Sensors

34 pages, 1278 KiB

Open AccessReview

Exploring the Potential of Microservices in Internet of Things: A Systematic Review of Security and Prospects

by Abir El Akhdar, Chafik Baidada, Ali Kartit, Mohamed Hanine, Carlos Osorio García, Roberto Garcia Lara and Imran Ashraf

Sensors 2024, 24(20), 6771; https://doi.org/10.3390/s24206771 - 21 Oct 2024

Viewed by 891

Abstract

With the rapid growth of Internet of Things (IoT) systems, ensuring robust security measures has become paramount. Microservices Architecture (MSA) has emerged as a promising approach for enhancing IoT systems security, yet its adoption in this context lacks comprehensive analysis. This systematic review [...] Read more.

With the rapid growth of Internet of Things (IoT) systems, ensuring robust security measures has become paramount. Microservices Architecture (MSA) has emerged as a promising approach for enhancing IoT systems security, yet its adoption in this context lacks comprehensive analysis. This systematic review addresses this research gap by examining the incorporation of MSA in IoT systems from 2010 to 2024. From an initial pool of 4388 studies, selected articles underwent thorough quality assessment with weighted critical appraisal questions and a defined inclusion threshold. This study represents the first comprehensive systematic review to investigate the potential of microservices in IoT, with a particular focus on security aspects. The review explores the merits of MSA, highlighting twelve benefits, eight key challenges, and eight security risks. Additionally, the eight best practices for implementing MSA in IoT systems are extracted. The findings underscore MSA’s utility in fortifying IoT security while also acknowledging complexities and potential vulnerabilities. Moreover, the study calls attention to the importance of incorporating complementary technologies including blockchain and machine learning to address identified gaps effectively. Finally, we propose a taxonomic classification for Microservice-based IoT security patterns, facilitating the categorization and organization of security measures in this context. Such a review can help researchers and practitioners identify existing gaps, highlight potential research directions, and provide guidelines for designing secure and efficient microservice-based IoT systems. Full article

(This article belongs to the Section Internet of Things)

► Show Figures

Figure 1

16 pages, 4662 KiB

Open AccessArticle

How to Make the Skin Contact Area Controllable by Optical Calibration in Wearable Tactile Displays of Softness

by Gabriele Frediani and Federico Carpi

Sensors 2024, 24(20), 6770; https://doi.org/10.3390/s24206770 - 21 Oct 2024

Viewed by 694

Abstract

Virtual reality systems may benefit from wearable (fingertip-mounted) haptic displays capable of rendering the softness of virtual objects. According to neurophysiological evidence, the easiest reliable way to render a virtual softness is to generate purely tactile (as opposed to kinaesthetic) feedback to be [...] Read more.

Virtual reality systems may benefit from wearable (fingertip-mounted) haptic displays capable of rendering the softness of virtual objects. According to neurophysiological evidence, the easiest reliable way to render a virtual softness is to generate purely tactile (as opposed to kinaesthetic) feedback to be delivered via a finger-pulp-interfaced deformable surface. Moreover, it is necessary to control not only the skin indentation depth by applying quasi-static (non-vibratory) contact pressures, but also the skin contact area. This is typically impossible with available devices, even with those that can vary the contact area, because the latter cannot be controlled due to the complexity of sensing it at high resolutions. This causes indetermination on an important tactile cue to render softness. Here, we present a technology that allows the contact area to be open-loop controlled via personalised optical calibrations. We demonstrate the solution on a modified, pneumatic wearable tactile display of softness previously described by us, consisting of a small chamber containing a transparent membrane inflated against the finger pulp. A window on the device allowed for monitoring the skin contact area with a camera from an external unit to generate a calibration curve by processing photos of the skin membrane interface at different pressures. The solution was validated by comparisons with an ink-stain-based method. Moreover, to avoid manual calibrations, a preliminary automated procedure was developed. This calibration strategy may be applied also to other kinds of displays where finger pulps are in contact with transparent deformable structures. Full article

(This article belongs to the Special Issue Virtual Reality and Sensing Techniques for Human)

► Show Figures

Figure 1

23 pages, 3739 KiB

Open AccessArticle

The Shared Experience Actor–Critic (SEAC) Approach for Allocating Radio Resources and Mitigating Resource Collisions in 5G-NR-V2X Mode 2 Under Aperiodic Traffic Conditions

by Sawera Aslam, Daud Khan and KyungHi Chang

Sensors 2024, 24(20), 6769; https://doi.org/10.3390/s24206769 - 21 Oct 2024

Viewed by 656

Abstract

5G New Radio (NR)-V2X, standardized by 3GPP Release 16, includes a distributed resource allocation Mode, known as Mode 2, that allows vehicles to autonomously select transmission resources using either sensing-based semi-persistent scheduling (SB-SPS) or dynamic scheduling (DS). In unmanaged 5G-NR-V2X scenarios, SB-SPS loses [...] Read more.

5G New Radio (NR)-V2X, standardized by 3GPP Release 16, includes a distributed resource allocation Mode, known as Mode 2, that allows vehicles to autonomously select transmission resources using either sensing-based semi-persistent scheduling (SB-SPS) or dynamic scheduling (DS). In unmanaged 5G-NR-V2X scenarios, SB-SPS loses effectiveness with aperiodic and variable data. DS, while better for aperiodic traffic, faces challenges due to random selection, particularly in high traffic density scenarios, leading to increased collisions. To address these limitations, this study models the Cellular V2X network as a decentralized multi-agent networked Markov decision process (MDP), where each vehicle agent uses the Shared Experience Actor–Critic (SEAC) technique to optimize performance. The superiority of SEAC over SB-SPS and DS is demonstrated through simulations, showing that the SEAC with an N-step approach achieves an average improvement of approximately 18–20% in enhancing reliability, reducing collisions, and improving resource utilization under high vehicular density scenarios with aperiodic traffic patterns. Full article

(This article belongs to the Special Issue Advanced Vehicular Ad Hoc Networks: 2nd Edition)

► Show Figures

Figure 1

21 pages, 18455 KiB

Open AccessArticle

Marine Oil Pollution Monitoring Based on a Morphological Attention U-Net Using SAR Images

by Lena Chang, Yi-Ting Chen, Ching-Min Cheng, Yang-Lang Chang and Shang-Chih Ma

Sensors 2024, 24(20), 6768; https://doi.org/10.3390/s24206768 - 21 Oct 2024

Viewed by 662

Abstract

This study proposed an improved full-scale aggregated MobileUNet (FA-MobileUNet) model to achieve more complete detection results of oil spill areas using synthetic aperture radar (SAR) images. The convolutional block attention module (CBAM) in the FA-MobileUNet was modified based on morphological concepts. By introducing [...] Read more.

This study proposed an improved full-scale aggregated MobileUNet (FA-MobileUNet) model to achieve more complete detection results of oil spill areas using synthetic aperture radar (SAR) images. The convolutional block attention module (CBAM) in the FA-MobileUNet was modified based on morphological concepts. By introducing the morphological attention module (MAM), the improved FA-MobileUNet model can reduce the fragments and holes in the detection results, providing complete oil spill areas which were more suitable for describing the location and scope of oil pollution incidents. In addition, to overcome the inherent category imbalance of the dataset, label smoothing was applied in model training to reduce the model’s overconfidence in majority class samples while improving the model’s generalization ability. The detection performance of the improved FA-MobileUNet model reached an mIoU (mean intersection over union) of 84.55%, which was 17.15% higher than that of the original U-Net model. The effectiveness of the proposed model was then verified using the oil pollution incidents that significantly impacted Taiwan’s marine environment. Experimental results showed that the extent of the detected oil spill was consistent with the oil pollution area recorded in the incident reports. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

13 pages, 1777 KiB

Open AccessArticle

Blind Recognition of Frame Synchronization Based on Deep Learning

by Jiazheng Wei, Shitian Zhang, Mingchao Jin, Xiandeng He, Dongxiao Quan and Chen Chen

Sensors 2024, 24(20), 6767; https://doi.org/10.3390/s24206767 - 21 Oct 2024

Viewed by 598

Abstract

In this paper, a deep-learning-based frame synchronization blind recognition algorithm is proposed to improve the detection performance in non-cooperative communication systems. Current methods face challenges in accurately detecting frames under high bit error rates (BER). Our approach begins with flat-top interpolation of binary [...] Read more.

In this paper, a deep-learning-based frame synchronization blind recognition algorithm is proposed to improve the detection performance in non-cooperative communication systems. Current methods face challenges in accurately detecting frames under high bit error rates (BER). Our approach begins with flat-top interpolation of binary data and converting it into a series of grayscale images, enabling the application of image processing techniques. By incorporating a scaling factor, we generate RGB images. Based on the matching radius, frame length, and frame synchronization code, RGB images with distinct stripe features are classified as positive samples for each category, while the remaining images are classified as negative samples. Finally, the neural network is trained on these sets to classify test data effectively. Simulation results demonstrate that the proposed algorithm achieves a 100% probability in frame recognition when BER is below 0.2. Even with a BER of 0.25, the recognition probability remains above 90%, which exhibits a performance improvement of over 60% compared with traditional algorithms. This work addresses the shortcomings of existing methods under high error conditions, and the idea of converting sequences into RGB images also provides a reliable solution for frame synchronization in challenging communication environments. Full article

(This article belongs to the Section Communications)

► Show Figures

Figure 1

38 pages, 16115 KiB

Open AccessArticle

Neural Approach to Coordinate Transformation for LiDAR–Camera Data Fusion in Coastal Observation

by Ilona Garczyńska-Cyprysiak, Witold Kazimierski and Marta Włodarczyk-Sielicka

Sensors 2024, 24(20), 6766; https://doi.org/10.3390/s24206766 - 21 Oct 2024

Viewed by 809

Abstract

The paper presents research related to coastal observation using a camera and LiDAR (Light Detection and Ranging) mounted on an unmanned surface vehicle (USV). Fusion of data from these two sensors can provide wider and more accurate information about shore features, utilizing the [...] Read more.

The paper presents research related to coastal observation using a camera and LiDAR (Light Detection and Ranging) mounted on an unmanned surface vehicle (USV). Fusion of data from these two sensors can provide wider and more accurate information about shore features, utilizing the synergy effect and combining the advantages of both systems. Fusion is used in autonomous cars and robots, despite many challenges related to spatiotemporal alignment or sensor calibration. Measurements from various sensors with different timestamps have to be aligned, and the measurement systems need to be calibrated to avoid errors related to offsets. When using data from unstable, moving platforms, such as surface vehicles, it is more difficult to match sensors in time and space, and thus, data acquired from different devices will be subject to some misalignment. In this article, we try to overcome these problems by proposing the use of a point matching algorithm for coordinate transformation for data from both systems. The essence of the paper is to verify algorithms based on selected basic neural networks, namely the multilayer perceptron (MLP), the radial basis function network (RBF), and the general regression neural network (GRNN) for the alignment process. They are tested with real recorded data from the USV and verified against numerical methods commonly used for coordinate transformation. The results show that the proposed approach can be an effective solution as an alternative to numerical calculations, due to process improvement. The image data can provide information for identifying characteristic objects, and the obtained accuracies for platform dynamics in the water environment are satisfactory (root mean square error—RMSE—smaller than 1 m in many cases). The networks provided outstanding results for the training set; however, they did not perform as well as expected, in terms of the generalization capability of the model. This leads to the conclusion that processing algorithms cannot overcome the limitations of matching point accuracy. Further research will extend the approach to include information on the position and direction of the vessel. Full article

(This article belongs to the Special Issue Multi-Sensor Data Fusion)

► Show Figures

Figure 1

19 pages, 8857 KiB

Open AccessArticle

Enhanced Vital Parameter Estimation Using Short-Range Radars with Advanced Motion Compensation and Super-Resolution Techniques

by Sewon Yoon, Seungjae Baek, Inoh Choi, Soobum Kim, Bontae Koo, Youngseok Baek, Jooho Jung, Sanghong Park and Min Kim

Sensors 2024, 24(20), 6765; https://doi.org/10.3390/s24206765 - 21 Oct 2024

Viewed by 648

Abstract

Various short-range radars, such as impulse-radio ultra-wideband (IR-UWB) and frequency-modulated continuous-wave (FMCW) radars, are currently employed to monitor vital signs, including respiratory and cardiac rates (RRs and CRs). However, these methods do not consider the motion of an individual, which can distort the [...] Read more.

Various short-range radars, such as impulse-radio ultra-wideband (IR-UWB) and frequency-modulated continuous-wave (FMCW) radars, are currently employed to monitor vital signs, including respiratory and cardiac rates (RRs and CRs). However, these methods do not consider the motion of an individual, which can distort the phase of the reflected signal, leading to inaccurate estimation of RR and CR because of a smeared spectrum. Therefore, motion compensation (MOCOM) is crucial for accurately estimating these vital rates. This paper proposes an efficient method incorporating MOCOM to estimate RR and CR with super-resolution accuracy. The proposed method effectively models the radar signal phase and compensates for motion. Additionally, applying the super-resolution technique to RR and CR separately further increases the estimation accuracy. Experimental results from the IR-UWB and FMCW radars demonstrate that the proposed method successfully estimates RRs and CRs even in the presence of body movement. Full article

(This article belongs to the Special Issue Advances in IoT, AI and Sensor-Based Technologies for Disease Treatment, Health Promotion and Ageing Well)

► Show Figures

Figure 1

16 pages, 3331 KiB

Open AccessArticle

Piezo-VFETs: Vacuum Field Emission Transistors Controlled by Piezoelectric MEMS Sensors as an Artificial Mechanoreceptor with High Sensitivity and Low Power Consumption

by Chang Ge, Yuezhong Chen, Daolong Yu, Zhixia Liu and Ji Xu

Sensors 2024, 24(20), 6764; https://doi.org/10.3390/s24206764 - 21 Oct 2024

Viewed by 623

Abstract

As one of the most promising electronic devices in the post-Moore era, nanoscale vacuum field emission transistors (VFETs) have garnered significant attention due to their unique electron transport mechanism featuring ballistic transport within vacuum channels. Existing research on these nanoscale vacuum channel devices [...] Read more.

As one of the most promising electronic devices in the post-Moore era, nanoscale vacuum field emission transistors (VFETs) have garnered significant attention due to their unique electron transport mechanism featuring ballistic transport within vacuum channels. Existing research on these nanoscale vacuum channel devices has primarily focused on structural design for logic circuits. Studies exploring their application potential in other vital fields, such as sensors based on VFET, are more limited. In this study, for the first time, the design of a vacuum field emission transistor (VFET) coupled with a piezoelectric microelectromechanical (MEMS) sensing unit is proposed as the artificial mechanoreceptor for sensing purposes. With a negative threshold voltage similar to an N-channel depletion-mode metal oxide silicon field effect transistor, the proposed VFET has its continuous current tuned by the piezoelectric potential generated by the sensing unit, amplifying the magnitude of signals resulting from electromechanical coupling. Simulations have been conducted to validate the feasibility of such a configuration. As indictable from the simulation results, the proposed piezoelectric VFET exhibits high sensitivity and an electrically adjustable measurement range. Compared to the traditional combination of piezoelectric MEMS sensors and solid-state field effect transistors (FETs), the piezoelectric VFET design has a significantly reduced power consumption thanks to its continuous current that is orders of magnitude smaller. These findings reveal the immense potential of piezoelectric VFET in sensing applications, building up the basis for using VFETs for simple, effective, and low-power pre-amplification of piezoelectric MEMS sensors and broadening the application scope of VFET in general. Full article

(This article belongs to the Special Issue Advanced Sensors in MEMS: 2nd Edition)

► Show Figures

Figure 1

12 pages, 5253 KiB

Open AccessCommunication

Hand Gesture Recognition Using Ultrasonic Array with Machine Learning

by Jaewoo Joo, Jinhwan Koh and Hyungkeun Lee

Sensors 2024, 24(20), 6763; https://doi.org/10.3390/s24206763 - 21 Oct 2024

Viewed by 747

Abstract

In the field of gesture recognition technology, accurately detecting human gestures is crucial. In this research, ultrasonic transducers were utilized for gesture recognition. Due to the wide beamwidth of ultrasonic transducers, it is difficult to effectively distinguish between multiple objects within a single [...] Read more.

In the field of gesture recognition technology, accurately detecting human gestures is crucial. In this research, ultrasonic transducers were utilized for gesture recognition. Due to the wide beamwidth of ultrasonic transducers, it is difficult to effectively distinguish between multiple objects within a single beam. However, they are effective at accurately identifying individual objects. To leverage this characteristic of the ultrasonic transducer as an advantage, this research involved constructing an ultrasonic array. This array was created by arranging eight transmitting transducers in a circular formation and placing a single receiving transducer at the center. Through this, a wide beam area was formed extensively, enabling the measurement of unrestricted movement of a single hand in the X, Y, and Z axes. Hand gesture data were collected at distances of 10 cm, 30 cm, 50 cm, 70 cm, and 90 cm from the array. The collected data were trained and tested using a customized Convolutional Neural Network (CNN) model, demonstrating high accuracy on raw data, which is most suitable for immediate interaction with computers. The proposed system achieved over 98% accuracy. Full article

(This article belongs to the Section Electronic Sensors)

► Show Figures

Figure 1

24 pages, 8668 KiB

Open AccessArticle

Mobile Application Development for Prepaid Water Meter Based on LC Sensor

by Ario Kusuma Purboyo, Hanif Fakhrurroja, Dita Pramesti and Achmad Rozan Chaidir

Sensors 2024, 24(20), 6762; https://doi.org/10.3390/s24206762 - 21 Oct 2024

Viewed by 1153

Abstract

This study presents a novel low-cost and low-power prepaid water meter system that combines tokenization and LC sensors to monitor water consumption accurately with mobile application via Bluetooth Low Energy (BLE) connectivity compared to conventional meters. Water meters play a vital role in [...] Read more.

This study presents a novel low-cost and low-power prepaid water meter system that combines tokenization and LC sensors to monitor water consumption accurately with mobile application via Bluetooth Low Energy (BLE) connectivity compared to conventional meters. Water meters play a vital role in monitoring water usage in Indonesia. Postpaid billing methods that rely on manual data recording are a source of concern due to potential inaccuracies caused by human error. This study presents the development of a prepaid water meter system that integrates LC sensors, BLE connectivity, a tokenization mechanism, and a mobile application to address this issue. The system offers a cost-effective solution by utilizing BLE + Global System for Mobile (GSM) from the user’s mobile phone. Using the design thinking methodology, the mobile application for the prepaid water meter achieved a usability testing score of 80. The load testing results for the back-end server, conducted with a sample size of 515 users, revealed a back-end latency of 1.973 milliseconds and an error rate of 8.74%. Furthermore, the LC sensors integrated into the PWM device showed an average error rate of 1.33%. The power consumption during each work cycle was measured at 129 mA and each battery is expected to last six years. Overall, with simple LC sensors, this system can precisely measure water usage. Full article

(This article belongs to the Special Issue Innovative Applications and Strategies for IoT)

► Show Figures

Figure 1

40 pages, 12728 KiB

Open AccessArticle

Structure-Based Training: A Training Method Aimed at Pixel Errors for a Correlation-Coefficient-Based Neural Network

by Jun Su, Wei He, Yingguan Wang, Zhiyong Bu and Tiantian Zhang

Sensors 2024, 24(20), 6761; https://doi.org/10.3390/s24206761 - 21 Oct 2024

Viewed by 578

Abstract

In research on building a one-shot learning neural network without pre-training using mass data, the limitation on the information obtained from a single training sample downgrades the performance of the network. In order to improve performance and take full advantage of the support [...] Read more.

In research on building a one-shot learning neural network without pre-training using mass data, the limitation on the information obtained from a single training sample downgrades the performance of the network. In order to improve performance and take full advantage of the support set, in this study, we design three kinds of shadow nodes and propose a structure-based training method for a correlation-coefficient-based neural network. This training strategy focuses on branches that are not activated or inactivated as expected. In contrast to existing networks that optimize the parameters using back-propagation, the training method proposed in this paper optimizes the structure of the correlation-coefficient-based network by correcting its pixel errors. For the shadow nodes and training process based on this strategy, the intersection over union (IOU) of a detected target increases by 4.83% in the experiments when using the Fashion-Mnist dataset, increases by 4.02% when using the Omniglot dataset, and increases by 3.89% when using the Cifar-10 dataset. The samples in category “7” wrongly classified as “1” decreased by 27.32% when using the Mnist dataset after training. This training strategy, along with shadow nodes, makes the correlation-coefficient-based network a more practical model and enables the network to develop during the accumulation of reliable samples, thus making it more suitable for simple target detection projects that collect samples over time. Moreover, the shadow nodes and training method proposed in this paper supplement the non-gradient-based parameter-gaining strategy. Additionally, it is a new attempt to explore the imitation of a human’s ability to learn a new pattern from a low number of references. Full article

(This article belongs to the Section Sensor Networks)

► Show Figures

Figure 1

21 pages, 10071 KiB

Open AccessArticle

Deformation Monitoring and Analysis of Baige Landslide (China) Based on the Fusion Monitoring of Multi-Orbit Time-Series InSAR Technology

by Kai Ye, Zhe Wang, Ting Wang, Ying Luo, Yiming Chen, Jiaqian Zhang and Jialun Cai

Sensors 2024, 24(20), 6760; https://doi.org/10.3390/s24206760 - 21 Oct 2024

Viewed by 913

Abstract

Due to the limitations inherent in SAR satellite imaging modes, utilizing time-series InSAR technology to process single-orbit satellite image data typically only yields one-dimensional deformation information along the LOS direction. This constraint impedes a comprehensive representation of the true surface deformation of landslides. [...] Read more.

Due to the limitations inherent in SAR satellite imaging modes, utilizing time-series InSAR technology to process single-orbit satellite image data typically only yields one-dimensional deformation information along the LOS direction. This constraint impedes a comprehensive representation of the true surface deformation of landslides. Consequently, in this paper, after the SBAS-InSAR and PS-InSAR processing of the 30-view ascending and 30-view descending orbit images of the Sentinel-1A satellite, based on the imaging geometric relationship of the SAR satellite, we propose a novel computational method of fusing ascending and descending orbital LOS-direction time-series deformation to extract the landslide’s downslope direction deformation of landslides. By applying this method to Baige landslide monitoring and integrating it with an improved tangential angle warning criterion, we classified the landslide’s trailing edge into a high-speed, a uniform-speed, and a low-speed deformation region, with deformation magnitudes of 7~8 cm, 5~7 cm, and 3~4 cm, respectively. A comparative analysis with measured data for landslide deformation monitoring revealed that the average root mean square error between the fused landslide’s downslope direction deformation and the measured data was a mere 3.62 mm. This represents a reduction of 56.9% and 57.5% in the average root mean square error compared to the single ascending and descending orbit LOS-direction time-series deformations, respectively, indicating higher monitoring accuracy. Finally, based on the analysis of landslide deformation and its inducing factors derived from the calculated time-series deformation results, it was determined that the precipitation, lithology of the strata, and ongoing geological activity are significant contributors to the sliding of the Baige land-slide. This method offers more comprehensive and accurate surface deformation information for dynamic landslide monitoring, aiding relevant departments in landslide surveillance and management, and providing technical recommendations for the fusion of multi-orbital satellite LOS-direction deformations to accurately reconstruct the true surface deformation of landslides. Full article

(This article belongs to the Special Issue Editorial Board Members’ Collection Series: Application of InSAR Technology in Geodesy, Earthquake, Landslides and Other Disaster Warning)

► Show Figures

Figure 1

15 pages, 535 KiB

Open AccessArticle

Thought-Controlled Computer Applications: A Brain–Computer Interface System for Severe Disability Support

by Kais Belwafi and Fakhreddine Ghaffari

Sensors 2024, 24(20), 6759; https://doi.org/10.3390/s24206759 - 21 Oct 2024

Viewed by 836

Abstract

This study introduces an integrated computational environment that leverages Brain–Computer Interface (BCI) technology to enhance information access for individuals with severe disabilities. Traditional assistive technologies often rely on physical interactions, which can be challenging for this demographic. Our innovation focuses on creating new [...] Read more.

This study introduces an integrated computational environment that leverages Brain–Computer Interface (BCI) technology to enhance information access for individuals with severe disabilities. Traditional assistive technologies often rely on physical interactions, which can be challenging for this demographic. Our innovation focuses on creating new assistive technologies that use novel Human–Computer interfaces to provide a more intuitive and accessible experience. The proposed system offers four key applications to users controlled by four thoughts: an email client, a web browser, an e-learning tool, and both command-line and graphical user interfaces for managing computer resources. The BCI framework translates ElectroEncephaloGraphy (EEG) signals into commands or events using advanced signal processing and machine learning techniques. These identified commands are then processed by an integrative strategy that triggers the appropriate actions and provides real-time feedback on the screen. Our study shows that our framework achieved an 82% average classification accuracy using four distinct thoughts of 62 subjects and a 95% recognition rate for P300 signals from two users, highlighting its effectiveness in translating brain signals into actionable commands. Unlike most existing prototypes that rely on visual stimulation, our system is controlled by thought, inducing brain activity to manage the system’s Application Programming Interfaces (APIs). It switches to P300 mode for a virtual keyboard and text input. The proposed BCI system significantly improves the ability of individuals with severe disabilities to interact with various applications and manage computer resources. Our approach demonstrates superior performance in terms of classification accuracy and signal recognition compared to existing methods. Full article

(This article belongs to the Special Issue Advanced Non-Invasive Sensors: Methods and Applications)

► Show Figures

Figure 1

14 pages, 860 KiB

Open AccessArticle

High-Resolution Phase-Based Ranging Using Inverse Fourier Transform in an Iterative Bayesian Approach

by Jan Mazur

Sensors 2024, 24(20), 6758; https://doi.org/10.3390/s24206758 - 21 Oct 2024

Viewed by 511

Abstract

This article proposes an algorithm that determines the distance between two transceivers based on phase information collected in a specific frequency range. Even though we have focused on BLE technology, we do not necessarily adhere strictly to this standard regarding the procedures used [...] Read more.

This article proposes an algorithm that determines the distance between two transceivers based on phase information collected in a specific frequency range. Even though we have focused on BLE technology, we do not necessarily adhere strictly to this standard regarding the procedures used to obtain phased samples. We assume that phase samples are given and propose an algorithm using a Bayesian approach to find delays in a multi-path environment. Analyzing these delays allows for determining the distance between both transceivers. We show several examples confirming the high accuracy and resolution of the proposed algorithm. Finally, we conclude with some pros and cons of the proposed solution, suggesting its use in such applications as, for example, virtual acoustics. Full article

(This article belongs to the Section Sensor Networks)

► Show Figures

Figure 1

14 pages, 3654 KiB

Open AccessArticle

Research on Road Internal Disease Identification Algorithm Based on Attention Fusion Mechanisms

by Yangyang Wang, Shoujing Yan, Chenchen Xi, Zhi Yu, Chunpeng Zhou, Fengxia Chi and Jintao Wei

Sensors 2024, 24(20), 6757; https://doi.org/10.3390/s24206757 - 21 Oct 2024

Viewed by 589

Abstract

Internal disease in asphalt pavement is a crucial indicator of pavement health and serves as a vital basis for maintenance and rehabilitation decisions. It is closely related to the optimization and allocation of funds by highway maintenance management departments. Accurate and rapid identification [...] Read more.

Internal disease in asphalt pavement is a crucial indicator of pavement health and serves as a vital basis for maintenance and rehabilitation decisions. It is closely related to the optimization and allocation of funds by highway maintenance management departments. Accurate and rapid identification of internal pavement diseases is essential for improving overall pavement quality. This study aimed to identify internal pavement diseases using deep learning algorithms, thereby improving the efficiency of determining internal pavement diseases. In this work, a multi-view recognition algorithm model based on deep learning is proposed, with attention fusion mechanisms embedded both between channels and between views. By comparing and analyzing the training and recognition results of different neural networks, it was found that the multi-view recognition algorithm model based on attention fusion demonstrates the best performance in identifying internal pavement diseases. Full article

(This article belongs to the Section Fault Diagnosis & Sensors)

► Show Figures

Figure 1

11 pages, 1876 KiB

Open AccessArticle

Blood Biomarker Detection Using Integrated Microfluidics with Optical Label-Free Biosensor

by Chiung-Hsi Li, Chen-Yuan Chang, Yan-Ru Chen and Cheng-Sheng Huang

Sensors 2024, 24(20), 6756; https://doi.org/10.3390/s24206756 - 21 Oct 2024

Viewed by 776

Abstract

In this study, we developed an optofluidic chip consisting of a guided-mode resonance (GMR) sensor incorporated into a microfluidic chip to achieve simultaneous blood plasma separation and label-free albumin detection. A sedimentation chamber is integrated into the microfluidic chip to achieve plasma separation [...] Read more.

In this study, we developed an optofluidic chip consisting of a guided-mode resonance (GMR) sensor incorporated into a microfluidic chip to achieve simultaneous blood plasma separation and label-free albumin detection. A sedimentation chamber is integrated into the microfluidic chip to achieve plasma separation through differences in density. After a blood sample is loaded into the optofluidic chip in two stages with controlled flow rates, the blood cells are kept in the sedimentation chamber, enabling only the plasma to reach the GMR sensor for albumin detection. This GMR sensor, fabricated using plastic replica molding, achieved a bulk sensitivity of 175.66 nm/RIU. With surface-bound antibodies, the GMR sensor exhibited a limit of detection of 0.16 μg/mL for recombinant albumin in buffer solution. Overall, our findings demonstrate the potential of our integrated chip for use in clinical samples for biomarker detection in point-of-care applications. Full article

(This article belongs to the Collection Sensors, Image, and Signal Processing for Biomedical Applications)

► Show Figures

Graphical abstract

14 pages, 3862 KiB

Open AccessArticle

Comparison of Lower-Limb Muscle Synergies Between Young and Old People During Cycling Based on Electromyography Sensors—A Preliminary Cross-Sectional Study

by Li Kong, Kun Yang, Haojie Li, Xie Wu and Qiang Zhang

Sensors 2024, 24(20), 6755; https://doi.org/10.3390/s24206755 - 21 Oct 2024

Viewed by 686

Abstract

The purpose of this study was to analyze the lower-limb muscle synergies of young and older adults during stationary cycling across various mechanical conditions to reveal adaptive strategies employed by the elderly to address various common pedaling tasks and function degradation. By comparing [...] Read more.

The purpose of this study was to analyze the lower-limb muscle synergies of young and older adults during stationary cycling across various mechanical conditions to reveal adaptive strategies employed by the elderly to address various common pedaling tasks and function degradation. By comparing lower-limb muscle synergies during stationary cycling between young and old people, this study examined changes in muscle synergy patterns during exercise in older individuals. This is crucial for understanding neuromuscular degeneration and changes in movement patterns in older individuals. Sixteen young and sixteen older experienced cyclists were recruited to perform stationary cycling tasks at two levels of power (60 and 100 W) and three cadences (40, 60, and 90 rpm) in random order. The lower-limb muscle synergies and their inter- and intra-individual variability were analyzed. Three synergies were extracted in this study under all riding conditions in both groups while satisfying overall variance accounted for (VAF) > 85% and muscle VAF > 75%. The older adults exhibited lower variability in synergy vector two and a higher trend in the variability of activation coefficient three, as determined by calculating the variance ratio. Further analyses of muscle synergy structures revealed increased weighting in major contribution muscles, the forward-shifting peak activation in synergy one, and lower peak magnitude in synergy three among older adults. To produce the same cycling power and cadence as younger individuals, older adults make adaptive adjustments in muscle control—increased weighting in major contribution muscles, greater consistency in the use of primary force-producing synergies, and earlier peak activation of subsequent synergy. Full article

(This article belongs to the Special Issue Combining Machine Learning and Sensors in Human Movement Biomechanics)

► Show Figures

Figure 1

13 pages, 10871 KiB

Open AccessCommunication

Spatial Resolution Enhancement Framework Using Convolutional Attention-Based Token Mixer

by Mingyuan Peng, Canhai Li, Guoyuan Li and Xiaoqing Zhou

Sensors 2024, 24(20), 6754; https://doi.org/10.3390/s24206754 - 21 Oct 2024

Viewed by 543

Abstract

Spatial resolution enhancement in remote sensing data aims to augment the level of detail and accuracy in images captured by satellite sensors. We proposed a novel spatial resolution enhancement framework using the convolutional attention-based token mixer method. This approach leveraged spatial context and [...] Read more.

Spatial resolution enhancement in remote sensing data aims to augment the level of detail and accuracy in images captured by satellite sensors. We proposed a novel spatial resolution enhancement framework using the convolutional attention-based token mixer method. This approach leveraged spatial context and semantic information to improve the spatial resolution of images. This method used the multi-head convolutional attention block and sub-pixel convolution to extract spatial and spectral information and fused them using the same technique. The multi-head convolutional attention block can effectively utilize the local information of spatial and spectral dimensions. The method was tested on two kinds of data types, which were the visual-thermal dataset and the visual-hyperspectral dataset. Our method was also compared with the state-of-the-art methods, including traditional methods and deep learning methods. The experiment results showed that the method was effective and outperformed state-of-the-art methods in overall, spatial, and spectral accuracies. Full article

(This article belongs to the Collection Remote Sensing Image Processing)

► Show Figures

Figure 1

24 pages, 14731 KiB

Open AccessArticle

Classification, Localization and Quantization of Eddy Current Detection Defects in CFRP Based on EDC-YOLO

by Rongyan Wen, Chongcong Tao, Hongli Ji and Jinhao Qiu

Sensors 2024, 24(20), 6753; https://doi.org/10.3390/s24206753 - 21 Oct 2024

Viewed by 621

Abstract

The accurate detection and quantification of defects is vital for the effectiveness of the eddy current nondestructive testing (ECNDT) of carbon fiber-reinforced plastic (CFRP) materials. This study investigates the identification and measurement of three common CFRP defects—cracks, delamination, and low-velocity impact damage—by employing [...] Read more.

The accurate detection and quantification of defects is vital for the effectiveness of the eddy current nondestructive testing (ECNDT) of carbon fiber-reinforced plastic (CFRP) materials. This study investigates the identification and measurement of three common CFRP defects—cracks, delamination, and low-velocity impact damage—by employing the You Only Look Once (YOLO) model and an improved Eddy Current YOLO (EDC-YOLO) model. YOLO’s limitations in detecting multi-scale features are addressed through the integration of Transformer-based self-attention mechanisms and deformable convolutional sub-modules, with additional global feature extraction via CBAM. By leveraging the Wise-IoU loss function, the model performance is further enhanced, leading to a 4.4% increase in the mAP50 for defect detection. EDC-YOLO proves to be effective for defect identification and quantification in industrial inspections, providing detailed insights, such as the correlation between the impact damage size and energy levels. Full article

(This article belongs to the Section Fault Diagnosis & Sensors)

► Show Figures

Figure 1

20 pages, 2288 KiB

Open AccessArticle

Deep Neural Network-Based Cigarette Filter Defect Detection System with FPGA Acceleration for Online Recognition

by Liang Huang, Qiongxia Shen, Chao Jiang and You Yang

Sensors 2024, 24(20), 6752; https://doi.org/10.3390/s24206752 - 21 Oct 2024

Viewed by 595

Abstract

In the cigarette manufacturing industry, machine vision and artificial intelligence algorithms have been employed to improve production efficiency by detecting product defects. However, achieving both high accuracy and real-time defect detection for cigarettes with complex patterns remains a challenge. To address these issues, [...] Read more.

In the cigarette manufacturing industry, machine vision and artificial intelligence algorithms have been employed to improve production efficiency by detecting product defects. However, achieving both high accuracy and real-time defect detection for cigarettes with complex patterns remains a challenge. To address these issues, this study proposes a model based on RESNET18, combined with a feature enhancement algorithm, to improve detection accuracy. Additionally, a method is designed to deploy the model on a field-programmable gate array (FPGA) with high parallel processing capabilities to achieve high-speed detection. Experimental results demonstrate that the proposed detection model achieves a detection accuracy of 95.88% on a cigarette filter defect dataset with an end-to-end detection speed of only 9.38 ms. Full article

(This article belongs to the Section Industrial Sensors)

► Show Figures

Graphical abstract

20 pages, 5033 KiB

Open AccessArticle

Lumbar Sitting Behavior of Individuals with Low Back Pain: A Preliminary Study Using Extended Real-World Data

by Frederick A. McClintock, Andrew J. Callaway, Carol J. Clark, Raee S. Alqhtani and Jonathan M. Williams

Sensors 2024, 24(20), 6751; https://doi.org/10.3390/s24206751 - 21 Oct 2024

Viewed by 949

Abstract

Low back pain affects 619 million people worldwide and is commonly provoked by sitting. Current assessment methods constrain task variability, removing real-world, task-switching behaviors. This study utilized accelerometers to provide an original validated method of in vivo real-world assessment of lumbar sitting behavior [...] Read more.

Low back pain affects 619 million people worldwide and is commonly provoked by sitting. Current assessment methods constrain task variability, removing real-world, task-switching behaviors. This study utilized accelerometers to provide an original validated method of in vivo real-world assessment of lumbar sitting behavior throughout a full day. A three-stage study design was used, which involved (1) blinded verification of our sitting detection algorithm, (2) full-day data collection from participants with low back discomfort, quantifying lumbar angles, and end-user acceptability explored, (3) case study application to two clinical low back pain (LBP) patients, incorporating measurement of provocative sitting. Focus group discussions demonstrated that data collection methods were acceptable. Sitting ‘windows’ were created and analyzed using novel histograms, amplitude probability distribution functions, and variability, demonstrating that sitting behavior was unique and varied across individuals. One LBP patient demonstrated two frequent lumbar postures (<15% flexion and ~75% flexion), with pain provocation at 62% lumbar flexion. The second patient demonstrated a single dominant posture (~90% flexion), with pain provoked at 86% lumbar flexion. Our in vivo approach offers an acceptable method to gain new insights into provocative sitting behavior in individuals with LBP, allowing individualized unconstrained data for full-day postures and pain provocation behaviors to be quantified, which are otherwise unattainable. Full article

(This article belongs to the Special Issue Applications of Body Worn Sensors and Wearables)

► Show Figures

Figure 1

23 pages, 4902 KiB

Open AccessArticle

Concatenated CNN-Based Pneumonia Detection Using a Fuzzy-Enhanced Dataset

by Abror Shavkatovich Buriboev, Dilnoz Muhamediyeva, Holida Primova, Djamshid Sultanov, Komil Tashev and Heung Seok Jeon

Sensors 2024, 24(20), 6750; https://doi.org/10.3390/s24206750 - 21 Oct 2024

Viewed by 768

Abstract

Pneumonia is a form of acute respiratory infection affecting the lungs. Symptoms of viral and bacterial pneumonia are similar. Rapid diagnosis of the disease is difficult, since polymerase chain reaction-based methods, which have the greatest reliability, provide results in a few hours, while [...] Read more.

Pneumonia is a form of acute respiratory infection affecting the lungs. Symptoms of viral and bacterial pneumonia are similar. Rapid diagnosis of the disease is difficult, since polymerase chain reaction-based methods, which have the greatest reliability, provide results in a few hours, while ensuring high requirements for compliance with the analysis technology and professionalism of the personnel. This study proposed a Concatenated CNN model for pneumonia detection combined with a fuzzy logic-based image improvement method. The fuzzy logic-based image enhancement process is based on a new fuzzification refinement algorithm, with significantly improved image quality and feature extraction for the CCNN model. Four datasets, original and upgraded images utilizing fuzzy entropy, standard deviation, and histogram equalization, were utilized to train the algorithm. The CCNN’s performance was demonstrated to be significantly improved by the upgraded datasets, with the fuzzy entropy-added dataset producing the best results. The suggested CCNN attained remarkable classification metrics, including 98.9% accuracy, 99.3% precision, 99.8% F1-score, and 99.6% recall. Experimental comparisons showed that the fuzzy logic-based enhancement worked significantly better than traditional image enhancement methods, resulting in higher diagnostic precision. This study demonstrates how well deep learning models and sophisticated image enhancement techniques work together to analyze medical images. Full article

(This article belongs to the Special Issue Machine and Deep Learning in Sensing and Imaging)

► Show Figures

Figure 1

11 pages, 1366 KiB

Open AccessArticle

A Method for Compensating Hemoglobin Interference in Total Serum Bilirubin Measurement Using a Simple Two-Wavelength Reflectance Photometer

by Lorenzo Zucchini, Carlos Daniel Coda Zabetta, Miloš Ajčević and Agostino Accardo

Sensors 2024, 24(20), 6749; https://doi.org/10.3390/s24206749 - 20 Oct 2024

Viewed by 1065

Abstract

Neonatal hyperbilirubinemia (NH) is a common condition in newborns, with elevated bilirubin levels potentially causing neurological damage or death. Accurate and timely measurements of total serum bilirubin are essential to prevent these outcomes. Direct spectrophotometry, a reliable method for measuring bilirubin, is particularly [...] Read more.

Neonatal hyperbilirubinemia (NH) is a common condition in newborns, with elevated bilirubin levels potentially causing neurological damage or death. Accurate and timely measurements of total serum bilirubin are essential to prevent these outcomes. Direct spectrophotometry, a reliable method for measuring bilirubin, is particularly useful in constrained settings due to its potential for portable low-cost instrumentation. However, this method is susceptible to interference from hemoglobin, often present due to hemolysis. Typically, this interference is reduced using complex optical filters, reagents, multiple wavelengths, or combinations thereof, which increase costs and complexity while reducing usability. This study presents a hemoglobin compensation algorithm applied to a simple, portable, two-wavelength (465 and 590 nm) reflectance photometer designed to receive 30 µL of plasma or whole blood samples and perform the measurement without any reagents. Testing across five bilirubin and hemoglobin levels (4.96 to 28 mg/dL and 0.06 to 0.99 g/dL, respectively) demonstrated that the algorithm effectively reduces hemoglobin interference and overestimation errors. The overall root mean square error was reduced from 4.86 to 1.45 mg/dL, while the measurement bias decreased from −4.46 to −0.10 mg/dL. This substantial reduction in overestimation errors supports future clinical trials with neonatal blood samples. Full article

(This article belongs to the Special Issue Sensors and Algorithms for Biomarker Detection)

► Show Figures

Figure 1

23 pages, 4145 KiB

Open AccessArticle

A Student Facial Expression Recognition Model Based on Multi-Scale and Deep Fine-Grained Feature Attention Enhancement

by Zhaoyu Shou, Yi Huang, Dongxu Li, Cheng Feng, Huibing Zhang, Yuming Lin and Guangxiang Wu

Sensors 2024, 24(20), 6748; https://doi.org/10.3390/s24206748 - 20 Oct 2024

Viewed by 1063

Abstract

In smart classroom environments, accurately recognizing students’ facial expressions is crucial for teachers to efficiently assess students’ learning states, timely adjust teaching strategies, and enhance teaching quality and effectiveness. In this paper, we propose a student facial expression recognition model based on multi-scale [...] Read more.

In smart classroom environments, accurately recognizing students’ facial expressions is crucial for teachers to efficiently assess students’ learning states, timely adjust teaching strategies, and enhance teaching quality and effectiveness. In this paper, we propose a student facial expression recognition model based on multi-scale and deep fine-grained feature attention enhancement (SFER-MDFAE) to address the issues of inaccurate facial feature extraction and poor robustness of facial expression recognition in smart classroom scenarios. Firstly, we construct a novel multi-scale dual-pooling feature aggregation module to capture and fuse facial information at different scales, thereby obtaining a comprehensive representation of key facial features; secondly, we design a key region-oriented attention mechanism to focus more on the nuances of facial expressions, further enhancing the representation of multi-scale deep fine-grained feature; finally, the fusion of multi-scale and deep fine-grained attention-enhanced features is used to obtain richer and more accurate facial key information and realize accurate facial expression recognition. The experimental results demonstrate that the proposed SFER-MDFAE outperforms the existing state-of-the-art methods, achieving an accuracy of 76.18% on FER2013, 92.75% on FERPlus, 92.93% on RAF-DB, 67.86% on AffectNet, and 93.74% on the real smart classroom facial expression dataset (SCFED). These results validate the effectiveness of the proposed method. Full article

(This article belongs to the Special Issue Machine Learning and Deep Learning in Image/Video Processing and Sensing)

► Show Figures

Figure 1

18 pages, 14512 KiB

Open AccessArticle

Vision-Based Real-Time Bolt Loosening Detection by Identifying Anti-Loosening Lines

by Wenyang Lei, Fang Yuan, Jiang Guo, Haoyang Wang, Zaiming Geng, Tao Wu and Haipeng Gong

Sensors 2024, 24(20), 6747; https://doi.org/10.3390/s24206747 - 20 Oct 2024

Viewed by 1032

Abstract

Bolt loosening detection is crucial for ensuring the safe operation of equipment. This paper presents a vision-based real-time detection method that identifies bolt loosening by recognizing anti-loosening line markers at bolt connections. The method employs the YOLOv10-S deep learning model for high-precision, real-time [...] Read more.

Bolt loosening detection is crucial for ensuring the safe operation of equipment. This paper presents a vision-based real-time detection method that identifies bolt loosening by recognizing anti-loosening line markers at bolt connections. The method employs the YOLOv10-S deep learning model for high-precision, real-time bolt detection, followed by a two-step Fast-SCNN image segmentation technique. This approach effectively isolates the bolt and nut regions, enabling accurate extraction of the anti-loosening line markers. Key intersection points are calculated using ellipse and line fitting techniques, and the loosening angle is determined through spatial projection transformation. The experimental results demonstrate that, for high-resolution images of 2048 × 1024 pixels, the proposed method achieves an average angle detection error of 1.145° with a detection speed of 32 FPS. Compared to traditional methods and other vision-based approaches, this method offers non-contact measurement, real-time detection capabilities, reduced detection error, and general adaptability to various bolt types and configurations, indicating significant application potential. Full article

(This article belongs to the Section Fault Diagnosis & Sensors)

► Show Figures

Figure 1

16 pages, 7311 KiB

Open AccessArticle

Vehicle Localization Method in Complex SAR Images Based on Feature Reconstruction and Aggregation

by Jinwei Han, Lihong Kang, Jing Tian, Mingyong Jiang and Ningbo Guo

Sensors 2024, 24(20), 6746; https://doi.org/10.3390/s24206746 - 20 Oct 2024

Viewed by 645

Abstract

Due to the small size of vehicle targets, complex background environments, and the discrete scattering characteristics of high-resolution synthetic aperture radar (SAR) images, existing deep learning networks face challenges in extracting high-quality vehicle features from SAR images, which impacts vehicle localization accuracy. To [...] Read more.

Due to the small size of vehicle targets, complex background environments, and the discrete scattering characteristics of high-resolution synthetic aperture radar (SAR) images, existing deep learning networks face challenges in extracting high-quality vehicle features from SAR images, which impacts vehicle localization accuracy. To address this issue, this paper proposes a vehicle localization method for SAR images based on feature reconstruction and aggregation with rotating boxes. Specifically, our method first employs a backbone network that integrates the space-channel reconfiguration module (SCRM), which contains spatial and channel attention mechanisms specifically designed for SAR images to extract features. The network then connects a progressive cross-fusion mechanism (PCFM) that effectively combines multi-view features from different feature layers, enhancing the information content of feature maps and improving feature representation quality. Finally, these features containing a large receptive field region and enhanced rich contextual information are input into a rotating box vehicle detection head, which effectively reduces false alarms and missed detections. Experiments on a complex scene SAR image vehicle dataset demonstrate that the proposed method significantly improves vehicle localization accuracy. Our method achieves state-of-the-art performance, which demonstrates the superiority and effectiveness of the proposed method. Full article

(This article belongs to the Special Issue Intelligent SAR Target Detection and Recognition)

► Show Figures

Figure 1

24 pages, 7592 KiB

Open AccessArticle

Decorated Electrode Surfaces with Nanostructures and Metal-Organic Frameworks as Transducers for Sensing

by Sara Caruncho-Pérez, Aida M. Díez, Ana Prado-Comesaña, Marta Pazos, María Ángeles Sanromán and Elisa González-Romero

Sensors 2024, 24(20), 6745; https://doi.org/10.3390/s24206745 - 20 Oct 2024

Viewed by 799

Abstract

In this study, several materials are presented as modifiers of the screen-printed carbon electrodes with the aim of developing new sensing platforms for the voltammetric analysis of drugs. Specifically, Clotiapine and Sulfamethoxazole were selected as models for antipsychotics and antibiotics, respectively. Different nanostructures [...] Read more.

In this study, several materials are presented as modifiers of the screen-printed carbon electrodes with the aim of developing new sensing platforms for the voltammetric analysis of drugs. Specifically, Clotiapine and Sulfamethoxazole were selected as models for antipsychotics and antibiotics, respectively. Different nanostructures were studied as modifiers, including both transition metals and carbon-based materials. Moreover, biochar and two metal-organic frameworks (MOFs) were tested as well. The NH₂-MIL-125(Ti) MOF showed an 80% improvement in the analytical signal of Sulfamethoxazole, but it partially overlapped with an additional signal associated with the loss of the MOF ligand. For this reason, several immobilization strategies were tested, but none of them met the requirements for the development of a sensor for this analyte. Conversely, carbon nanotubes and the NH₂-MIL-101(Fe) MOF were successfully applied for the analysis of Clotiapine in the medicine Etumine^®, with RSD below 2% and relative errors that did not exceed 9% in any case, which demonstrates the precision and accuracy achieved with the tested modifications. Despite these promising results, it was not possible to lower the limits of detection and quantification, so in this sense further investigation must be performed to increase the sensitivity of the developed sensors. Full article

(This article belongs to the Special Issue Next-Generation Screen-Printed and Additive-Manufactured Electrochemical Platforms for Sensing)

► Show Figures

Figure 1

15 pages, 6252 KiB

Open AccessArticle

Passive Inclination Sensor Based on a Patch Antenna with a Reconfigurable Water Load

by Zhuoran Yi, Zihan Xia, Xianzhi Li, Kangqian Xu, Liyu Xie, Songtao Xue and Yiyu Wu

Sensors 2024, 24(20), 6744; https://doi.org/10.3390/s24206744 - 20 Oct 2024

Viewed by 625

Abstract

In order to ensure the safety and preserve the value of historical buildings, inclination is an essential parameter during the continuous structural health monitoring process. However, the wire and price of a traditional sensor limit application. This paper proposes a low-cost inclination sensor [...] Read more.

In order to ensure the safety and preserve the value of historical buildings, inclination is an essential parameter during the continuous structural health monitoring process. However, the wire and price of a traditional sensor limit application. This paper proposes a low-cost inclination sensor based on a patch antenna with a reconfigurable water load. Only the water directly on the antenna is considered effective. The different volume of the effective water load, which is determined by the inclination of the attached surface, will affect the effective permittivity of the dielectric plate of the patch antenna, further causing a variation in the resonant frequency. Therefore, the proposed antenna sensor can monitor the inclination of the attached surface by interrogating the resonant frequency. The working mechanism is first clarified by theoretically investigating the relationship between the dielectric properties and the inclination of the covering medium. The antenna sensor is then simulated using High-Frequency Structure Simulator ver.15 (HFSS 15), which helps to determine geometric parameters and confirm accuracy and sensitivity. An experiment has been conducted based on the design verified in the simulation. The inclination detection shows a correlation coefficient of 0.9771 with a sensitivity of 7.92 MHz/°, indicating a potential for real application. Full article

(This article belongs to the Section Physical Sensors)

► Show Figures

Figure 1

34 pages, 5156 KiB

Open AccessReview

Sensing and Perception in Robotic Weeding: Innovations and Limitations for Digital Agriculture

by Redmond R. Shamshiri, Abdullah Kaviani Rad, Maryam Behjati and Siva K. Balasundram

Sensors 2024, 24(20), 6743; https://doi.org/10.3390/s24206743 - 20 Oct 2024

Viewed by 1249

Abstract

The challenges and drawbacks of manual weeding and herbicide usage, such as inefficiency, high costs, time-consuming tasks, and environmental pollution, have led to a shift in the agricultural industry toward digital agriculture. The utilization of advanced robotic technologies in the process of weeding [...] Read more.

The challenges and drawbacks of manual weeding and herbicide usage, such as inefficiency, high costs, time-consuming tasks, and environmental pollution, have led to a shift in the agricultural industry toward digital agriculture. The utilization of advanced robotic technologies in the process of weeding serves as prominent and symbolic proof of innovations under the umbrella of digital agriculture. Typically, robotic weeding consists of three primary phases: sensing, thinking, and acting. Among these stages, sensing has considerable significance, which has resulted in the development of sophisticated sensing technology. The present study specifically examines a variety of image-based sensing systems, such as RGB, NIR, spectral, and thermal cameras. Furthermore, it discusses non-imaging systems, including lasers, seed mapping, LIDAR, ToF, and ultrasonic systems. Regarding the benefits, we can highlight the reduced expenses and zero water and soil pollution. As for the obstacles, we can point out the significant initial investment, limited precision, unfavorable environmental circumstances, as well as the scarcity of professionals and subject knowledge. This study intends to address the advantages and challenges associated with each of these sensing technologies. Moreover, the technical remarks and solutions explored in this investigation provide a straightforward framework for future studies by both scholars and administrators in the context of robotic weeding. Full article

(This article belongs to the Section Smart Agriculture)

► Show Figures

Figure 1

17 pages, 3337 KiB

Open AccessArticle

MulCPred: Learning Multi-Modal Concepts for Explainable Pedestrian Action Prediction

by Yan Feng, Alexander Carballo, Keisuke Fujii, Robin Karlsson, Ming Ding and Kazuya Takeda

Sensors 2024, 24(20), 6742; https://doi.org/10.3390/s24206742 - 20 Oct 2024

Viewed by 625

Abstract

Pedestrian action prediction is crucial for many applications such as autonomous driving. However, state-of-the-art methods lack the explainability needed for trustworthy predictions. In this paper, a novel framework called MulCPred is proposed that explains its predictions based on multi-modal concepts represented by training [...] Read more.

Pedestrian action prediction is crucial for many applications such as autonomous driving. However, state-of-the-art methods lack the explainability needed for trustworthy predictions. In this paper, a novel framework called MulCPred is proposed that explains its predictions based on multi-modal concepts represented by training samples. Previous concept-based methods have limitations, including the following: (1) they cannot be directly applied to multi-modal cases; (2) they lack the locality needed to attend to details in the inputs; (3) they are susceptible to mode collapse. These limitations are tackled accordingly through the following approaches: (1) a linear aggregator to integrate the activation results of the concepts into predictions, which associates concepts of different modalities and provides ante hoc explanations of the relevance between the concepts and the predictions; (2) a channel-wise recalibration module that attends to local spatiotemporal regions, which enables the concepts with locality; (3) a feature regularization loss that encourages the concepts to learn diverse patterns. MulCPred is evaluated on multiple datasets and tasks. Both qualitative and quantitative results demonstrate that MulCPred is promising in improving the explainability of pedestrian action prediction without obvious performance degradation. Moreover, by removing unrecognizable concepts, MulCPred shows improved cross-dataset prediction performance, suggesting its potential for further generalization. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Sensors, Volume 24, Issue 20 (October-2 2024) – 272 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI