Corroded Bolt Identification Using Mask Region-Based Deep Learning Trained on Synthesized Data.

The performance of a neural network depends on the availability of datasets, and most deep learning techniques lack accuracy and generalization when they are trained using limited datasets. Using synthesized training data is one of the effective ways to overcome the above limitation. Besides, the previous corroded bolt detection method has focused on classifying only two classes, clean and fully rusted bolts, and its performance for detecting partially rusted bolts is still questionable. This study presents a deep learning method to identify corroded bolts in steel structures using a mask region-based convolutional neural network (Mask-RCNN) trained on synthesized data. The Resnet50 integrated with a feature pyramid network is used as the backbone for feature extraction in the Mask-RCNN-based corroded bolt detector. A four-step data synthesis procedure is proposed to autonomously generate the training datasets of corroded bolts with different severities. Afterwards, the proposed detector is trained by the synthesized datasets, and its robustness is demonstrated by detecting corroded bolts in a lab-scale steel structure under varying capturing distances and perspectives. The results show that the proposed method has detected corroded bolts well and identified their corrosion levels with the most desired overall accuracy rate = 96.3% for a 1.0 m capturing distance and 97.5% for a 15° perspective angle.

Correction: Pham et al. Bolt-Loosening Monitoring Framework Using an Image-Based Deep Learning and Graphical Model. Sensors 2020, 20, 3382.

The authors wish to make the following correction to this paper [...].

A smart LED therapy device with an automatic facial acne vulgaris diagnosis based on deep learning and internet of things application.

In low-level laser therapy, providing an optimal dosage and proposing a proper diagnosis before dermatological treatment are essential to reduce the side effects and potential dangers. In this article, a smart LED therapy system for automatic facial acne vulgaris diagnosis based on deep learning and Internet of Things application is proposed. The main goals of this study were to (1) develop an LED therapy device with different power densities and LED grid control; (2) propose a deep learning model based on modified ResNet50 and YOLOv2 for an automatic acne diagnosis; and (3) develop a smartphone application for facial photography image capture and LED therapy parameter configuration. Furthermore, a healthcare Internet of Things (H-IoT) platform for the connectivity between smartphone apps, the cloud server, and the LED therapy device is proposed to improve the efficiency of the treatment process. Experiments were conducted on test data sets divided by a cross-validation method to verify the feasibility of the proposed LED therapy system with automatic facial acne detection. The obtained results evidenced the practical application of the proposed LED therapy system for automatic acne diagnosis and H-IoT-based solutions.

Roles of Chitosan in Green Synthesis of Metal Nanoparticles for Biomedical Applications.

Chitosan (CS) is a well-known stabilizer for metal nanoparticles in biomedical engineering. However, very few studies have explored other important roles of CS including reducing, shape-directing, and size-controlling. This review aims to provide the latest and most comprehensive overview of the roles of CS in the green synthesis of metal nanoparticles for biomedical applications. To the best of our knowledge, this is the first review that highlights these potentialities of CS. At first, a brief overview of the properties and the bioactivity of CS is presented. Next, the benefits of CS for enhancing the physicochemical behaviors of metal nanoparticles are discussed in detail. The representative biomedical applications of CS-metal nanoparticles are also given. Lastly, the review outlines the perceptual vision for the future development of CS-metal nanoparticles in the biomedicine field.

Application of deep neural network to capture groundwater potential zone in mountainous terrain, Nepal Himalaya.

This study aims to capture groundwater potential zones integrating deep neural network and groundwater influencing factors. The present work was carried out for Gopi khola watershed, mountainous terrain in Nepal Himalaya as the watershed mainly relies upon the groundwater assets; it is a need to explore groundwater potential for better management of the aquifer framework. Ten groundwater influencing factors were collected such as elevation, slope, curvature, topographic positioning index, topographic roughness index, drainage density, topographic wetness index, geology, lineament density, and land use thematic layers. Among those influencing factors, topographic roughness index was removed because of multicollinearity issue to reduce the dimension of the dataset. A spring inventory map of 145 spring locations was prepared using field survey method and an equal number of spring absence points were randomly generated. The 70% of spring and spring absence pixels were used as training dataset and remaining as test dataset. The final map was created based on predicted probabilities ranging from 0 to 1. The validation was done using the receiver operating characteristic curve, which shows that the area under the curve is 76.1% for the training dataset and 82.1% for the test dataset. The sensitivity analysis was performed using Jackknife test which shows that the lineament density is the most important factor. The experimental results demonstrated that deep neural network is highly capable to capture groundwater potential zone in mountainous terrain. The present study might be useful and preliminary work to exploit the groundwater. The consequences of the current study may be valuable to water administrators to settle on appropriate choices on the ideal utilization of groundwater assets for future arranging in the basic investigation zone.

Bolt-Loosening Monitoring Framework Using an Image-Based Deep Learning and Graphical Model.

In this study, we investigate a novel idea of using synthetic images of bolts which are generated from a graphical model to train a deep learning model for loosened bolt detection. Firstly, a framework for bolt-loosening detection using image-based deep learning and computer graphics is proposed. Next, the feasibility of the proposed framework is demonstrated through the bolt-loosening monitoring of a lab-scaled bolted joint model. For practicality, the proposed idea is evaluated on the real-scale bolted connections of a historical truss bridge in Danang, Vietnam. The results show that the deep learning model trained by the synthesized images can achieve accurate bolt recognitions and looseness detections. The proposed methodology could help to reduce the time and cost associated with the collection of high-quality training data and further accelerate the applicability of vision-based deep learning models trained on synthetic data in practice.

Sensor Fault Diagnosis for Impedance Monitoring Using a Piezoelectric-Based Smart Interface Technique.

For a structural health monitoring (SHM) system, the operational functionality of sensors is critical for successful implementation of a damage identification process. This study presents experimental and analytical investigations on sensor fault diagnosis for impedance-based SHM using the piezoelectric interface technique. Firstly, the piezoelectric interface-based impedance monitoring is experimentally conducted on a steel bolted connection to investigate the effect of structural damage and sensor defect on electromechanical (EM) impedance responses. Based on the experimental analysis, sensor diagnostic approaches using EM impedance features are designed to distinguish the sensor defect from the structural damage. Next, a novel impedance model of the piezoelectric interface-driven system is proposed for the analytical investigation of sensor fault diagnosis. Various parameters are introduced into the EM impedance formulation to model the effect of shear-lag phenomenon, sensor breakage, sensor debonding, and structural damage. Finally, the proposed impedance model is used to analytically estimate the change in EM impedance responses induced by the structural damage and the sensor defect. The analytical results are found to be consistent with experimental observations, thus evidencing the feasibility of the novel impedance model for sensor diagnosis and structural integrity assessment. The study is expected to provide theoretical and experimental foundations for impedance monitoring practices, using the piezoelectric interface technique, with the existence of sensor faults.

Photothermal Responsive Porous Membrane for Treatment of Infected Wound.

Wound infection is a big issue of modern medicine because of multi-drug resistance bacteria; thus, developing an advanced therapy is curial. Photothermal therapy (PTT) is a newly noninvasive strategy that employs PTT agents to transfer near-infrared (NIR) light energy into heat to kill bacterial pathogens. In this work, the PTT agent-containing dressing was developed for the first time to treat the wound infection. Palladium nanoparticles (PdNPs) were chosen as PTT agents because of their high stability, good biocompatibility, excellent photothermal property, and simple-green preparation. With the flexibility and wettability, highly porous membrane chitosan/polyvinyl alcohol (CS/PVA) membrane was chosen as the dressing. The prepared wound dressings exhibited excellent biocompatibility, high porosity, a high degree of swelling, high moisture retention, and high photothermal performance. The treatment of PdNPs loading CS/PVA dressing (CS/PVA/Pd) and laser irradiation killed most of the bacteria in vitro. The proposed PTT agent containing wound dressing introduces a novel strategy for the treatment of wound infection.

Sensitivity of Piezoelectric-Based Smart Interfaces to Structural Damage in Bolted Connections.

This study presents a set of experimental and numerical investigations to study the sensitivity of the piezoelectric-based smart interface device to structural damage in a bolted connection. The study aims to identify the proper geometric sizes of smart interfaces for damage detection tasks. First, the fundamentals of the damage monitoring technique via lead zirconate titanate(PZT) interface is briefly described for a bolted connection. Second, a lab-scaled girder connection is selected as the test structure for the experimental investigation. PZT interface prototypes with varying geometric sizes are designed for the test connection. Under the bolt-loosening inflicted in the connection, the impedance responses of the PZT interfaces are analyzed to understand the effect of geometric parameters on the damage sensitivity of the impedance responses. Subsequently, the bolt-loosening detection capabilities of the PZT interfaces are comparatively evaluated for identifying the proper geometric sizes of the devices. Finally, a finite element model of the PZT interface-bolted connection system is established for the numerical investigation. The damage sensitivity of the numerical impedance responses is compared with the experimental results for the verification.

Sensing Region Characteristics of Smart Piezoelectric Interface for Damage Monitoring in Plate-Like Structures.

For impedance-based damage detection practices, the sensing range of piezoelectric devices is an important parameter that should be determined before real implementations. This study presents numerical and experimental analyses for characterizing the sensing region of a smart PZT (lead⁻zirconate⁻titanate) interface for damage monitoring in plate-like structures. First, a finite element (FE) model of the PZT interface mounted on a plate structure is established. The impedance responses of the PZT interface are numerically simulated under different damage locations inflicted in the plate domain. The impedance features are extracted from the impedance signatures to analyze the sensing distance and the damage detectability of the PZT interface. Next, the splice plate of a bolted connection is selected as a practical plate-like structure for the experimental examination of the PZT interface's sensing region on a limited plate domain. The damage sensitivity behavior of the PZT interface is analyzed with respect to the damage location on the splice plate. An FE analysis of the corresponding PZT interface-splice plate system is also conducted to support the experimental results.

Local Strand-Breakage Detection in Multi-Strand Anchorage System Using an Impedance-Based Stress Monitoring Method-Feasibility Study.

This study investigates the feasibility of impedance-based stress monitoring method for local-strand breakage detection in multi-strand anchorage systems. Firstly, stress fields of a multi-strand anchorage system are numerically analyzed to examine anchorage's responses sensitive to local strand breakage. Secondly, an impedance-based stress monitoring technique via the PZT interface is outlined. Thirdly, a novel hoop-type PZT interface is designed for the multi-strands anchorage to monitor the stress variation induced by the strand breakage. Local dynamic responses of the hoop-type PZT interface are analyzed to predetermine the effective frequency ranges. Finally, the numerical feasibility of the proposed method is verified on a seven-strand anchorage system under various strand breakage cases. Variations in impedance responses are statistically quantified, and broken strands are localized by linear tomography analysis of damage indices. A lab-scale experiment is also conducted on a multi-strands anchorage to evaluate the realistic performance of the hoop PZT interface for impedance-based stress monitoring method.

An Up-To-Date Review on Biomedical Applications of Palladium Nanoparticles.

Palladium nanoparticles (PdNPs) have intrinsic features, such as brilliant catalytic, electronic, physical, mechanical, and optical properties, as well as diversity in shape and size. The initial researches proved that PdNPs have impressive potential for the development of novel photothermal agents, photoacoustic agents, antimicrobial/antitumor agents, gene/drug carriers, prodrug activators, and biosensors. However, very few studies have taken the benefit of the unique characteristics of PdNPs for applications in the biomedical field in comparison with other metals like gold, silver, or iron. Thus, this review aims to highlight the potential applications in the biomedical field of PdNPs. From that, the review provides the perceptual vision for the future development of PdNPs in this field.

Tension Force Estimation in Axially Loaded Members using Wearable Piezoelectric Interface Technique.

Force changes in axially loaded members can be monitored by quantifying variations in impedance signatures. However, statistical damage metrics, which are not physically related to the axial load, often lead to difficulties in accurately estimating the amount of axial force changes. Inspired by the wearable technology, this study proposes a novel wearable piezoelectric interface that can be used to monitor and quantitatively estimate the force changes in axial members. Firstly, an impedance-based force estimation method was developed for axially loaded members. The estimation was based on the relationship between the axial force level and the peak frequencies of impedance signatures, which were obtained from the wearable piezoelectric interface. The estimation of the load transfer capability from the axial member to the wearable interface was found to be an important factor for the accurate prediction of axial force. Secondly, a prototype of the wearable piezoelectric interface was designed to be easily fitted into existing axial members. Finally, the feasibility of the proposed technique was established by assessing tension force changes in a numerical model of an axially loaded cylindrical member and a lab-scale model of a prestressed cable structure.

Preload Monitoring in Bolted Connection Using Piezoelectric-Based Smart Interface.

In this study, a preload monitoring method using impedance signatures obtained from a piezoelectric-based smart interface is presented for bolted girder connections. Firstly, the background theory of the piezoelectric-based smart interface and its implementation into the health monitoring of bolted connections are outlined. A simplified electro-mechanical (EM) impedance model of a smart interface-embedded bolted connection system is formulated to interpret a mechanistic understanding of the EM impedance signatures under the effect of bolt preload. Secondly, finite element modeling of a bolted connection is carried out to show the numerical feasibility of the presented method, and to predetermine the sensitive frequency band of the impedance signatures. Finally, impedance measurements are conducted on a lab-scaled bolted girder connection, to verify the predetermined sensitive frequency range and to assess the bolt preload changes in the test structure.