Search

A medical cyber-physical system (MCPS) integrates medical sensor devices with cyber (information) components, which creates a sensitive approach and provides security. The MCPS plays a vital role in hospitals by detecting attacks and protecting patients' medical information. Many research projects have been carried out to detect attacks on the generation of medical information in MCPS. The issues with existing algorithms are their inefficiency and time-consuming maximization of error rates. To overcome the challenges, this paper proposes detecting the attack using the fuzzy C-Means algorithm with artificial bee colony optimization (FCM-ABC). The novelty of the work is flexibility in deciding whether data points belong to actual users or attackers using the fuzzy c means degree [0,1] measuring technique of cluster formation. ABC is used in self-organizing the clusters with ABC collective intelligence. It monitors health information using sensor networks. The MCPS model interconnects the sensor devices remotely and collects the information. SVM has an accuracy rate of 76.32%, FCM has an accuracy rate of 81.34%, LSTM has an accuracy rate of 86.22%, and our proposed work, FCM-ABC, has an accuracy rate of 93.34%. [ABSTRACT FROM AUTHOR]

• An approach for detection of damper malfunction is developed by implementing isolation forest algorithm on characterized cumulative displacement measurements. • Physics-informed correlation between the temperature variation and the displacement measurements are utilized for identifying measurement noise to ensure reliable datasets for malfunction detection. • Characterization with hourly cumulative displacement can significantly reduce the data complexity while capturing the intrinsic data characteristics that influence the bridge behavior. • The approach was verified with real monitoring data in a suspension bridge by detection of malfunction in the viscous damper. Long-span cable-supported bridges are flexible and prone to significant deformations under temperature, wind, and vehicle loads. Such large deformations induce frequent longitudinal movement at the end of the bridge girder, which can cause malfunction or failure in the components such as expansion joints, bearings, or longitudinal viscous dampers. This paper develops a condition assessment approach using the girder end displacement measurements, which primarily includes four steps, namely, data preprocessing, feature characterization, datasets preparation and splitting, and anomaly detection. The data preprocessing step considers the physics-based correlation between the temperature and displacement, which is used to pre-check noisy data issues in the displacement monitoring data. Subsequently, hourly cumulative displacement is calculated as the feature to feed into the machine learning model. The third step prepares the datasets and splits them into training and testing datasets. Then the isolation forest algorithm is implemented for anomaly detection with well-tuned parameters of the number of decision trees and the number of samples in each decision tree. Structural health monitoring data of a suspension bridge are collected to verify the proposed approach, and the detection targets are specified as viscous damper malfunction and a specific holiday period. The proposed approach demonstrates its ability to detect both events successfully, which can shed light on the predictive and preventive maintenance of the bridge. [ABSTRACT FROM AUTHOR]

In this paper, a new hybrid YUKI-ANN is implemented for Structural Health Monitoring (SHM) of laminated composite plates. A finite element model is constructed and used to identify damage at five randomly selected elements in a laminated composite plate. The process of damage identification is divided into two main steps, namely damage localization and quantification. During the localization step, damaged elements are identified using a damage indicator based on Modal Strain Energy change ratio (MSEcr). After excluding the healthy elements, the level of damage is predicted using ANN modified with four optimization algorithms: Arithmetic Optimizing Algorithm (AOA), Balancing Composite Motion Optimization (BCMO), Particle Swarm Optimization (PSO), and YUKI algorithm. The performance of these optimization algorithms is evaluated, and it is found that the YUKI algorithm (YA) outperforms AOA, BCMO, and PSO algorithms without exception. YA gives better predictions with lower errors when compared to PSO and BCMO algorithms with equivalent computational time. In some cases, AOA provides slightly better predictions than YA, but the computational time for these predictions is eight times more that of YA. If both performance and efficiency are considered, YA seems to be the best choice. Find the MATLAB code for YUKI-ANN at https://github.com/Brahim-Benaissa/YUKI_ANN. [ABSTRACT FROM AUTHOR]

This paper proposes an automatic defect localization and sizing procedure for Structural Health Monitoring based on guided waves imaging. The procedure is applied to an aluminum plate equipped with active piezoelectric sensors. The defect localization and sizing strategy is obtained through to the use of a convolutional neural network trained exclusively on numerical simulations of guided wave signals and post-processed by the delay and sum imaging algorithm. The paper shows the effectiveness of the proposed approach to invert both synthetic and experimental data. [ABSTRACT FROM AUTHOR]

• Developing an enhanced inverse beam element iEBT2 for deformation estimation. • iEBT2 allowing deformation reconstruction even with missing strain measures. • Using weighting constants to penalize contributions from "measure-less" stations. • All the results have demonstrated the effectiveness of iEBT2 element. The inverse finite element method (iFEM) is a mechanics-based algorithm for deformed-shape estimation of structures. In this paper, an enhanced inverse beam element named iEBT2 is developed based on classical beam theory. The element formulation is derived by minimizing a weighted-errors functional that consists of experimental and numerical section strains. The improved coefficient matrix K R is always non-singular, assuring that the solution of iFEM formulation exists. Location-independent feature of matrix K R simplifies the inverse finite element modeling, especially for complicated structures. Weighting constants are utilized to define error functional, aiming to penalize the contributions from "measure-less" stations. Numerical and experimental cases have been performed and demonstrated excellent predictive capability when iEBT2 model has complete strain measures. In the case of missing strain components, iEBT2 enables deformation estimation and its accuracy is acceptable in general. The enhanced inverse element extends the practical usefulness of iFEM in shape-sensing analysis of civil infrastructures. [ABSTRACT FROM AUTHOR]

• A DIC algorithm that can deal with discontinuous displacement is proposed. • The algorithm can automatically select the most suitable subset form. • The concept of pixel-level ZNCC distribution map is proposed. • The method has good applicability and scalability in engineering applications. Digital image correlation (DIC) is one of the most used techniques for measuring deformation. It is widely used in mechanical performance testing, structural health monitoring and many other fields. The standard subset based DIC technology assumes that the deformation is continuous. However, discontinuous deformation such as cracks and dislocations are quite common in practical applications. The measurement accuracy of DIC in these areas will be significantly reduced, or even measurement failure. This is a limitation for the application of DIC. To overcome this problem, this paper proposes a variable subset DIC algorithm. Taking the zero-mean normalized cross-correlation (ZNCC) function as the correlation criterion, the concept of pixel-level ZNCC value distribution map is proposed. The proposed algorithm can automatically select the most suitable subset for matching under the guidance of the pixel-level ZNCC value distribution map. This method has the advantages of good flexibility, strong applicability, and high precision. [ABSTRACT FROM AUTHOR]