Computer vision and deep learning–based data anomaly detection method for structural health monitoring

By Yuequan Bao, Zhiyi Tang, Yufeng Zhang. 2019

529 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Civil and Structural Engineering

View Paper: https://www.semanticscholar.org/paper/37c949ec31a7e8eef6a8bb68e2daf5f2e8cd902d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Civil and Structural Engineering

Citations in the corpus

Multi-head CNN-RNN for multi-time series anomaly detection: An industrial case study (2019, methodology): “Nevertheless, some approaches can be found such as the use of Support Vector Machines [50, 15], ensemble methods [51], or DL algorithms [52, 53].”
Rethinking Graph Neural Networks for Anomaly Detection (2022, background): “As a well-established problem, anomaly detection has received much attention due to its vast applicable tasks, e.g., cyber security (Ten et al., 2011), fraud detection (Ngai et al., 2011), health monitoring (Bao et al., 2019), device failure detection (Sipple, 2020), to name a few.”
Review of Bridge Structural Health Monitoring Aided by Big Data and Artificial Intelligence: From Condition Assessment to Damage Detection (2020, unknown): “Bao et al. (2019) trained stacked autoencoders with acceleration images as input to automatically detect anomalies concerning serious sensor faults.”
Machine learning paradigm for structural health monitoring (2020, methodology): “13,14 The advantage of the CV-and ML-based method is that it can detect the multipattern anomalies of SHM data efficiently with high accuracy.”
Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines (2021, methodology): “Bao et al. [16], imitating the recognition process of humans, transformed data as image ﬁles and fed them into stacked autoencoders (SAE) for anomaly classiﬁcation.”
Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring (2019, background): “Bao et al. [122] proposed the use of DCNNs as an anomaly detector to aid inspectors in ﬁltering out anomalous data from a bridge structural health monitoring (SHM) system recording acceleration data.”
Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete (2018, methodology): “Unlike the past studies [30, 26, 62], the metrics to evaluate the 270 performance of each edge detector was defined very clearly on a pixel level.”
Convolutional neural network‐based data anomaly detection method using multiple information for structural health monitoring (2018, methodology): “According to the composite graphical features, each T‐F image was labeled as one of the patterns shown in Table 1, which was slightly different from the time domain‐based labeling.(49) The coordinate system was invisible in these images because quantitative values were not required for the qualitati”
Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review (2020, methodology): “[30] prop sed a framework for anomaly detectiosn that is inspired by human vision and thinking.”