information within attributed graphs, enabling effective feature extraction for tasks like quality index prediction. 2) Spatial-temporal Graph Attention Block (SGAB): This module employs an attention mechanism to sele ctively focus on crucial areas of the graph sequence.”
ShenyangPeople’s Republic of ChinaAs iaComputational IntelligenceMachine LearningNortheastern University
NETL
NSTL
