Sensors

22 pages, 4207 KiB

Open AccessReview

A Survey on Sensor Failures in Autonomous Vehicles: Challenges and Solutions

by Francisco Matos, Jorge Bernardino, João Durães and João Cunha

Sensors 2024, 24(16), 5108; https://doi.org/10.3390/s24165108 (registering DOI) - 7 Aug 2024

Abstract

Autonomous vehicles (AVs) rely heavily on sensors to perceive their surrounding environment and then make decisions and act on them. However, these sensors have weaknesses, and are prone to failure, resulting in decision errors by vehicle controllers that pose significant challenges to their [...] Read more.

Autonomous vehicles (AVs) rely heavily on sensors to perceive their surrounding environment and then make decisions and act on them. However, these sensors have weaknesses, and are prone to failure, resulting in decision errors by vehicle controllers that pose significant challenges to their safe operation. To mitigate sensor failures, it is necessary to understand how they occur and how they affect the vehicle’s behavior so that fault-tolerant and fault-masking strategies can be applied. This survey covers 108 publications and presents an overview of the sensors used in AVs today, categorizes the sensor’s failures that can occur, such as radar interferences, ambiguities detection, or camera image failures, and provides an overview of mitigation strategies such as sensor fusion, redundancy, and sensor calibration. It also provides insights into research areas critical to improving safety in the autonomous vehicle industry, so that new or more in-depth research may emerge. Full article

(This article belongs to the Special Issue Intelligent Sensors and Control for Vehicle Automation)

► Show Figures

Figure 1

21 pages, 4580 KiB

Open AccessArticle

Driving Attention State Detection Based on GRU-EEGNet

by Xiaoli Wu, Changcheng Shi and Lirong Yan

Sensors 2024, 24(16), 5086; https://doi.org/10.3390/s24165086 (registering DOI) - 7 Aug 2024

Viewed by 181

Abstract

The present study utilizes the significant differences in θ, α, and β band power spectra observed in electroencephalograms (EEGs) during distracted versus focused driving. Three subtasks, visual distraction, auditory distraction, and cognitive distraction, were designed to appear randomly during driving simulations. The θ, [...] Read more.

The present study utilizes the significant differences in θ, α, and β band power spectra observed in electroencephalograms (EEGs) during distracted versus focused driving. Three subtasks, visual distraction, auditory distraction, and cognitive distraction, were designed to appear randomly during driving simulations. The θ, α, and β band power spectra of the EEG signals of the four driving attention states were extracted, and SVM, EEGNet, and GRU-EEGNet models were employed for the detection of the driving attention states, respectively. Online experiments were conducted. The extraction of the θ, α, and β band power spectrum features of the EEG signals was found to be a more effective method than the extraction of the power spectrum features of the whole EEG signals for the detection of driving attention states. The driving attention state detection accuracy of the proposed GRU-EEGNet model is improved by 6.3% and 12.8% over the EEGNet model and PSD_SVM method, respectively. The EEG decoding method combining EEG features and an improved deep learning algorithm, which effectively improves the driving attention state detection accuracy, was manually and preliminarily selected based on the results of existing studies. Full article

(This article belongs to the Section Vehicular Sensing)

► Show Figures

Figure 1

15 pages, 1831 KiB

Open AccessArticle

Exploring the Feasibility of Bidirectional Control of Beta Oscillatory Power in Healthy Controls as a Potential Intervention for Parkinson’s Disease Movement Impairment

by Krithika Anil, Giorgio Ganis, Jennifer A. Freeman, Jonathan Marsden and Stephen D. Hall

Sensors 2024, 24(16), 5107; https://doi.org/10.3390/s24165107 (registering DOI) - 6 Aug 2024

Viewed by 245

Abstract

Neurofeedback (NF) is a promising intervention for improvements in motor performance in Parkinson’s disease. This NF pilot study in healthy participants aimed to achieve the following: (1) determine participants’ ability to bi-directionally modulate sensorimotor beta power and (2) determine the effect of NF [...] Read more.

Neurofeedback (NF) is a promising intervention for improvements in motor performance in Parkinson’s disease. This NF pilot study in healthy participants aimed to achieve the following: (1) determine participants’ ability to bi-directionally modulate sensorimotor beta power and (2) determine the effect of NF on movement performance. A real-time EEG-NF protocol was used to train participants to increase and decrease their individual motor cortex beta power amplitude, using a within-subject double-blind sham-controlled approach. Movement was assessed using a Go/No-go task. Participants completed the NASA Task Load Index and provided verbal feedback of the NF task difficulty. All 17 participants (median age = 38 (19–65); 10 females) reliably reduced sensorimotor beta power. No participant could reliably increase their beta activity. Participants reported that the NF task was challenging, particularly increasing beta. A modest but significant increase in reaction time correlated with a reduction in beta power only in the real condition. Findings suggest that beta power control difficulty varies by modulation direction, affecting participant perceptions. A correlation between beta power reduction and reaction times only in the real condition suggests that intentional beta power reduction may shorten reaction times. Future research should examine the minimum beta threshold for meaningful motor improvements, and the relationship between EEG mechanisms and NF learning to optimise NF outcomes. Full article

(This article belongs to the Special Issue Advances in Brain–Computer Interfaces and Sensors)

► Show Figures

Figure 1

14 pages, 3040 KiB

Open AccessArticle

User Privacy Protection via Windows Registry Hooking and Runtime Encryption

by Edward L. Amoruso, Richard Leinecker and Cliff C. Zou

Sensors 2024, 24(16), 5106; https://doi.org/10.3390/s24165106 (registering DOI) - 6 Aug 2024

Viewed by 226

Abstract

The Windows registry contains a plethora of information in a hierarchical database. It includes system-wide settings, user preferences, installed programs, and recently accessed files and maintains timestamps that can be used to construct a detailed timeline of user activities. However, these data are [...] Read more.

The Windows registry contains a plethora of information in a hierarchical database. It includes system-wide settings, user preferences, installed programs, and recently accessed files and maintains timestamps that can be used to construct a detailed timeline of user activities. However, these data are unencrypted and thus vulnerable to exploitation by malicious actors who gain access to this repository. To address this security and privacy concern, we propose a novel approach that efficiently encrypts and decrypts sensitive registry data in real time. Our developed proof-of-concept program intercepts interactions between the registry’s application programming interfaces (APIs) and other Windows applications using an advanced hooking technique. This enables the proposed system to be transparent to users without requiring any changes to the operating system or installed software. Our approach also implements the data protection API (DPAPI) developed by Microsoft to securely manage each user’s encryption key. Ultimately, our research provides an enhanced security and privacy framework for the Windows registry, effectively fortifying the registry against security and privacy threats while maintaining its accessibility to legitimate users and applications. Full article

(This article belongs to the Special Issue Data Privacy, Security, and Trust in New Technological Trends—2nd Edition)

► Show Figures

Figure 1

20 pages, 6166 KiB

Open AccessArticle

Research on the Method for Recognizing Bulk Grain-Loading Status Based on LiDAR

by Jiazun Hu, Xin Wen, Yunbo Liu, Haonan Hu and Hui Zhang

Sensors 2024, 24(16), 5105; https://doi.org/10.3390/s24165105 (registering DOI) - 6 Aug 2024

Viewed by 219

Abstract

Grain is a common bulk cargo. To ensure optimal utilization of transportation space and prevent overflow accidents, it is necessary to observe the grain’s shape and determine the loading status during the loading process. Traditional methods often rely on manual judgment, which results [...] Read more.

Grain is a common bulk cargo. To ensure optimal utilization of transportation space and prevent overflow accidents, it is necessary to observe the grain’s shape and determine the loading status during the loading process. Traditional methods often rely on manual judgment, which results in high labor intensity, poor safety, and low loading efficiency. Therefore, this paper proposes a method for recognizing the bulk grain-loading status based on Light Detection and Ranging (LiDAR). This method uses LiDAR to obtain point cloud data and constructs a deep learning network to perform target recognition and component segmentation on loading vehicles, extract vehicle positions and grain shapes, and recognize and make known the bulk grain-loading status. Based on the measured point cloud data of bulk grain loading, in the point cloud-classification task, the overall accuracy is 97.9% and the mean accuracy is 98.1%. In the vehicle component-segmentation task, the overall accuracy is 99.1% and the Mean Intersection over Union is 96.6%. The results indicate that the method has reliable performance in the research tasks of extracting vehicle positions, detecting grain shapes, and recognizing loading status. Full article

(This article belongs to the Section Vehicular Sensing)

► Show Figures

Figure 1

19 pages, 8866 KiB

Open AccessArticle

A Precise Pulmonary Airway Tree Segmentation Method Using Quasi-Spherical Region Constraint and Tracheal Wall Gap Sealing

by Zhanming Hu, Tonglong Ren, Meirong Ren, Wentao Cui, Enqing Dong and Peng Xue

Sensors 2024, 24(16), 5104; https://doi.org/10.3390/s24165104 - 6 Aug 2024

Viewed by 214

Abstract

Accurate segmentation of the pulmonary airway tree is crucial for diagnosing lung diseases. To tackle the issues of low segmentation accuracy and frequent leaks in existing methods, this paper proposes a precise segmentation method using quasi-spherical region-constrained wavefront propagation with tracheal wall gap [...] Read more.

Accurate segmentation of the pulmonary airway tree is crucial for diagnosing lung diseases. To tackle the issues of low segmentation accuracy and frequent leaks in existing methods, this paper proposes a precise segmentation method using quasi-spherical region-constrained wavefront propagation with tracheal wall gap sealing. Based on the characteristic that the surface formed by seed points approximates the airway cross-section, the width of the unsegmented airway is calculated, determining the initial quasi-spherical constraint region. Using the wavefront propagation method, seed points are continuously propagated and segmented along the tracheal wall within the quasi-spherical constraint region, thus overcoming the need to determine complex segmentation directions. To seal tracheal wall gaps, a morphological closing operation is utilized to extract the characteristics of small holes and locate low-brightness tracheal wall gaps. By filling the CT values at these gaps, the method seals the tracheal wall gaps. Extensive experiments on the EXACT09 dataset demonstrate that our algorithm ranks third in segmentation completeness. Moreover, its performance in preventing airway leaks is significantly better than the top-two algorithms, effectively preventing large-scale leak-induced spread. Full article

(This article belongs to the Section Biomedical Sensors)

► Show Figures

Figure 1

23 pages, 796 KiB

Open AccessArticle

A Lightweight Double Compression Detector for HEIF Images Based on Encoding Information

by Yoshihisa Furushita, Marco Fontani, Stefano Bianchi, Alessandro Piva and Giovanni Ramponi

Sensors 2024, 24(16), 5103; https://doi.org/10.3390/s24165103 - 6 Aug 2024

Viewed by 166

Abstract

Extensive research has been conducted in image forensics on the analysis of double-compressed images, particularly in the widely adopted JPEG format. However, there is a lack of methods to detect double compression in the HEIF format, which has recently gained popularity since it [...] Read more.

Extensive research has been conducted in image forensics on the analysis of double-compressed images, particularly in the widely adopted JPEG format. However, there is a lack of methods to detect double compression in the HEIF format, which has recently gained popularity since it allows for reduced file size while maintaining image quality. Traditional JPEG-based techniques do not apply to HEIF due to its distinct encoding algorithms. We previously proposed a method to detect double compression in HEIF images based on Farid’s work on coding ghosts in JPEG images. However, this method was limited to scenarios where the quality parameter used for the first encoding was larger than for the second encoding. In this study, we propose a lightweight image classifier to extend the existing model, enabling the identification of double-compressed images without heavily depending on the input image’s quantization history. This extended model outperforms the previous approach and, despite its lightness, demonstrates excellent detection accuracy. Full article

(This article belongs to the Special Issue Image/Video Coding and Processing Techniques for Intelligent Sensor Nodes: 2nd Edition)

16 pages, 4935 KiB

Open AccessArticle

Design and Implementation of a Generalized Safety Fault Diagnosis System for China Space Station Scientific Experimental Rack

by Yifeng Wang, Tianji Zou, Lin Guo, Chenchen Zhang and Lu Zhang

Sensors 2024, 24(16), 5102; https://doi.org/10.3390/s24165102 - 6 Aug 2024

Viewed by 255

Abstract

As astronauts stay in the China Space Station for a long time during the operation phase, how to ensure the long-term safety of the scientific experimental rack (SER) in the field of space application is a problem that needs to be solved urgently. [...] Read more.

As astronauts stay in the China Space Station for a long time during the operation phase, how to ensure the long-term safety of the scientific experimental rack (SER) in the field of space application is a problem that needs to be solved urgently. Each SER in the field of space station applications is a complex system that faces risks from different hazards. At present, there is no generalized monitoring and diagnosis system for the common risks faced by the SER. In this paper, a generalized safety fault diagnosis system is proposed to ensure the long-term safe and stable work of SERs in orbit, considering the actual risks faced by the SER. With the design of a generalized main control board, a measurement and control board, and an SSPC (solid-state power controller) board, the software and hardware cooperate to realize the acquisition of various physical quantities, data processing, power supply and distribution management, and other functions. Combined with relevant fault detection algorithms, the real-time detection and diagnosis of the relevant risks, abnormality warnings, and fault disposal operations are realized, which can effectively ensure the safety of the payloads in the field of space application, astronauts, and the space-station system. Full article

(This article belongs to the Topic Innovation and Inventions in Aerospace and UAV Applications)

► Show Figures

Figure 1

14 pages, 3044 KiB

Open AccessArticle

Eddy Current-Based Identification and Depth Investigation of Microdefects in Steel Filaments

by Kim Sang Tran, Bijan Shirinzadeh and Julian Smith

Sensors 2024, 24(16), 5101; https://doi.org/10.3390/s24165101 - 6 Aug 2024

Viewed by 219

Abstract

In the field of quality control, the critical challenge of analyzing microdefects in steel filament holds significant importance. This is particularly vital, as steel filaments serve as reinforced fibers in the use and applications within various component manufacturing industries. This paper addresses the [...] Read more.

In the field of quality control, the critical challenge of analyzing microdefects in steel filament holds significant importance. This is particularly vital, as steel filaments serve as reinforced fibers in the use and applications within various component manufacturing industries. This paper addresses the crucial requirement of identifying and investigating microdefects in steel filaments. Eddy current signals are used for the identification of microdefects, and an in-depth investigation is conducted. The core objective is to establish the relationship between the depth of defects and the signals detected through the eddy current sensing principle. The threshold of the eddy current instrument was set at 10%, corresponding to a created depth of 20 µm, to identify defective specimens. A total of 30 defective samples were analyzed, and the phase angles between the experimental and theoretical results were compared. The depths of defects ranged from 20 to 60 µm, with one sample having a depth exceeding 75 µm. The calculated threshold of 10.18% closely aligns with the set threshold of 10%, with a difference of only 1.77%. The resulting root mean square error (RMSE) was found to be 10.53 degrees, equivalent to 3.49 µm for the difference in depth and phase between measured results and estimated results. This underscores the methodology’s accuracy and its applicability across diverse manufacturing industries. Full article

(This article belongs to the Topic Applications of Non-destructive Testing Technologies in Materials or Engineering)

► Show Figures

Figure 1

19 pages, 937 KiB

Open AccessReview

Handgrip Strength in Health Applications: A Review of the Measurement Methodologies and Influencing Factors

by Antonino Quattrocchi, Giada Garufi, Giovanni Gugliandolo, Cristiano De Marchis, Domenicantonio Collufio, Salvatore Massimiliano Cardali and Nicola Donato

Sensors 2024, 24(16), 5100; https://doi.org/10.3390/s24165100 - 6 Aug 2024

Viewed by 202

Abstract

This narrative review provides a comprehensive analysis of the several methods and technologies employed to measure handgrip strength (HGS), a significant indicator of neuromuscular strength and overall health. The document evaluates a range of devices, from traditional dynamometers to innovative sensor-based systems, and [...] Read more.

This narrative review provides a comprehensive analysis of the several methods and technologies employed to measure handgrip strength (HGS), a significant indicator of neuromuscular strength and overall health. The document evaluates a range of devices, from traditional dynamometers to innovative sensor-based systems, and assesses their effectiveness and application in different demographic groups. Special attention is given to the methodological aspects of HGS estimation, including the influence of device design and measurement protocols. Endogenous factors such as hand dominance and size, body mass, age and gender, as well as exogenous factors including circadian influences and psychological factors, are examined. The review identifies significant variations in the implementation of HGS measurements and interpretation of the resultant data, emphasizing the need for careful consideration of these factors when using HGS as a diagnostic or research tool. It highlights the necessity of standardizing measurement protocols to establish universal guidelines that enhance the comparability and consistency of HGS assessments across various settings and populations. Full article

(This article belongs to the Special Issue Assistive and Rehabilitation Technologies Based on Intelligent Sensors)

► Show Figures

Figure 1

19 pages, 9956 KiB

Open AccessArticle

Optimized Radio Frequency Footprint Identification Based on UAV Telemetry Radios

by Yuan Tian, Hong Wen, Jiaxin Zhou, Zhiqiang Duan and Tao Li

Sensors 2024, 24(16), 5099; https://doi.org/10.3390/s24165099 - 6 Aug 2024

Viewed by 254

Abstract

With the widespread use of unmanned aerial vehicles (UAVs), the detection and identification of UAVs is a vital security issue for the safety of airspace and ground facilities in the no-fly zone. Telemetry radios are important wireless communication devices for UAVs, especially in [...] Read more.

With the widespread use of unmanned aerial vehicles (UAVs), the detection and identification of UAVs is a vital security issue for the safety of airspace and ground facilities in the no-fly zone. Telemetry radios are important wireless communication devices for UAVs, especially in UAVs beyond the visual line of sight (BVLOS) operating mode. This work focuses on the UAV identification approach using transient signals from UAV telemetry radios instead of the signals from UAV controllers that the former research work depended on. In our novel UAV Radio Frequency (RF) identification system framework based on telemetry radio signals, the

E C - α

algorithm is optimized to detect the starting point of the UAV transient signal and the detection accuracy at different signal-to-noise ratios (SNR) is evaluated. In the training stage, the Convolutional Neural Network (CNN) model is trained to extract features from raw I/Q data of the transient signals with different waveforms. Its architecture and hyperparameters are analyzed and optimized. In the identification stage, the extracted transient signals are clustered through the Self-Organizing Map (SOM) algorithm and the Clustering Signals Joint Identification (CSJI) algorithm is proposed to improve the accuracy of RF fingerprint identification. To evaluate the performance of our proposed approach, we design a testbed, including two UAVs as the flight platform, a Universal Software Radio Peripheral (USRP) as the receiver, and 20 telemetry radios with the same model as targets for identification. Indoor test results show that the optimized identification approach achieves an average accuracy of 92.3% at 30 dB. In comparison, the identification accuracy of SVM and KNN is 69.7% and 74.5%, respectively, at the same SNR condition. Extensive experiments are conducted outdoors to demonstrate the feasibility of this approach. Full article

(This article belongs to the Section Remote Sensors)

► Show Figures

Figure 1

21 pages, 46218 KiB

Open AccessArticle

Lightweight Single Image Super-Resolution via Efficient Mixture of Transformers and Convolutional Networks

by Luyang Xiao, Xiangyu Liao and Chao Ren

Sensors 2024, 24(16), 5098; https://doi.org/10.3390/s24165098 - 6 Aug 2024

Viewed by 214

Abstract

In this paper, we propose a Local Global Union Network (LGUN), which effectively combines the strengths of Transformers and Convolutional Networks to develop a lightweight and high-performance network suitable for Single Image Super-Resolution (SISR). Specifically, we make use of the advantages of Transformers [...] Read more.

In this paper, we propose a Local Global Union Network (LGUN), which effectively combines the strengths of Transformers and Convolutional Networks to develop a lightweight and high-performance network suitable for Single Image Super-Resolution (SISR). Specifically, we make use of the advantages of Transformers to provide input-adaptation weighting and global context interaction. We also make use of the advantages of Convolutional Networks to include spatial inductive biases and local connectivity. In the shallow layer, the local spatial information is encoded by Multi-order Local Hierarchical Attention (MLHA). In the deeper layer, we utilize Dynamic Global Sparse Attention (DGSA), which is based on the Multi-stage Token Selection (MTS) strategy to model global context dependencies. Moreover, we also conduct extensive experiments on both natural and satellite datasets, acquired through optical and satellite sensors, respectively, demonstrating that LGUN outperforms existing methods. Full article

(This article belongs to the Special Issue Deep Learning-Based Image and Signal Sensing and Processing: 2nd Edition)

► Show Figures

Figure 1

17 pages, 8641 KiB

Open AccessArticle

Affordable 3D Orientation Visualization Solution for Working Class Remotely Operated Vehicles (ROV)

by Mohammad Afif Kasno, Izzat Nadzmi Yahaya and Jin-Woo Jung

Sensors 2024, 24(16), 5097; https://doi.org/10.3390/s24165097 - 6 Aug 2024

Viewed by 286

Abstract

ROV operators often encounter challenges with orientation awareness while operating underwater, primarily due to relying solely on 2D camera feeds to manually control the ROV robot arm. This limitation in underwater visibility and orientation awareness, as observed among Malaysian ROV operators, can compromise [...] Read more.

ROV operators often encounter challenges with orientation awareness while operating underwater, primarily due to relying solely on 2D camera feeds to manually control the ROV robot arm. This limitation in underwater visibility and orientation awareness, as observed among Malaysian ROV operators, can compromise the accuracy of arm placement, and pose a risk of tool damage if not handle with care. To address this, a 3D orientation monitoring system for ROVs has been developed, leveraging measurement sensors with nine degrees of freedom (DOF). These sensors capture crucial parameters such as roll, pitch, yaw, and heading, providing real-time data on the ROV’s position along the X, Y, and Z axes to ensure precise orientation. These data are then utilized to generate and process 3D imaging and develop a corresponding 3D model of the operational ROV underwater, accurately reflecting its orientation in a visual representation by using an open-source platform. Due to constraints set by an agreement with the working class ROV operators, only short-term tests (up to 1 min) could be performed at the dockyard. A video demonstration of a working class ROV replica moving and reflecting in a 3D simulation in real-time was also presented. Despite these limitations, our findings demonstrate the feasibility and potential of a cost-effective 3D orientation visualization system for working class ROVs. With mean absolute error (MAE) error less than 2%, the results align with the performance expectations of the actual working ROV. Full article

(This article belongs to the Special Issue Advanced Sensing Technologies and Intelligent Systems: Selected Papers From the 24th International Symposium on Advanced Intelligent Systems (ISIS))

► Show Figures

Figure 1

10 pages, 1512 KiB

Open AccessCommunication

Errors in Estimating Lower-Limb Joint Angles and Moments during Walking Based on Pelvic Accelerations: Influence of Virtual Inertial Measurement Unit’s Frontal Plane Misalignment

by Takuma Inai, Yoshiyuki Kobayashi, Motoki Sudo, Yukari Yamashiro and Tomoya Ueda

Sensors 2024, 24(16), 5096; https://doi.org/10.3390/s24165096 - 6 Aug 2024

Viewed by 249

Abstract

The accurate estimation of lower-limb joint angles and moments is crucial for assessing the progression of orthopedic diseases, with continuous monitoring during daily walking being essential. An inertial measurement unit (IMU) attached to the lower back has been used for this purpose, but [...] Read more.

The accurate estimation of lower-limb joint angles and moments is crucial for assessing the progression of orthopedic diseases, with continuous monitoring during daily walking being essential. An inertial measurement unit (IMU) attached to the lower back has been used for this purpose, but the effect of IMU misalignment in the frontal plane on estimation accuracy remains unclear. This study investigated the impact of virtual IMU misalignment in the frontal plane on estimation errors of lower-limb joint angles and moments during walking. Motion capture data were recorded from 278 healthy adults walking at a comfortable speed. An estimation model was developed using principal component analysis and linear regression, with pelvic accelerations as independent variables and lower-limb joint angles and moments as dependent variables. Virtual IMU misalignments of −20°, −10°, 0°, 10°, and 20° in the frontal plane (five conditions) were simulated. The joint angles and moments were estimated and compared across these conditions. The results indicated that increasing virtual IMU misalignment in the frontal plane led to greater errors in the estimation of pelvis and hip angles, particularly in the frontal plane. For misalignments of ±20°, the errors in pelvis and hip angles were significantly amplified compared to well-aligned conditions. These findings underscore the importance of accounting for IMU misalignment when estimating these variables. Full article

(This article belongs to the Special Issue Wearable Sensors for Biomechanics Applications—2nd Edition)

► Show Figures

Figure 1

18 pages, 2728 KiB

Open AccessArticle

PSA-FL-CDM: A Novel Federated Learning-Based Consensus Model for Post-Stroke Assessment

by Najmeh Razfar, Rasha Kashef and Farah Mohammadi

Sensors 2024, 24(16), 5095; https://doi.org/10.3390/s24165095 - 6 Aug 2024

Viewed by 287

Abstract

The rapid development of Internet of Things (IoT) technologies and the potential benefits of employing the vast datasets generated by IoT devices, including wearable sensors and camera systems, has ushered in a new era of opportunities for enhancing smart rehabilitation in various healthcare [...] Read more.

The rapid development of Internet of Things (IoT) technologies and the potential benefits of employing the vast datasets generated by IoT devices, including wearable sensors and camera systems, has ushered in a new era of opportunities for enhancing smart rehabilitation in various healthcare systems. Maintaining patient privacy is paramount in healthcare while providing smart insights and recommendations. This study proposed the adoption of federated learning to develop a scalable AI model for post-stroke assessment while protecting patients’ privacy. This research compares the centralized (PSA-MNMF) model performance with the proposed scalable federated PSA-FL-CDM model for sensor- and camera-based datasets. The computational time indicates that the federated PSA-FL-CDM model significantly reduces the execution time and attains comparable performance while preserving the patient’s privacy. Impact Statement—This research introduces groundbreaking contributions to stroke assessment by successfully implementing federated learning for the first time in this domain and applying consensus models in each node. It enables collaborative model training among multiple nodes or clients while ensuring the privacy of raw data. The study explores eight different clustering methods independently on each node, revolutionizing data organization based on similarities in stroke assessment. Additionally, the research applies the centralized PSA-MNMF consensus clustering technique to each client, resulting in more accurate and robust clustering solutions. By utilizing the FedAvg federated learning algorithm strategy, locally trained models are combined to create a global model that captures the collective knowledge of all participants. Comparative performance measurements and computational time analyses are conducted, facilitating a fair evaluation between centralized and federated learning models in stroke assessment. Moreover, the research extends beyond a single type of database by conducting experiments on two distinct datasets, wearable and camera-based, broadening the understanding of the proposed methods across different data modalities. These contributions develop stroke assessment methodologies, enabling efficient collaboration and accurate consensus clustering models and maintaining data privacy. Full article

(This article belongs to the Special Issue IoT-Based Smart Environments, Applications and Tools)

► Show Figures

Figure 1

15 pages, 3699 KiB

Open AccessArticle

Large-Area Film Thickness Identification of Transparent Glass by Hyperspectral Imaging

by Shuan-Yu Huang, Riya Karmakar, Yu-Yang Chen, Wei-Chin Hung, Arvind Mukundan and Hsiang-Chen Wang

Sensors 2024, 24(16), 5094; https://doi.org/10.3390/s24165094 - 6 Aug 2024

Viewed by 286

Abstract

This study introduces a novel method for detecting and measuring transparent glass sheets using hyperspectral imaging (HSI). The main goal of this study is to create a conversion technique that can accurately display spectral information from collected images, particularly in the visible light [...] Read more.

This study introduces a novel method for detecting and measuring transparent glass sheets using hyperspectral imaging (HSI). The main goal of this study is to create a conversion technique that can accurately display spectral information from collected images, particularly in the visible light spectrum (VIS) and near-infrared (NIR) areas. This technique enables the capture of relevant spectral data when used with images provided by industrial cameras. The next step in this investigation is using principal component analysis to examine the obtained hyperspectral images derived from different treated glass samples. This analytical procedure standardizes the magnitude of light wavelengths that are inherent in the HSI images. The simulated spectral profiles are obtained using the generalized inverse matrix technique on the normalized HSI images. These profiles are then matched with spectroscopic data obtained from microscopic imaging, resulting in the observation of distinct dispersion patterns. The novel use of images coloring methods effectively displays the thickness of the glass processing sheet in a visually noticeable way. Based on empirical research, changes in the thickness of the glass coating in the NIR-HSI range cause significant changes in the transmission of infrared light at different wavelengths within the NIR spectrum. This phenomenon serves as the foundation for the study of film thickness. The root mean square error inside the NIR area is impressively low, calculated to be just 0.02. This highlights the high level of accuracy achieved by the technique stated above. Potential areas of investigation that arise from this study are incorporating the proposed approach into the design of a real-time, wide-scale automated optical inspection system. Full article

► Show Figures

Figure 1

14 pages, 3218 KiB

Open AccessArticle

Adaptive Navigation Performance Evaluation Method for Civil Aircraft Navigation Systems with Unknown Time-Varying Sensor Noise

by Yuting Dai, Jizhou Lai, Qieqie Zhang, Zhimin Li and Rui Liu

Sensors 2024, 24(16), 5093; https://doi.org/10.3390/s24165093 - 6 Aug 2024

Viewed by 236

Abstract

During civil aviation flights, the aircraft needs to accurately monitor the real-time navigation capability and determine whether the onboard navigation system performance meets the required navigation performance (RNP). The airborne flight management system (FMS) uses actual navigation performance (ANP) to quantitatively calculate the [...] Read more.

During civil aviation flights, the aircraft needs to accurately monitor the real-time navigation capability and determine whether the onboard navigation system performance meets the required navigation performance (RNP). The airborne flight management system (FMS) uses actual navigation performance (ANP) to quantitatively calculate the uncertainty of aircraft position estimation, and its evaluation accuracy is highly dependent on the position estimation covariance matrix (PECM) provided by the airborne integrated navigation system. This paper proposed an adaptive PECM estimation method based on variational Bayes (VB) to solve the problem of ANP misevaluation, which is caused by the traditional simple ANP model failing to accurately estimate PECM under unknown time-varying noise. Combined with the 3D ANP model proposed in this paper, the accuracy of ANP evaluation can be significantly improved. This enhancement contributes to ensured navigation integrity and operational safety during civil flight. Full article

(This article belongs to the Section Navigation and Positioning)

► Show Figures

Figure 1

13 pages, 9982 KiB

Open AccessArticle

The Focusing Properties of a Modular All-Metal Lens in the Near-Field Region

by Qifei Zhang, Linyan Guo, Yunqing Li and Chen Wang

Sensors 2024, 24(16), 5092; https://doi.org/10.3390/s24165092 - 6 Aug 2024

Viewed by 228

Abstract

This article proposes a modular and passive all-metal lens to achieve near-field focusing with adjustable focus. The proposed lens consists of all-metal units with the phase coverage range exceeding 360°, and the arrangement of units is guided by the phase compensation method. Specifically, [...] Read more.

This article proposes a modular and passive all-metal lens to achieve near-field focusing with adjustable focus. The proposed lens consists of all-metal units with the phase coverage range exceeding 360°, and the arrangement of units is guided by the phase compensation method. Specifically, using the strategy of module unit synthesis, the arrangement of lens units under different focuses can be assembled arbitrarily, which reduces the production costs by 39.3% and improves the freedom of lens design. The simulation and experimental results show that the lens exhibits excellent focusing properties and freely changes the position of the expected focus (0.30 m–0.75 m). Therefore, the modular all-metal lens designed in this article has the characteristics of high transparency and a high degree of freedom, which can provide low-cost and lightweight solutions for various applications in the field of antennas, such as near-field target detection, microwave imaging, biomedicine, and so on. Full article

(This article belongs to the Special Issue Metamaterials and Antennas for Enhancing Sensing, Imaging and Communication System)

► Show Figures

Figure 1

21 pages, 8720 KiB

Open AccessReview

Advancements in Flexible Sensors for Monitoring Body Movements during Sleep: A Review

by Zongyi Jiang, Yee Sum Lee, Yunzhong Wang, Honey John, Liming Fang and Youhong Tang

Sensors 2024, 24(16), 5091; https://doi.org/10.3390/s24165091 - 6 Aug 2024

Viewed by 224

Abstract

Sleep plays a role in maintaining our physical well-being. However, sleep-related issues impact millions of people globally. Accurate monitoring of sleep is vital for identifying and addressing these problems. While traditional methods like polysomnography (PSG) are commonly used in settings, they may not [...] Read more.

Sleep plays a role in maintaining our physical well-being. However, sleep-related issues impact millions of people globally. Accurate monitoring of sleep is vital for identifying and addressing these problems. While traditional methods like polysomnography (PSG) are commonly used in settings, they may not fully capture natural sleep patterns at home. Moreover, PSG equipment can disrupt sleep quality. In recent years, there has been growing interest in the use of sensors for sleep monitoring. These lightweight sensors can be easily integrated into textiles or wearable devices using technology. The flexible sensors can be designed for skin contact to offer continuous monitoring without being obtrusive in a home environment. This review presents an overview of the advancements made in flexible sensors for tracking body movements during sleep, which focus on their principles, mechanisms, and strategies for improved flexibility, practical applications, and future trends. Full article

(This article belongs to the Special Issue Flexible Electronic Sensors Based on Nanomaterials)

► Show Figures

Graphical abstract

13 pages, 3543 KiB

Open AccessArticle

Search for Strange Quark Matter and Nuclearites on Board the International Space Station (SQM-ISS): A Future Detector to Search for Massive, Non-Relativistic Objects in Space

by Massimo Bianchi, Francesca Bisconti, Carl Blaksley, Valerio Bocci, Marco Casolino, Francesco Di Clemente, Alessandro Drago, Christer Fuglesang, Francesco Iacoangeli, Massimiliano Lattanzi, Alessandro Marcelli, Laura Marcelli, Paolo Natoli, Etienne Parizot, Piergiorgio Picozza, Lech Wiktor Piotrowski, Zbigniew Plebaniak, Enzo Reali, Marco Ricci, Alessandro Rizzo, Gabriele Rizzo and Jacek Szabelski Show full author list Hide full author list

Sensors 2024, 24(16), 5090; https://doi.org/10.3390/s24165090 - 6 Aug 2024

Viewed by 195

Abstract

SQM-ISS is a detector that will search from the International Space Station for massive particles possibly present among the cosmic rays. Among them, we mention strange quark matter, Q-Balls, lumps of fermionic exotic compact stars, Primordial Black Holes, mirror matter, Fermi balls, etc. [...] Read more.

SQM-ISS is a detector that will search from the International Space Station for massive particles possibly present among the cosmic rays. Among them, we mention strange quark matter, Q-Balls, lumps of fermionic exotic compact stars, Primordial Black Holes, mirror matter, Fermi balls, etc. These compact, dense objects would be much heavier than normal nuclei, have velocities of galaxy-bound systems, and would be deeply penetrating. The detector is based on a stack of scintillator and piezoelectric elements which can provide information on both the charge state and mass, with the additional timing information allowing to determine the speed of the particle, searching for particles with velocities of the order of galactic rotation speed (v ≲ 250 km/s). In this work, we describe the apparatus and its observational capabilities. Full article

(This article belongs to the Section Physical Sensors)

► Show Figures

Figure 1

19 pages, 2231 KiB

Open AccessReview

Review of Methods for Automatic Plastic Detection in Water Areas Using Satellite Images and Machine Learning

by Aleksandr Danilov and Elizaveta Serdiukova

Sensors 2024, 24(16), 5089; https://doi.org/10.3390/s24165089 - 6 Aug 2024

Viewed by 287

Abstract

Ocean plastic pollution is one of the global environmental problems of our time. “Rubbish islands” formed in the ocean are increasing every year, damaging the marine ecosystem. In order to effectively address this type of pollution, it is necessary to accurately and quickly [...] Read more.

Ocean plastic pollution is one of the global environmental problems of our time. “Rubbish islands” formed in the ocean are increasing every year, damaging the marine ecosystem. In order to effectively address this type of pollution, it is necessary to accurately and quickly identify the sources of plastic entering the ocean, identify where it is accumulating, and track the dynamics of waste movement. To this end, remote sensing methods using satellite imagery and aerial photographs from unmanned aerial vehicles are a reliable source of data. Modern machine learning technologies make it possible to automate the detection of floating plastics. This review presents the main projects and research aimed at solving the “plastic” problem. The main data acquisition techniques and the most effective deep learning algorithms are described, various limitations of working with space images are analyzed, and ways to eliminate such shortcomings are proposed. Full article

(This article belongs to the Section Environmental Sensing)

► Show Figures

Graphical abstract

20 pages, 1249 KiB

Open AccessArticle

User-Centric Cell-Free Massive MIMO with Low-Resolution ADCs for Massive Access

by Jin-Woo Kim, Hyoung-Do Kim, Kyung-Ho Shin, Sang-Wook Park, Seung-Hwan Seo, Yoon-Ju Choi, Young-Hwan You and Hyoung-Kyu Song

Sensors 2024, 24(16), 5088; https://doi.org/10.3390/s24165088 - 6 Aug 2024

Viewed by 274

Abstract

This paper proposes a heuristic association algorithm between access points (APs) and user equipment (UE) in user-centric cell-free massive multiple-input-multiple-output (MIMO) systems, specifically targeting scenarios where UEs share the same frequency and time resources. The proposed algorithm prevents overserving APs and ensures the [...] Read more.

This paper proposes a heuristic association algorithm between access points (APs) and user equipment (UE) in user-centric cell-free massive multiple-input-multiple-output (MIMO) systems, specifically targeting scenarios where UEs share the same frequency and time resources. The proposed algorithm prevents overserving APs and ensures the connectivity of all UEs, even when the number of UEs is significantly greater than the number of APs. Additionally, we assume the use of low-resolution analog-to-digital converters (ADCs) to reduce fronthaul capacity. While realistic massive access scenarios, such as those in Internet-of-Things (IoT) environments, often involve hundreds or thousands of UEs per AP using multiple access techniques to allocate different frequency and time resources, our study focuses on scenarios where UEs within each AP cluster share the same frequency and time resources to highlight the impact of pilot contamination in dense network environments. The proposed algorithm is validated through simulations, confirming that it guarantees the connection of all UEs and prevents overserving APs. Furthermore, we analyze the required fronthaul capacity based on quantization bits and confirm that the proposed algorithm outperforms existing algorithms in terms of SE and average SE performance for UEs. Full article

(This article belongs to the Section Sensor Networks)

► Show Figures

Figure 1

20 pages, 19406 KiB

Open AccessArticle

A Novel Real-Time Detection and Classification Method for ECG Signal Images Based on Deep Learning

by Linjuan Ma and Fuquan Zhang

Sensors 2024, 24(16), 5087; https://doi.org/10.3390/s24165087 - 6 Aug 2024

Viewed by 196

Abstract

In this paper, a novel deep learning method Mamba-RAYOLO is presented, which can improve detection and classification in the processing and analysis of ECG images in real time by integrating three advanced modules. The feature extraction module in our work with a multi-branch [...] Read more.

In this paper, a novel deep learning method Mamba-RAYOLO is presented, which can improve detection and classification in the processing and analysis of ECG images in real time by integrating three advanced modules. The feature extraction module in our work with a multi-branch structure during training can capture a wide range of features to ensure efficient inference and rich feature extraction. The attention mechanism module utilized in our proposed network can dynamically focus on the most relevant spatial and channel-wise features to improve detection accuracy and computational efficiency. Then, the extracted features can be refined for efficient spatial feature processing and robust feature fusion. Several sets of experiments have been carried out to test the validity of the proposed Mamba-RAYOLO and these indicate that our method has made significant improvements in the detection and classification of ECG images. The research offers a promising framework for more accurate and efficient medical ECG diagnostics. Full article

(This article belongs to the Special Issue Sensors Technology and Application in ECG Signal Processing)

► Show Figures

Figure 1

15 pages, 547 KiB

Open AccessArticle

An Explainable Deep Learning Approach for Stress Detection in Wearable Sensor Measurements

by Martin Karl Moser, Maximilian Ehrhart and Bernd Resch

Sensors 2024, 24(16), 5085; https://doi.org/10.3390/s24165085 - 6 Aug 2024

Viewed by 243

Abstract

Stress has various impacts on the health of human beings. Recent success in wearable sensor development, combined with advancements in deep learning to automatically detect features from raw data, opens several interesting applications related to detecting emotional states. Being able to accurately detect [...] Read more.

Stress has various impacts on the health of human beings. Recent success in wearable sensor development, combined with advancements in deep learning to automatically detect features from raw data, opens several interesting applications related to detecting emotional states. Being able to accurately detect stress-related emotional arousal in an acute setting can positively impact the imminent health status of humans, i.e., through avoiding dangerous locations in an urban traffic setting. This work proposes an explainable deep learning methodology for the automatic detection of stress in physiological sensor data, recorded through a non-invasive wearable sensor device, the Empatica E4 wristband. We propose a Long-Short Term-Memory (LSTM) network, extended through a Deep Generative Ensemble of conditional GANs (LSTM DGE), to deal with the low data regime of sparsely labeled sensor measurements. As explainability is often a main concern of deep learning models, we leverage Integrated Gradients (IG) to highlight the most essential features used by the model for prediction and to compare the results to state-of-the-art expert-based stress-detection methodologies in terms of precision, recall, and interpretability. The results show that our LSTM DGE outperforms the state-of-the-art algorithm by 3 percentage points in terms of recall, and 7.18 percentage points in terms of precision. More importantly, through the use of Integrated Gradients as a layer of explainability, we show that there is a strong overlap between model-derived stress features for electrodermal activity and existing literature, which current state-of-the-art stress detection systems in medical research and psychology are based on. Full article

(This article belongs to the Special Issue Artificial-Intelligence-Enhanced Wearable Sensing Technologies for Biomechanical and Physiological Monitoring and Analysis)

► Show Figures

Figure 1

16 pages, 9926 KiB

Open AccessArticle

Automatic Methodology for Forest Fire Mapping with SuperDove Imagery

by Dionisio Rodríguez-Esparragón, Paolo Gamba and Javier Marcello

Sensors 2024, 24(16), 5084; https://doi.org/10.3390/s24165084 - 6 Aug 2024

Viewed by 192

Abstract

The global increase in wildfires due to climate change highlights the need for accurate wildfire mapping. This study performs a proof of concept on the usefulness of SuperDove imagery for wildfire mapping. To address this topic, we present an automatic methodology that combines [...] Read more.

The global increase in wildfires due to climate change highlights the need for accurate wildfire mapping. This study performs a proof of concept on the usefulness of SuperDove imagery for wildfire mapping. To address this topic, we present an automatic methodology that combines the use of various vegetation indices with clustering algorithms (bisecting k-means and k-means) to analyze images before and after fires, with the aim of improving the precision of the burned area and severity assessments. The results demonstrate the potential of using this PlanetScope sensor, showing that the methodology effectively delineates burned areas and classifies them by severity level, in comparison with data from the Copernicus Emergency Management Service (CEMS). Thus, the potential of the SuperDove satellite sensor constellation for fire monitoring is highlighted, despite its limitations regarding radiometric distortion and the absence of Short-Wave Infrared (SWIR) bands, suggesting that the methodology could contribute to better fire management strategies. Full article

(This article belongs to the Special Issue Sensors for Smart Industry and Environment)

► Show Figures

Figure 1

16 pages, 12248 KiB

Open AccessArticle

Transformer-Based Reinforcement Learning for Multi-Robot Autonomous Exploration

by Qihong Chen, Rui Wang, Ming Lyu and Jie Zhang

Sensors 2024, 24(16), 5083; https://doi.org/10.3390/s24165083 - 6 Aug 2024

Viewed by 225

Abstract

A map of the environment is the basis for the robot’s navigation. Multi-robot collaborative autonomous exploration allows for rapidly constructing maps of unknown environments, essential for application areas such as search and rescue missions. Traditional autonomous exploration methods are inefficient due to the [...] Read more.

A map of the environment is the basis for the robot’s navigation. Multi-robot collaborative autonomous exploration allows for rapidly constructing maps of unknown environments, essential for application areas such as search and rescue missions. Traditional autonomous exploration methods are inefficient due to the repetitive exploration problem. For this reason, we propose a multi-robot autonomous exploration method based on the Transformer model. Our multi-agent deep reinforcement learning method includes a multi-agent learning method to effectively improve exploration efficiency. We conducted experiments comparing our proposed method with existing methods in a simulation environment, and the experimental results showed that our proposed method had a good performance and a specific generalization ability. Full article

(This article belongs to the Section Sensors and Robotics)

► Show Figures

Figure 1

13 pages, 1930 KiB

Open AccessArticle

A Reflected-Light-Mode Multiwavelength Interferometer for Measurement of Step Height Standards

by Dariusz Litwin, Kamil Radziak, Adam Czyżewski, Jacek Galas, Tadeusz Kryszczyński, Narcyz Błocki, Robert Szumski and Justyna Niedziela

Sensors 2024, 24(16), 5082; https://doi.org/10.3390/s24165082 - 6 Aug 2024

Viewed by 228

Abstract

The article is dedicated to measuring the thickness of step height standards using the author’s version of the variable wavelength interferometer (VAWI) in the reflected-light mode, where the interference pattern is created by the combination of two Wollaston prisms. The element of novelty [...] Read more.

The article is dedicated to measuring the thickness of step height standards using the author’s version of the variable wavelength interferometer (VAWI) in the reflected-light mode, where the interference pattern is created by the combination of two Wollaston prisms. The element of novelty consists in replacing the traditional search for the coincidence of fringes in the object and background with a continuous measurement of their periods and phases relative to the zero-order fringe. The resulting system of sinusoids is then analyzed using two methods: the classical one and the second utilizing the criterion of uniform thickness. The theory is followed by simulation and experimental parts, providing insight to the metrological potential of the VAWI technology. Full article

(This article belongs to the Special Issue Precision Optical Metrology and Smart Sensing)

► Show Figures

Figure 1

16 pages, 3793 KiB

Open AccessArticle

Rapid In Situ Near-Infrared Assessment of Tetrahydrocannabinolic Acid in Cannabis Inflorescences before Harvest Using Machine Learning

by Jonathan Tran, Simone Vassiliadis, Aaron C. Elkins, Noel O. O. Cogan and Simone J. Rochfort

Sensors 2024, 24(16), 5081; https://doi.org/10.3390/s24165081 - 6 Aug 2024

Viewed by 276

Abstract

Cannabis is cultivated for therapeutic and recreational purposes where delta-9 tetrahydrocannabinol (THC) is a main target for its therapeutic effects. As the global cannabis industry and research into cannabinoids expands, more efficient and cost-effective analysis methods for determining cannabinoid concentrations will be beneficial [...] Read more.

Cannabis is cultivated for therapeutic and recreational purposes where delta-9 tetrahydrocannabinol (THC) is a main target for its therapeutic effects. As the global cannabis industry and research into cannabinoids expands, more efficient and cost-effective analysis methods for determining cannabinoid concentrations will be beneficial to increase efficiencies and maximize productivity. The utilization of machine learning tools to develop near-infrared (NIR) spectroscopy-based prediction models, which have been validated from accurate and sensitive chemical analysis, such as gas chromatography (GC) or liquid chromatography mass spectroscopy (LCMS), is essential. Previous research on cannabinoid prediction models targeted decarboxylated cannabinoids, such as THC, rather than the naturally occurring precursor, tetrahydrocannabinolic acid (THCA), and utilize finely ground cannabis inflorescence. The current study focuses on building prediction models for THCA concentrations in whole cannabis inflorescences prior to harvest, by employing non-destructive screening techniques so cultivators may rapidly characterize high-performing cultivars for chemotype in real time, thus facilitating targeted optimization of crossbreeding efforts. Using NIR spectroscopy and LCMS to create prediction models we can differentiate between high-THCA and even ratio classes with 100% prediction accuracy. We have also developed prediction models for THCA concentration with a R² = 0.78 with a prediction error average of 13%. This study demonstrates the viability of a portable handheld NIR device to predict THCA concentrations on whole cannabis samples before harvest, allowing the evaluation of cannabinoid profiles to be made earlier, therefore increasing high-throughput and rapid capabilities. Full article

(This article belongs to the Section Smart Agriculture)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Sensors, Volume 24, Issue 16 (August-2 2024) – 28 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI