Next Issue
Volume 24, May-1
Previous Issue
Volume 24, April-1
 
 
sensors-logo

Journal Browser

Journal Browser

Sensors, Volume 24, Issue 8 (April-2 2024) – 283 articles

Cover Story (view full-size image): The human–robot collaboration system relies on advanced cameras and image processing technologies, where high-precision distortion correction is crucial for accurately perceiving and understanding the environment. However, traditional methods that optimize both camera parameters and distortion coefficients simultaneously based on the model, or correct distortion individually based on specific graphical features, do not adhere to the actual principles of camera lens imaging. This work discusses how to correct distortion using a model-independent approach from the perspective of the actual camera lens distortion principle. The study addresses the effect of large edge pixel distortion in the correction process, improves correction accuracy, and shortens optimization time. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Select all
Export citation of selected articles as:
30 pages, 10257 KiB  
Article
Towards a Distributed Digital Twin Framework for Predictive Maintenance in Industrial Internet of Things (IIoT)
by Ibrahim Abdullahi, Stefano Longo and Mohammad Samie
Sensors 2024, 24(8), 2663; https://doi.org/10.3390/s24082663 - 22 Apr 2024
Cited by 1 | Viewed by 851
Abstract
This study uses a wind turbine case study as a subdomain of Industrial Internet of Things (IIoT) to showcase an architecture for implementing a distributed digital twin in which all important aspects of a predictive maintenance solution in a DT use a fog [...] Read more.
This study uses a wind turbine case study as a subdomain of Industrial Internet of Things (IIoT) to showcase an architecture for implementing a distributed digital twin in which all important aspects of a predictive maintenance solution in a DT use a fog computing paradigm, and the typical predictive maintenance DT is improved to offer better asset utilization and management through real-time condition monitoring, predictive analytics, and health management of selected components of wind turbines in a wind farm. Digital twin (DT) is a technology that sits at the intersection of Internet of Things, Cloud Computing, and Software Engineering to provide a suitable tool for replicating physical objects in the digital space. This can facilitate the implementation of asset management in manufacturing systems through predictive maintenance solutions leveraged by machine learning (ML). With DTs, a solution architecture can easily use data and software to implement asset management solutions such as condition monitoring and predictive maintenance using acquired sensor data from physical objects and computing capabilities in the digital space. While DT offers a good solution, it is an emerging technology that could be improved with better standards, architectural framework, and implementation methodologies. Researchers in both academia and industry have showcased DT implementations with different levels of success. However, DTs remain limited in standards and architectures that offer efficient predictive maintenance solutions with real-time sensor data and intelligent DT capabilities. An appropriate feedback mechanism is also needed to improve asset management operations. Full article
(This article belongs to the Section Internet of Things)
Show Figures

Figure 1

16 pages, 1612 KiB  
Article
Using a Slit to Suppress Optical Aberrations in Laser Triangulation Sensors
by Steven Pigeon and Benjamin Lapointe-Pinel
Sensors 2024, 24(8), 2662; https://doi.org/10.3390/s24082662 - 22 Apr 2024
Viewed by 568
Abstract
In this paper, we present a laser triangulation sensor to measure the distance between the sensor and an object without contact using a diffraction slit rather than a traditional lens. We show that by replacing the lens with a slit, we can exploit [...] Read more.
In this paper, we present a laser triangulation sensor to measure the distance between the sensor and an object without contact using a diffraction slit rather than a traditional lens. We show that by replacing the lens with a slit, we can exploit the resulting diffraction pattern to have finer and yet simpler image analysis, yielding better estimation of the distance to the object. To test our hypothesis, we build a precision position table and a laser triangulation sensor, generate large data sets to test different estimation algorithms on various materials, and compare data acquisition using a traditional lens versus using a slit. We show that position estimation when using a slit is both more precise and more accurate than comparable methods using a lens. Full article
Show Figures

Figure 1

25 pages, 8576 KiB  
Article
Fault Diagnosis of Hydraulic Components Based on Multi-Sensor Information Fusion Using Improved TSO-CNN-BiLSTM
by Da Zhang, Kun Zheng, Fuqi Liu and Beili Li
Sensors 2024, 24(8), 2661; https://doi.org/10.3390/s24082661 - 22 Apr 2024
Viewed by 439
Abstract
In order to realize the accurate and reliable fault diagnosis of hydraulic systems, a diagnostic model based on improved tuna swarm optimization (ITSO), optimized convolutional neural networks (CNNs), and bi-directional long short-term memory (BiLSTM) networks is proposed. Firstly, sensor selection is implemented using [...] Read more.
In order to realize the accurate and reliable fault diagnosis of hydraulic systems, a diagnostic model based on improved tuna swarm optimization (ITSO), optimized convolutional neural networks (CNNs), and bi-directional long short-term memory (BiLSTM) networks is proposed. Firstly, sensor selection is implemented using the random forest algorithm to select useful signals from six kinds of physical or virtual sensors including pressure, temperature, flow rate, vibration, motor power, and motor efficiency coefficient. After that, fused features are extracted by CNN, and then, BiLSTM is applied to learn the forward and backward information contained in the data. The ITSO algorithm is adopted to adaptively optimize the learning rate, regularization coefficient, and node number to obtain the optimal CNN-BiLSTM network. Improved Chebyshev chaotic mapping and the nonlinear reduction strategy are adopted to improve population initialization and individual position updating, further promoting the optimization effect of TSO. The experimental results show that the proposed method can automatically extract fusion features and effectively utilize multi-sensor information. The diagnostic accuracies of the plunger pump, cooler, throttle valve, and accumulator are 99.07%, 99.4%, 98.81%, and 98.51%, respectively. The diagnostic results of noisy data with 0 dB, 5 dB, and 10 dB signal-to-noise ratios (SNRs) show that the ITSO-CNN-BiLSTM model has good robustness to noise interference. Full article
(This article belongs to the Section Fault Diagnosis & Sensors)
Show Figures

Figure 1

18 pages, 8309 KiB  
Article
Convolutional Neural Network-Based Pattern Recognition of Partial Discharge in High-Speed Electric-Multiple-Unit Cable Termination
by Chuanming Sun, Guangning Wu, Guixiang Pan, Tingyu Zhang, Jiali Li, Shibo Jiao, Yong-Chao Liu, Kui Chen, Kai Liu, Dongli Xin and Guoqiang Gao
Sensors 2024, 24(8), 2660; https://doi.org/10.3390/s24082660 - 22 Apr 2024
Cited by 2 | Viewed by 583
Abstract
Partial discharge detection is considered a crucial technique for evaluating insulation performance and identifying defect types in cable terminals of high-speed electric multiple units (EMUs). In this study, terminal samples exhibiting four typical defects were prepared from high-speed EMUs. A cable discharge testing [...] Read more.
Partial discharge detection is considered a crucial technique for evaluating insulation performance and identifying defect types in cable terminals of high-speed electric multiple units (EMUs). In this study, terminal samples exhibiting four typical defects were prepared from high-speed EMUs. A cable discharge testing system, utilizing high-frequency current sensing, was developed to collect discharge signals, and datasets corresponding to these defects were established. This study proposes the use of the convolutional neural network (CNN) for the classification of discharge signals associated with specific defects, comparing this method with two existing neural network (NN)-based classification models that employ the back-propagation NN and the radial basis function NN, respectively. The comparative results demonstrate that the CNN-based model excels in accurately identifying signals from various defect types in the cable terminals of high-speed EMUs, surpassing the two existing NN-based classification models. Full article
(This article belongs to the Section Fault Diagnosis & Sensors)
Show Figures

Figure 1

26 pages, 4982 KiB  
Article
Reengineering Indoor Air Quality Monitoring Systems to Improve End-User Experience
by Radu Nicolae Pietraru, Adriana Olteanu, Ioana-Raluca Adochiei and Felix-Constantin Adochiei
Sensors 2024, 24(8), 2659; https://doi.org/10.3390/s24082659 - 22 Apr 2024
Viewed by 663
Abstract
This paper presents an indoor air quality (IAQ) monitoring system designed for a better end-user experience. The monitoring system consists of elements, from the monitoring sensor to the monitoring interface, designed and implemented by the research team, especially for the proposed monitoring system. [...] Read more.
This paper presents an indoor air quality (IAQ) monitoring system designed for a better end-user experience. The monitoring system consists of elements, from the monitoring sensor to the monitoring interface, designed and implemented by the research team, especially for the proposed monitoring system. The monitoring solution is intended for users who live in houses without automatic ventilation systems. The air quality sensor is designed at a minimum cost and complexity to allow multi-zone implementation without significant effort. The user interface uses a spatial graphic representation that facilitates understanding areas with different air quality levels. Presentation of the outdoor air quality level supports the user’s decision to ventilate a space. An innovative element of the proposed monitoring interface is the real-time forecast of air quality evolution in each monitored space. The paper describes the implementation of an original monitoring solution (monitoring device, Edge/Cloud management system, innovative user monitoring interface) and presents the results of testing this system in a relevant environment. The research conclusions show the proposed solution’s benefits in improving the end-user experience, justified both by the technical results obtained and by the opinion of the users who tested the monitoring system. Full article
(This article belongs to the Special Issue Internet of Things and Sensor Technologies in Smart Agriculture)
Show Figures

Figure 1

13 pages, 2623 KiB  
Article
Tunable High-Sensitivity Four-Frequency Refractive Index Sensor Based on Graphene Metamaterial
by Xu Bao, Shujun Yu, Wenqiang Lu, Zhiqiang Hao, Zao Yi, Shubo Cheng, Bin Tang, Jianguo Zhang, Chaojun Tang and Yougen Yi
Sensors 2024, 24(8), 2658; https://doi.org/10.3390/s24082658 - 22 Apr 2024
Viewed by 527
Abstract
As graphene-related technology advances, the benefits of graphene metamaterials become more apparent. In this study, a surface-isolated exciton-based absorber is built by running relevant simulations on graphene, which can achieve more than 98% perfect absorption at multiple frequencies in the MWIR (MediumWavelength Infra-Red [...] Read more.
As graphene-related technology advances, the benefits of graphene metamaterials become more apparent. In this study, a surface-isolated exciton-based absorber is built by running relevant simulations on graphene, which can achieve more than 98% perfect absorption at multiple frequencies in the MWIR (MediumWavelength Infra-Red (MWIR) band as compared to the typical absorber. The absorber consists of three layers: the bottom layer is gold, the middle layer is dielectric, and the top layer is patterned with graphene. Tunability was achieved by electrically altering graphene’s Fermi energy, hence the position of the absorption peak. The influence of graphene’s relaxation time on the sensor is discussed. Due to the symmetry of its structure, different angles of light source incidence have little effect on the absorption rate, leading to polarization insensitivity, especially for TE waves, and this absorber has polarization insensitivity at ultra-wide-angle degrees. The sensor is characterized by its tunability, polarisation insensitivity, and high sensitivity, with a sensitivity of up to 21.60 THz/refractive index unit (RIU). This paper demonstrates the feasibility of the multi-frequency sensor and provides a theoretical basis for the realization of the multi-frequency sensor. This makes it possible to apply it to high-sensitivity sensors. Full article
(This article belongs to the Special Issue Terahertz Sensors)
Show Figures

Figure 1

18 pages, 5214 KiB  
Article
Adaptive Cruise Control Based on Safe Deep Reinforcement Learning
by Rui Zhao, Kui Wang, Wenbo Che, Yun Li, Yuze Fan and Fei Gao
Sensors 2024, 24(8), 2657; https://doi.org/10.3390/s24082657 - 22 Apr 2024
Viewed by 599
Abstract
Adaptive cruise control (ACC) enables efficient, safe, and intelligent vehicle control by autonomously adjusting speed and ensuring a safe following distance from the vehicle in front. This paper proposes a novel adaptive cruise system, namely the Safety-First Reinforcement Learning Adaptive Cruise Control (SFRL-ACC). [...] Read more.
Adaptive cruise control (ACC) enables efficient, safe, and intelligent vehicle control by autonomously adjusting speed and ensuring a safe following distance from the vehicle in front. This paper proposes a novel adaptive cruise system, namely the Safety-First Reinforcement Learning Adaptive Cruise Control (SFRL-ACC). This system aims to leverage the model-free nature and high real-time inference efficiency of Deep Reinforcement Learning (DRL) to overcome the challenges of modeling difficulties and lower computational efficiency faced by current optimization control-based ACC methods while simultaneously maintaining safety advantages and optimizing ride comfort. Firstly, we transform the ACC problem into a safe DRL formulation Constrained Markov Decision Process (CMDP) by carefully designing state, action, reward, and cost functions. Subsequently, we propose the Projected Constrained Policy Optimization (PCPO)-based ACC Algorithm SFRL-ACC, which is specifically tailored to solve the CMDP problem. PCPO incorporates safety constraints that further restrict the trust region formed by the Kullback–Leibler (KL) divergence, facilitating DRL policy updates that maximize performance while keeping safety costs within their limit bounds. Finally, we train an SFRL-ACC policy and compare its computation time, traffic efficiency, ride comfort, and safety with state-of-the-art MPC-based ACC control methods. The experimental results prove the superiority of the proposed method in the aforementioned performance aspects. Full article
(This article belongs to the Section Vehicular Sensing)
Show Figures

Figure 1

17 pages, 294 KiB  
Review
Recent Advances in Intelligent Algorithms for Fault Detection and Diagnosis
by Paolo Mercorelli
Sensors 2024, 24(8), 2656; https://doi.org/10.3390/s24082656 - 22 Apr 2024
Viewed by 682
Abstract
Fault-finding diagnostics is a model-driven approach that identifies a system’s malfunctioning portion. It uses residual generators to identify faults, and various methods like isolation techniques and structural analysis are used. However, diagnostic equipment doesn’t measure the remaining signal-to-noise ratio. Residual selection identifies fault-detecting [...] Read more.
Fault-finding diagnostics is a model-driven approach that identifies a system’s malfunctioning portion. It uses residual generators to identify faults, and various methods like isolation techniques and structural analysis are used. However, diagnostic equipment doesn’t measure the remaining signal-to-noise ratio. Residual selection identifies fault-detecting generators. Fault detective diagnostic (FDD) approaches have been investigated and implemented for various industrial processes. However, industrial operations make it difficult to implement FDD techniques. To bridge the gap between theoretical methodologies and implementations, hybrid approaches and intelligent procedures are needed. Future research should focus on improving fault prognosis, allowing for accurate prediction of process failures and avoiding safety hazards. Real-time and comprehensive FDD strategies should be implemented in the age of big data. Full article
(This article belongs to the Special Issue Trends and Applications in Sensor Fault Diagnosis)
Show Figures

Figure 1

20 pages, 1826 KiB  
Article
Prototype Learning for Medical Time Series Classification via Human–Machine Collaboration
by Jia Xie, Zhu Wang, Zhiwen Yu, Yasan Ding and Bin Guo
Sensors 2024, 24(8), 2655; https://doi.org/10.3390/s24082655 - 22 Apr 2024
Viewed by 564
Abstract
Deep neural networks must address the dual challenge of delivering high-accuracy predictions and providing user-friendly explanations. While deep models are widely used in the field of time series modeling, deciphering the core principles that govern the models’ outputs remains a significant challenge. This [...] Read more.
Deep neural networks must address the dual challenge of delivering high-accuracy predictions and providing user-friendly explanations. While deep models are widely used in the field of time series modeling, deciphering the core principles that govern the models’ outputs remains a significant challenge. This is crucial for fostering the development of trusted models and facilitating domain expert validation, thereby empowering users and domain experts to utilize them confidently in high-risk decision-making contexts (e.g., decision-support systems in healthcare). In this work, we put forward a deep prototype learning model that supports interpretable and manipulable modeling and classification of medical time series (i.e., ECG signal). Specifically, we first optimize the representation of single heartbeat data by employing a bidirectional long short-term memory and attention mechanism, and then construct prototypes during the training phase. The final classification outcomes (i.e., normal sinus rhythm, atrial fibrillation, and other rhythm) are determined by comparing the input with the obtained prototypes. Moreover, the proposed model presents a human–machine collaboration mechanism, allowing domain experts to refine the prototypes by integrating their expertise to further enhance the model’s performance (contrary to the human-in-the-loop paradigm, where humans primarily act as supervisors or correctors, intervening when required, our approach focuses on a human–machine collaboration, wherein both parties engage as partners, enabling more fluid and integrated interactions). The experimental outcomes presented herein delineate that, within the realm of binary classification tasks—specifically distinguishing between normal sinus rhythm and atrial fibrillation—our proposed model, albeit registering marginally lower performance in comparison to certain established baseline models such as Convolutional Neural Networks (CNNs) and bidirectional long short-term memory with attention mechanisms (Bi-LSTMAttns), evidently surpasses other contemporary state-of-the-art prototype baseline models. Moreover, it demonstrates significantly enhanced performance relative to these prototype baseline models in the context of triple classification tasks, which encompass normal sinus rhythm, atrial fibrillation, and other rhythm classifications. The proposed model manifests a commendable prediction accuracy of 0.8414, coupled with macro precision, recall, and F1-score metrics of 0.8449, 0.8224, and 0.8235, respectively, achieving both high classification accuracy as well as good interpretability. Full article
(This article belongs to the Special Issue Sensors Technology and Application in ECG Signal Processing)
Show Figures

Figure 1

20 pages, 5430 KiB  
Article
Gain and Bandwidth Enhancement of 3D-Printed Short Backfire Antennas Using Rim Flaring and Iris Matching
by Yewande Mariam Aragbaiye and Dustin Isleifson
Sensors 2024, 24(8), 2654; https://doi.org/10.3390/s24082654 - 22 Apr 2024
Viewed by 585
Abstract
In this article, we present new design techniques to improve the gain and impedance bandwidth of short backfire antennas. For the gain enhancement procedure, our approach was to flare the rim of the antenna, which simultaneously led to an increase in the impedance [...] Read more.
In this article, we present new design techniques to improve the gain and impedance bandwidth of short backfire antennas. For the gain enhancement procedure, our approach was to flare the rim of the antenna, which simultaneously led to an increase in the impedance bandwidth of the antenna. Parametric studies were carried out to obtain the optimal flaring angle. The peak realized gain was obtained as 17.2 dBi with an impedance bandwidth of 55% (2.4 dB and 28.6% increase in gain and bandwidth, respectively, compared to the unflared antenna). To further enhance the impedance bandwidth, an inductive iris was added to improve impedance matching at the waveguide aperture. We varied the width of the iris to obtain the optimal width that provided the best gain and impedance bandwidth result of 17.1 dBi and 66% (~40% increase compared to the unflared antenna without iris). To experimentally verify the work, prototypes were fabricated and tested. We found good agreement between simulation and measurement. The results of this study indicate that gain and bandwidth can be enhanced through optimized geometrical modification of the SBF structure. Furthermore, our 3D-printed technique demonstrates a mass reduction compared with conventional metallic structures. Full article
(This article belongs to the Section Physical Sensors)
Show Figures

Figure 1

25 pages, 13193 KiB  
Article
FPGA-Microprocessor Based Sensor for Faults Detection in Induction Motors Using Time-Frequency and Machine Learning Methods
by Roque Alfredo Osornio-Rios, Isaias Cueva-Perez, Alvaro Ivan Alvarado-Hernandez, Larisa Dunai, Israel Zamudio-Ramirez and Jose Alfonso Antonino-Daviu
Sensors 2024, 24(8), 2653; https://doi.org/10.3390/s24082653 - 22 Apr 2024
Viewed by 1006
Abstract
Induction motors (IM) play a fundamental role in the industrial sector because they are robust, efficient, and low-cost machines. Changes in the environment, installation errors, or modifications to working conditions can generate faults in induction motors. The trend on IM fault detection is [...] Read more.
Induction motors (IM) play a fundamental role in the industrial sector because they are robust, efficient, and low-cost machines. Changes in the environment, installation errors, or modifications to working conditions can generate faults in induction motors. The trend on IM fault detection is focused on the design techniques and sensors capable of evaluating multiple faults with various signals using non-invasive analysis. The methodology is based on processing electric current signals by applying the short-time Fourier transform (STFT). Additionally, the computation of the mean and standard deviation of infrared thermograms is proposed as main indicators. The proposed system combines both parameters by means of Support Vector Machine and k-nearest-neighbor classifiers. The development of the diagnostic system was done with digital hardware implementations using a Xilinx PYNQ Z2 card that integrates an FPGA with a microprocessor, thus taking advantage of the acquisition and processing of digital signals and images in hardware. The proposed method has proved to be effective for the classification of healthy (HLT), misalignment (MAMT), unbalance (UNB), damaged bearing (BDF), and broken rotor bar (BRB) faults with an accuracy close to 99%. Full article
(This article belongs to the Special Issue Feature Papers in Fault Diagnosis & Sensors 2024)
Show Figures

Figure 1

24 pages, 11197 KiB  
Article
Machine Tool Wear Prediction Technology Based on Multi-Sensor Information Fusion
by Kang Wang, Aimin Wang, Long Wu and Guangjun Xie
Sensors 2024, 24(8), 2652; https://doi.org/10.3390/s24082652 - 21 Apr 2024
Viewed by 692
Abstract
The intelligent monitoring of cutting tools used in the manufacturing industry is steadily becoming more convenient. To accurately predict the state of tools and tool breakages, this study proposes a tool wear prediction technique based on multi-sensor information fusion. First, the vibrational, current, [...] Read more.
The intelligent monitoring of cutting tools used in the manufacturing industry is steadily becoming more convenient. To accurately predict the state of tools and tool breakages, this study proposes a tool wear prediction technique based on multi-sensor information fusion. First, the vibrational, current, and cutting force signals transmitted during the machining process were collected, and the features were extracted. Next, the Kalman filtering algorithm was used for feature fusion, and a predictive model for tool wear was constructed by combining the ResNet and long short-term memory (LSTM) models (called ResNet-LSTM). Experimental data for thin-walled parts obtained under various machining conditions were utilized to monitor the changes in tool conditions. A comparison between the ResNet and LSTM tool wear prediction models indicated that the proposed ResNet-LSTM model significantly improved the prediction accuracy compared to the individual LSTM and ResNet models. Moreover, ResNet-LSTM exhibited adaptive noise reduction capabilities at the front end of the network for signal feature extraction, thereby enhancing the signal feature extraction capability. The ResNet-LSTM model yielded an average prediction error of 0.0085 mm and a tool wear prediction accuracy of 98.25%. These results validate the feasibility of the tool wear prediction method proposed in this study. Full article
(This article belongs to the Section Fault Diagnosis & Sensors)
Show Figures

Figure 1

14 pages, 730 KiB  
Article
Robust Cooperative Fault-Tolerant Control for Uncertain Multi-Agent Systems Subject to Actuator Faults
by Jiantao Shi, Xiang Chen, Shuangqing Xing, Anning Liu and Chuang Chen
Sensors 2024, 24(8), 2651; https://doi.org/10.3390/s24082651 - 21 Apr 2024
Viewed by 497
Abstract
This article investigates the robust cooperative fault-tolerant control problem of multi-agent systems subject to mismatched uncertainties and actuator faults. During the design process of the intermediate variable estimator, there is no need to satisfy fault estimation matching conditions, and this overcomes a crucial [...] Read more.
This article investigates the robust cooperative fault-tolerant control problem of multi-agent systems subject to mismatched uncertainties and actuator faults. During the design process of the intermediate variable estimator, there is no need to satisfy fault estimation matching conditions, and this overcomes a crucial constraint of traditional observers and estimators. The feedback term of the designed estimator contains the centralized estimation errors and the distributed estimation errors of the agent, and this further improves the design freedom of the proposed estimator. A novel fault-tolerant control protocol is designed based on the fault estimation information. In this work, the bounds of the fault and its derivatives are unknown, and the considered method is applicable to both directed and undirected multi-agent systems. Furthermore, the parameters of the estimator are determined through the resolution of a linear matrix inequality (LMI), which is decoupled by employing coordinate transformation and Schur decomposition. Lastly, a numerical simulation result is used to demonstrate the effectiveness of the proposed method. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
Show Figures

Figure 1

14 pages, 8041 KiB  
Article
Vehicle-Type Recognition Method for Images Based on Improved Faster R-CNN Model
by Tong Bai, Jiasai Luo, Sen Zhou, Yi Lu and Yuanfa Wang
Sensors 2024, 24(8), 2650; https://doi.org/10.3390/s24082650 - 21 Apr 2024
Viewed by 556
Abstract
The rapid increase in the number of vehicles has led to increasing traffic congestion, traffic accidents, and motor vehicle crime rates. The management of various parking lots has also become increasingly challenging. Vehicle-type recognition technology can reduce the workload of humans in vehicle [...] Read more.
The rapid increase in the number of vehicles has led to increasing traffic congestion, traffic accidents, and motor vehicle crime rates. The management of various parking lots has also become increasingly challenging. Vehicle-type recognition technology can reduce the workload of humans in vehicle management operations. Therefore, the application of image technology for vehicle-type recognition is of great significance for integrated traffic management. In this paper, an improved faster region with convolutional neural network features (Faster R-CNN) model was proposed for vehicle-type recognition. Firstly, the output features of different convolution layers were combined to improve the recognition accuracy. Then, the average precision (AP) of the recognition model was improved through the contextual features of the original image and the object bounding box optimization strategy. Finally, the comparison experiment used the vehicle image dataset of three vehicle types, including cars, sports utility vehicles (SUVs), and vans. The experimental results show that the improved recognition model can effectively identify vehicle types in the images. The AP of the three vehicle types is 83.2%, 79.2%, and 78.4%, respectively, and the mean average precision (mAP) is 1.7% higher than that of the traditional Faster R-CNN model. Full article
(This article belongs to the Section Sensing and Imaging)
Show Figures

Figure 1

16 pages, 3983 KiB  
Article
Implementing Gait Kinematic Trajectory Forecasting Models on an Embedded System
by Madina Shayne, Leonardo A. Molina, Bin Hu and Taylor Chomiak
Sensors 2024, 24(8), 2649; https://doi.org/10.3390/s24082649 - 21 Apr 2024
Viewed by 591
Abstract
Smart algorithms for gait kinematic motion prediction in wearable assistive devices including prostheses, bionics, and exoskeletons can ensure safer and more effective device functionality. Although embedded systems can support the use of smart algorithms, there are important limitations associated with computational load. This [...] Read more.
Smart algorithms for gait kinematic motion prediction in wearable assistive devices including prostheses, bionics, and exoskeletons can ensure safer and more effective device functionality. Although embedded systems can support the use of smart algorithms, there are important limitations associated with computational load. This poses a tangible barrier for models with increased complexity that demand substantial computational resources for superior performance. Forecasting through Recurrent Topology (FReT) represents a computationally lightweight time-series data forecasting algorithm with the ability to update and adapt to the input data structure that can predict complex dynamics. Here, we deployed FReT on an embedded system and evaluated its accuracy, computational time, and precision to forecast gait kinematics from lower-limb motion sensor data from fifteen subjects. FReT was compared to pretrained hyperparameter-optimized NNET and deep-NNET (D-NNET) model architectures, both with static model weight parameters and iteratively updated model weight parameters to enable adaptability to evolving data structures. We found that FReT was not only more accurate than all the network models, reducing the normalized root-mean-square error by almost half on average, but that it also provided the best balance between accuracy, computational time, and precision when considering the combination of these performance variables. The proposed FReT framework on an embedded system, with its improved performance, represents an important step towards the development of new sensor-aided technologies for assistive ambulatory devices. Full article
(This article belongs to the Special Issue Sensor Technologies for Gait Analysis: 2nd Edition)
Show Figures

Figure 1

22 pages, 597 KiB  
Article
Understanding the Nonlinear Response of SiPMs
by Víctor Moya-Zamanillo and Jaime Rosado
Sensors 2024, 24(8), 2648; https://doi.org/10.3390/s24082648 - 21 Apr 2024
Viewed by 464
Abstract
A systematic study of the nonlinear response of Silicon Photomultipliers (SiPMs) was conducted through Monte Carlo (MC) simulations. The MC code was validated against experimental data for two different SiPMs. Nonlinearity mainly depends on the balance between the photon rate and the pixel [...] Read more.
A systematic study of the nonlinear response of Silicon Photomultipliers (SiPMs) was conducted through Monte Carlo (MC) simulations. The MC code was validated against experimental data for two different SiPMs. Nonlinearity mainly depends on the balance between the photon rate and the pixel recovery time. Additionally, nonlinearity has been found to depend on the light pulse shape, the correlated noise, the overvoltage dependence of the photon detection efficiency, and the impedance of the readout circuit. Correlated noise has been shown to have a minor impact on nonlinearity, but it can significantly affect the shape of the SiPM output current. Considering these dependencies and a previous statistical analysis of the nonlinear response of SiPMs, two phenomenological fitting models were proposed for exponential-like and finite light pulses, explaining the roles of their various terms and parameters. These models provide an accurate description of the nonlinear responses of SiPMs at the level of a few percentages for a wide range of situations. Full article
(This article belongs to the Special Issue Precision Optical Metrology and Smart Sensing)
Show Figures

Graphical abstract

32 pages, 2237 KiB  
Review
Smart Sensors and Smart Data for Precision Agriculture: A Review
by Abdellatif Soussi, Enrico Zero, Roberto Sacile, Daniele Trinchero and Marco Fossa
Sensors 2024, 24(8), 2647; https://doi.org/10.3390/s24082647 - 21 Apr 2024
Viewed by 1946
Abstract
Precision agriculture, driven by the convergence of smart sensors and advanced technologies, has emerged as a transformative force in modern farming practices. The present review synthesizes insights from a multitude of research papers, exploring the dynamic landscape of precision agriculture. The main focus [...] Read more.
Precision agriculture, driven by the convergence of smart sensors and advanced technologies, has emerged as a transformative force in modern farming practices. The present review synthesizes insights from a multitude of research papers, exploring the dynamic landscape of precision agriculture. The main focus is on the integration of smart sensors, coupled with technologies such as the Internet of Things (IoT), big data analytics, and Artificial Intelligence (AI). This analysis is set in the context of optimizing crop management, using resources wisely, and promoting sustainability in the agricultural sector. This review aims to provide an in-depth understanding of emerging trends and key developments in the field of precision agriculture. By highlighting the benefits of integrating smart sensors and innovative technologies, it aspires to enlighten farming practitioners, researchers, and policymakers on best practices, current challenges, and prospects. It aims to foster a transition towards more sustainable, efficient, and intelligent farming practices while encouraging the continued adoption and adaptation of new technologies. Full article
(This article belongs to the Special Issue Feature Review Papers in Intelligent Sensors)
Show Figures

Figure 1

15 pages, 1409 KiB  
Article
A gm/ID-Based Low-Power LNA for Ka-Band Applications
by David Galante-Sempere, Jeffrey Torres-Clarke, Javier del Pino and Sunil Lalchand Khemchandani
Sensors 2024, 24(8), 2646; https://doi.org/10.3390/s24082646 - 21 Apr 2024
Viewed by 481
Abstract
This article presents the design of a low-power low noise amplifier (LNA) implemented in 45 nm silicon-on-insulator (SOI) technology using the gm/ID methodology. The Ka-band LNA achieves a very low power consumption of only 1.98 mW andis the first [...] Read more.
This article presents the design of a low-power low noise amplifier (LNA) implemented in 45 nm silicon-on-insulator (SOI) technology using the gm/ID methodology. The Ka-band LNA achieves a very low power consumption of only 1.98 mW andis the first time the gm/ID approach is applied at such a high frequency. The circuit is suitable for Ka-band applications with a central frequency of 28 GHz, as the circuit is intended to operate in the n257 frequency band defined by the 3GPP 5G new radio (NR) specification. The proposed cascode LNA uses the gm/ID methodology in an RF/MW scenario to exploit the advantages of moderate inversion region operation. The circuit occupies a total area of 1.23 mm2 excluding pads and draws 1.98 mW from a DC supply of 0.9 V. Post-layout simulation results reveal a total gain of 11.4 dB, a noise figure (NF) of 3.8 dB, and an input return loss (IRL) better than 12 dB. Compared to conventional circuits, this design obtains a remarkable figure of merit (FoM) as the LNA reports a gain and NF in line with other approaches with very low power consumption. Full article
(This article belongs to the Section Electronic Sensors)
Show Figures

Figure 1

11 pages, 6084 KiB  
Article
Exploring Human–Exoskeleton Interaction Dynamics: An In-Depth Analysis of Knee Flexion–Extension Performance across Varied Robot Assistance–Resistance Configurations
by Denis Mosconi, Yecid Moreno and Adriano Siqueira
Sensors 2024, 24(8), 2645; https://doi.org/10.3390/s24082645 - 21 Apr 2024
Viewed by 615
Abstract
Knee rehabilitation therapy after trauma or neuromotor diseases is fundamental to restore the joint functions as best as possible, exoskeleton robots being an important resource in this context, since they optimize therapy by applying tailored forces to assist or resist movements, contributing to [...] Read more.
Knee rehabilitation therapy after trauma or neuromotor diseases is fundamental to restore the joint functions as best as possible, exoskeleton robots being an important resource in this context, since they optimize therapy by applying tailored forces to assist or resist movements, contributing to improved patient outcomes and treatment efficiency. One of the points that must be taken into account when using robots in rehabilitation is their interaction with the patient, which must be safe for both and guarantee the effectiveness of the treatment. Therefore, the objective of this study was to assess the interaction between humans and an exoskeleton during the execution of knee flexion–extension movements under various configurations of robot assistance and resistance. The evaluation encompassed considerations of myoelectric activity, muscle recruitment, robot torque, and performed movement. To achieve this, an experimental protocol was implemented, involving an individual wearing the exoskeleton and executing knee flexion–extension motions while seated, with the robot configured in five distinct modes: passive (P), assistance on flexion (FA), assistance on extension (EA), assistance on flexion and extension (CA), and resistance on flexion and extension (CR). Results revealed distinctive patterns of movement and muscle recruitment for each mode, highlighting the complex interplay between human and robot; for example, the largest RMS tracking errors were for the EA mode (13.72 degrees) while the smallest for the CR mode (4.47 degrees), a non-obvious result; in addition, myoelectric activity was demonstrated to be greater for the completely assisted mode than without the robot (the maximum activation levels for the vastus medialis and vastus lateralis muscles were more than double those when the user had assistance from the robot). Tracking errors, muscle activations, and torque values varied across modes, emphasizing the need for careful consideration in configuring exoskeleton assistance and resistance to ensure effective and safe rehabilitation. Understanding these human–robot interactions is essential for developing precise rehabilitation programs, optimizing treatment effectiveness, and enhancing patient safety. Full article
Show Figures

Figure 1

10 pages, 2750 KiB  
Article
Characterization of Running Intensity in Canadian Football Based on Tactical Position
by Abdullah Zafar, Samuel Guay, Sophie-Andrée Vinet, Amélie Apinis-Deshaies, Raphaëlle Creniault, Géraldine Martens, François Prince and Louis De Beaumont
Sensors 2024, 24(8), 2644; https://doi.org/10.3390/s24082644 - 21 Apr 2024
Viewed by 649
Abstract
This study aimed to use a data-driven approach to identify individualized speed thresholds to characterize running demands and athlete workload during games and practices in skill and linemen football players. Data were recorded from wearable sensors over 28 sessions from 30 male Canadian [...] Read more.
This study aimed to use a data-driven approach to identify individualized speed thresholds to characterize running demands and athlete workload during games and practices in skill and linemen football players. Data were recorded from wearable sensors over 28 sessions from 30 male Canadian varsity football athletes, resulting in a total of 287 performances analyzed, including 137 games and 150 practices, using a global positioning system. Speed zones were identified for each performance by fitting a 5-dimensional Gaussian mixture model (GMM) corresponding to 5 running intensity zones from minimal (zone 1) to maximal (zone 5). Skill players had significantly higher (p < 0.001) speed thresholds, percentage of time spent, and distance covered in maximal intensity zones compared to linemen. The distance covered in game settings was significantly higher (p < 0.001) compared to practices. This study highlighted the use of individualized speed thresholds to determine running intensity and athlete workloads for American and Canadian football athletes, as well as compare running performances between practice and game scenarios. This approach can be used to monitor physical workload in athletes with respect to their tactical positions during practices and games, and to ensure that athletes are adequately trained to meet in-game physical demands. Full article
(This article belongs to the Special Issue Feature Papers in Wearables 2024)
Show Figures

Figure 1

11 pages, 1692 KiB  
Article
Electrochemical Impedance Spectroscopy for the Sensing of the Kinetic Parameters of Engineered Enzymes
by Adriána Dusíková, Timea Baranová, Ján Krahulec, Olívia Dakošová, Ján Híveš, Monika Naumowicz and Miroslav Gál
Sensors 2024, 24(8), 2643; https://doi.org/10.3390/s24082643 - 20 Apr 2024
Viewed by 618
Abstract
The study presents a promising approach to enzymatic kinetics using Electrochemical Impedance Spectroscopy (EIS) to assess fundamental parameters of modified enteropeptidases. Traditional methods for determining these parameters, while effective, often lack versatility and convenience, especially under varying environmental conditions. The use of EIS [...] Read more.
The study presents a promising approach to enzymatic kinetics using Electrochemical Impedance Spectroscopy (EIS) to assess fundamental parameters of modified enteropeptidases. Traditional methods for determining these parameters, while effective, often lack versatility and convenience, especially under varying environmental conditions. The use of EIS provides a novel approach that overcomes these limitations. The enteropeptidase underwent genetic modification through the introduction of single amino acid modifications to assess their effect on enzyme kinetics. However, according to the one-sample t-test results, the difference between the engineered enzymes and hEKL was not statistically significant by conventional criteria. The kinetic parameters were analyzed using fluorescence spectroscopy and EIS, which was found to be an effective tool for the real-time measurement of enzyme kinetics. The results obtained through EIS were not significantly different from those obtained through traditional fluorescence spectroscopy methods (p value >> 0.05). The study validates the use of EIS for measuring enzyme kinetics and provides insight into the effects of specific amino acid changes on enteropeptidase function. These findings have potential applications in biotechnology and biochemical research, suggesting a new method for rapidly assessing enzymatic activity. Full article
(This article belongs to the Special Issue Electrochemical Sensors: Technologies and Applications)
Show Figures

Figure 1

15 pages, 5504 KiB  
Article
A High-Quality Sample Generation Method for Improving Steel Surface Defect Inspection
by Yu He, Shuai Li, Xin Wen and Jing Xu
Sensors 2024, 24(8), 2642; https://doi.org/10.3390/s24082642 - 20 Apr 2024
Viewed by 437
Abstract
Defect inspection is a critical task in ensuring the surface quality of steel plates. Deep neural networks have the potential to achieve excellent inspection accuracy if defect samples are sufficient. Nevertheless, it is very different to collect enough samples using cameras alone. To [...] Read more.
Defect inspection is a critical task in ensuring the surface quality of steel plates. Deep neural networks have the potential to achieve excellent inspection accuracy if defect samples are sufficient. Nevertheless, it is very different to collect enough samples using cameras alone. To a certain extent, generative models can alleviate this problem but poor sample quality can greatly affect the final inspection performance. A sample generation method, which employs a generative adversarial network (GAN), is proposed to generate high-quality defect samples for training accurate inspection models. To improve generation quality, we propose a production-and-elimination, two-stage sample generation process by simulating the formation of defects on the surface of steel plates. The production stage learns to generate defects on defect-free background samples, and the elimination stage learns to erase defects on defective samples. By minimizing the differences between the samples at both stages, the proposed model can make generated background samples close to real ones while guiding the generated defect samples to be more realistic. Experimental results show that the proposed method has the ability to generate high-quality samples that can help train powerful inspection models and thereby improve inspection performance. Full article
(This article belongs to the Special Issue Multi-Modal Image Processing Methods, Systems, and Applications)
Show Figures

Figure 1

31 pages, 7204 KiB  
Article
COVID-19 Hierarchical Classification Using a Deep Learning Multi-Modal
by Albatoul S. Althenayan, Shada A. AlSalamah, Sherin Aly, Thamer Nouh, Bassam Mahboub, Laila Salameh, Metab Alkubeyyer and Abdulrahman Mirza
Sensors 2024, 24(8), 2641; https://doi.org/10.3390/s24082641 - 20 Apr 2024
Viewed by 656
Abstract
Coronavirus disease 2019 (COVID-19), originating in China, has rapidly spread worldwide. Physicians must examine infected patients and make timely decisions to isolate them. However, completing these processes is difficult due to limited time and availability of expert radiologists, as well as limitations of [...] Read more.
Coronavirus disease 2019 (COVID-19), originating in China, has rapidly spread worldwide. Physicians must examine infected patients and make timely decisions to isolate them. However, completing these processes is difficult due to limited time and availability of expert radiologists, as well as limitations of the reverse-transcription polymerase chain reaction (RT-PCR) method. Deep learning, a sophisticated machine learning technique, leverages radiological imaging modalities for disease diagnosis and image classification tasks. Previous research on COVID-19 classification has encountered several limitations, including binary classification methods, single-feature modalities, small public datasets, and reliance on CT diagnostic processes. Additionally, studies have often utilized a flat structure, disregarding the hierarchical structure of pneumonia classification. This study aims to overcome these limitations by identifying pneumonia caused by COVID-19, distinguishing it from other types of pneumonia and healthy lungs using chest X-ray (CXR) images and related tabular medical data, and demonstrate the value of incorporating tabular medical data in achieving more accurate diagnoses. Resnet-based and VGG-based pre-trained convolutional neural network (CNN) models were employed to extract features, which were then combined using early fusion for the classification of eight distinct classes. We leveraged the hierarchal structure of pneumonia classification within our approach to achieve improved classification outcomes. Since an imbalanced dataset is common in this field, a variety of versions of generative adversarial networks (GANs) were used to generate synthetic data. The proposed approach tested in our private datasets of 4523 patients achieved a macro-avg F1-score of 95.9% and an F1-score of 87.5% for COVID-19 identification using a Resnet-based structure. In conclusion, in this study, we were able to create an accurate deep learning multi-modal to diagnose COVID-19 and differentiate it from other kinds of pneumonia and normal lungs, which will enhance the radiological diagnostic process. Full article
(This article belongs to the Special Issue Advanced Deep Learning for Biomedical Sensing and Imaging)
Show Figures

Figure 1

18 pages, 2592 KiB  
Article
Personalized Machine Learning-Based Prediction of Wellbeing and Empathy in Healthcare Professionals
by Jason Nan, Matthew S. Herbert, Suzanna Purpura, Andrea N. Henneken, Dhakshin Ramanathan and Jyoti Mishra
Sensors 2024, 24(8), 2640; https://doi.org/10.3390/s24082640 - 20 Apr 2024
Viewed by 609
Abstract
Healthcare professionals are known to suffer from workplace stress and burnout, which can negatively affect their empathy for patients and quality of care. While existing research has identified factors associated with wellbeing and empathy in healthcare professionals, these efforts are typically focused on [...] Read more.
Healthcare professionals are known to suffer from workplace stress and burnout, which can negatively affect their empathy for patients and quality of care. While existing research has identified factors associated with wellbeing and empathy in healthcare professionals, these efforts are typically focused on the group level, ignoring potentially important individual differences and implications for individualized intervention approaches. In the current study, we implemented N-of-1 personalized machine learning (PML) to predict wellbeing and empathy in healthcare professionals at the individual level, leveraging ecological momentary assessments (EMAs) and smartwatch wearable data. A total of 47 mood and lifestyle feature variables (relating to sleep, diet, exercise, and social connections) were collected daily for up to three months followed by applying eight supervised machine learning (ML) models in a PML pipeline to predict wellbeing and empathy separately. Predictive insight into the model architecture was obtained using Shapley statistics for each of the best-fit personalized models, ranking the importance of each feature for each participant. The best-fit model and top features varied across participants, with anxious mood (13/19) and depressed mood (10/19) being the top predictors in most models. Social connection was a top predictor for wellbeing in 9/12 participants but not for empathy models (1/7). Additionally, empathy and wellbeing were the top predictors of each other in 64% of cases. These findings highlight shared and individual features of wellbeing and empathy in healthcare professionals and suggest that a one-size-fits-all approach to addressing modifiable factors to improve wellbeing and empathy will likely be suboptimal. In the future, such personalized models may serve as actionable insights for healthcare professionals that lead to increased wellness and quality of patient care. Full article
(This article belongs to the Special Issue Wearable Sensors for Continuous Health Monitoring and Analysis)
Show Figures

Figure 1

19 pages, 2230 KiB  
Article
Modelling Inductive Sensors for Arc Fault Detection in Aviation
by Gabriel Barroso-de-María, Guillermo Robles, Juan Manuel Martínez-Tarifa and Alexander Cuadrado
Sensors 2024, 24(8), 2639; https://doi.org/10.3390/s24082639 - 20 Apr 2024
Viewed by 501
Abstract
Modern aircraft are being equipped with high-voltage and direct current (HVDC) architectures to address the increase in electrical power. Unfortunately, the rise of voltage in low pressure environments brings about a problem with unexpected ionisation phenomena such as arcing. Series arcs in HVDC [...] Read more.
Modern aircraft are being equipped with high-voltage and direct current (HVDC) architectures to address the increase in electrical power. Unfortunately, the rise of voltage in low pressure environments brings about a problem with unexpected ionisation phenomena such as arcing. Series arcs in HVDC cannot be detected with conventional means, and finding methods to avoid the potentially catastrophic hazards of these events becomes critical to assure further development of more electric and all electric aviation. Inductive sensors are one of the most promising detectors in terms of sensitivity, cost, weight and adaptability to the circuit wiring in aircraft electric systems. In particular, the solutions based on the detection of the high-frequency (HF) pulses created by the arc have been found to be good candidates in practical applications. This paper proposes a method for designing series arc fault inductive sensors able to capture the aforementioned HF pulses. The methodology relies on modelling the parameters of the sensor based on the physics that intervenes in the HF pulses interaction with the sensor itself. To this end, a comparative analysis with different topologies is carried out. For every approach, the key parameters influencing the HF pulses detection are studied theoretically, modelled with a finite elements method and tested in the laboratory in terms of frequency response. The final validation tests were conducted using the prototypes in real cases of detection of DC series arcs. Full article
(This article belongs to the Section Physical Sensors)
Show Figures

Figure 1

14 pages, 3798 KiB  
Article
Automatic Detection of the Running Surface of Railway Tracks Based on Laser Profilometer Data and Supervised Machine Learning
by Florian Mauz, Remo Wigger, Alexandru-Elisiu Gota and Michal Kuffa
Sensors 2024, 24(8), 2638; https://doi.org/10.3390/s24082638 - 20 Apr 2024
Viewed by 549
Abstract
The measurement of the longitudinal rail profile is relevant to the condition monitoring of the rail infrastructure. The running surface is recognizable as a shiny metallic area on top of the rail head. The detection of the running surface is crucial for vehicle-based [...] Read more.
The measurement of the longitudinal rail profile is relevant to the condition monitoring of the rail infrastructure. The running surface is recognizable as a shiny metallic area on top of the rail head. The detection of the running surface is crucial for vehicle-based rail profile measurements, as well as for defect detection. This paper presents a methodology for the automatic detection of the running surface based on a laser profilometer. The detection of the running surface is performed based on the light reflected from the rail surface. Three rail surfaces with different surface conditions are considered. Supervised machine learning is applied to classify individual surface elements as part of the running surface. Detection by a linear support vector machine is performed with accuracy of >90%. The lateral position of the running surface and its width are calculated. The average deviation from the labeled widths varies between 1.2mm and 5.6mm. The proposed measurement approach could be installed on a train for the future onboard monitoring of the rail network. Full article
(This article belongs to the Section Vehicular Sensing)
Show Figures

Figure 1

39 pages, 61918 KiB  
Article
Learning Ground Displacement Signals Directly from InSAR-Wrapped Interferograms
by Lama Moualla, Alessio Rucci, Giampiero Naletto and Nantheera Anantrasirichai
Sensors 2024, 24(8), 2637; https://doi.org/10.3390/s24082637 - 20 Apr 2024
Viewed by 450
Abstract
Monitoring ground displacements identifies potential geohazard risks early before they cause critical damage. Interferometric synthetic aperture radar (InSAR) is one of the techniques that can monitor these displacements with sub-millimeter accuracy. However, using the InSAR technique is challenging due to the need for [...] Read more.
Monitoring ground displacements identifies potential geohazard risks early before they cause critical damage. Interferometric synthetic aperture radar (InSAR) is one of the techniques that can monitor these displacements with sub-millimeter accuracy. However, using the InSAR technique is challenging due to the need for high expertise, large data volumes, and other complexities. Accordingly, the development of an automated system to indicate ground displacements directly from the wrapped interferograms and coherence maps could be highly advantageous. Here, we compare different machine learning algorithms to evaluate the feasibility of achieving this objective. The inputs for the implemented machine learning models were pixels selected from the filtered-wrapped interferograms of Sentinel-1, using a coherence threshold. The outputs were the same pixels labeled as fast positive, positive, fast negative, negative, and undefined movements. These labels were assigned based on the velocity values of the measurement points located within the pixels. We used the Parallel Small Baseline Subset service of the European Space Agency’s GeoHazards Exploitation Platform to create the necessary interferograms, coherence, and deformation velocity maps. Subsequently, we applied a high-pass filter to the wrapped interferograms to separate the displacement signal from the atmospheric errors. We successfully identified the patterns associated with slow and fast movements by discerning the unique distributions within the matrices representing each movement class. The experiments included three case studies (from Italy, Portugal, and the United States), noted for their high sensitivity to landslides. We found that the Cosine K-nearest neighbor model achieved the best test accuracy. It is important to note that the test sets were not merely hidden parts of the training set within the same region but also included adjacent areas. We further improved the performance with pseudo-labeling, an approach aimed at evaluating the generalizability and robustness of the trained model beyond its immediate training environment. The lowest test accuracy achieved by the implemented algorithm was 80.1%. Furthermore, we used ArcGIS Pro 3.3 to compare the ground truth with the predictions to visualize the results better. The comparison aimed to explore indications of displacements affecting the main roads in the studied area. Full article
(This article belongs to the Special Issue Intelligent SAR Target Detection and Recognition)
Show Figures

Figure 1

30 pages, 1044 KiB  
Article
Comparative Analysis of Anomaly Detection Approaches in Firewall Logs: Integrating Light-Weight Synthesis of Security Logs and Artificially Generated Attack Detection
by Adrian Komadina, Ivan Kovačević, Bruno Štengl and Stjepan Groš
Sensors 2024, 24(8), 2636; https://doi.org/10.3390/s24082636 - 20 Apr 2024
Viewed by 435
Abstract
Detecting anomalies in large networks is a major challenge. Nowadays, many studies rely on machine learning techniques to solve this problem. However, much of this research depends on synthetic or limited datasets and tends to use specialized machine learning methods to achieve good [...] Read more.
Detecting anomalies in large networks is a major challenge. Nowadays, many studies rely on machine learning techniques to solve this problem. However, much of this research depends on synthetic or limited datasets and tends to use specialized machine learning methods to achieve good detection results. This study focuses on analyzing firewall logs from a large industrial control network and presents a novel method for generating anomalies that simulate real attacker actions within the network without the need for a dedicated testbed or installed security controls. To demonstrate that the proposed method is feasible and that the constructed logs behave as one would expect real-world logs to behave, different supervised and unsupervised learning models were compared using different feature subsets, feature construction methods, scaling methods, and aggregation levels. The experimental results show that unsupervised learning methods have difficulty in detecting the injected anomalies, suggesting that they can be seamlessly integrated into existing firewall logs. Conversely, the use of supervised learning methods showed significantly better performance compared to unsupervised approaches and a better suitability for use in real systems. Full article
(This article belongs to the Special Issue Recent Trends and Advances in Telecommunications and Sensing)
Show Figures

Figure 1

10 pages, 3601 KiB  
Article
Assessing the Impact of COVID-19 on Amateur Runners’ Performance: An Analysis through Monitoring Devices
by María García-Arrabé, María-José Giménez, Juliette Moriceau, Amandine Fevre, Jean-Sebastien Roy, Ángel González-de-la-Flor and Marta de la Plaza San Frutos
Sensors 2024, 24(8), 2635; https://doi.org/10.3390/s24082635 - 20 Apr 2024
Viewed by 528
Abstract
This retrospective study aimed to analyze the return to running of non-professional runners after experiencing asymptomatic or mild COVID-19. Participants aged 18–55 years who maintained a training load of ≥10 km/week for at least three months prior to diagnosis and utilized Garmin/Polar apps [...] Read more.
This retrospective study aimed to analyze the return to running of non-professional runners after experiencing asymptomatic or mild COVID-19. Participants aged 18–55 years who maintained a training load of ≥10 km/week for at least three months prior to diagnosis and utilized Garmin/Polar apps were included. From these devices, parameters such as pace, distance, total running time, cadence, and heart rate were collected at three intervals: pre-COVID, immediately post-COVID, and three months after diagnosis. The Wilcoxon signed rank test was used for analysis (significance was set at ≤0.05). Twenty-one participants (57.1% male; mean age 35.0 ± 9.8 years) were included. The results revealed a significant decrease in running duration and distance two weeks after diagnosis, without significant changes in other parameters. Three months after infection, no differences were observed compared to pre-infection data, indicating a return to the pre-disease training load. These findings underscore the transient impact of COVID-19 on training performance among non-professional runners with mild or asymptomatic symptoms, highlighting the importance of tailored strategies for resuming running after infection. Full article
Show Figures

Figure 1

30 pages, 16244 KiB  
Article
Analysis and Prediction of Urban Surface Transformation Based on Small Baseline Subset Interferometric Synthetic Aperture Radar and Sparrow Search Algorithm–Convolutional Neural Network–Long Short-Term Memory Model
by Yuejuan Chen, Siai Du, Pingping Huang, Huifang Ren, Bo Yin, Yaolong Qi, Cong Ding and Wei Xu
Sensors 2024, 24(8), 2634; https://doi.org/10.3390/s24082634 - 20 Apr 2024
Viewed by 483
Abstract
With the acceleration of urbanisation, urban areas are subject to the combined effects of the accumulation of various natural factors, such as changes in temperature leading to the thermal expansion or contraction of surface materials (rock, soil, etc.) and changes in precipitation and [...] Read more.
With the acceleration of urbanisation, urban areas are subject to the combined effects of the accumulation of various natural factors, such as changes in temperature leading to the thermal expansion or contraction of surface materials (rock, soil, etc.) and changes in precipitation and humidity leading to an increase in the self-weight of soil due to the infiltration of water along the cracks or pores in the ground. Therefore, the subsidence of urban areas has now become a serious geological disaster phenomenon. However, the use of traditional neural network prediction models has limitations when examining the causal relationships between time series surface deformation data and multiple influencing factors and when applying multiple influencing factors for predictive analyses. To this end, Sentinel-1A data from March 2017 to February 2023 were used as the data source in this paper, based on time series deformation data acquired using the small baseline subset interferometric synthetic aperture radar (SBAS-InSAR) technique. A sparrow search algorithm–convolutional neural network–long short-term memory (SSA-CNN-LSTM) neural network prediction model was built. The six factors of temperature, humidity, precipitation, and ground temperature at three different depths below the surface (5 cm, 10 cm, and 15 cm) were taken as the input of the model, and the surface deformation data were taken as the output of the neural network model. The correlation between the spatial and temporal evolution characteristics of the ground subsidence in urban areas and various influencing factors was analysed using grey correlation analysis, which proved that these six factors contribute to some extent to the deformation of the urban surface. The main urban area of Hohhot City, Inner Mongolia Autonomous Region, was used as the study area. In order to verify the efficacy of this neural network prediction model, the prediction effects of the multilayer perceptron (MLP), backpropagation (BP), and SSA-CNN-LSTM models were compared and analysed, with the values of the correlation coefficients of the feature points of A1, B1, and C1 being in the range of 0.92, 0.83, and 0.93, respectively. The results show that compared with the traditional MLP and BP neural network models, the SSA-CNN-LSTM model achieves a higher performance in predicting time series surface deformation data in urban areas, which provides new ideas and methods for this area of research. Full article
(This article belongs to the Section Remote Sensors)
Show Figures

Figure 1

Previous Issue
Next Issue
Back to TopTop