Next Issue
Volume 24, October-1
Previous Issue
Volume 24, September-1
 
 
sensors-logo

Journal Browser

Journal Browser

Sensors, Volume 24, Issue 18 (September-2 2024) – 299 articles

Cover Story (view full-size image): In public security and surveillance, efficacy and privacy protection measures must be continually evaluated. Our work deploys sensor fusion for the discrete detection of concealed metal objects on persons whilst preserving their privacy. This is achieved by coupling mmWave radar and depth camera technology with a novel neural network architecture that processes radar signals using convolutional Long Short-Term Memory blocks and depth signals using convolutional operations. We demonstrate the detection of presence and 3D location of concealed metal objects, achieving accuracies of up to 95% using a technique that is robust to multiple persons. This work provides a demonstration of the potential for cost-effective and portable sensor fusion with strong opportunities for further development. 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:
16 pages, 5276 KiB  
Article
Comparative Study of Lightweight Target Detection Methods for Unmanned Aerial Vehicle-Based Road Distress Survey
by Feifei Xu, Yan Wan, Zhipeng Ning and Hui Wang
Sensors 2024, 24(18), 6159; https://doi.org/10.3390/s24186159 - 23 Sep 2024
Viewed by 1056
Abstract
Unmanned aerial vehicles (UAVs) are effective tools for identifying road anomalies with limited detection coverage due to the discrete spatial distribution of roads. Despite computational, storage, and transmission challenges, existing detection algorithms can be improved to support this task with robustness and efficiency. [...] Read more.
Unmanned aerial vehicles (UAVs) are effective tools for identifying road anomalies with limited detection coverage due to the discrete spatial distribution of roads. Despite computational, storage, and transmission challenges, existing detection algorithms can be improved to support this task with robustness and efficiency. In this study, the K-means clustering algorithm was used to calculate the best prior anchor boxes; Faster R-CNN (region-based convolutional neural network), YOLOX-s (You Only Look Once version X-small), YOLOv5-s, YOLOv7-tiny, YOLO-MobileNet, and YOLO-RDD models were built based on image data collected by UAVs. YOLO-MobileNet has the most lightweight model but performed worst in accuracy, but greatly reduces detection accuracy. YOLO-RDD (road distress detection) performed best with a mean average precision (mAP) of 0.701 above the Intersection over Union (IoU) value of 0.5 and achieved relatively high accuracy in detecting all four types of distress. The YOLO-RDD model most successfully detected potholes with an AP of 0.790. Significant or severe distresses were better identified, and minor cracks were relatively poorly identified. The YOLO-RDD model achieved an 85% computational reduction compared to YOLOv7-tiny while maintaining high detection accuracy. Full article
Show Figures

Figure 1

31 pages, 2932 KiB  
Article
flyDetect: An Android Application for Flight Detection
by Jonas Reinholdt, Eric Jul and Paulo Ferreira
Sensors 2024, 24(18), 6158; https://doi.org/10.3390/s24186158 - 23 Sep 2024
Viewed by 996
Abstract
Over the past years, transport mode recognition has become a large field of research. However, flight as a type of transportation has been mostly overlooked. A system for flight detection might be useful for context-aware applications, but more importantly, it can be used [...] Read more.
Over the past years, transport mode recognition has become a large field of research. However, flight as a type of transportation has been mostly overlooked. A system for flight detection might be useful for context-aware applications, but more importantly, it can be used to automatically manage airplane mode on smartphones. Smartphones transmit radio frequency signals which could potentially interfere with aircraft systems, and it is therefore important that devices enable airplane mode to avoid this problem. This paper proposes flyDetect, a method for automatic flight mode detection and an embodiment in the form of an app that demonstrates the viability of the method. Thus, the system uses the accelerometer and barometer in an Android smartphone, can detect the start and end of a flight, and notify other apps or systems on the device when this happens. Our evaluation shows that flyDetect meets the requirements set for the solution, and the results are very promising. Full article
(This article belongs to the Section Intelligent Sensors)
Show Figures

Figure 1

22 pages, 5199 KiB  
Article
Machine Learning-Based Gesture Recognition Glove: Design and Implementation
by Anna Filipowska, Wojciech Filipowski, Paweł Raif, Marcin Pieniążek, Julia Bodak, Piotr Ferst, Kamil Pilarski, Szymon Sieciński, Rafał Jan Doniec, Julia Mieszczanin, Emilia Skwarek, Katarzyna Bryzik, Maciej Henkel and Marcin Grzegorzek
Sensors 2024, 24(18), 6157; https://doi.org/10.3390/s24186157 - 23 Sep 2024
Cited by 1 | Viewed by 1852
Abstract
In the evolving field of human–computer interaction (HCI), gesture recognition has emerged as a critical focus, with smart gloves equipped with sensors playing one of the most important roles. Despite the significance of dynamic gesture recognition, most research on data gloves has concentrated [...] Read more.
In the evolving field of human–computer interaction (HCI), gesture recognition has emerged as a critical focus, with smart gloves equipped with sensors playing one of the most important roles. Despite the significance of dynamic gesture recognition, most research on data gloves has concentrated on static gestures, with only a small percentage addressing dynamic gestures or both. This study explores the development of a low-cost smart glove prototype designed to capture and classify dynamic hand gestures for game control and presents a prototype of data gloves equipped with five flex sensors, five force sensors, and one inertial measurement unit (IMU) sensor. To classify dynamic gestures, we developed a neural network-based classifier, utilizing a convolutional neural network (CNN) with three two-dimensional convolutional layers and rectified linear unit (ReLU) activation where its accuracy was 90%. The developed glove effectively captures dynamic gestures for game control, achieving high classification accuracy, precision, and recall, as evidenced by the confusion matrix and training metrics. Despite limitations in the number of gestures and participants, the solution offers a cost-effective and accurate approach to gesture recognition, with potential applications in VR/AR environments. Full article
(This article belongs to the Special Issue Wearable Sensors for Human Activity Monitoring)
Show Figures

Figure 1

22 pages, 1367 KiB  
Article
Detection of GPS Spoofing Attacks in UAVs Based on Adversarial Machine Learning Model
by Lamia Alhoraibi, Daniyal Alghazzawi and Reemah Alhebshi
Sensors 2024, 24(18), 6156; https://doi.org/10.3390/s24186156 - 23 Sep 2024
Viewed by 1563
Abstract
Advancements in wireless communication and automation have revolutionized mobility systems, notably through autonomous vehicles and unmanned aerial vehicles (UAVs). UAV spatial coordinates, determined via Global Positioning System (GPS) signals, are susceptible to cyberattacks due to unencrypted and unauthenticated transmissions with GPS spoofing being [...] Read more.
Advancements in wireless communication and automation have revolutionized mobility systems, notably through autonomous vehicles and unmanned aerial vehicles (UAVs). UAV spatial coordinates, determined via Global Positioning System (GPS) signals, are susceptible to cyberattacks due to unencrypted and unauthenticated transmissions with GPS spoofing being a significant threat. To mitigate these vulnerabilities, intrusion detection systems (IDSs) for UAVs have been developed and enhanced using machine learning (ML) algorithms. However, Adversarial Machine Learning (AML) has introduced new risks by exploiting ML models. This study presents a UAV-IDS employing AML methodology to enhance the detection and classification of GPS spoofing attacks. The key contribution is the development of an AML detection model that significantly improves UAV system robustness and security. Our findings indicate that the model achieves a detection accuracy of 98%, demonstrating its effectiveness in managing large-scale datasets and complex tasks. This study emphasizes the importance of physical layer security for enhancing IDSs in UAVs by introducing a novel detection model centered on an adversarial training defense method and advanced deep learning techniques. Full article
(This article belongs to the Section Sensor Networks)
Show Figures

Figure 1

11 pages, 2637 KiB  
Article
A Mixed Approach for Clock Synchronization in Distributed Data Acquisition Systems
by Gabriele Manduchi, Andrea Rigoni, Luca Trevisan and Tommaso Patton
Sensors 2024, 24(18), 6155; https://doi.org/10.3390/s24186155 - 23 Sep 2024
Viewed by 753
Abstract
Proper timing synchronization is important when data from sensors are acquired by different devices. This paper proposes a simple but effective solution for System on Chip (SoC) architectures that integrates a general-purpose Field Programmable Gate Array (FPGA) with a CPU. The proposed approach [...] Read more.
Proper timing synchronization is important when data from sensors are acquired by different devices. This paper proposes a simple but effective solution for System on Chip (SoC) architectures that integrates a general-purpose Field Programmable Gate Array (FPGA) with a CPU. The proposed approach relies on a network synchronization protocol implemented in software, such as Network Time Protocol (NTP) or Precision Time Protocol (PTP), and uses the FPGA to generate a clock reference that is maintained in step with the synchronized system clock. The clock generated by the FPGA is obtained from the FPGA oscillator via appropriate fractional clock division. Clock drift is avoided via a software program that periodically compares the FPGA and the system counters, respectively, and adjusts the fractional clock divider in order to slightly adjust the FPGA clock frequency using a Proportional Integral controller. A specific implementation is presented on the RedPitaya platform, generating a 1 MHz clock in step with the NTP synchronized system clock. The presented system has been used in a distributed data acquisition system for fast transient recording in the neutral beam test facility for the ITER nuclear fusion experiment. Full article
(This article belongs to the Special Issue Sensors Based SoCs, FPGA in IoT Applications)
Show Figures

Figure 1

14 pages, 3811 KiB  
Article
Signal Quality in Continuous Transcutaneous Bilirubinometry
by Fernando Crivellaro, Anselmo Costa and Pedro Vieira
Sensors 2024, 24(18), 6154; https://doi.org/10.3390/s24186154 - 23 Sep 2024
Viewed by 731
Abstract
Bilirubin is a product of the metabolism of hemoglobin from red blood cells. Higher levels of bilirubin are a sign that either there is an unusual breaking down rate of red blood cells or the liver is not able to eliminate bilirubin, through [...] Read more.
Bilirubin is a product of the metabolism of hemoglobin from red blood cells. Higher levels of bilirubin are a sign that either there is an unusual breaking down rate of red blood cells or the liver is not able to eliminate bilirubin, through bile, into the gastrointestinal tract. For adults, bilirubin is occasionally monitored through urine or invasive blood sampling, whilst all newborns are routinely monitored visually, or non-invasively with transcutaneous measurements (TcBs), due to their biological immaturity to conjugate bilirubin. Neonatal jaundice is a common condition, with higher levels of unconjugated bilirubin concentration having neurotoxic effects. Actual devices used in TcBs are focused on newborn populations, are hand-held, and, in some cases, operate in only two wavelengths, which does not necessarily guarantee reliable results over all skin tones. The same occurs with visual inspections. Based on that, a continuous bilirubin monitoring device for newborns is being developed to overcome visual inspection errors and to reduce invasive procedures. This device, operating optically with a mini-spectrometer in the visible range, is susceptible to patient movements and, consequently, to situations with a lower signal quality for reliable bilirubin concentration estimates on different types of skin. Therefore, as an intermediate development step and, based on skin spectra measurements from adults, this work addresses the device’s placement status prediction as a signal quality indication index. This was implemented by using machine learning (ML), with the best performances being achieved by support vector machine (SVM) models, based on the spectra acquired on the arm and forehead areas. Full article
(This article belongs to the Special Issue Wearable Sensors for Continuous Health Monitoring and Analysis)
Show Figures

Figure 1

24 pages, 6162 KiB  
Article
Location Privacy Protection for the Internet of Things with Edge Computing Based on Clustering K-Anonymity
by Nanlan Jiang, Yinan Zhai, Yujun Wang, Xuesong Yin, Sai Yang and Pingping Xu
Sensors 2024, 24(18), 6153; https://doi.org/10.3390/s24186153 - 23 Sep 2024
Viewed by 752
Abstract
With the development of the Internet of Things (IoT) and edge computing, more and more devices, such as sensor nodes and intelligent automated guided vehicles (AGVs), can serve as edge devices to provide Location-Based Services (LBS) through the IoT. As the number of [...] Read more.
With the development of the Internet of Things (IoT) and edge computing, more and more devices, such as sensor nodes and intelligent automated guided vehicles (AGVs), can serve as edge devices to provide Location-Based Services (LBS) through the IoT. As the number of applications increases, there is an abundance of sensitive information in the communication process, pushing the focus of privacy protection towards the communication process and edge devices. The challenge lies in the fact that most traditional location privacy protection algorithms are not suited for the IoT with edge computing, as they primarily focus on the security of remote servers. To enhance the capability of location privacy protection, this paper proposes a novel K-anonymity algorithm based on clustering. This novel algorithm incorporates a scheme that flexibly combines real and virtual locations based on the requirements of applications. Simulation results demonstrate that the proposed algorithm significantly improves location privacy protection for the IoT with edge computing. When compared to traditional K-anonymity algorithms, the proposed algorithm further enhances the security of location privacy by expanding the potential region in which the real node may be located, thereby limiting the effectiveness of “narrow-region” attacks. Full article
(This article belongs to the Special Issue Advanced Mobile Edge Computing in 5G Networks)
Show Figures

Figure 1

24 pages, 4457 KiB  
Article
An Adaptive and Automatic Power Supply Distribution System with Active Landmarks for Autonomous Mobile Robots
by Zhen Li, Yuliang Gao, Miaomiao Zhu, Haonan Tang and Lifeng Zhang
Sensors 2024, 24(18), 6152; https://doi.org/10.3390/s24186152 - 23 Sep 2024
Viewed by 739
Abstract
With the development of automation and intelligent technologies, the demand for autonomous mobile robots in the industry has surged to alleviate labor-intensive tasks and mitigate labor shortages. However, conventional industrial mobile robots’ route-tracking algorithms typically rely on passive markers, leading to issues such [...] Read more.
With the development of automation and intelligent technologies, the demand for autonomous mobile robots in the industry has surged to alleviate labor-intensive tasks and mitigate labor shortages. However, conventional industrial mobile robots’ route-tracking algorithms typically rely on passive markers, leading to issues such as inflexibility in changing routes and high deployment costs. To address these challenges, this study proposes a novel approach utilizing active landmarks—battery-powered luminous landmarks that enable robots to recognize and adapt to flexible navigation requirements. However, the reliance on batteries necessitates frequent recharging, prompting the development of an automatic power supply system. This system integrates omnidirectional contact electrodes on mobile robots, allowing to recharge active landmarks without precise positional alignment. Despite these advancements, challenges such as the large size of electrodes and non-adaptive battery charging across landmarks persist, affecting system efficiency. To mitigate these issues, this research focuses on miniaturizing active landmarks and optimizing power distribution among landmarks. The experimental results of this study demonstrated the effectiveness of our automatic power supply method and the high accuracy of landmark detection. Our power distribution calculation method can adaptively manage energy distribution, improving the system’s persistence by nearly three times. This study aims to enhance the practicality and efficiency of mobile robot remote control systems utilizing active landmarks by simplifying installation processes and extending operational durations with adaptive and automatic power supply distribution. Full article
(This article belongs to the Section Sensors and Robotics)
Show Figures

Figure 1

19 pages, 508 KiB  
Article
A Recommendation System for Trigger–Action Programming Rules via Graph Contrastive Learning
by Zhejun Kuang, Xingbo Xiong, Gang Wu, Feng Wang, Jian Zhao and Dawen Sun
Sensors 2024, 24(18), 6151; https://doi.org/10.3390/s24186151 - 23 Sep 2024
Viewed by 683
Abstract
Trigger–action programming (TAP) enables users to automate Internet of Things (IoT) devices by creating rules such as “IF Device1.TriggerState is triggered, THEN Device2.ActionState is executed”. As the number of IoT devices grows, the combination space between the functions provided by devices expands, making [...] Read more.
Trigger–action programming (TAP) enables users to automate Internet of Things (IoT) devices by creating rules such as “IF Device1.TriggerState is triggered, THEN Device2.ActionState is executed”. As the number of IoT devices grows, the combination space between the functions provided by devices expands, making manual rule creation time-consuming for end-users. Existing TAP recommendation systems enhance the efficiency of rule discovery but face two primary issues: they ignore the association of rules between users and fail to model collaborative information among users. To address these issues, this article proposes a graph contrastive learning-based recommendation system for TAP rules, named GCL4TAP. In GCL4TAP, we first devise a data partitioning method called DATA2DIV, which establishes cross-user rule relationships and is represented by a user–rule bipartite graph. Then, we design a user–user graph to model the similarities among users based on the categories and quantities of devices that they own. Finally, these graphs are converted into low-dimensional vector representations of users and rules using graph contrastive learning techniques. Extensive experiments conducted on a real-world smart home dataset demonstrate the superior performance of GCL4TAP compared to other state-of-the-art methods. Full article
(This article belongs to the Section Internet of Things)
Show Figures

Figure 1

26 pages, 9754 KiB  
Review
Gas Sensing Properties of Indium–Oxide–Based Field–Effect Transistor: A Review
by Chengyao Liang, Zhongyu Cao, Jiongyue Hao, Shili Zhao, Yuanting Yu, Yingchun Dong, Hangyu Liu, Chun Huang, Chao Gao, Yong Zhou and Yong He
Sensors 2024, 24(18), 6150; https://doi.org/10.3390/s24186150 - 23 Sep 2024
Viewed by 1280
Abstract
Excellent stability, low cost, high response, and sensitivity of indium oxide (In2O3), a metal oxide semiconductor, have been verified in the field of gas sensing. Conventional In2O3 gas sensors employ simple and easy–to–manufacture resistive components as [...] Read more.
Excellent stability, low cost, high response, and sensitivity of indium oxide (In2O3), a metal oxide semiconductor, have been verified in the field of gas sensing. Conventional In2O3 gas sensors employ simple and easy–to–manufacture resistive components as transducers. However, the swift advancement of the Internet of Things has raised higher requirements for gas sensors based on metal oxides, primarily including lowering operating temperatures, improving selectivity, and realizing integrability. In response to these three main concerns, field–effect transistor (FET) gas sensors have garnered growing interest over the past decade. When compared with other metal oxide semiconductors, In2O3 exhibits greater carrier concentration and mobility. The property is advantageous for manufacturing FETs with exceptional electrical performance, provided that the off–state current is controlled at a sufficiently low level. This review presents the significant progress made in In2O3 FET gas sensors during the last ten years, covering typical device designs, gas sensing performance indicators, optimization techniques, and strategies for the future development based on In2O3 FET gas sensors. Full article
(This article belongs to the Special Issue Inorganic Nanostructure-Based Sensors: Design and Applications)
Show Figures

Figure 1

28 pages, 3622 KiB  
Review
From Biosensors to Robotics: Pioneering Advances in Breast Cancer Management
by Mohd. Rahil Hasan, Mohd Mughees, Shifa Shaikh, Furqan Choudhary, Anam Nizam, Amber Rizwan, Onaiza Ansari, Yusra Iqbal, Roberto Pilloton, Saima Wajid and Jagriti Narang
Sensors 2024, 24(18), 6149; https://doi.org/10.3390/s24186149 - 23 Sep 2024
Viewed by 1467
Abstract
Breast cancer stands as the most prevalent form of cancer amongst females, constituting more than one-third of all cancer cases affecting women. It causes aberrant cell development, which can assault or spread to other sections of the body, perhaps leading to the patient’s [...] Read more.
Breast cancer stands as the most prevalent form of cancer amongst females, constituting more than one-third of all cancer cases affecting women. It causes aberrant cell development, which can assault or spread to other sections of the body, perhaps leading to the patient’s death. Based on research findings, timely detection can diminish the likelihood of mortality and enhance the quality of healthcare provided for the illness. However, current technologies can only identify cancer at an advanced stage. Consequently, there is a substantial demand for rapid and productive approaches to detecting breast cancer. Researchers are actively pursuing precise and timely methods for the diagnosis of breast cancer, aiming to achieve enhanced accuracy and early detection. Biosensor technology can allow for the speedy and accurate diagnosis of cancer-related cells, as well as a more sensitive and specialized technique for generating them. Additionally, numerous treatments for breast cancer are depicted such as herbal therapy, nanomaterial-based drug delivery, miRNA targeting, CRISPR technology, immunotherapy, and precision medicine. Early detection and efficient therapy are necessary to manage such a severe illness properly. Full article
(This article belongs to the Special Issue Feature Papers in Biosensors Section 2024)
Show Figures

Figure 1

25 pages, 1006 KiB  
Article
Statistics of the Sum of Double Random Variables and Their Applications in Performance Analysis and Optimization of Simultaneously Transmitting and Reflecting Reconfigurable Intelligent Surface-Assisted Non-Orthogonal Multi-Access Systems
by Bui Vu Minh, Phuong T. Tran, Thu-Ha Thi Pham, Anh-Tu Le, Si-Phu Le and Pavol Partila
Sensors 2024, 24(18), 6148; https://doi.org/10.3390/s24186148 - 23 Sep 2024
Viewed by 592
Abstract
For the future of sixth-generation (6G) wireless communication, simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) technology is emerging as a promising solution to achieve lower power transmission and flawless coverage. To facilitate the performance analysis of RIS-assisted networks, the statistics of the [...] Read more.
For the future of sixth-generation (6G) wireless communication, simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) technology is emerging as a promising solution to achieve lower power transmission and flawless coverage. To facilitate the performance analysis of RIS-assisted networks, the statistics of the sum of double random variables, i.e., the sum of the products of two random variables of the same distribution type, become vitally necessary. This paper applies the statistics of the sum of double random variables in the performance analysis of an integrated power beacon (PB) energy-harvesting (EH)-based NOMA-assisted STAR-RIS network to improve its outage probability (OP), ergodic rate, and average symbol error rate. Furthermore, the impact of imperfect successive interference cancellation (ipSIC) on system performance is also analyzed. The analysis provides the closed-form expressions of the OP and ergodic rate derived for both imperfect and perfect SIC (pSIC) cases. All analyses are supported by extensive simulation results, which help recommend optimized system parameters, including the time-switching factor, the number of reflecting elements, and the power allocation coefficients, to minimize the OP. Finally, the results demonstrate the superiority of the proposed framework compared to conventional NOMA and OMA systems. Full article
(This article belongs to the Special Issue 5G/6G Networks for Wireless Communication and IoT)
Show Figures

Figure 1

13 pages, 11445 KiB  
Article
Compact VHF/UHF Ultrawideband Discone Antenna with Consistent Pattern
by Guang Li, Fushun Zhang and Bingnan Wang
Sensors 2024, 24(18), 6147; https://doi.org/10.3390/s24186147 - 23 Sep 2024
Viewed by 595
Abstract
A compact VHF/UHF ultrawideband discone antenna with consistent patterns is proposed in this article. The proposed antenna consists of a disk, a modified cone, an inverted cone, four shorting probes, and two sleeves. To improve the radiation angular distortion at high frequencies, two [...] Read more.
A compact VHF/UHF ultrawideband discone antenna with consistent patterns is proposed in this article. The proposed antenna consists of a disk, a modified cone, an inverted cone, four shorting probes, and two sleeves. To improve the radiation angular distortion at high frequencies, two sleeves are inserted into the discone antenna. Higher-order modes are suppressed, and ultrawideband consistent patterns are obtained without antenna size increasing. An inverted cone and four shorting probes are introduced to achieve broadband and profile reduction. An antenna prototype is fabricated and measured. The proposed antenna possesses consistent patterns in a 11.36:1 bandwidth. The pattern nulls is improved by 26.1 dB. The antenna occupies a cylindrical volume of 0.227 λ0 (D) and 0.096 λ0 (H). It is a competitive candidate for future in-vehicle communication systems. Full article
(This article belongs to the Section Radar Sensors)
Show Figures

Figure 1

19 pages, 16985 KiB  
Article
Farm Monitoring System with Drones and Optical Camera Communication
by Shinnosuke Kondo, Naoto Yoshimoto and Yu Nakayama
Sensors 2024, 24(18), 6146; https://doi.org/10.3390/s24186146 - 23 Sep 2024
Viewed by 890
Abstract
Drones have been attracting significant attention in the field of agriculture. They can be used for various tasks such as spraying pesticides, monitoring pests, and assessing crop growth. Sensors are also widely used in agriculture to monitor environmental parameters such as soil moisture [...] Read more.
Drones have been attracting significant attention in the field of agriculture. They can be used for various tasks such as spraying pesticides, monitoring pests, and assessing crop growth. Sensors are also widely used in agriculture to monitor environmental parameters such as soil moisture and temperature. Due to the high cost of communication infrastructure and radio-wave modules, the adoption of high-density sensing systems in agriculture is limited. To address this issue, we propose an agricultural sensor network system using drones and Optical Camera Communication (OCC). The idea is to transmit sensor data from LED panels mounted on sensor nodes and receive the data using a drone-mounted camera. This enables high-density sensing at low cost and can be deployed in areas with underdeveloped infrastructure and radio silence. We propose a trajectory control algorithm for the receiving drone to efficiently collect the sensor data. From computer simulations, we confirmed that the proposed algorithm reduces total flight time by 30% compared to a shortest-path algorithm. We also conducted a preliminary experiment at a leaf mustard farm in Kamitonda-cho, Wakayama, Japan, to demonstrate the effectiveness of the proposed system. We collected 5178 images of LED panels with a drone-mounted camera to train YOLOv5 for object detection. With simple On–Off Keying (OOK) modulation, we achieved sufficiently low bit error rates (BERs) under 103 in the real-world environment. The experimental results show that the proposed system is applicable for drone-based sensor data collection in agriculture. Full article
(This article belongs to the Section Internet of Things)
Show Figures

Figure 1

30 pages, 21758 KiB  
Article
Study of Acoustic Emission Signal Noise Attenuation Based on Unsupervised Skip Neural Network
by Tuoya Wulan, Guodong Li, Yupeng Huo, Jiangjiang Yu, Ruiqi Wang, Zhongzheng Kou and Wen Yang
Sensors 2024, 24(18), 6145; https://doi.org/10.3390/s24186145 - 23 Sep 2024
Viewed by 599
Abstract
Acoustic emission (AE) technology, as a non-destructive testing methodology, is extensively utilized to monitor various materials’ structural integrity. However, AE signals captured during experimental processes are often tainted with assorted noise factors that degrade the signal clarity and integrity, complicating precise analytical evaluations [...] Read more.
Acoustic emission (AE) technology, as a non-destructive testing methodology, is extensively utilized to monitor various materials’ structural integrity. However, AE signals captured during experimental processes are often tainted with assorted noise factors that degrade the signal clarity and integrity, complicating precise analytical evaluations of the experimental outcomes. In response to these challenges, this paper introduces an unsupervised deep learning-based denoising model tailored for AE signals. It juxtaposes its efficacy against established methods, such as wavelet packet denoising, Hilbert transform denoising, and complete ensemble empirical mode decomposition with adaptive noise denoising. The results demonstrate that the unsupervised skip autoencoder model exhibits substantial potential in noise reduction, marking a significant advancement in AE signal processing. Subsequently, the paper focuses on applying this advanced denoising technique to AE signals collected during the tensile testing of steel fiber-reinforced concrete (SFRC), the tensile testing of steel, and flexural experiments of reinforced concrete beam, and it meticulously discusses the variations in the waveform and the spectrogram of the original signal and the signal after noise reduction. The results show that the model can also remove the noise of AE signals. Full article
(This article belongs to the Section Fault Diagnosis & Sensors)
Show Figures

Figure 1

22 pages, 4119 KiB  
Review
Dual-Band Passive Beam Steering Antenna Technologies for Satellite Communication and Modern Wireless Systems: A Review
by Maira I. Nabeel, Khushboo Singh, Muhammad U. Afzal, Dushmantha N. Thalakotuna and Karu P. Esselle
Sensors 2024, 24(18), 6144; https://doi.org/10.3390/s24186144 - 23 Sep 2024
Viewed by 1262
Abstract
Efficient beam steerable high-gain antennas enable high-speed data rates over long-distance networks, including wireless backhaul, satellite communications (SATCOM), and SATCOM On-the-Move. These characteristics are essential for advancing contemporary wireless communication networks, particularly within 5G and beyond. Various beam steering solutions have been proposed [...] Read more.
Efficient beam steerable high-gain antennas enable high-speed data rates over long-distance networks, including wireless backhaul, satellite communications (SATCOM), and SATCOM On-the-Move. These characteristics are essential for advancing contemporary wireless communication networks, particularly within 5G and beyond. Various beam steering solutions have been proposed in the literature, with passive beam steering mechanisms employing planar metasurfaces emerging as cost-effective, power-efficient, and compact options. These attributes make them well-suited for use in confined spaces, large-scale production and widespread distribution to meet the demands of the mass market. Utilizing a dual-band antenna terminal setup is often advantageous for full duplex communication in wireless systems. Therefore, this article presents a comprehensive review of the dual-band beam steering techniques for enabling full-duplex communication in modern wireless systems, highlighting their design methodologies, scanning mechanisms, physical characteristics, and constraints. Despite the advantages of planar metasurface-based beam steering solutions, the literature on dual-band beam steering antennas supporting full duplex communication is limited. This review article identifies research gaps and outlines future directions for developing economically feasible passive dual-band beam steering solutions for mass deployment. Full article
Show Figures

Figure 1

19 pages, 2751 KiB  
Article
Blockchain 6G-Based Wireless Network Security Management with Optimization Using Machine Learning Techniques
by Ponnusamy Chinnasamy, G. Charles Babu, Ramesh Kumar Ayyasamy, S. Amutha, Keshav Sinha and Allam Balaram
Sensors 2024, 24(18), 6143; https://doi.org/10.3390/s24186143 - 23 Sep 2024
Viewed by 1333
Abstract
6G mobile network technology will set new standards to meet performance goals that are too ambitious for 5G networks to satisfy. The limitations of 5G networks have been apparent with the deployment of more and more 5G networks, which certainly encourages the investigation [...] Read more.
6G mobile network technology will set new standards to meet performance goals that are too ambitious for 5G networks to satisfy. The limitations of 5G networks have been apparent with the deployment of more and more 5G networks, which certainly encourages the investigation of 6G networks as the answer for the future. This research includes fundamental privacy and security issues related to 6G technology. Keeping an eye on real-time systems requires secure wireless sensor networks (WSNs). Denial of service (DoS) attacks mark a significant security vulnerability that WSNs face, and they can compromise the system as a whole. This research proposes a novel method in blockchain 6G-based wireless network security management and optimization using a machine learning model. In this research, the deployed 6G wireless sensor network security management is carried out using a blockchain user datagram transport protocol with reinforcement projection regression. Then, the network optimization is completed using artificial democratic cuckoo glowworm remora optimization. The simulation results have been based on various network parameters regarding throughput, energy efficiency, packet delivery ratio, end–end delay, and accuracy. In order to minimise network traffic, it also offers the capacity to determine the optimal node and path selection for data transmission. The proposed technique obtained 97% throughput, 95% energy efficiency, 96% accuracy, 50% end–end delay, and 94% packet delivery ratio. Full article
Show Figures

Figure 1

14 pages, 5577 KiB  
Article
Multilayer Fused Correntropy Reprsenstation for Fault Diagnosis of Mechanical Equipment
by Qi Deng, Guanhui Zhao, Weixiong Jiang, Jun Wu and Tianjiao Dai
Sensors 2024, 24(18), 6142; https://doi.org/10.3390/s24186142 - 23 Sep 2024
Viewed by 517
Abstract
Fault diagnosis is vital for improving the reliability and safety of mechanical equipment. Existing fault diagnosis methods require a large number of samples for model training. However, in real-world environments, mechanical equipment usually operates under healthy conditions during most of its service life, [...] Read more.
Fault diagnosis is vital for improving the reliability and safety of mechanical equipment. Existing fault diagnosis methods require a large number of samples for model training. However, in real-world environments, mechanical equipment usually operates under healthy conditions during most of its service life, resulting in a scarcity of fault samples. To solve this problem, a novel multilayer fusion correntropy representation method combined with a support vector machine is proposed for the fault diagnosis of mechanical equipment. First, the monitoring signal is expanded into multilayer signal components using wavelet packet decomposition. Then, the correlation between the signal components of each layer is expressed by correntropy, and the corresponding correntropy matrix is constructed. After performing the matrix logarithm operator, all correntropy matrices composed of correntropy values are fused into a vector, which is viewed as a feature of the signal. Finally, a support vector machine is established using small samples to realize fault classification. The effectiveness of the proposed method is validated on four public datasets. The results indicate that compared with other methods, the proposed method has advantages in terms of diagnosis accuracy and noise immunity ability. Full article
(This article belongs to the Special Issue Feature Papers in Fault Diagnosis & Sensors 2024)
Show Figures

Figure 1

26 pages, 4522 KiB  
Article
an-QNA: An Adaptive Nesterov Quasi-Newton Acceleration-Optimized CMOS LNA for 65 nm Automotive Radar Applications
by Unal Aras, Lee Sun Woo, Tahesin Samira Delwar, Abrar Siddique, Anindya Jana, Yangwon Lee and Jee-Youl Ryu
Sensors 2024, 24(18), 6141; https://doi.org/10.3390/s24186141 - 23 Sep 2024
Viewed by 715
Abstract
An adaptive Nesterov quasi-Newton acceleration (an-QNA)-optimized low-noise amplifier (LNA) is proposed in this paper. An optimized single-ended-to-differential two-stage LNA circuit is presented. It includes an improved post-linearization (IPL) technique to enhance the linearity. Traditional methods like conventional quasi-Newton (c-QN) often suffer [...] Read more.
An adaptive Nesterov quasi-Newton acceleration (an-QNA)-optimized low-noise amplifier (LNA) is proposed in this paper. An optimized single-ended-to-differential two-stage LNA circuit is presented. It includes an improved post-linearization (IPL) technique to enhance the linearity. Traditional methods like conventional quasi-Newton (c-QN) often suffer from slow convergence and the tendency to get trapped in local minima. However, the proposed an-QNA method significantly accelerates the convergence speed. Furthermore, in this paper, modifications have been made to the an-QNA algorithm using a quadratic estimation to guarantee global convergence. The optimized an-QNA-based LNA, using standard 65 nm CMOS technology, achieves a simulated gain of 17.5 dB, a noise figure (NF) of 3.7 dB, and a 1 dB input compression point (IP1dB) of −13.1 dBm. It is also noted that the optimized LNA achieves a measured gain of 12.9 dB and an NF of 4.98 dB, and the IP1dB is −17.8 dB. The optimized LNA has a chip area of 0.67 mm2. Full article
(This article belongs to the Special Issue CMOS Integrated Circuits for Sensor Applications)
Show Figures

Figure 1

16 pages, 2720 KiB  
Article
eHealth Assistant AI Chatbot Using a Large Language Model to Provide Personalized Answers through Secure Decentralized Communication
by Iuliu Alexandru Pap and Stefan Oniga
Sensors 2024, 24(18), 6140; https://doi.org/10.3390/s24186140 - 23 Sep 2024
Viewed by 1345
Abstract
In this paper, we present the implementation of an artificial intelligence health assistant designed to complement a previously built eHealth data acquisition system for helping both patients and medical staff. The assistant allows users to query medical information in a smarter, more natural [...] Read more.
In this paper, we present the implementation of an artificial intelligence health assistant designed to complement a previously built eHealth data acquisition system for helping both patients and medical staff. The assistant allows users to query medical information in a smarter, more natural way, respecting patient privacy and using secure communications through a chat style interface based on the Matrix decentralized open protocol. Assistant responses are constructed locally by an interchangeable large language model (LLM) that can form rich and complete answers like most human medical staff would. Restricted access to patient information and other related resources is provided to the LLM through various methods for it to be able to respond correctly based on specific patient data. The Matrix protocol allows deployments to be run in an open federation; hence, the system can be easily scaled. Full article
(This article belongs to the Special Issue e-Health Systems and Technologies)
Show Figures

Figure 1

21 pages, 1029 KiB  
Review
Automotive Cybersecurity: A Survey on Frameworks, Standards, and Testing and Monitoring Technologies
by Claudiu Vasile Kifor and Aurelian Popescu
Sensors 2024, 24(18), 6139; https://doi.org/10.3390/s24186139 - 23 Sep 2024
Viewed by 2918
Abstract
Modern vehicles are increasingly interconnected through various communication channels, which requires secure access for authorized users, the protection of driver assistance and autonomous driving system data, and the assurance of data integrity against misuse or manipulation. While these advancements offer numerous benefits, recent [...] Read more.
Modern vehicles are increasingly interconnected through various communication channels, which requires secure access for authorized users, the protection of driver assistance and autonomous driving system data, and the assurance of data integrity against misuse or manipulation. While these advancements offer numerous benefits, recent years have exposed many intrusion incidents, revealing vulnerabilities and weaknesses in current systems. To sustain and enhance the performance, quality, and reliability of vehicle systems, software engineers face significant challenges, including in diverse communication channels, software integration, complex testing, compatibility, core reusability, safety and reliability assurance, data privacy, and software security. Addressing cybersecurity risks presents a substantial challenge in finding practical solutions to these issues. This study aims to analyze the current state of research regarding automotive cybersecurity, with a particular focus on four main themes: frameworks and technologies, standards and regulations, monitoring and vulnerability management, and testing and validation. This paper highlights key findings, identifies existing research gaps, and proposes directions for future research that will be useful for both researchers and practitioners. Full article
Show Figures

Figure 1

13 pages, 3459 KiB  
Article
A Photoelectrochemical Biosensor Mediated by CRISPR/Cas13a for Direct and Specific Detection of MiRNA-21
by Yang Zhang, Pei Miao, Jingyuan Wang, Yan Sun, Jing Zhang, Bin Wang and Mei Yan
Sensors 2024, 24(18), 6138; https://doi.org/10.3390/s24186138 - 23 Sep 2024
Viewed by 894
Abstract
Direct detection of miRNA is currently limited by the complex amplification and reverse transcription processes of existing methods, leading to low sensitivity and high operational demands. Herein, we developed a CRISPR/Cas13a-mediated photoelectrochemical (PEC) biosensing platform for direct and sensitive detection of miRNA-21. The [...] Read more.
Direct detection of miRNA is currently limited by the complex amplification and reverse transcription processes of existing methods, leading to low sensitivity and high operational demands. Herein, we developed a CRISPR/Cas13a-mediated photoelectrochemical (PEC) biosensing platform for direct and sensitive detection of miRNA-21. The direct and specific recognition of target miRNA-21 by crRNA-21 eliminates the need for pre-amplification and reverse transcription of miRNA-21, thereby preventing signal distortion and enhancing the sensitivity and precision of target detection. When crRNA-21 binds to miRNA-21, it activates the trans-cleavage activity of CRISPR/Cas13a, leading to the non-specific cleavage of biotin-modified DNA with uracil bases (biotin-rU-DNA). This cleavage prevents the biotin-rU-DNA from being immobilized on the electrode surface. As a result, streptavidin cannot attach to the electrode via specific biotin binding, reducing spatial resistance and causing a positively correlated increase in the photocurrent response. This Cas-PEC biosensor has good analytical capabilities, linear responses between 10 fM and 10 nM, a minimum detection limit of 9 fM, and an excellent recovery rate in the analysis of real human serum samples. This work presented an innovative solution for detecting other biomarkers in bioanalysis and clinical diagnostics. Full article
(This article belongs to the Special Issue Recent Advances in Photoelectrochemical Sensors)
Show Figures

Figure 1

30 pages, 4306 KiB  
Review
A Comprehensive Review on the Viscoelastic Parameters Used for Engineering Materials, Including Soft Materials, and the Relationships between Different Damping Parameters
by Hasan Koruk and Srinath Rajagopal
Sensors 2024, 24(18), 6137; https://doi.org/10.3390/s24186137 - 23 Sep 2024
Viewed by 1179
Abstract
Although the physical properties of a structure, such as stiffness, can be determined using some statical tests, the identification of damping parameters requires a dynamic test. In general, both theoretical prediction and experimental identification of damping are quite difficult. There are many different [...] Read more.
Although the physical properties of a structure, such as stiffness, can be determined using some statical tests, the identification of damping parameters requires a dynamic test. In general, both theoretical prediction and experimental identification of damping are quite difficult. There are many different techniques available for damping identification, and each method gives a different damping parameter. The dynamic indentation method, rheometry, atomic force microscopy, and resonant vibration tests are commonly used to identify the damping of materials, including soft materials. While the viscous damping ratio, loss factor, complex modulus, and viscosity are quite common to describe the damping of materials, there are also other parameters, such as the specific damping capacity, loss angle, half-power bandwidth, and logarithmic decrement, to describe the damping of various materials. Often, one of these parameters is measured, and the measured parameter needs to be converted into another damping parameter for comparison purposes. In this review, the theoretical derivations of different parameters for the description and quantification of damping and their relationships are presented. The expressions for both high damping and low damping are included and evaluated. This study is considered as the first comprehensive review article presenting the theoretical derivations of a large number of damping parameters and the relationships among many damping parameters, with a quantitative evaluation of accurate and approximate formulas. This paper could be a primary resource for damping research and teaching. Full article
Show Figures

Figure 1

20 pages, 417 KiB  
Article
Beamforming for Multi-Bit Intelligent Reflecting Surface with Phase Shift-Dependent Power Consumption Model
by Huimin Zhang, Qiucen Wu and Yu Zhu
Sensors 2024, 24(18), 6136; https://doi.org/10.3390/s24186136 - 23 Sep 2024
Viewed by 705
Abstract
In recent years, the intelligent reflecting surface (IRS) has attracted increasing attention for its capability to intelligently reconfigure the wireless propagation channel. However, most existing works ignore the dynamic power consumption of IRS related to the phase shift configuration. This relationship gets even [...] Read more.
In recent years, the intelligent reflecting surface (IRS) has attracted increasing attention for its capability to intelligently reconfigure the wireless propagation channel. However, most existing works ignore the dynamic power consumption of IRS related to the phase shift configuration. This relationship gets even more intractable for a multi-bit IRS because of its nonlinearity and implicit form. In this paper, we investigate the beamforming optimization for multi-bit IRS-aided systems with the practical phase shift-dependent power consumption (PS-DPC) model, aiming at minimizing the power consumption of the system. To solve the implicit and nonlinear relationship, we introduce a selection matrix to explicitly represent the power consumption and the phase shift matrix of the IRS, respectively. Then, we propose a generalized Benders decomposition-based beamforming optimization algorithm in the single-user scenario. Furthermore, in the multi-user scenario, we design a coordinate descent-based algorithm and a genetic algorithm for the beamforming optimization. The simulation results show that the proposed algorithms significantly decrease the power consumption of the multi-bit IRS-aided systems. Full article
(This article belongs to the Section Communications)
Show Figures

Figure 1

23 pages, 6636 KiB  
Article
High-Precision Bi-Directional Beam-Pointing Measurement Method Based on Space Solar Power Station System
by Xinyue Hou, Xue Li, Shun Zhao, Yinsen Zhang and Lulu Wang
Sensors 2024, 24(18), 6135; https://doi.org/10.3390/s24186135 - 23 Sep 2024
Viewed by 669
Abstract
In the process of wireless energy transmission from a Space Solar Power Station (SSPS) to a satellite, the efficiency of energy transmission is closely related to the accuracy of beam control. The existing methods commonly ignore the impact of array position, structural deviation [...] Read more.
In the process of wireless energy transmission from a Space Solar Power Station (SSPS) to a satellite, the efficiency of energy transmission is closely related to the accuracy of beam control. The existing methods commonly ignore the impact of array position, structural deviation of the transmitting antenna, and modulation errors, which leads to the deviation error in actual energy transmission beams and the reduction of energy transmission efficiency. This paper innovatively proposes a high-precision bi-directional beam-pointing measurement method, which provides a technical basis for advancing the beam-pointing control accuracy from the perspective of improving the beam-pointing measurement accuracy. The method consists of (1) the interferometer goniometry method to realize high-precision guiding beam pointing measurement; and (2) the power field reconstruction method to realize offset angle measurement of the energy-transmitting beam. Simulation results demonstrate that under dynamic conditions, the guiding beam-pointing measurement accuracy of this method reaches 0.05°, which is better than the traditional 0.1° measurement accuracy based on the guiding beam. The measurement accuracy of the offset distance of the energy center is better than 0.11 m, and the measurement accuracy of the offset angle is better than 0.012°. Full article
(This article belongs to the Section Physical Sensors)
Show Figures

Figure 1

18 pages, 1924 KiB  
Article
Safety, Efficiency, and Mental Workload in Simulated Teledriving of a Vehicle as Functions of Camera Viewpoint
by Oren Musicant, Assaf Botzer and Bar Richmond-Hacham
Sensors 2024, 24(18), 6134; https://doi.org/10.3390/s24186134 - 23 Sep 2024
Viewed by 544
Abstract
Teleoperation services are expected to operate on-road and often in urban areas. In current teleoperation applications, teleoperators gain a higher viewpoint of the environment from a camera on the vehicle’s roof. However, it is unclear how this viewpoint compares to a conventional viewpoint [...] Read more.
Teleoperation services are expected to operate on-road and often in urban areas. In current teleoperation applications, teleoperators gain a higher viewpoint of the environment from a camera on the vehicle’s roof. However, it is unclear how this viewpoint compares to a conventional viewpoint in terms of safety, efficiency, and mental workload. In the current study, teleoperators (n = 148) performed driving tasks in a simulated urban environment with a conventional viewpoint (i.e., the simulated camera was positioned inside the vehicle at the height of a driver’s eyes) and a higher viewpoint (the simulated camera was positioned on the vehicle roof). The tasks required negotiating road geometry and other road users. At the end of the session, participants completed the NASA-TLX questionnaire. Results showed that participants completed most tasks faster with the higher viewpoint and reported lower frustration and mental demand. The camera position did not affect collision rates nor the probability of hard braking and steering events. We conclude that a viewpoint from the vehicle roof may improve teleoperation efficiency without compromising driving safety, while also lowering the teleoperators’ mental workload. Full article
(This article belongs to the Special Issue On-Board and Remote Sensors in Intelligent Vehicles-2nd Edition)
Show Figures

Figure 1

16 pages, 6001 KiB  
Article
Experimental Investigation on the Effect of Coil Shape on Planar Eddy Current Sensor Characteristic for Blade Tip Clearance
by Lingqiang Zhao, Yaguo Lyu, Fulin Liu, Zhenxia Liu and Ziyu Zhao
Sensors 2024, 24(18), 6133; https://doi.org/10.3390/s24186133 - 23 Sep 2024
Viewed by 460
Abstract
Given the increasing application of eddy current sensors for measuring turbine tip clearance in aero engines, enhancing the performance of these sensors is essential for improving measurement accuracy. This study investigates the influence of coil shape on the measurement performance of planar eddy [...] Read more.
Given the increasing application of eddy current sensors for measuring turbine tip clearance in aero engines, enhancing the performance of these sensors is essential for improving measurement accuracy. This study investigates the influence of coil shape on the measurement performance of planar eddy current sensors and identifies an optimal coil shape to enhance sensing capabilities. To achieve this, various coil shapes—specifically circular, square, rectangular wave, and triangular wave—were designed and fabricated, featuring different numbers of turns for the experiment at room temperature. By employing a method for calculating coil inductance, the performance of each sensor was evaluated based on key metrics: measurement range, sensitivity, and linearity. Experimental results reveal that the square coil configuration outperforms other shapes in overall measurement performance. Notably, the square coil demonstrated a measurement range of 0 mm to 8 mm, a sensitivity of 0.115685 μH/mm, and an impressive linearity of 98.41% within the range of 0 mm to 2 mm. These findings indicate that the square coil configuration enhances measurement capabilities. The conclusions drawn from this study provide valuable insights for selecting coil shapes and optimizing the performance of planar eddy current sensors, thereby contributing to the advancement of turbine tip clearance measurement techniques in aero engines. Full article
(This article belongs to the Special Issue Digital Twin-Enabled Deep Learning for Machinery Health Monitoring)
Show Figures

Figure 1

13 pages, 2051 KiB  
Article
Augmented Physics-Based Models for High-Order Markov Filtering
by Shuo Tang, Tales Imbiriba, Jindřich Duník, Ondřej Straka and Pau Closas
Sensors 2024, 24(18), 6132; https://doi.org/10.3390/s24186132 - 23 Sep 2024
Viewed by 615
Abstract
Hybrid physics-based data-driven models, namely, augmented physics-based models (APBMs), are capable of learning complex state dynamics while maintaining some level of model interpretability that can be controlled through appropriate regularizations of the data-driven component. In this article, we extend the APBM formulation for [...] Read more.
Hybrid physics-based data-driven models, namely, augmented physics-based models (APBMs), are capable of learning complex state dynamics while maintaining some level of model interpretability that can be controlled through appropriate regularizations of the data-driven component. In this article, we extend the APBM formulation for high-order Markov models, where the state space is further augmented with past states (AG-APBM). Typically, state augmentation is a powerful method for state estimation for a high-order Markov model, but it requires the exact knowledge of the system dynamics. The proposed approach, however, does not require full knowledge of dynamics, especially the Markovity order. To mitigate the extra computational burden of such augmentation we propose an approximated-state APBM (AP-APBM) implementation leveraging summaries from past time steps. We demonstrate the performance of AG- and AP-APBMs in an autoregressive model and a target-tracking scenario based on the trajectory of a controlled aircraft with delay-feedback control. The experiments showed that both proposed strategies outperformed the standard APBM approach in terms of estimation error and that the AP-APBM only degraded slightly when compared to AG-APBM. For example, the autoregressive (AR) model simulation in our settings showed that AG-APBM and AP-APBM reduced the estimate error by 31.1% and 26.7%. The time cost and memory usage were reduced by 37.5% and 20% by AP-APBM compared to AG-APBM. Full article
(This article belongs to the Section Navigation and Positioning)
Show Figures

Figure 1

23 pages, 3083 KiB  
Article
Anomaly Detection Method for Industrial Control System Operation Data Based on Time–Frequency Fusion Feature Attention Encoding
by Jiayi Liu, Yun Sha, Wenchang Zhang, Yong Yan and Xuejun Liu
Sensors 2024, 24(18), 6131; https://doi.org/10.3390/s24186131 - 23 Sep 2024
Viewed by 937
Abstract
Anomaly detection in industrial control system (ICS) data is one of the key technologies for ensuring the security monitoring of ICSs. ICS data are characterized as complex, multi-dimensional, and long-sequence time-series data that embody ICS business logic. Due to its complex and varying [...] Read more.
Anomaly detection in industrial control system (ICS) data is one of the key technologies for ensuring the security monitoring of ICSs. ICS data are characterized as complex, multi-dimensional, and long-sequence time-series data that embody ICS business logic. Due to its complex and varying periodic characteristics, as well as the presence of long-distance and misaligned temporal associations among features, current anomaly detection methods in ICS are insufficient for feature extraction. This paper proposes an anomaly detection method named TFANet, based on time–frequency fusion feature attention encoding. Considering that periodic variations are more concentrated in the frequency domain, this method first transforms the time-domain data into the frequency domain, obtaining both amplitude and phase data. Then, these data, together with the original time-series data, are used to extract features from two perspectives: long-term temporal changes and long-distance associations. Finally, the six features learned from both the time and frequency domains are fused, and the feature weights are calculated using an attention mechanism to complete the anomaly classification. In multi-classification tasks on three ICS datasets, the proposed method outperforms three popular time-series models—iTransformer, Crossformer, and TimesNet—across five metrics: accuracy, precision, recall, F1 score, and AUC-ROC, with average improvements of approximately 19%, 37%, 31%, 35%, and 22%, respectively. Full article
(This article belongs to the Special Issue Advanced Sensor Fusion in Industry 4.0)
Show Figures

Figure 1

16 pages, 12099 KiB  
Article
Application of the Semi-Supervised Learning Approach for Pavement Defect Detection
by Peng Cui, Nurjihan Ala Bidzikrillah, Jiancong Xu and Yazhou Qin
Sensors 2024, 24(18), 6130; https://doi.org/10.3390/s24186130 - 23 Sep 2024
Viewed by 814
Abstract
Road surface quality is essential for driver comfort and safety, making it crucial to monitor pavement conditions and detect defects in real time. However, the diversity of defects and the complexity of ambient conditions make it challenging to develop an effective and robust [...] Read more.
Road surface quality is essential for driver comfort and safety, making it crucial to monitor pavement conditions and detect defects in real time. However, the diversity of defects and the complexity of ambient conditions make it challenging to develop an effective and robust classification and detection algorithm. In this study, we adopted a semi-supervised learning approach to train ResNet-18 for image feature retrieval and then classification and detection of pavement defects. The resulting feature embedding vectors from image patches were retrieved, concatenated, and randomly sampled to model a multivariate normal distribution based on the only one-class training pavement image dataset. The calibration pavement image dataset was used to determine the defect score threshold based on the receiver operating characteristic curve, with the Mahalanobis distance employed as a metric to evaluate differences between normal and defect pavement images. Finally, a heatmap derived from the defect score map for the testing dataset was overlaid on the original pavement images to provide insight into the network’s decisions and guide measures to improve its performance. The results demonstrate that the model’s classification accuracy improved from 0.868 to 0.887 using the expanded and augmented pavement image data based on the analysis of heatmaps. Full article
Show Figures

Figure 1

Previous Issue
Back to TopTop