Sensors

33 pages, 8101 KiB

Open AccessArticle

DIMScern: A Framework for Discerning DIMSE Services on Remote Medical Devices

by Gunhee Kim, Dohyun Kim, Jeonghun Seo, Seyoung Lee and Wonjun Song

Sensors 2024, 24(23), 7470; https://doi.org/10.3390/s24237470 - 22 Nov 2024

In the medical domain, computer systems in digital healthcare have increased connectivity continuously and the DICOM Message Service Element (DIMSE) protocol has a critical role in exchanging biomedical imaging data among different digital healthcare systems. As the data communication technology is used to [...] Read more.

In the medical domain, computer systems in digital healthcare have increased connectivity continuously and the DICOM Message Service Element (DIMSE) protocol has a critical role in exchanging biomedical imaging data among different digital healthcare systems. As the data communication technology is used to handle sensitive information such as patient information (e.g., patient’s name, date of birth, and address) and medical images (e.g., ultrasound, X-ray, and MRI), it has emerged as a major target for security attacks. In this work, we study security concerns on the message exchange method used in the DIMSE protocol. It is important to know which DIMSE services are available on a given healthcare IT system to an adversary and we observe that the DIMSE protocol can be implemented in various ways across products, with each supporting different DIMSE services as well. We present DIMScern, a framework for discerning DIMSE services on remote medical devices. To show the effectiveness of DIMScern, we evaluate our framework on multiple DIMSE implementations, including commercial products and libraries, and identify the supported DIMSE services of them. We demonstrate that DIMScern successfully identifies medical services that are supported differently across 22 healthcare IT systems in a remote environment. Full article

(This article belongs to the Special Issue Biomedical Imaging: Present and Future Challenges, from Image Processing Sensors through Artificial Intelligence)

15 pages, 18055 KiB

Open AccessArticle

Precise Mechanical Oscillator Design and Calibration for Characterising Sub-Millimetre Movements in mmWave Radar Systems

by Felipe Parralejo, Fernando J. Álvarez, José A. Paredes, Fernando J. Aranda and Teodoro Aguilera

Sensors 2024, 24(23), 7469; https://doi.org/10.3390/s24237469 - 22 Nov 2024

Abstract

For many industrial and medical applications, measuring sub-millimetre movements has become crucial, for instance, for the precise guidance of surgical robots. The literature shows the feasibility of millimetre-wave (mmWave) radars to deal with such micro-vibrations. However, the availability of reference devices to configure [...] Read more.

For many industrial and medical applications, measuring sub-millimetre movements has become crucial, for instance, for the precise guidance of surgical robots. The literature shows the feasibility of millimetre-wave (mmWave) radars to deal with such micro-vibrations. However, the availability of reference devices to configure and test these systems is very limited. This work proposes the design of a mechanical oscillator to characterise sub-millimetre vibration detection and measurement using a mmWave radar. The final implementation is fully controllable in both amplitude and frequency. Additionally, it can be wirelessly controlled and synchronised with other systems. Its functioning was experimentally calibrated and tested using the sub-millimetre motion capture system OptiTrack. It was tested to generate low-frequency oscillations from 0.80 Hz to 3.50 Hz with reliable peak amplitudes of 0.05 mm and above, with less than 6% peak amplitude relative error. Finally, the device was used to characterise a 60 GHz mmWave radar with those values. Full article

(This article belongs to the Special Issue Feature Papers in Physical Sensors 2024)

► Show Figures

Figure 1

20 pages, 4515 KiB

Open AccessArticle

Evaluation of Different Commercial Sensors for the Development of Their Automatic Irrigation System

by Sandra Millán, Cristina Montesinos and Carlos Campillo

Sensors 2024, 24(23), 7468; https://doi.org/10.3390/s24237468 - 22 Nov 2024

Abstract

Reliable soil moisture information is essential for accurate irrigation scheduling. A wide range of soil moisture sensors are currently available on the market, but their performance needs to be evaluated as most sensors are calibrated under limited laboratory conditions. The aim of this [...] Read more.

Reliable soil moisture information is essential for accurate irrigation scheduling. A wide range of soil moisture sensors are currently available on the market, but their performance needs to be evaluated as most sensors are calibrated under limited laboratory conditions. The aim of this study was to evaluate the performance of six commercially available moisture sensors (HydraProbe, Teros 10, Teros 11, EnviroPro, CS616 and Drill & Drop) and three tensiometers (Irrometer RSU-C-34, Teros 32 and Teros 21) and to establish calibration equations for a typical sandy soil of the Doñana National Park (Huelva, Spain). The calibration process for soil moisture sensors indicated differences between factory and corrected equations. All tested sensors improved with adjustments made to the factory calibration, except for the HydraProbe sensor which had a more accurate factory equation for a sandy soil. Among the various sensors tested, the Teros 10, Teros 11, and HydraProbe were found to be the easiest to install, typically positioned with an auger to prevent preferential pathways and ensure adequate sensor-soil contact. For tensiometers, the Teros 32 sensor requires specialized labor for its correct installation, as it must be positioned at a specific angle and maintained with distilled water. All tensiometers need a stabilization period after installation. Full article

(This article belongs to the Special Issue Sensor-Based Crop and Soil Monitoring in Precise Agriculture)

► Show Figures

Figure 1

11 pages, 1332 KiB

Open AccessArticle

THz Polarimetric Imaging of Carbon Fiber-Reinforced Composites Using the Portable Handled Spectral Reflection (PHASR) Scanner

by Kuangyi Xu, Zachery B. Harris, Paul Vahey and M. Hassan Arbab

Sensors 2024, 24(23), 7467; https://doi.org/10.3390/s24237467 - 22 Nov 2024

Abstract

Recent advancements in novel fiber-coupled and portable terahertz (THz) spectroscopic imaging technology have accelerated applications in nondestructive testing (NDT). Although the polarization information of THz waves can play a critical role in material characterization, there are few demonstrations of polarization-resolved THz imaging as [...] Read more.

Recent advancements in novel fiber-coupled and portable terahertz (THz) spectroscopic imaging technology have accelerated applications in nondestructive testing (NDT). Although the polarization information of THz waves can play a critical role in material characterization, there are few demonstrations of polarization-resolved THz imaging as an NDT modality due to the deficiency of such polarimetric imaging devices. In this paper, we have inspected industrial carbon fiber composites using a portable and handheld imaging scanner in which the THz polarizations of two orthogonal channels are simultaneously captured by two photoconductive antennas. We observed significant polarimetric differences between the two-channel images of the same sample and the resulting THz Stokes vectors, which are attributed to the anisotropic conductivity of carbon fiber composites. Using both polarimetric channels, we can visualize the superficial and underlying interfaces of the first laminate. These results pave the way for the future applications of THz polarimetry to the assessment of coatings or surface quality on carbon fiber-reinforced substrates. Full article

(This article belongs to the Special Issue Millimeter Wave and Terahertz Source, Sensing and Imaging)

21 pages, 2010 KiB

Open AccessArticle

Enhanced Fault Diagnosis in Milling Machines Using CWT Image Augmentation and Ant Colony Optimized AlexNet

by Niamat Ullah, Muhammad Umar, Jae-Young Kim and Jong-Myon Kim

Sensors 2024, 24(23), 7466; https://doi.org/10.3390/s24237466 - 22 Nov 2024

Abstract

A method is proposed for fault classification in milling machines using advanced image processing and machine learning. First, raw data are obtained from real-world industries, representing various fault types (tool, bearing, and gear faults) and normal conditions. These data are converted into two-dimensional [...] Read more.

A method is proposed for fault classification in milling machines using advanced image processing and machine learning. First, raw data are obtained from real-world industries, representing various fault types (tool, bearing, and gear faults) and normal conditions. These data are converted into two-dimensional continuous wavelet transform (CWT) images for superior time-frequency localization. The images are then augmented to increase dataset diversity using techniques such as rotating, scaling, and flipping. A contrast enhancement filter is applied to highlight key features, thereby improving the model’s learning and fault detection capability. The enhanced images are fed into a modified AlexNet model with three residual blocks to efficiently extract both spatial and temporal features from the CWT images. The modified AlexNet architecture is particularly well-suited to identifying complex patterns associated with different fault types. The deep features are optimized using ant colony optimization to reduce dimensionality while preserving relevant information, ensuring effective feature representation. These optimized features are then classified using a support vector machine, effectively distinguishing between fault types and normal conditions with high accuracy. The proposed method provides significant improvements in fault classification while outperforming state-of-the-art methods. It is thus a promising solution for industrial fault diagnosis and has potential for broader applications in predictive maintenance. Full article

(This article belongs to the Special Issue Advances in Sensor Technology and Applications for Fault Diagnosis: Design, Architecture, and Approaches)

11 pages, 4189 KiB

Open AccessArticle

Identification of Intrinsic Friction and Torque Ripple for a Robotic Joint with Integrated Torque Sensors with Application to Wheel-Bearing Characterization

by Harsha Turlapati Sri, Van Pho Nguyen, Juhi Gurnani, Mohammad Zaidi Bin Ariffin, Sreekanth Kana, Alvin Hong Yee Wong, Boon Siew Han and Domenico Campolo

Sensors 2024, 24(23), 7465; https://doi.org/10.3390/s24237465 - 22 Nov 2024

Abstract

Although integrated joint torque sensors in robots dispel the need for external force/torque sensors at the wrist to measure interactions, an inherent challenge is that they also measure the robot’s intrinsic dynamics. This is especially problematic for delicate robot manipulation tasks, where interaction [...] Read more.

Although integrated joint torque sensors in robots dispel the need for external force/torque sensors at the wrist to measure interactions, an inherent challenge is that they also measure the robot’s intrinsic dynamics. This is especially problematic for delicate robot manipulation tasks, where interaction forces may be comparable to the robot intrinsic dynamics. Therefore, the intrinsic dynamics must first be experimentally estimated under no-load conditions, when the measurement only consists of torques due to the transmission of the robot actuator, before external interactions may be measured. In this work, we propose an approach for identifying and predicting the intrinsic dynamics using linear regression with non-linear radial basis functions. Then, we validate this regression on a wheel-bearing turning task, in which its friction is a measure of quality, and thus must be accurately measured. The results showed that the bearing torque measured by the joint 7 torque sensor was within an RMS error of 11% of the torque measured by the external force/torque sensor. This error is much lower than that before our proposed model in compensating the intrinsic dynamics of the robot arm. Full article

(This article belongs to the Special Issue Advances in Sensing, Control and Path Planning for Robotic Systems)

13 pages, 3196 KiB

Open AccessCommunication

Eyelid Dynamics Characterization with 120 GHz mmW Radar

by Dominik Patscheider, Ruochen Wu, Antoni Broquetas, Albert Aguasca and Jordi Romeu

Sensors 2024, 24(23), 7464; https://doi.org/10.3390/s24237464 - 22 Nov 2024

Abstract

This paper presents a new approach to measuring eyelid movement using millimeter wave (mmW) radar technology. A two-step method is proposed, involving the observation of a small resolution cell corresponding to the monitored eye and the evaluation of the phase evolution over the [...] Read more.

This paper presents a new approach to measuring eyelid movement using millimeter wave (mmW) radar technology. A two-step method is proposed, involving the observation of a small resolution cell corresponding to the monitored eye and the evaluation of the phase evolution over the measurement period. Simulations are conducted to support radar system optimization and data interpretation with a focus on detecting eyelid movement patterns and compensating for interference from other parts of the body. The feasibility of using this method with eyeglasses is also explored. The proposed technique’s advantages and limitations are discussed in comparison with existing measurement alternatives. The characteristics of eyelid dynamics, including blink frequency, regularity, duration, and velocity can be used to assess neurological conditions and driver drowsiness. Full article

(This article belongs to the Section Radar Sensors)

42 pages, 6682 KiB

Open AccessArticle

A Tensor Space for Multi-View and Multitask Learning Based on Einstein and Hadamard Products: A Case Study on Vehicle Traffic Surveillance Systems

by Fernando Hermosillo-Reynoso and Deni Torres-Roman

Sensors 2024, 24(23), 7463; https://doi.org/10.3390/s24237463 - 22 Nov 2024

Abstract

Since multi-view learning leverages complementary information from multiple feature sets to improve model performance, a tensor-based data fusion layer for neural networks, called Multi-View Data Tensor Fusion (MV-DTF), is used. It fuses M feature spaces

X_{1}, \dots, X_{M}

, [...] Read more.

Since multi-view learning leverages complementary information from multiple feature sets to improve model performance, a tensor-based data fusion layer for neural networks, called Multi-View Data Tensor Fusion (MV-DTF), is used. It fuses M feature spaces

X_{1}, \dots, X_{M}

, referred to as views, in a new latent tensor space,

S

, of order P and dimension

J_{1} \times \dots \times J_{P}

, defined in the space of affine mappings composed of a multilinear map

T : X_{1} \times \dots \times X_{M} \to S

—represented as the Einstein product between a

(P + M)

-order tensor

A

anda rank-one tensor,

X = x^{(1)} \otimes \dots \otimes x^{(M)}

, where

x^{(m)} \in X_{m}

is the m-th view—and a translation. Unfortunately, as the number of views increases, the number of parameters that determine the MV-DTF layer grows exponentially, and consequently, so does its computational complexity. To address this issue, we enforce low-rank constraints on certain subtensors of tensor

A

using canonical polyadic decomposition, from which M other tensors

U^{(1)}, \dots, U^{(M)}

, called here Hadamard factor tensors, are obtained. We found that the Einstein product

A ⊛_{M} X

can be approximated using a sum of R Hadamard products of M Einstein products encoded as

U^{(m)} ⊛_{1} x^{(m)}

, where R is related to the decomposition rank of subtensors of

A

. For this relationship, the lower the rank values, the more computationally efficient the approximation. To the best of our knowledge, this relationship has not previously been reported in the literature. As a case study, we present a multitask model of vehicle traffic surveillance for occlusion detection and vehicle-size classification tasks, with a low-rank MV-DTF layer, achieving up to

92.81 %

and

95.10 %

in the normalized weighted Matthews correlation coefficient metric in individual tasks, representing a significant

6 %

and

7 %

improvement compared to the single-task single-view models. Full article

(This article belongs to the Section Vehicular Sensing)

14 pages, 1474 KiB

Open AccessArticle

LOTUS Software to Process Wearable EmbracePlus Data

by Jack S. Fogarty

Sensors 2024, 24(23), 7462; https://doi.org/10.3390/s24237462 - 22 Nov 2024

Abstract

The Empatica EmbracePlus is a recent innovation in medical-grade wristband wearable sensors that enable unobtrusive continuous measurement of pulse rate, electrodermal activity, skin temperature, and various accelerometry-based actigraphy measures using a minimalistic smartwatch design. The advantage of this lightweight wearable is the potential [...] Read more.

The Empatica EmbracePlus is a recent innovation in medical-grade wristband wearable sensors that enable unobtrusive continuous measurement of pulse rate, electrodermal activity, skin temperature, and various accelerometry-based actigraphy measures using a minimalistic smartwatch design. The advantage of this lightweight wearable is the potential for holistic longitudinal recording and monitoring of physiological processes that index a suite of autonomic functions, as well as to provide ecologically valid insights into human behaviour, health, physical activity, and psychophysiological processes. Given the longitudinal nature of wearable recordings, EmbracePlus data collection is managed by storing raw timeseries in short ‘chunks’ in avro file format organised by universal standard time. This is memory-efficient but requires programming expertise to compile the raw data into continuous file formats that can be processed using standard techniques. Currently, there are no accessible tools available to compile and analyse raw EmbracePlus data over user-defined time periods. To address that, we introduce the LOTUS toolkit, an open-source graphical user interface that allows users to reconstitute and process EmbracePlus datasets over select time intervals. LOTUS is available on GitHub, and currently allows users to compile raw EmbracePlus data into unified timeseries stored in more familiar Excel or Matlab file formats to facilitate signal processing and analysis. Future work will expand the toolkit to process Empatica E4 and other wearable signal data, while also integrating more sophisticated functions for feature extraction and analysis. Full article

(This article belongs to the Special Issue Wearable Sensors for Behavioral and Physiological Monitoring)

17 pages, 4478 KiB

Open AccessArticle

Carbon-Efficient Scheduling in Fresh Food Supply Chains with a Time-Window-Constrained Deep Reinforcement Learning Model

by Yuansu Zou, Qixian Gao, Hao Wu and Nianbo Liu

Sensors 2024, 24(23), 7461; https://doi.org/10.3390/s24237461 - 22 Nov 2024

Abstract

Intelligent Transportation Systems (ITSs) leverage Internet of Things (IoT) technology to facilitate smart interconnectivity among vehicles, infrastructure, and users, thereby optimizing traffic flow. This paper constructs an optimization model for the fresh food supply chain distribution route of fresh products, considering factors such [...] Read more.

Intelligent Transportation Systems (ITSs) leverage Internet of Things (IoT) technology to facilitate smart interconnectivity among vehicles, infrastructure, and users, thereby optimizing traffic flow. This paper constructs an optimization model for the fresh food supply chain distribution route of fresh products, considering factors such as carbon emissions, time windows, and cooling costs. By calculating carbon emission costs through carbon taxes, the model aims to minimize distribution costs. With a graph attention network structure adopted to describe node locations, accessible paths, and data with collection windows for path planning, it integrates to solve for the optimal distribution routes, taking into account carbon emissions and cooling costs under varying temperatures. Extensive simulation experiments and comparative analyses demonstrate that the proposed time-window-constrained reinforcement learning model provides effective decision-making information for optimizing fresh product fresh food supply chain transportation and distribution, controlling logistics costs, and reducing carbon emissions. Full article

(This article belongs to the Special Issue Feature Papers in the Internet of Things Section 2024)

24 pages, 4041 KiB

Open AccessArticle

Unsupervised Deep Learning for Synthetic CT Generation from CBCT Images for Proton and Carbon Ion Therapy for Paediatric Patients

by Matteo Pepa, Siavash Taleghani, Giulia Sellaro, Alfredo Mirandola, Francesca Colombo, Sabina Vennarini, Mario Ciocca, Chiara Paganelli, Ester Orlandi, Guido Baroni and Andrea Pella

Sensors 2024, 24(23), 7460; https://doi.org/10.3390/s24237460 - 22 Nov 2024

Abstract

Image-guided treatment adaptation is a game changer in oncological particle therapy (PT), especially for younger patients. The purpose of this study is to present a cycle generative adversarial network (CycleGAN)-based method for synthetic computed tomography (sCT) generation from cone beam CT (CBCT) towards [...] Read more.

Image-guided treatment adaptation is a game changer in oncological particle therapy (PT), especially for younger patients. The purpose of this study is to present a cycle generative adversarial network (CycleGAN)-based method for synthetic computed tomography (sCT) generation from cone beam CT (CBCT) towards adaptive PT (APT) of paediatric patients. Firstly, 44 CBCTs of 15 young pelvic patients were pre-processed to reduce ring artefacts and rigidly registered on same-day CT scans (i.e., verification CT scans, vCT scans) and then inputted to the CycleGAN network (employing either Res-Net and U-Net generators) to synthesise sCT. In particular, 36 and 8 volumes were used for training and testing, respectively. Image quality was evaluated qualitatively and quantitatively using the structural similarity index metric (SSIM) and the peak signal-to-noise ratio (PSNR) between registered CBCT (rCBCT) and vCT and between sCT and vCT to evaluate the improvements brought by CycleGAN. Despite limitations due to the sub-optimal input image quality and the small field of view (FOV), the quality of sCT was found to be overall satisfactory from a quantitative and qualitative perspective. Our findings indicate that CycleGAN is promising to produce sCT scans with acceptable CT-like image texture in paediatric settings, even when CBCT with narrow fields of view (FOV) are employed. Full article

(This article belongs to the Special Issue Feature Papers in Sensing and Imaging 2024)

16 pages, 3933 KiB

Open AccessArticle

Monitoring Biochemical Changes of Neuroblastoma Cells in Early Stages After X-Ray Exposure by Using Fourier-Transform Infrared Spectroscopy

by Rosario Esposito, Marianna Portaccio, Roberta Meschini, Ines Delfino and Maria Lepore

Sensors 2024, 24(23), 7459; https://doi.org/10.3390/s24237459 - 22 Nov 2024

Abstract

X-ray radiation treatments are largely adopted in radiotherapy, and Fourier-transform infrared microspectroscopy (μ-FTIR) has already been demonstrated to be a useful instrument for monitoring radiotherapy effects. Previous works in this field have focused on studying the changes occurring in cells when they are [...] Read more.

X-ray radiation treatments are largely adopted in radiotherapy, and Fourier-transform infrared microspectroscopy (μ-FTIR) has already been demonstrated to be a useful instrument for monitoring radiotherapy effects. Previous works in this field have focused on studying the changes occurring in cells when they are fixed immediately after the irradiation or 24 and 48 h later. In the present paper, changes occurring in SH-SY5Y neuroblastoma cells in the first hours after the irradiation are examined to obtain information on the processes taking place in this not-yet-investigated time window by using μ-FTIR. For this purpose, cell samples were fixed immediately after X-ray exposure, and 2 and 4 h after irradiation and investigated along with unexposed cells. Different data analysis procedures were implemented to estimate the changes in lipid, protein, and DNA spectral contributions. The present investigation on the effects of X-ray in the first hours after the exposure is helpful for better describing the processes occurring in this time window that offer the possibility of a timely check on the efficacy of X-ray treatments and can potentially be applied for planning personalized treatment as required by the most advanced medical therapy. Full article

(This article belongs to the Special Issue Novel Optical Sensors for Biomedical Applications—2nd Edition)

► Show Figures

Figure 1

32 pages, 10068 KiB

Open AccessArticle

An Automated Feature-Based Image Registration Strategy for Tool Condition Monitoring in CNC Machine Applications

by Eden Lazar, Kristin S. Bennett, Andres Hurtado Carreon and Stephen C. Veldhuis

Sensors 2024, 24(23), 7458; https://doi.org/10.3390/s24237458 - 22 Nov 2024

Abstract

The implementation of Machine Vision (MV) systems for Tool Condition Monitoring (TCM) plays a critical role in reducing the total cost of operation in manufacturing while expediting tool wear testing in research settings. However, conventional MV-TCM edge detection strategies process each image independently [...] Read more.

The implementation of Machine Vision (MV) systems for Tool Condition Monitoring (TCM) plays a critical role in reducing the total cost of operation in manufacturing while expediting tool wear testing in research settings. However, conventional MV-TCM edge detection strategies process each image independently to infer edge positions, rendering them susceptible to inaccuracies when tool edges are compromised by material adhesion or chipping, resulting in imprecise wear measurements. In this study, an MV system is developed alongside an automated, feature-based image registration strategy to spatially align tool wear images, enabling a more consistent and accurate detection of tool edge position. The MV system was shown to be robust to the machining environment, versatile across both turning and milling machining centers and capable of reducing tool wear image capturing time up to 85% in reference to standard approaches. A comparison of feature detector-descriptor algorithms found SIFT, KAZE, and ORB to be the most suitable for MV-TCM registration, with KAZE presenting the highest accuracy and ORB being the most computationally efficient. The automated registration algorithm was shown to be efficient, performing registrations in 1.3 s on average and effective across a wide range of tool geometries and coating variations. The proposed tool reference line detection strategy, based on spatially aligned tool wear images, outperformed standard methods, resulting in average tool wear measurement errors of 2.5% and 4.5% in the turning and milling tests, respectively. Such a system allows machine tool operators to more efficiently capture cutting tool images while ensuring more reliable tool wear measurements. Full article

(This article belongs to the Special Issue Feature Papers in Sensing and Imaging 2024)

21 pages, 4574 KiB

Open AccessArticle

Effect of Post-Heat Treatment on the Mechanical and Residual Stress Behavior of Pulsed Wave S316L Fabricated by Directed Energy Deposition

by Zhou Yan, Jia Guo and Xi Zou

Sensors 2024, 24(23), 7457; https://doi.org/10.3390/s24237457 - 22 Nov 2024

Abstract

The influence of annealing at various temperatures on the phase stability and microstructure of pulsed-wave laser mode (PW) 316L stainless steel fabricated via Directed Energy Deposition (DED) was systematically investigated. The microstructural alterations resulting from heat treatment were examined to clarify their influence [...] Read more.

The influence of annealing at various temperatures on the phase stability and microstructure of pulsed-wave laser mode (PW) 316L stainless steel fabricated via Directed Energy Deposition (DED) was systematically investigated. The microstructural alterations resulting from heat treatment were examined to clarify their influence on the mechanical properties of the specimens subjected to tensile loading. The results showed that cell size increased with annealing temperature, with the cellular microstructure disappearing at higher temperatures (T ≥ 1000 °C). A decrease in the mechanical strength of the specimens was observed as annealing temperature increased. Additionally, the influence of different laser pulse frequencies and duty cycles on residual stresses was examined, revealing that moderate laser frequencies and duty cycles effectively reduced residual stress levels. Full article

(This article belongs to the Section Optical Sensors)

14 pages, 3994 KiB

Open AccessArticle

Study on the Optimization of b-Value for Analyzing Weld Defects in the Primary System

by Do-Yun Jung, Young-Chul Choi and Byun-Young Chung

Sensors 2024, 24(23), 7456; https://doi.org/10.3390/s24237456 - 22 Nov 2024

Abstract

This study presents a method to add a crack analysis algorithm to the Acoustic Leak Monitoring System (ALMS) to detect and evaluate the crack growth process in the primary system piping of nuclear power plants. To achieve this, a fracture test was conducted [...] Read more.

This study presents a method to add a crack analysis algorithm to the Acoustic Leak Monitoring System (ALMS) to detect and evaluate the crack growth process in the primary system piping of nuclear power plants. To achieve this, a fracture test was conducted by applying stepwise loading to welded specimens that simulate the cold leg section, and acoustic emission (AE) signals were measured in relation to the increase in strain using an AE testing system. The experimental results indicated that the stability and instability of cracks could be assessed through the Kaiser effect and the Felicity effect when detecting crack growth using AE signals. Additionally, by utilizing both root mean square (RMS) and amplitude parameters simultaneously to calculate the b-value, it was confirmed that the RMS-based b-value minimizes the effects of AE signal attenuation and allows for a more stable assessment of crack progression. This demonstrates that the RMS, which reflects signal energy, is effective for real-time monitoring of the crack growth state. Finally, the results of this study suggest the potential for real-time crack monitoring using AE data in piping systems of critical structures, such as nuclear power plants; by adding a simple AE analysis method to the ALMS system, a practical approach has been derived that enhances the safety of the structure and allows for quantitative assessment of crack progression. Future research is expected to further refine the AE parameters and algorithms, leading to the advancement of safety monitoring systems in various industrial settings. Full article

(This article belongs to the Special Issue Sensors and Acoustic Emission Technology for Nondestructive Evaluation)

► Show Figures

Figure 1

15 pages, 3245 KiB

Open AccessArticle

A Spatial-Temporal Multi-Feature Network (STMF-Net) for Skeleton-Based Construction Worker Action Recognition

by Yuanyuan Tian, Sen Lin, Hejun Xu and Guangchong Chen

Sensors 2024, 24(23), 7455; https://doi.org/10.3390/s24237455 - 22 Nov 2024

Abstract

Globally, monitoring productivity, occupational health, and safety of construction workers has long been a significant concern. To address this issue, there is an urgent need for efficient methods to continuously monitor construction sites and recognize workers’ actions in a timely manner. Recently, advances [...] Read more.

Globally, monitoring productivity, occupational health, and safety of construction workers has long been a significant concern. To address this issue, there is an urgent need for efficient methods to continuously monitor construction sites and recognize workers’ actions in a timely manner. Recently, advances in electronic technology and pose estimation algorithms have made it easier to obtain skeleton and joint trajectories of human bodies. Deep learning algorithms have emerged as robust and automated tools for extracting and processing 3D skeleton information on construction sites, proving effective for workforce action assessment. However, most previous studies on action recognition have primarily focused on single-stream data, which limited the network’s ability to capture more comprehensive worker action features. Therefore, this research proposes a Spatial-Temporal Multi-Feature Network (STMF-Net) designed to utilize six 3D skeleton-based features to monitor and capture the movements of construction workers, thereby recognizing their actions. The experimental results demonstrate an accuracy of 79.36%. The significance of this work lies in its potential to enhance management models within the construction industry, ultimately improving workers’ health and work efficiency. Full article

(This article belongs to the Section Intelligent Sensors)

► Show Figures

Figure 1

31 pages, 870 KiB

Open AccessArticle

Advances in Data Pre-Processing Methods for Distributed Fiber Optic Strain Sensing

by Bertram Richter, Lisa Ulbrich, Max Herbers and Steffen Marx

Sensors 2024, 24(23), 7454; https://doi.org/10.3390/s24237454 - 22 Nov 2024

Abstract

Because of their high spatial resolution over extended lengths, distributed fiber optic sensors (DFOS) enable us to monitor a wide range of structural effects and offer great potential for diverse structural health monitoring (SHM) applications. However, even under controlled conditions, the useful signal [...] Read more.

Because of their high spatial resolution over extended lengths, distributed fiber optic sensors (DFOS) enable us to monitor a wide range of structural effects and offer great potential for diverse structural health monitoring (SHM) applications. However, even under controlled conditions, the useful signal in distributed strain sensing (DSS) data can be concealed by different types of measurement principle-related disturbances: strain reading anomalies (SRAs), dropouts, and noise. These disturbances can render the extraction of information for SHM difficult or even impossible. Hence, cleaning the raw measurement data in a pre-processing stage is key for successful subsequent data evaluation and damage detection on engineering structures. To improve the capabilities of pre-processing procedures tailored to DSS data, characteristics and common remediation approaches for SRAs, dropouts, and noise are discussed. Four advanced pre-processing algorithms (geometric threshold method (GTM), outlier-specific correction procedure (OSCP), sliding modified z-score (SMZS), and the cluster filter) are presented. An artificial but realistic benchmark data set simulating different measurement scenarios is used to discuss the features of these algorithms. A flexible and modular pre-processing workflow is implemented and made available with the algorithms. Dedicated algorithms should be used to detect and remove SRAs. GTM, OSCP, and SMZS show promising results, and the sliding average is inappropriate for this purpose. The preservation of crack-induced strain peaks’ tips is imperative for reliable crack monitoring. Full article

(This article belongs to the Section Optical Sensors)

► Show Figures

Figure 1

25 pages, 6447 KiB

Open AccessArticle

ReLU, Sparseness, and the Encoding of Optic Flow in Neural Networks

by Oliver W. Layton, Siyuan Peng and Scott T. Steinmetz

Sensors 2024, 24(23), 7453; https://doi.org/10.3390/s24237453 - 22 Nov 2024

Abstract

Accurate self-motion estimation is critical for various navigational tasks in mobile robotics. Optic flow provides a means to estimate self-motion using a camera sensor and is particularly valuable in GPS- and radio-denied environments. The present study investigates the influence of different activation functions—ReLU, [...] Read more.

Accurate self-motion estimation is critical for various navigational tasks in mobile robotics. Optic flow provides a means to estimate self-motion using a camera sensor and is particularly valuable in GPS- and radio-denied environments. The present study investigates the influence of different activation functions—ReLU, leaky ReLU, GELU, and Mish—on the accuracy, robustness, and encoding properties of convolutional neural networks (CNNs) and multi-layer perceptrons (MLPs) trained to estimate self-motion from optic flow. Our results demonstrate that networks with ReLU and leaky ReLU activation functions not only achieved superior accuracy in self-motion estimation from novel optic flow patterns but also exhibited greater robustness under challenging conditions. The advantages offered by ReLU and leaky ReLU may stem from their ability to induce sparser representations than GELU and Mish do. Our work characterizes the encoding of optic flow in neural networks and highlights how the sparseness induced by ReLU may enhance robust and accurate self-motion estimation from optic flow. Full article

(This article belongs to the Section Navigation and Positioning)

► Show Figures

Figure 1

18 pages, 3714 KiB

Open AccessCommunication

Enhancing Railway Earthquake Early Warning Systems with a Low Computational Cost STA/LTA-Based S-Wave Detection Method

by Satoshi Katakami and Naoyasu Iwata

Sensors 2024, 24(23), 7452; https://doi.org/10.3390/s24237452 - 22 Nov 2024

Abstract

To enhance real-time S-wave detection in the railway earthquake early warning (EEW) system, we improved the existing short-term average/long-term average (STA/LTA) algorithm. This enhancement focused on developing a more robust and computationally efficient method. Specifically, we introduced noise reflecting P-wave amplitude information before [...] Read more.

To enhance real-time S-wave detection in the railway earthquake early warning (EEW) system, we improved the existing short-term average/long-term average (STA/LTA) algorithm. This enhancement focused on developing a more robust and computationally efficient method. Specifically, we introduced noise reflecting P-wave amplitude information before the P-wave to better distinguish between P- and S-waves. By applying this modified STA/LTA method, we achieved a significant improvement in S-wave detection accuracy. For seismic waveforms from stations located within 100 km of the epicenter of each earthquake, with magnitude of M5.5–6.5 and depths ≤ 100 km, the detection accuracy within 1.5 s of the correct time (manual picking) was 81.0%, compared to the 49.0% accuracy of the currently operational railway EEW system. Importantly, despite the improved accuracy, the computational cost of the new method remains comparable to the existing system, allowing for easy integration into the operational EEW system. This development is crucial for preventing false alarms, especially moderate earthquakes (~M6) because issuing warn-ings in unnecessary areas can have a significant social impact. Future plans involve implementing this method into the current system to further improve early warning capabilities and minimize false alarms. Full article

(This article belongs to the Special Issue Automatic Detection of Seismic Signals—Second Edition)

► Show Figures

Figure 1

Journal Description

Sensors

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI