Sensors

15 pages, 1109 KiB

Open AccessReview

Recent Progress in Nanomaterial-Based Fluorescence Assays for the Detection of Food-Borne Pathogens

by Shiyu Song, Lu Han, Min Chen, Leiqing Pan and Kang Tu

Sensors 2024, 24(23), 7715; https://doi.org/10.3390/s24237715 (registering DOI) - 2 Dec 2024

Food safety is of great concern, and food-borne bacterial infections and diseases are a major crisis for health. Therefore, it is necessary to develop rapid detection techniques for the prevention and recognition of food safety hazards caused by food-borne pathogens. In recent years, [...] Read more.

Food safety is of great concern, and food-borne bacterial infections and diseases are a major crisis for health. Therefore, it is necessary to develop rapid detection techniques for the prevention and recognition of food safety hazards caused by food-borne pathogens. In recent years, the fluorescence assay has become a widely utilized detection method due to its good signal amplification effect, high detection sensitivity, high stability, and short detection time. In this review, the different kinds of fluorescence materials were concentrated, including quantum dots (QDs), carbon dots (CDs), metal–organic frameworks (MOFs), and upconversion nanoparticles (UCNPs). The optical properties and applications of different kinds of fluorescent materials were analyzed and compared. Furthermore, according to the biosensing components, different fluorescence biosensors are reviewed, including label-free based fluorescence probes, aptamer-based biosensors, and antibody-based biosensors. Finally, we focused our attention on the discussion of fluorescent detection techniques combined with other techniques and their applications. The review presents future trends in fluorescence sensors, providing new sights for the detection of food-borne pathogens. Full article

(This article belongs to the Special Issue Technology Trends in Fluorescence Detection Based on Biosensor)

27 pages, 7927 KiB

Open AccessArticle

Aspherical Surface Wavefront Testing Based on Multi-Directional Orthogonal Lateral Shearing Interferometry

by Yahui Zhu, Ailing Tian, Hongjun Wang and Bingcai Liu

Sensors 2024, 24(23), 7714; https://doi.org/10.3390/s24237714 (registering DOI) - 2 Dec 2024

Abstract

To overcome the limitations of phase sampling points in testing aspherical surface wavefronts using traditional interferometers, we propose a high-spatial-resolution method based on multi-directional orthogonal lateral shearing interferometry. In this study, we provide a detailed description of the methodology, which includes the theoretical [...] Read more.

To overcome the limitations of phase sampling points in testing aspherical surface wavefronts using traditional interferometers, we propose a high-spatial-resolution method based on multi-directional orthogonal lateral shearing interferometry. In this study, we provide a detailed description of the methodology, which includes the theoretical foundations and experimental setup, along with the results from simulations and experiments. By establishing a relational model between the multi-directional differential wavefront and differential Zernike polynomials, we demonstrate high-spatial-resolution wavefront reconstruction using multi-directional orthogonal lateral shearing interferometry. Theoretical calculations and simulations of aspherical surface wavefront testing are followed by experimental verification on an aspherical surface with a known asphericity. Comparing the measurement results with those from the LuphoScan profilometer, we achieve a relative measurement error with an RMS precision better than λ/100. Full article

(This article belongs to the Special Issue Advanced Sensing Technology in Optical Coherence Tomography)

19 pages, 7770 KiB

Open AccessArticle

An Improved Generative Adversarial Network-Based and U-Shaped Transformer Method for Glass Curtain Crack Deblurring Using UAVs

by Jiaxi Huang and Guixiong Liu

Sensors 2024, 24(23), 7713; https://doi.org/10.3390/s24237713 (registering DOI) - 2 Dec 2024

Abstract

Drones have emerged as a critical tool for the detection of high-altitude glass curtain cracks. However, their utility is often compromised by vibrations and other environmental factors that can induce motion blur, compromising image quality and the accuracy of crack detection. This paper [...] Read more.

Drones have emerged as a critical tool for the detection of high-altitude glass curtain cracks. However, their utility is often compromised by vibrations and other environmental factors that can induce motion blur, compromising image quality and the accuracy of crack detection. This paper presents a novel GAN-based and enhanced U-shaped Transformer network, named GlassCurtainCrackDeblurNet, designed specifically for the deblurring of drone-captured images of glass curtain cracks. To optimize the performance of our proposed method for this application, we have meticulously created the GlassCurtainCrackDeblur Dataset. Our method demonstrates superior qualitative and quantitative outcomes when compared to other established deblurring techniques on both the GoPro Dataset and the GlassCurtainCrackDeblur Dataset. Full article

(This article belongs to the Section Remote Sensors)

16 pages, 4053 KiB

Open AccessArticle

Quantum Positioning Scheme Based on Microwave–Optical Entanglement

by Qiang Miao and Dewei Wu

Sensors 2024, 24(23), 7712; https://doi.org/10.3390/s24237712 (registering DOI) - 2 Dec 2024

Abstract

Microwaves exhibit superior performance in free-space transmission compared to optical waves, primarily due to their ability to penetrate fog and experience lower losses in the Earth’s atmosphere. Based on microwave–optical entanglement prepared by nano-cavity electro-opto-mechanic converters, we propose a scheme of a quantum [...] Read more.

Microwaves exhibit superior performance in free-space transmission compared to optical waves, primarily due to their ability to penetrate fog and experience lower losses in the Earth’s atmosphere. Based on microwave–optical entanglement prepared by nano-cavity electro-opto-mechanic converters, we propose a scheme of a quantum positioning system using the distance-based positioning method. Principles of microwave–optical entanglement preparation and our QPS scheme are introduced in detail. The entanglement feature, system stability and positioning feature of the scheme are analyzed after simulations. Furthermore, we delve into the impact of key parameters, such as transmissivity and photon conversion efficiency, on positioning. Notably, the entanglement degrees for both microwave–optic entanglement at the transmitter and optic–optic entanglement at the receiver surpass one, affirming the efficiency of the scheme in preparing and maintaining entanglement. When transmissivity in beam-splitter models of both ground stations equals 0.5, our scheme achieves a minimal positioning error of

6 . 4 \times 10^{- 7} m^{2}

under ideal conditions. Additionally, we map out traces of a plane through continuous positioning using our scheme. These results demonstrate the theoretical efficiency and robustness of our proposed approach. Full article

(This article belongs to the Collection Navigation Systems and Sensors)

► Show Figures

Figure 1

23 pages, 1709 KiB

Open AccessArticle

Re-Parameterization After Pruning: Lightweight Algorithm Based on UAV Remote Sensing Target Detection

by Yang Yang, Pinde Song, Yongchao Wang and Lijia Cao

Sensors 2024, 24(23), 7711; https://doi.org/10.3390/s24237711 (registering DOI) - 2 Dec 2024

Abstract

Lightweight object detection algorithms play a paramount role in unmanned aerial vehicles (UAVs) remote sensing. However, UAV remote sensing requires target detection algorithms to have higher inference speeds and greater accuracy in detection. At present, most lightweight object detection algorithms have achieved fast [...] Read more.

Lightweight object detection algorithms play a paramount role in unmanned aerial vehicles (UAVs) remote sensing. However, UAV remote sensing requires target detection algorithms to have higher inference speeds and greater accuracy in detection. At present, most lightweight object detection algorithms have achieved fast inference speed, but their detection precision is not satisfactory. Consequently, this paper presents a refined iteration of the lightweight object detection algorithm to address the above issues. The MobileNetV3 based on the efficient channel attention (ECA) module is used as the backbone network of the model. In addition, the focal and efficient intersection over union (FocalEIoU) is used to improve the regression performance of the algorithm and reduce the false-negative rate. Furthermore, the entire model is pruned using the convolution kernel pruning method. After pruning, model parameters and floating-point operations (FLOPs) on VisDrone and DIOR datasets are reduced to 1.2 M and 1.5 M and 6.2 G and 6.5 G, respectively. The pruned model achieves 49 frames per second (FPS) and 44 FPS inference speeds on Jetson AGX Xavier for VisDrone and DIOR datasets, respectively. To fully exploit the performance of the pruned model, a plug-and-play structural re-parameterization fine-tuning method is proposed. The experimental results show that this fine-tuned method improves [email protected] and [email protected]:0.95 by 0.4% on the VisDrone dataset and increases [email protected]:0.95 by 0.5% on the DIOR dataset. The proposed algorithm outperforms other mainstream lightweight object detection algorithms (except for FLOPs higher than SSDLite and [email protected] Below YOLOv7 Tiny) in terms of parameters, FLOPs, [email protected], and [email protected]:0.95. Furthermore, practical validation tests have also demonstrated that the proposed algorithm significantly reduces instances of missed detection and duplicate detection. Full article

(This article belongs to the Section Remote Sensors)

23 pages, 1158 KiB

Open AccessArticle

Automated Detection of Gastrointestinal Diseases Using Resnet50*-Based Explainable Deep Feature Engineering Model with Endoscopy Images

by Veysel Yusuf Cambay, Prabal Datta Barua, Abdul Hafeez Baig, Sengul Dogan, Mehmet Baygin, Turker Tuncer and U. R. Acharya

Sensors 2024, 24(23), 7710; https://doi.org/10.3390/s24237710 (registering DOI) - 2 Dec 2024

Abstract

This work aims to develop a novel convolutional neural network (CNN) named ResNet50* to detect various gastrointestinal diseases using a new ResNet50*-based deep feature engineering model with endoscopy images. The novelty of this work is the development of ResNet50*, a new variant of [...] Read more.

This work aims to develop a novel convolutional neural network (CNN) named ResNet50* to detect various gastrointestinal diseases using a new ResNet50*-based deep feature engineering model with endoscopy images. The novelty of this work is the development of ResNet50*, a new variant of the ResNet model, featuring convolution-based residual blocks and a pooling-based attention mechanism similar to PoolFormer. Using ResNet50*, a gastrointestinal image dataset was trained, and an explainable deep feature engineering (DFE) model was developed. This DFE model comprises four primary stages: (i) feature extraction, (ii) iterative feature selection, (iii) classification using shallow classifiers, and (iv) information fusion. The DFE model is self-organizing, producing 14 different outcomes (8 classifier-specific and 6 voted) and selecting the most effective result as the final decision. During feature extraction, heatmaps are identified using gradient-weighted class activation mapping (Grad-CAM) with features derived from these regions via the final global average pooling layer of the pretrained ResNet50*. Four iterative feature selectors are employed in the feature selection stage to obtain distinct feature vectors. The classifiers k-nearest neighbors (kNN) and support vector machine (SVM) are used to produce specific outcomes. Iterative majority voting is employed in the final stage to obtain voted outcomes using the top result determined by the greedy algorithm based on classification accuracy. The presented ResNet50* was trained on an augmented version of the Kvasir dataset, and its performance was tested using Kvasir, Kvasir version 2, and wireless capsule endoscopy (WCE) curated colon disease image datasets. Our proposed ResNet50* model demonstrated a classification accuracy of more than 92% for all three datasets and a remarkable 99.13% accuracy for the WCE dataset. These findings affirm the superior classification ability of the ResNet50* model and confirm the generalizability of the developed architecture, showing consistent performance across all three distinct datasets. Full article

(This article belongs to the Special Issue AI-Based Automated Recognition and Detection in Healthcare)

37 pages, 1218 KiB

Open AccessReview

FPGA-Based Sensors for Distributed Digital Manufacturing Systems: A State-of-the-Art Review

by Laraib Khan, Sriram Praneeth Isanaka and Frank Liou

Sensors 2024, 24(23), 7709; https://doi.org/10.3390/s24237709 (registering DOI) - 2 Dec 2024

Abstract

The combination of distributed digital factories (D²Fs) with sustainable practices has been proposed as a revolutionary technique in modern manufacturing. This review paper explores the convergence of D²F with innovative sensor technology, concentrating on the role of Field Programmable [...] Read more.

The combination of distributed digital factories (D²Fs) with sustainable practices has been proposed as a revolutionary technique in modern manufacturing. This review paper explores the convergence of D²F with innovative sensor technology, concentrating on the role of Field Programmable Gate Arrays (FPGAs) in promoting this paradigm. A D²F is defined as an integrated framework where digital twins (DTs), sensors, laser additive manufacturing (laser-AM), and subtractive manufacturing (SM) work in synchronization. Here, DTs serve as a virtual replica of physical machines, allowing accurate monitoring and control of a given manufacturing process. These DTs are supplemented by sensors, providing near-real-time data to assure the effectiveness of the manufacturing processes. FPGAs, identified for their re-programmability, reduced power usage, and enhanced processing compared to traditional processors, are increasingly being used to develop near-real-time monitoring systems within manufacturing networks. This review paper identifies the recent expansions in FPGA-based sensors and their exploration within the D²Fs operations. The primary topics incorporate the deployment of eco-efficient data management and near-real-time monitoring, targeted at lowering waste and optimizing resources. The review paper also identifies the future research directions in this field. By incorporating advanced sensors, DTs, laser-AM, and SM processes, this review emphasizes a path toward more sustainable and resilient D²Fs operations. Full article

(This article belongs to the Special Issue Feature Review Papers in Optical Sensors)

13 pages, 272 KiB

Open AccessArticle

Identification of Game Periods and Playing Position Activity Profiles in Elite-Level Beach Soccer Players Through Principal Component Analysis

by Pau Vaccaro Benet, Alexis Ugalde-Ramírez, Carlos D. Gómez-Carmona, José Pino-Ortega and Boryi A. Becerra-Patiño

Sensors 2024, 24(23), 7708; https://doi.org/10.3390/s24237708 (registering DOI) - 2 Dec 2024

Abstract

Beach soccer has gained increasing interest for study in the sports sciences. In this sense, the analysis of activity profiles is important for training design and load individualization. Therefore, the aims of this study were to identify the most important variables to assess [...] Read more.

Beach soccer has gained increasing interest for study in the sports sciences. In this sense, the analysis of activity profiles is important for training design and load individualization. Therefore, the aims of this study were to identify the most important variables to assess the activity profile and to compare them according to the playing position and game periods in international beach soccer matches. A total of 19 matches of the Spanish national beach soccer team were analyzed during their participation in different international competitions during the 2021–2022 season. A Principal Component Analysis (PCA) was applied to objectively select the external load variables that best explain the data. Kaiser–Meyer–Olkin values of 0.705 and Bartlett’s Sphericity (p < 0.01) were obtained. Kruskal–Wallis and Friedman tests was performed for playing positions and game period comparisons, respectively. The PCA showed seven components that grouped a total of 20 variables, explaining 66% of the total variance. Only PC1 and PC2 explained more than 15% (23% and 17%, respectively). Differences were found between playing positions (H > 22.73; p < 0.01) and between game periods (X2 > 16.46; p < 0.01). A significant decrease was found throughout the game, with the highest demands in period 1 and the lowest in period 3. The highest workloads were performed by wingers and the lowest by goalkeepers. The differences between positions and game periods were found in the following: Total Distance (m/min), HIBD (m/min), High Acc (m/s), High Dec (m/s), Acc 1–2 m/s² (m), Acc 2–3 m/s² (m), Imp 4–5G (n), Imp 5–6G (n), Sprint (n), and Dec 10–6 m/s² (m) (p < 0.01). In conclusion, physical and tactical demands faced by elite-level beach soccer players will be influenced by playing positions and game periods. Coaches needs to develop position-specific training programs and optimize substitution strategies for enhancing overall team performance. Full article

(This article belongs to the Special Issue Sensing Technology and Wearables for Physical Activity)

17 pages, 5352 KiB

Open AccessArticle

Evaluation of a Non-Enzymatic Electrochemical Sensor Based on Co(OH)₂-Functionalized Carbon Nanotubes for Glucose Detection

by Diego Bolaños-Mendez, Lenys Fernández, Rafael Uribe, Alisson Cunalata-Castro, Gema González, Isamara Rojas, Andrés Chico-Proano, Alexis Debut, Luis Alberto Celi and Patricio Espinoza-Montero

Sensors 2024, 24(23), 7707; https://doi.org/10.3390/s24237707 (registering DOI) - 2 Dec 2024

Abstract

This work reports on the assessment of a non-hydrolytic electrochemical sensor for glucose sensing that is developed using functionalized carbon nanotubes (fCNTs)/Co(OH)₂. The morphology of the nanocomposite was investigated by scanning electron microscopy, which revealed that the CNTs interacted with Co(OH) [...] Read more.

This work reports on the assessment of a non-hydrolytic electrochemical sensor for glucose sensing that is developed using functionalized carbon nanotubes (fCNTs)/Co(OH)₂. The morphology of the nanocomposite was investigated by scanning electron microscopy, which revealed that the CNTs interacted with Co(OH)₂. This content formed a nanocomposite that improved the electrochemical characterizations of the electrode, including the electrochemical active surface area and capacitance, thus improving sensitivity to glucose. In the electrochemical characterization by cyclic voltammetry and chronoamperometry, the increase in catalytic activity by Co(OH)₂ improved the stability and reproducibility of the glucose sensor without the use of enzymes, and its concentration range was between 50 and 700 μmol L⁻¹. The sensor exhibited good linearity towards glucose with LOD value of 43.200 µmol L⁻¹, which proved that the Co(OH)₂-fCNTs composite is judicious for constructing cost effective and feasible sensor for glucose detection. Full article

(This article belongs to the Special Issue Nanomaterials for Sensor Applications)

► Show Figures

Figure 1

14 pages, 2922 KiB

Open AccessArticle

Impact of Power and Time in Hepatic Microwave Ablation: Effect of Different Energy Delivery Schemes

by Macarena Trujillo, Mahtab Ebad Najafabadi, Antonio Romero, Punit Prakash and Francois H. Cornelis

Sensors 2024, 24(23), 7706; https://doi.org/10.3390/s24237706 (registering DOI) - 2 Dec 2024

Abstract

Microwave ablation often involves the use of continuous energy-delivery protocols with a fixed power and time. To achieve larger ablation zones, a range of protocols and power levels have been studied in experimental studies. The objective of the present study was to develop [...] Read more.

Microwave ablation often involves the use of continuous energy-delivery protocols with a fixed power and time. To achieve larger ablation zones, a range of protocols and power levels have been studied in experimental studies. The objective of the present study was to develop and experimentally evaluate the performance of a coupled computational electromagnetic–bioheat transfer model of 2.45 GHz microwave ablation under a variety of continuous and pulsed power delivery schemes. The main aim was to obtain an in-depth knowledge of the influence of energy delivery settings on ablation zone profiles and thermal damage in the peri-ablation zone. In addition to the theoretical model, we evaluated the power delivery schemes using ex vivo experiments and compared them to previously published data from in vivo experiments. The results showed slight differences in terms of the ablation zone size for different power delivery schemes under ex vivo conditions, with the applied energy level being the most important factor that determines ablation zone size; however, under in vivo conditions, applying a high-power pulse prior to and following a longer constant power application (BOOKEND 95 W protocol) presented the most favorable ablation zones. Moreover, the modeling and experimental studies identified threshold applied power and ablation times beyond which increases did not yield substantive increases in ablation zone extents. Full article

(This article belongs to the Special Issue Microwaves for Biomedical Applications and Sensing)

► Show Figures

Figure 1

14 pages, 5943 KiB

Open AccessArticle

Comparative Analysis of Force-Sensitive Resistors and Triaxial Accelerometers for Sitting Posture Classification

by Zhuofu Liu, Zihao Shu, Vincenzo Cascioli and Peter W. McCarthy

Sensors 2024, 24(23), 7705; https://doi.org/10.3390/s24237705 (registering DOI) - 2 Dec 2024

Abstract

Sedentary behaviors, including poor postures, are significantly detrimental to health, particularly for individuals losing motion ability. This study presents a posture detection system utilizing four force-sensitive resistors (FSRs) and two triaxial accelerometers selected after rigorous assessment for consistency and linearity. We compared various [...] Read more.

Sedentary behaviors, including poor postures, are significantly detrimental to health, particularly for individuals losing motion ability. This study presents a posture detection system utilizing four force-sensitive resistors (FSRs) and two triaxial accelerometers selected after rigorous assessment for consistency and linearity. We compared various machine learning algorithms based on classification accuracy and computational efficiency. The k-nearest neighbor (KNN) algorithm demonstrated superior performance over Decision Tree, Discriminant Analysis, Naive Bayes, and Support Vector Machine (SVM). Further analysis of KNN hyperparameters revealed that the city block metric with K = 3 yielded optimal classification results. Triaxial accelerometers exhibited higher accuracy in both training (99.4%) and testing (99.0%) phases compared to FSRs (96.6% and 95.4%, respectively), with slightly reduced processing times (0.83 s vs. 0.85 s for training; 0.51 s vs. 0.54 s for testing). These findings suggest that, apart from being cost-effective and compact, triaxial accelerometers are more effective than FSRs for posture detection. Full article

(This article belongs to the Special Issue Advanced Sensing and Measurement Control Applications)

► Show Figures

Figure 1

18 pages, 4660 KiB

Open AccessArticle

Early Technology Readiness Level (TRL) Development of the Microfluidic Inorganic Conductivity Detector for Europa and the Solenoid-Based Actuator Assembly for Impact Penetrators

by Chinmayee Govinda Raj, Mohamed Odeh, Cambrie Salyards and Amanda Stockton

Sensors 2024, 24(23), 7704; https://doi.org/10.3390/s24237704 (registering DOI) - 2 Dec 2024

Abstract

This study introduces an innovative in situ lander/impact-penetrator design tailored for Discovery-class missions to Europa, specifically focused on conducting astrobiological analyses. The platform integrates a microfluidic capacitively coupled contactless conductivity detector (C4D), optimized for the detection of low-concentration salts potentially indicative of biological [...] Read more.

This study introduces an innovative in situ lander/impact-penetrator design tailored for Discovery-class missions to Europa, specifically focused on conducting astrobiological analyses. The platform integrates a microfluidic capacitively coupled contactless conductivity detector (C4D), optimized for the detection of low-concentration salts potentially indicative of biological activity. Our microfluidic system allows for automated sample routing and precise conductivity-based detection, making it suitable for the harsh environmental and logistical demands of Europa’s icy surface. This technology provides a robust toolset for exploring extraterrestrial habitability by enabling in situ chemical analyses with minimal operational intervention, paving the way for advanced astrobiological investigations on Europa. Full article

(This article belongs to the Special Issue (Electro)chemical and Optical (Bio)sensing Devices for Decentralized Cost-Effective (Bio)chemical Monitoring)

► Show Figures

Figure 1

24 pages, 6411 KiB

Open AccessArticle

CNN-Based Kidney Segmentation Using a Modified CLAHE Algorithm

by Abror Shavkatovich Buriboev, Ahmadjon Khashimov, Akmal Abduvaitov and Heung Seok Jeon

Sensors 2024, 24(23), 7703; https://doi.org/10.3390/s24237703 (registering DOI) - 2 Dec 2024

Abstract

This paper presents an enhanced approach to kidney segmentation using a modified CLAHE preprocessing method, aimed at improving image clarity and CNN performance on the KiTS19 dataset. To assess the impact of the modified CLAHE method, we conducted quality evaluations using the BRISQUE [...] Read more.

This paper presents an enhanced approach to kidney segmentation using a modified CLAHE preprocessing method, aimed at improving image clarity and CNN performance on the KiTS19 dataset. To assess the impact of the modified CLAHE method, we conducted quality evaluations using the BRISQUE metric, comparing the original, standard CLAHE and modified CLAHE versions of the dataset. The BRISQUE score decreased from 28.8 in the original dataset to 21.1 with the modified CLAHE method, indicating a significant improvement in image quality. Furthermore, CNN segmentation accuracy rose from 0.951 with the original dataset to 0.996 with the modified CLAHE method, outperforming the accuracy achieved with standard CLAHE preprocessing (0.969). These results highlight the benefits of the modified CLAHE method in refining image quality and enhancing segmentation performance. This study highlights the value of adaptive preprocessing in medical imaging workflows and shows that CNN-based kidney segmentation accuracy may be greatly increased by altering conventional CLAHE. Our method provides insightful information on optimizing preprocessing for medical imaging applications, leading to more accurate and dependable segmentation results for better clinical diagnosis. Full article

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

► Show Figures

Figure 1

18 pages, 2648 KiB

Open AccessArticle

Semantic Scene Completion in Autonomous Driving: A Two-Stream Multi-Vehicle Collaboration Approach

by Junxuan Li, Yuanfang Zhang, Jiayi Han, Peng Han and Kaiqing Luo

Sensors 2024, 24(23), 7702; https://doi.org/10.3390/s24237702 (registering DOI) - 2 Dec 2024

Abstract

Vehicle-to-vehicle communication enables capturing sensor information from diverse perspectives, greatly aiding in semantic scene completion in autonomous driving. However, the misalignment of features between ego vehicle and cooperative vehicles leads to ambiguity problems, affecting accuracy and semantic information. In this paper, we propose [...] Read more.

Vehicle-to-vehicle communication enables capturing sensor information from diverse perspectives, greatly aiding in semantic scene completion in autonomous driving. However, the misalignment of features between ego vehicle and cooperative vehicles leads to ambiguity problems, affecting accuracy and semantic information. In this paper, we propose a Two-Stream Multi-Vehicle collaboration approach (TSMV), which divides the features of collaborative vehicles into two streams and regresses interactively. To overcome the problems caused by feature misalignment, the Neighborhood Self-Cross Attention Transformer (NSCAT) module is designed to enable the ego vehicle to query the most similar local features from collaborative vehicles through cross-attention, rather than assuming spatial-temporal synchronization. A 3D occupancy map is finally generated from the features of collaborative vehicle aggregation. Experimental results on both V2VSSC and SemanticOPV2V datasets demonstrate TSMV outpace state-of-the-art collaborative semantic scene completion techniques. Full article

(This article belongs to the Special Issue Intelligent Sensing and Computing for Smart and Autonomous Vehicles)

► Show Figures

Figure 1

22 pages, 27876 KiB

Open AccessArticle

Plug-and-Play PRNU Enhancement Algorithm with Guided Filtering

by Yufei Liu, Yanhui Xiao and Huawei Tian

Sensors 2024, 24(23), 7701; https://doi.org/10.3390/s24237701 (registering DOI) - 2 Dec 2024

Abstract

As a weak high-frequency signal embedded in digital images, Photo Response Non-Uniformity (PRNU) is particularly vulnerable to interference from low-frequency components during the extraction process, which affects its reliability in real-world forensic applications. Previous studies have not successfully identified the effective frequency band [...] Read more.

As a weak high-frequency signal embedded in digital images, Photo Response Non-Uniformity (PRNU) is particularly vulnerable to interference from low-frequency components during the extraction process, which affects its reliability in real-world forensic applications. Previous studies have not successfully identified the effective frequency band of PRNU, leaving low-frequency interference insufficiently suppressed and impacting PRNU’s utility in scenarios such as source camera identification, image integrity verification, and identity verification. Additionally, due to differing operational mechanisms, current mainstream PRNU enhancement algorithms cannot be integrated to improve their performance further. To address these issues, we conducted a frequency-by-frequency analysis of the estimated PRNU and discovered that it predominantly resides in the frequency band above 10 Hz. Based on this finding, we propose a guided-filtering PRNU enhancement algorithm. This algorithm can function as a plug-and-play module, seamlessly integrating with existing mainstream enhancement techniques to further boost PRNU performance. Specifically, we use the PRNU components below 10 Hz as a guide image and apply guided filtering to reconstruct the low-frequency interference components. By filtering out these low-frequency components, we retain and enhance the high-frequency PRNU signal. By setting appropriate enhancement coefficients, the low-frequency interference is suppressed, and the high-frequency components are further amplified. Extensive experiments on publicly available Dresden and Daxing digital device forensics datasets confirm the efficiency and robustness of the proposed method, making it highly suitable for reliable forensic analysis in practical settings. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

9 pages, 2256 KiB

Open AccessCommunication

Progressive and Asymmetrical Deadlift Loads Captured by Wearable Motion Tape Sensors

by Elijah Wyckoff, David Sten, Regan Wareham and Kenneth J. Loh

Sensors 2024, 24(23), 7700; https://doi.org/10.3390/s24237700 (registering DOI) - 2 Dec 2024

Abstract

Weight training is widely adopted and highly effective for enhancing both muscular strength and endurance. A popular weightlifting exercise is the deadlift, which targets multiple muscle groups including the lower back, glutes, and hamstrings. However, incorrect technique (i.e., poor form) can slow training [...] Read more.

Weight training is widely adopted and highly effective for enhancing both muscular strength and endurance. A popular weightlifting exercise is the deadlift, which targets multiple muscle groups including the lower back, glutes, and hamstrings. However, incorrect technique (i.e., poor form) can slow training progress, result in asymmetrical muscle development, and cause serious injuries. The objective of this study was to validate that a self-adhesive, elastic fabric, wearable, skin-strain sensor called Motion Tape (MT) could monitor a person’s posture while performing deadlift exercises. Two pairs of Motion Tape were attached on the front and back sides of the pelvis at each posterior superior iliac spine to record muscle engagement during deadlift exercises. The results of this preliminary study confirmed that the MT identified asymmetry in muscle engagement during deadlifting repetitions. In addition, the sensors could quantify the different levels of effort exerted according to the deadlift weight load. Full article

(This article belongs to the Special Issue Wearable Sensors for Optimising Rehabilitation and Sport Training)

► Show Figures

Figure 1

18 pages, 5180 KiB

Open AccessArticle

Development of Image-Based Water Level Sensor with High-Resolution and Low-Cost Using Image Processing Algorithm: Application to Outgassing Measurements from Gas-Enriched Polymer

by Ji Hun Lee and Jae Kap Jung

Sensors 2024, 24(23), 7699; https://doi.org/10.3390/s24237699 (registering DOI) - 1 Dec 2024

Abstract

A high-resolution and low-cost image-based water level sensor was developed using an image processing algorithm. The sensor measures water levels in six channels simultaneously. The image processing algorithm automatically identifies water level images and determines the water levels by analyzing the brightness of [...] Read more.

A high-resolution and low-cost image-based water level sensor was developed using an image processing algorithm. The sensor measures water levels in six channels simultaneously. The image processing algorithm automatically identifies water level images and determines the water levels by analyzing the brightness of the images. The measured water levels were verified by comparison with the calibrated water levels using known length standards. The performance test results of the developed water level sensor were compared with those of commercial water level sensors, demonstrating a superior resolution of 0.06 mm and an inexpensive cost of USD 80. In addition, the developed sensor demonstrated an accuracy of 0.9%, a stability of 0.3%, an adjustable measurement range, and an instantaneous response time. In conclusion, the image-based water level sensor that was developed provides a reliable method for real-time visual monitoring of water levels in six channels simultaneously. Full article

(This article belongs to the Section Environmental Sensing)

► Show Figures

Figure 1

23 pages, 1524 KiB

Open AccessArticle

Satellite Fingerprinting Methods for GNSS Spoofing Detection

by Francisco Gallardo, Antonio Pérez-Yuste and Andriy Konovaltsev

Sensors 2024, 24(23), 7698; https://doi.org/10.3390/s24237698 (registering DOI) - 1 Dec 2024

Abstract

Spoofing attacks pose a significant security risk for organizations and systems relying on global navigation satellite systems (GNSS) for their operations. While the existing spoofing detection methods have shown some effectiveness, these can be vulnerable to certain attacks, such as secure code estimation [...] Read more.

Spoofing attacks pose a significant security risk for organizations and systems relying on global navigation satellite systems (GNSS) for their operations. While the existing spoofing detection methods have shown some effectiveness, these can be vulnerable to certain attacks, such as secure code estimation and replay (SCER) attacks, among others.This paper analyzes the potential of satellite fingerprinting methods for GNSS spoofing detection and benchmarks their performance using real (in realistic scenarios by using GPS and Galileo signals generated and recorded in the advanced GNSS simulation facility of DLR) GNSS signals and scenarios. Our results show that our proposed fingerprinting methods can improve the detection accuracy of the existing methods and can be coupled with other techniques to enhance the overall performance of the detection systems, all based on relatively simple metrics. In this paper, we compare the performance of several fingerprinting methods, including those from the existing literature (based on signal Gaussian properties of the signal complex envelope, energy and in-phase symbol dispersion) and one proposed in this paper, based on the satellite instrumental delay. The innovation of this work is a new jamming and spoofing complementary detection technique, based on fingerprinting and machine learning, including a new fingerprinting metric (based on the satellite instrumental delay). Full article

(This article belongs to the Section Navigation and Positioning)

► Show Figures

Figure 1

27 pages, 4935 KiB

Open AccessArticle

Diverse Dataset for Eyeglasses Detection: Extending the Flickr-Faces-HQ (FFHQ) Dataset

by Dalius Matuzevičius

Sensors 2024, 24(23), 7697; https://doi.org/10.3390/s24237697 (registering DOI) - 1 Dec 2024

Abstract

Facial analysis is an important area of research in computer vision and machine learning, with applications spanning security, healthcare, and user interaction systems. The data-centric AI approach emphasizes the importance of high-quality, diverse, and well-annotated datasets in driving advancements in this field. However, [...] Read more.

Facial analysis is an important area of research in computer vision and machine learning, with applications spanning security, healthcare, and user interaction systems. The data-centric AI approach emphasizes the importance of high-quality, diverse, and well-annotated datasets in driving advancements in this field. However, current facial datasets, such as Flickr-Faces-HQ (FFHQ), lack detailed annotations for detecting facial accessories, particularly eyeglasses. This work addresses this limitation by extending the FFHQ dataset with precise bounding box annotations for eyeglasses detection, enhancing its utility for data-centric AI applications. The extended dataset comprises 70,000 images, including over 16,000 images containing eyewear, and it exceeds the CelebAMask-HQ dataset in size and diversity. A semi-automated protocol was employed to efficiently generate accurate bounding box annotations, minimizing the demand for extensive manual labeling. This enriched dataset serves as a valuable resource for training and benchmarking eyewear detection models. Additionally, the baseline benchmark results for eyeglasses detection were presented using deep learning methods, including YOLOv8 and MobileNetV3. The evaluation, conducted through cross-dataset validation, demonstrated the robustness of models trained on the extended FFHQ dataset with their superior performances over existing alternative CelebAMask-HQ. The extended dataset, which has been made publicly available, is expected to support future research and development in eyewear detection, contributing to advancements in facial analysis and related fields. Full article

(This article belongs to the Special Issue Image Processing and Pattern Recognition Based on Deep Learning—2nd Edition)

► Show Figures

Figure 1

Journal Description

Sensors

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI