Lightweight and Accurate DNN-Based Anomaly Detection at Edge

Deep neural networks (DNNs) have been showing significant success in various anomaly detection applications such as smart surveillance and industrial quality control. It is increasingly important to detect anomalies directly on edge devices, because of high responsiveness requirements and tight latency constraints. The accuracy of DNN-based...

Assessment of Flexural Behavior of Pultruded GFRP Laminates for Bridge Deck Applications

In this study, flexural behaviors of the pultruded composite laminate were evaluated through experiments and theoretical analysis. Three-point flexural tests were performed for pultruded specimens. The typical failure mode for the longitudinal flexural specimens was local crush on the top surface accompanied with local cracks on the bottom...

Numerical parametric study on ultimate load and ductility of concrete encased equal-leg angle steel composite columns

Steel-concrete composite high bridge pier has been applied increasingly in China and around the world. Most applied steel type in the composite piers are H-shaped steel and steel pipe, while seldom research or practice is associated with angle steel. This paper conducted parametric study on the composite column with equal-leg angle steel and...