Probabilistic reconstruction for spatiotemporal sensor data integrated with Gaussian process regression

• Published in: Probabilistic engineering mechanics Vol. 69; p. 103264
• Main Authors: Ma, Yafei, He, Yu, Wang, Lei, Zhang, Jianren
• Format: Journal Article
• Language: English
• Published: Barking Elsevier Ltd 01.07.2022; Elsevier Science Ltd
• Subjects: Artificial neural networks; Correlation coefficients; Data reconstruction; Gaussian process; Gaussian process regression; Kernel functions; Machine learning; Missing data; Network reliability; Neural networks; Nonlinear response; Normal distribution; Probability distribution; Probability theory; Reconstruction; Reliability analysis; Reliability engineering; Sensor failure; Sensors; Spatial data; Spatiotemporal correlation; Spatiotemporal data; Statistical analysis; Stochastic processes; Structural reliability; Vector spaces; Gaussian process regression; Sensor failure; Spatiotemporal correlation; Data reconstruction

The effective health management of sensor networks is very important for the reliability assessment of engineering structures. Sensor failure and data missing occur frequently due to the influences of signal noise and adverse environment. This paper proposes a probabilistic reconstruction framework...