Nadom K. Mutlib^1,*, Muna N. Ismael¹, Shahrizan Baharom²

Structural Durability & Health Monitoring, Vol.15, No.3, pp. 227-246, 2021, DOI:10.32604/sdhm.2021.010725 - 07 September 2021

Abstract Structural health monitoring employs different tools and techniques to provide a prediction for damages that occur in various structures. Damages such as debond and cracks in concrete-filled steel tube column (CFST) are serious defects that threaten the integrity of the structural members. Ultrasonic waves monitoring applied to the CFST column is necessary to detect damages and quantify their size. However, without appropriate signal processing tools, the results of the monitoring process could not be crucial. In this research, a monitoring process based on a Multiphysics numerical simulation study was carried out. Two signal processing tools:… More >

Ruikun Li^1,*, Yun Li², Wen He^1,3, Lirong Chen¹, Jianchao Luo¹

CMES-Computer Modeling in Engineering & Sciences, Vol.128, No.1, pp. 381-398, 2021, DOI:10.32604/cmes.2021.016264 - 28 June 2021

Abstract Anomaly detection is an important method for intrusion detection. In recent years, unsupervised methods have been widely researched because they do not require labeling. For example, a nonlinear autoencoder can use reconstruction errors to attain the discrimination threshold. This method is not effective when the model complexity is high or the data contains noise. The method for detecting the density of compressed features in a hidden layer can be used to reduce the influence of noise on the selection of the threshold because the density of abnormal data in hidden layers is smaller than normal… More >