Next Issue
Volume 25, October-1
Previous Issue
Volume 25, September-1
 
 
sensors-logo

Journal Browser

Journal Browser

Sensors, Volume 25, Issue 18 (September-2 2025) – 326 articles

Cover Story (view full-size image): A new high-speed infrared thermometer is redefining how we measure combustion. Designed around an InAsSb photodiode and operating across 3 to 11 μm, this non-contact instrument captures the surface temperature of Jet A kerosene droplets with microsecond precision, without disturbing the flame. Sensitive below 300 °C and accurate to within ±2 °C, it reveals transient thermal behaviour that conventional probes often miss. Validated against industry standards, the system offers a robust platform for fuel characterisation under controlled conditions. By enabling time-resolved thermal measurements with minimal interference, this technique supports the development of cleaner, more efficient aviation technologies and provides a valuable tool for advancing combustion diagnostics and sustainable fuel research. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Select all
Export citation of selected articles as:
26 pages, 10719 KB  
Article
MPGH-FS: A Hybrid Feature Selection Framework for Robust Multi-Temporal OBIA Classification
by Xiangchao Xu, Huijiao Qiao, Zhenfan Xu and Shuya Hu
Sensors 2025, 25(18), 5933; https://doi.org/10.3390/s25185933 - 22 Sep 2025
Viewed by 380
Abstract
Object-Based Image Analysis (OBIA) generates high-dimensional features that frequently induce the curse of dimensionality, impairing classification efficiency and generalizability in high-resolution remote sensing images. To address these challenges while simultaneously overcoming the limitations of single-criterion feature selection and enhancing temporal adaptability, we propose [...] Read more.
Object-Based Image Analysis (OBIA) generates high-dimensional features that frequently induce the curse of dimensionality, impairing classification efficiency and generalizability in high-resolution remote sensing images. To address these challenges while simultaneously overcoming the limitations of single-criterion feature selection and enhancing temporal adaptability, we propose a novel feature selection framework named Mutual information Pre-filtering and Genetic-Hill climbing hybrid Feature Selection (MPGH-FS), which integrates Mutual Information Correlation Coefficient (MICC) pre-filtering, Genetic Algorithm (GA) global search, and Hill Climbing (HC) local optimization. Experiments based on multi-temporal GF-2 imagery from 2018 to 2023 demonstrated that MPGH-FS could reduce the feature dimension from 232 to 9, and it achieved the highest Overall Accuracy (OA) of 85.55% and a Kappa coefficient of 0.75 in full-scene classification, with training and inference times limited to 6 s and 1 min, respectively. Cross-temporal transfer experiments further validated the method’s robustness to inter-annual variation within the same area, with classification accuracy fluctuations remaining below 4% across different years, outperforming comparative methods. These results confirm that MPGH-FS offers significant advantages in feature compression, classification performance, and temporal adaptability, providing a robust technical foundation for efficient and accurate multi-temporal remote sensing classification. Full article
(This article belongs to the Special Issue Remote Sensing Image Processing, Analysis and Application)
Show Figures

Figure 1

21 pages, 4145 KB  
Article
Temperature Calibration Using Machine Learning Algorithms for Flexible Temperature Sensors
by Ui-Jin Kim, Ju-Hun Ahn, Ji-Han Lee and Chang-Yull Lee
Sensors 2025, 25(18), 5932; https://doi.org/10.3390/s25185932 - 22 Sep 2025
Viewed by 427
Abstract
Thermal imbalance can cause significant stress in large-scale structures such as bridges and buildings, negatively impacting their structural health. To assist in the structural health monitoring systems that analyze these thermal effects, a flexible temperature sensor was fabricated using EHD inkjet printing. However, [...] Read more.
Thermal imbalance can cause significant stress in large-scale structures such as bridges and buildings, negatively impacting their structural health. To assist in the structural health monitoring systems that analyze these thermal effects, a flexible temperature sensor was fabricated using EHD inkjet printing. However, the reliability of such printed sensors is challenged by complex dynamic hysteresis under rapid thermal changes. To address this, an LSTM calibration model was developed and trained exclusively on quasi-static data across the 20–70 °C temperature range, where it achieved a low prediction error, a 33.563% improvement over a conventional polynomial regression. More importantly, when tested on unseen dynamic data, this statically trained model demonstrated superior generalization, reducing the RMSE from 12.451 °C for the polynomial model to 4.899 °C. These results suggest that data-driven approaches like LSTM can be a highly effective solution for ensuring the reliability of flexible sensors in real-world SHM applications. Full article
(This article belongs to the Section Sensors Development)
Show Figures

Figure 1

28 pages, 2869 KB  
Article
Enhancing Medical Image Segmentation and Classification Using a Fuzzy-Driven Method
by Akmal Abduvaitov, Abror Shavkatovich Buriboev, Djamshid Sultanov, Shavkat Buriboev, Ozod Yusupov, Kilichov Jasur and Andrew Jaeyong Choi
Sensors 2025, 25(18), 5931; https://doi.org/10.3390/s25185931 - 22 Sep 2025
Viewed by 624
Abstract
Automated analysis for tumor segmentation and illness classification is hampered by the noise, low contrast, and ambiguity that are common in medical pictures. This work introduces a new 12-step fuzzy-based improvement pipeline that uses fuzzy entropy, fuzzy standard deviation, and histogram spread functions [...] Read more.
Automated analysis for tumor segmentation and illness classification is hampered by the noise, low contrast, and ambiguity that are common in medical pictures. This work introduces a new 12-step fuzzy-based improvement pipeline that uses fuzzy entropy, fuzzy standard deviation, and histogram spread functions to enhance picture quality in CT, MRI, and X-ray modalities. The pipeline produces three improved versions per dataset, lowering BRISQUE scores from 28.8 to 21.7 (KiTS19), 30.3 to 23.4 (BraTS2020), and 26.8 to 22.1 (Chest X-ray). It is tested on KiTS19 (CT) for kidney tumor segmentation, BraTS2020 (MRI) for brain tumor segmentation, and Chest X-ray Pneumonia for classification. A Concatenated CNN (CCNN) uses the improved datasets to achieve a Dice coefficient of 99.60% (KiTS19, +2.40% over baseline), segmentation accuracy of 0.983 (KiTS19) and 0.981 (BraTS2020) versus 0.959 and 0.943 (CLAHE), and classification accuracy of 0.974 (Chest X-ray) versus 0.917 (CLAHE). A classic CNN is trained on original and CLAHE-filtered datasets. These outcomes demonstrate how well the pipeline works to improve image quality and increase segmentation/classification accuracy, offering a foundation for clinical diagnostics that is both scalable and interpretable. Full article
Show Figures

Figure 1

16 pages, 3004 KB  
Article
Lamb Wave-Based Damage Fusion Detection of Composite Laminate Panels Using Distance Analysis and Evidence Theory
by Li Wang, Guoqiang Liu, Xiaguang Wang and Yu Yang
Sensors 2025, 25(18), 5930; https://doi.org/10.3390/s25185930 - 22 Sep 2025
Viewed by 287
Abstract
The Lamb wave-based damage detection method shows great potential for composite impact failure assessments. However, the traditional single signal feature-based methods only depend on partial structural state monitoring information, without considering the inconsistency of damage sensitivity and detection capability for different signal features. [...] Read more.
The Lamb wave-based damage detection method shows great potential for composite impact failure assessments. However, the traditional single signal feature-based methods only depend on partial structural state monitoring information, without considering the inconsistency of damage sensitivity and detection capability for different signal features. Therefore, this paper proposes a damage fusion detection method based on distance analysis and evidence theory for composite laminate panels. Firstly, the signal features of different dimensions are extracted from time–frequency domain perspectives. Correlational analysis and cluster analysis are applied to achieve feature reduction and retain highly sensitive signal features. Secondly, the damage detection results of highly sensitive features and the corresponding basic probability assignments (BPAs) are acquired using distance analysis. Finally, the consistent damage detection result can be acquired by applying evidence theory to the decision level to fuse detection results for highly sensitive signal features. Impact tests on ten composite laminate panels are implemented to validate the proposed fusion detection method. The results show that the proposed method can accurately identify the delamination damage with different locations and different areas. In addition, the classification accuracy is above 85%, the false alarm rate is below 25% and the missing alarm rate is below 15%. Full article
(This article belongs to the Section Physical Sensors)
Show Figures

Figure 1

24 pages, 3574 KB  
Article
Monitoring the Impact of Two Pedagogical Models on Physical Load in an Alternative School Sport Using Inertial Devices
by Olga Calle, Antonio Antúnez, Sergio González-Espinosa, Sergio José Ibáñez and Sebastián Feu
Sensors 2025, 25(18), 5929; https://doi.org/10.3390/s25185929 - 22 Sep 2025
Viewed by 356
Abstract
(1) Background: Physical Education sessions subject students to various physical and physiological demands that teachers must understand to design interventions aimed at improving health and fitness. This study aimed to quantify and compare external and internal load before and after implementing two intervention [...] Read more.
(1) Background: Physical Education sessions subject students to various physical and physiological demands that teachers must understand to design interventions aimed at improving health and fitness. This study aimed to quantify and compare external and internal load before and after implementing two intervention programs: one based on the Game-Centered Model and another Hybrid Model that combines the Game-Centered Model with the Sport Education Model. (2) Methods: A total of 47 first-year secondary school students participated, divided into two naturally formed groups. Pre- and post-intervention assessments involved 4 vs. 4 matches monitored using WIMU Pro™ inertial measurement units and heart rate monitors to collect kinematic, neuromuscular, and physiological data. The combined use of inertial sensors and heart rate monitors enabled the objective quantification of students’ physical demands. (3) Results: No significant improvements were observed between pre- and post-tests, possibly due to the short duration of the interventions. However, the Hybrid Model generated higher levels of external load, both kinematic and neuromuscular, in the post-test. (4) Conclusions: The Hybrid Model appears more effective in increasing students’ physical engagement. Inertial sensors represent a valid and practical tool for monitoring and adjusting instructional strategies in school-based Physical Education. Full article
(This article belongs to the Special Issue Recent Innovations in Wearable Sensors for Biomedical Approaches)
Show Figures

Figure 1

18 pages, 1694 KB  
Article
FAIR-Net: A Fuzzy Autoencoder and Interpretable Rule-Based Network for Ancient Chinese Character Recognition
by Yanling Ge, Yunmeng Zhang and Seok-Beom Roh
Sensors 2025, 25(18), 5928; https://doi.org/10.3390/s25185928 - 22 Sep 2025
Viewed by 312
Abstract
Ancient Chinese scripts—including oracle bone carvings, bronze inscriptions, stone steles, Dunhuang scrolls, and bamboo slips—are rich in historical value but often degraded due to centuries of erosion, damage, and stylistic variability. These issues severely hinder manual transcription and render conventional OCR techniques inadequate, [...] Read more.
Ancient Chinese scripts—including oracle bone carvings, bronze inscriptions, stone steles, Dunhuang scrolls, and bamboo slips—are rich in historical value but often degraded due to centuries of erosion, damage, and stylistic variability. These issues severely hinder manual transcription and render conventional OCR techniques inadequate, as they are typically trained on modern printed or handwritten text and lack interpretability. To tackle these challenges, we propose FAIR-Net, a hybrid architecture that combines the unsupervised feature learning capacity of a deep autoencoder with the semantic transparency of a fuzzy rule-based classifier. In FAIR-Net, the deep autoencoder first compresses high-resolution character images into low-dimensional, noise-robust embeddings. These embeddings are then passed into a Fuzzy Neural Network (FNN), whose hidden layer leverages Fuzzy C-Means (FCM) clustering to model soft membership degrees and generate human-readable fuzzy rules. The output layer uses Iteratively Reweighted Least Squares Estimation (IRLSE) combined with a Softmax function to produce probabilistic predictions, with all weights constrained as linear mappings to maintain model transparency. We evaluate FAIR-Net on CASIA-HWDB1.0, HWDB1.1, and ICDAR 2013 CompetitionDB, where it achieves a recognition accuracy of 97.91%, significantly outperforming baseline CNNs (p < 0.01, Cohen’s d > 0.8) while maintaining the tightest confidence interval (96.88–98.94%) and lowest standard deviation (±1.03%). Additionally, FAIR-Net reduces inference time to 25 s, improving processing efficiency by 41.9% over AlexNet and up to 98.9% over CNN-Fujitsu, while preserving >97.5% accuracy across evaluations. To further assess generalization to historical scripts, FAIR-Net was tested on the Ancient Chinese Character Dataset (9233 classes; 979,907 images), achieving 83.25% accuracy—slightly higher than ResNet101 but 2.49% lower than SwinT-v2-small—while reducing training time by over 5.5× compared to transformer-based baselines. Fuzzy rule visualization confirms enhanced robustness to glyph ambiguities and erosion. Overall, FAIR-Net provides a practical, interpretable, and highly efficient solution for the digitization and preservation of ancient Chinese character corpora. Full article
(This article belongs to the Section Sensing and Imaging)
Show Figures

Figure 1

17 pages, 4032 KB  
Article
Design and Fabrication of Posture Sensing and Damage Evaluating System for Underwater Pipelines
by Sheng-Chih Shen, Yung-Chao Huang, Chih-Chieh Chao, Ling Lin and Zhen-Yu Tu
Sensors 2025, 25(18), 5927; https://doi.org/10.3390/s25185927 - 22 Sep 2025
Viewed by 276
Abstract
This study constructed an integrated underwater pipeline monitoring system, which combines pipeline posture sensing modules and pipeline leakage detection modules. The proposed system can achieve the real-time monitoring of pipeline posture and the comprehensive assessment of pipeline damage. By deploying pipeline posture sensing [...] Read more.
This study constructed an integrated underwater pipeline monitoring system, which combines pipeline posture sensing modules and pipeline leakage detection modules. The proposed system can achieve the real-time monitoring of pipeline posture and the comprehensive assessment of pipeline damage. By deploying pipeline posture sensing and leakage detection modules in array configurations along an underwater pipeline, information related to pipeline posture and flow variations is continuously collected. An array of inertial sensor nodes that form the pipeline posture sensing system is used for real-time pipeline posture monitoring. The system measures underwater motion signals and obtains bending and buckling postures using posture algorithms. Pipeline leakage is evaluated using flow and water temperature data from Hall sensors deployed at each node, assessing pipeline health while estimating the location and area of pipeline damage based on the flow values along the nodes. The human–machine interface designed in this study for underwater pipelines supports automated monitoring and alert functions, so as to provide early warnings for pipeline postures and the analysis of damage locations before water supply abnormalities occur in the pipelines. Underwater experiments validated that this system can precisely capture real-time postures and damage locations of pipelines using sensing modules. By taking flow changes at these locations into consideration, the damage area with an error margin was estimated. In the experiments, the damage areas were 8.04 cm2 to 25.96 cm2, the estimated results were close to the actual area trends (R2 = 0.9425), and the area error was within 5.16 cm2 (with an error percentage ranging from −20% to 26%). The findings of this study contribute to the management efficiency of underwater pipelines, enabling more timely maintenance while effectively reducing the risk of water supply interruption due to pipeline damage. Full article
(This article belongs to the Topic Innovation, Communication and Engineering)
Show Figures

Figure 1

28 pages, 14913 KB  
Article
Turning Seasonal Signals into Segmentation Cues: Recolouring the Harmonic Normalized Difference Vegetation Index for Agricultural Field Delineation
by Filip Papić, Luka Rumora, Damir Medak and Mario Miler
Sensors 2025, 25(18), 5926; https://doi.org/10.3390/s25185926 - 22 Sep 2025
Viewed by 311
Abstract
Accurate delineation of fields is difficult in fragmented landscapes where single-date images provide no seasonal cues and supervised models require labels. We propose a method that explicitly represents phenology to improve zero-shot delineation. Using 22 cloud-free PlanetScope scenes over a 5 × 5 [...] Read more.
Accurate delineation of fields is difficult in fragmented landscapes where single-date images provide no seasonal cues and supervised models require labels. We propose a method that explicitly represents phenology to improve zero-shot delineation. Using 22 cloud-free PlanetScope scenes over a 5 × 5 km area, a single harmonic model is fitted to the NDVI per pixel to obtain the phase, amplitude and mean. These values are then mapped into cylindrical colour spaces (Hue–Saturation–Value, Hue–Whiteness–Blackness, Luminance-Chroma-Hue). The resulting recoloured composites are segmented using the Segment Anything Model (SAM), without fine-tuning. The results are evaluated object-wise, object-wise grouped by area size, and pixel-wise. Pixel-wise evaluation achieved up to F1 = 0.898, and a mean Intersection-over-Union (mIoU) of 0.815, while object-wise performance reached F1 = 0.610. HSV achieved the strongest area match, while HWB produced the fewest fragments. The ordinal time-of-day basis provided better parcel separability than the annual radian adjustment. The main errors were over-segmentation and fragmentation. As the parcel size increased, the IoU increased, but the precision decreased. It is concluded that recolouring using harmonic NDVI time series is a simple, scalable, and interpretable basis for field delineation that can be easily improved. Full article
(This article belongs to the Special Issue Sensors and Data-Driven Precision Agriculture—Second Edition)
Show Figures

Figure 1

17 pages, 4091 KB  
Article
EEG-Based Prediction of Stress Responses to Naturalistic Decision-Making Stimuli in Police Cadets
by Abdulwahab Alasfour and Nasser AlSabah
Sensors 2025, 25(18), 5925; https://doi.org/10.3390/s25185925 - 22 Sep 2025
Viewed by 482
Abstract
The ability of police officers to make correct decisions under emotional stress is critical, as errors in high-pressure situations can have severe legal and physical consequences. This study aims to evaluate the neurophysiological responses of police academy cadets during stressful decision-making scenarios and [...] Read more.
The ability of police officers to make correct decisions under emotional stress is critical, as errors in high-pressure situations can have severe legal and physical consequences. This study aims to evaluate the neurophysiological responses of police academy cadets during stressful decision-making scenarios and to predict individual stress levels from those responses. Fifty-eight police academy cadets from three cohorts watched a custom-made, naturalistic video scene and then chose the appropriate course of action. Simultaneous 32-channel electroencephalography (EEG) and electrocardiography (ECG) captured brain and heart activity. Event-related potentials (ERPs) and band-specific power features (particularly delta) were extracted, and machine-learning models were trained with nested cross-validation to predict perceived stress scores. Global and broadband EEG activity was suppressed during the video stimulus and did not return to baseline during the cooldown phase. Widespread ERPs and pronounced delta-band dynamics emerged during decision-making, correlating with both cohort rank and self-reported stress. Crucially, a combined EEG + cohort model predicted perceived stress with an out-of-fold R2 of 0.32, outperforming EEG-only (R2 = 0.23) and cohort-only (R2 = 0.17) models. To our knowledge, this is the first study to both characterize EEG dynamics during stressful naturalistic decision tasks and demonstrate their predictive utility. These findings lay the groundwork for neurofeedback-based training paradigms that help officers modulate stress responses and calibrate decision-making under pressure. Full article
(This article belongs to the Special Issue Advances in ECG/EEG Monitoring)
Show Figures

Figure 1

20 pages, 1176 KB  
Article
QSEER-Quantum-Enhanced Secure and Energy-Efficient Routing Protocol for Wireless Sensor Networks (WSNs)
by Chindiyababy Uthayakumar, Ramkumar Jayaraman, Hadi A. Raja and Noman Shabbir
Sensors 2025, 25(18), 5924; https://doi.org/10.3390/s25185924 - 22 Sep 2025
Viewed by 372
Abstract
Wireless sensor networks (WSNs) play a major role in various applications, but the main challenge is to maintain security and balanced energy efficiency. Classical routing protocols struggle to achieve both energy efficiency and security because they are more vulnerable to security risks and [...] Read more.
Wireless sensor networks (WSNs) play a major role in various applications, but the main challenge is to maintain security and balanced energy efficiency. Classical routing protocols struggle to achieve both energy efficiency and security because they are more vulnerable to security risks and resource limitations. This paper introduces QSEER, a novel approach that uses quantum technologies to overcome these limitations. QSEER employs quantum-inspired optimization algorithms that leverage superposition and entanglement principles to efficiently explore multiple routing possibilities, thereby identifying energy-efficient paths and reducing redundant transmissions. The proposed protocol enhances the security of data transmission against eavesdropping and tampering by using the principles of quantum mechanics, thus mitigating potential security vulnerabilities. Through extensive simulations, we demonstrated the effectiveness of QSEER in achieving both security and energy efficiency objectives, which achieves 15.1% lower energy consumption compared to state-of-the-art protocols while maintaining 99.8% data integrity under various attack scenarios, extending network lifetime by an average of 42%. These results position QSEER as a significant advancement for next-generation WSN deployments in critical applications such as environmental monitoring, smart infrastructure, and healthcare systems. Full article
(This article belongs to the Section Sensor Networks)
Show Figures

Figure 1

28 pages, 8918 KB  
Article
A Multi-Channel Multi-Scale Spatiotemporal Convolutional Cross-Attention Fusion Network for Bearing Fault Diagnosis
by Ruixue Li, Guohai Zhang, Yi Niu, Kai Rong, Wei Liu and Haoxuan Hong
Sensors 2025, 25(18), 5923; https://doi.org/10.3390/s25185923 - 22 Sep 2025
Viewed by 411
Abstract
Bearings, as commonly used elements in mechanical apparatus, are essential in transmission systems. Fault diagnosis is of significant importance for the normal and safe functioning of mechanical systems. Conventional fault diagnosis methods depend on one or more vibration sensors, and their diagnostic results [...] Read more.
Bearings, as commonly used elements in mechanical apparatus, are essential in transmission systems. Fault diagnosis is of significant importance for the normal and safe functioning of mechanical systems. Conventional fault diagnosis methods depend on one or more vibration sensors, and their diagnostic results are often unsatisfactory under strong noise interference. To tackle this problem, this research develops a bearing fault diagnosis technique utilizing a multi-channel, multi-scale spatiotemporal convolutional cross-attention fusion network. At first, continuous wavelet transform (CWT) is applied to convert the raw 1D acoustic and vibration signals of the dataset into 2D time–frequency images. These acoustic and vibration time–frequency images are then simultaneously fed into two parallel structures. After rough feature extraction using ResNet, deep feature extraction is performed using the Multi-Scale Temporal Convolutional Module (MTCM) and the Multi-Feature Extraction Block (MFE). Next, these traits are input into a dual cross-attention mechanism module (DCA), where fusion is achieved using attention interaction. The experimental findings validate the efficacy of the proposed method using tests and comparisons on two bearing datasets. The testing findings validate that the suggested method outperforms the existing advanced multi-sensor fusion diagnostic methods. Compared with other existing multi-sensor fusion diagnostic methods, the proposed method was proven to outperform the five existing methods (1DCNN-VAF, MFAN-VAF, 2MNET, MRSDF, and FAC-CNN). Full article
(This article belongs to the Section Fault Diagnosis & Sensors)
Show Figures

Figure 1

21 pages, 4611 KB  
Article
Design of a Cylindrical Megahertz Miniature Ultrasonic Welding Oscillator
by Guang Yang, Ye Chen, Minghang Li, Junlin Yang and Shengyang Xi
Sensors 2025, 25(18), 5922; https://doi.org/10.3390/s25185922 - 22 Sep 2025
Viewed by 341
Abstract
Ultrasonic welding is an efficient and precise joining technology widely applied in aerospace, electronics, and medical industries. To overcome the limitations of conventional oscillators in high-frequency applications, this study proposes an innovative cylindrical oscillator design incorporating a 3.71 mm acoustic matching layer, operating [...] Read more.
Ultrasonic welding is an efficient and precise joining technology widely applied in aerospace, electronics, and medical industries. To overcome the limitations of conventional oscillators in high-frequency applications, this study proposes an innovative cylindrical oscillator design incorporating a 3.71 mm acoustic matching layer, operating at 1.76 MHz based on acoustic propagation theory. Through finite element analysis, a miniaturized oscillator with dimensions of 28 mm in diameter and 18 mm in height was developed, achieving optimized dynamic performance. Experimental validation via laser Doppler vibrometry confirmed a working surface amplitude exceeding 50 nm, while vibrations on non-functional walls were suppressed below 5 nm, with less than 5% deviation from simulation results. Prototype welding tests identified optimal process parameters—85 N welding pressure, 4 s welding time, and 3 s holding time—resulting in PVC joint tensile strengths exceeding 45 N. This work provides both an optimized hardware design and validated process guidelines, advancing the application of high-frequency micro-ultrasonic welding in precision, space-constrained environments. Full article
(This article belongs to the Section Intelligent Sensors)
Show Figures

Figure 1

16 pages, 7045 KB  
Article
Convolutional Neural Networks for Hole Inspection in Aerospace Systems
by Garrett Madison, Grayson Michael Griser, Gage Truelson, Cole Farris, Christopher Lee Colaw and Yildirim Hurmuzlu
Sensors 2025, 25(18), 5921; https://doi.org/10.3390/s25185921 - 22 Sep 2025
Viewed by 458
Abstract
Foreign object debris (FOd) in rivet holes, machined holes, and fastener sites poses a critical risk to aerospace manufacturing, where current inspections rely on manual visual checks with flashlights and mirrors. These methods are slow, fatiguing, and prone to error. This work introduces [...] Read more.
Foreign object debris (FOd) in rivet holes, machined holes, and fastener sites poses a critical risk to aerospace manufacturing, where current inspections rely on manual visual checks with flashlights and mirrors. These methods are slow, fatiguing, and prone to error. This work introduces HANNDI, a compact handheld inspection device that integrates controlled optics, illumination, and onboard deep learning for rapid and reliable inspection directly on the factory floor. The system performs focal sweeps, aligns and fuses the images into an all-in-focus representation, and applies a dual CNN pipeline based on the YOLO architecture: one network detects and localizes holes, while the other classifies debris. All training images were collected with the prototype, ensuring consistent geometry and lighting. On a withheld test set from a proprietary ≈3700 image dataset of aerospace assets, HANNDI achieved per-class precision and recall near 95%. An end-to-end demonstration on representative aircraft parts yielded an effective task time of 13.6 s per hole. To our knowledge, this is the first handheld automated optical inspection system that combines mechanical enforcement of imaging geometry, controlled illumination, and embedded CNN inference, providing a practical path toward robust factory floor deployment. Full article
(This article belongs to the Section Sensing and Imaging)
Show Figures

Figure 1

16 pages, 3708 KB  
Article
Myoelectric and Inertial Data Fusion Through a Novel Attention-Based Spatiotemporal Feature Extraction for Transhumeral Prosthetic Control: An Offline Analysis
by Andrea Tigrini, Alessandro Mengarelli, Ali H. Al-Timemy, Rami N. Khushaba, Rami Mobarak, Mara Scattolini, Gaith K. Sharba, Federica Verdini, Ennio Gambi and Laura Burattini
Sensors 2025, 25(18), 5920; https://doi.org/10.3390/s25185920 - 22 Sep 2025
Viewed by 278
Abstract
This study proposes a feature extraction scheme that fuses accelerometric (ACC) and electromyographic (EMG) data to improve shoulder movement identification in individuals with transhumeral amputation, in whom the clinical need for intuitive control strategies enabling reliable activation of full-arm prostheses is underinvestigated. A [...] Read more.
This study proposes a feature extraction scheme that fuses accelerometric (ACC) and electromyographic (EMG) data to improve shoulder movement identification in individuals with transhumeral amputation, in whom the clinical need for intuitive control strategies enabling reliable activation of full-arm prostheses is underinvestigated. A novel spatiotemporal warping feature extraction architecture was employed to realize EMG and ACC information fusion at the feature level. EMG and ACC data were collected from six participants with intact limbs and four participants with transhumeral amputation using an NI USB-6009 device at 1000 Hz to support the proposed feature extraction scheme. For each participant, a leave-one-trial-out (LOTO) training and testing approach was used for developing pattern recognition models for both the intact-limb (IL) and amputee (AMP) groups. The analysis revealed that the introduction of ACC information has a positive impact when using windows of length (WLs) lower than 150 ms. A linear discriminant analysis (LDA) classifier was able to exceed the accuracy of 90% in each WL condition and for each group. Similar results were observed for an extreme learning machine (ELM), whereas k-nearest neighbors (kNN) and an autonomous learning multi-model classifier showed a mean accuracy of less than 87% for both IL and AMP groups at different WLs, guaranteeing applicability over a large set of shallow pattern-recognition models that can be used in real scenarios. The present work lays the groundwork for future studies involving real-time validation of the proposed methodology on a larger population, acknowledging the current limitation of offline analysis. Full article
(This article belongs to the Special Issue Advanced Sensors and AI Integration for Human–Robot Teaming)
Show Figures

Figure 1

30 pages, 10206 KB  
Article
Evaluation and Improvement of Image Aesthetics Quality via Composition and Similarity
by Xinyu Cui, Guoqing Tu, Guoying Wang, Senjun Zhang and Lufeng Mo
Sensors 2025, 25(18), 5919; https://doi.org/10.3390/s25185919 - 22 Sep 2025
Viewed by 371
Abstract
The evaluation and enhancement of image aesthetics play a pivotal role in the development of visual media, impacting fields including photography, design, and computer vision. Composition, a key factor shaping visual aesthetics, significantly influences an image’s vividness and expressiveness. However, existing image optimization [...] Read more.
The evaluation and enhancement of image aesthetics play a pivotal role in the development of visual media, impacting fields including photography, design, and computer vision. Composition, a key factor shaping visual aesthetics, significantly influences an image’s vividness and expressiveness. However, existing image optimization methods face practical challenges: compression-induced distortion, imprecise object extraction, and cropping-caused unnatural proportions or content loss. To tackle these issues, this paper proposes an image aesthetic evaluation with composition and similarity (IACS) method that harmonizes composition aesthetics and image similarity through a unified function. When evaluating composition aesthetics, the method calculates the distance between the main semantic line (or salient object) and the nearest rule-of-thirds line or central line. For images featuring prominent semantic lines, a modified Hough transform is utilized to detect the main semantic line, while for images containing salient objects, a salient object detection method based on luminance channel salience features (LCSF) is applied to determine the salient object region. In evaluating similarity, edge similarity measured by the Canny operator is combined with the structural similarity index (SSIM). Furthermore, we introduce a Framework for Image Aesthetic Evaluation with Composition and Similarity-Based Optimization (FIACSO), which uses semantic segmentation and generative adversarial networks (GANs) to optimize composition while preserving the original content. Compared with prior approaches, the proposed method improves both the aesthetic appeal and fidelity of optimized images. Subjective evaluation involving 30 participants further confirms that FIACSO outperforms existing methods in overall aesthetics, compositional harmony, and content integrity. Beyond methodological contributions, this study also offers practical value: it supports photographers in refining image composition without losing context, assists designers in creating balanced layouts with minimal distortion, and provides computational tools to enhance the efficiency and quality of visual media production. Full article
(This article belongs to the Special Issue Recent Innovations in Computational Imaging and Sensing)
Show Figures

Figure 1

26 pages, 2120 KB  
Article
Continuous Vibration-Driven Virtual Tactile Motion Perception Across Fingertips
by Mehdi Adibi
Sensors 2025, 25(18), 5918; https://doi.org/10.3390/s25185918 - 22 Sep 2025
Viewed by 456
Abstract
Motion perception is a fundamental function of the tactile system, essential for object exploration and manipulation. While human studies have largely focused on discrete or pulsed stimuli with staggered onsets, many natural tactile signals are continuous and rhythmically patterned. Here, we investigate whether [...] Read more.
Motion perception is a fundamental function of the tactile system, essential for object exploration and manipulation. While human studies have largely focused on discrete or pulsed stimuli with staggered onsets, many natural tactile signals are continuous and rhythmically patterned. Here, we investigate whether phase differences between “simultaneously” presented, “continuous” amplitude-modulated vibrations can induce the perception of motion across fingertips. Participants reliably perceived motion direction at modulation frequencies up to 1 Hz, with discrimination performance systematically dependent on the phase lag between vibrations. Critically, trial-level confidence reports revealed the lowest certainty for anti-phase (180°) conditions, consistent with stimulus ambiguity as predicted by the mathematical framework. I propose two candidate computational mechanisms for tactile motion processing. The first is a conventional cross-correlation computation over the envelopes; the second is a probabilistic model based on the uncertain detection of temporal reference points (e.g., envelope peaks) within threshold-defined windows. This model, despite having only a single parameter (uncertainty width determined by an amplitude discrimination threshold), accounts for both the non-linear shape and asymmetries of observed psychometric functions. These results demonstrate that the human tactile system can extract directional information from distributed phase-coded signals in the absence of spatial displacement, revealing a motion perception mechanism that parallels arthropod systems but potentially arises from distinct perceptual constraints. The findings underscore the feasibility of sparse, phase-coded stimulation as a lightweight and reproducible method for conveying motion cues in wearable, motion-capable haptic devices. Full article
Show Figures

Figure 1

18 pages, 3326 KB  
Article
Micro-Vibrations Analysis in LEO CubeSats Using MEMS Accelerometers
by Sándor Gyányi, Róbert Szabolcsi, Péter János Varga, Gyula Horváth, Péter Horváth and Tibor Wührl
Sensors 2025, 25(18), 5917; https://doi.org/10.3390/s25185917 - 22 Sep 2025
Viewed by 444
Abstract
Small satellites or CubeSats orbiting in low Earth orbit (LEO) have become increasingly popular in Earth Observation missions, where high-resolution imaging is essential. Due to the lower mass of these spacecrafts, they are more sensitive to vibrations, and image quality can be particularly [...] Read more.
Small satellites or CubeSats orbiting in low Earth orbit (LEO) have become increasingly popular in Earth Observation missions, where high-resolution imaging is essential. Due to the lower mass of these spacecrafts, they are more sensitive to vibrations, and image quality can be particularly negatively affected by micro-vibrations. These vibrations originate from on-board subsystems, such as the Attitude Determination and Control System (ADCS), which uses reaction wheels to change the orientation of the satellite. The main goal of our research was to analyze these micro-vibrations so that the acquired data could be used for post-correction of camera images. Obuda University, as a participant in a research project, was tasked with designing and building a micro-vibration measuring device for the LEO CubeSat called WREN-1. In the first phase of the project, the satellite was launched into orbit, and test data were collected and analyzed. The results are presented in this article. Based on the data obtained in this way, the next step will be to analyze the images taken at the same time as the vibration measurements and to search for a correlation between the image quality and the vibrations. Based on the results of the entire project, it could be possible to improve the image quality of the onboard cameras of microsatellites. Full article
(This article belongs to the Special Issue Feature Papers in Physical Sensors 2025)
Show Figures

Figure 1

15 pages, 3462 KB  
Article
Numerical Assessment of Electric Underfloor Heating Enhanced by Photovoltaic Integration
by Hana Charvátová, Aleš Procházka, Martin Zálešák and Vladimír Mařík
Sensors 2025, 25(18), 5916; https://doi.org/10.3390/s25185916 - 22 Sep 2025
Viewed by 338
Abstract
The integration of electric underfloor heating systems with photovoltaic (PV) panels presents a promising approach to enhance thermal efficiency and energy sustainability in residential heating. This study investigates the performance of such hybrid systems under different energy supply scenarios. Numerical modeling and simulations [...] Read more.
The integration of electric underfloor heating systems with photovoltaic (PV) panels presents a promising approach to enhance thermal efficiency and energy sustainability in residential heating. This study investigates the performance of such hybrid systems under different energy supply scenarios. Numerical modeling and simulations were employed to evaluate underfloor heating performance using three electricity sources: standard electric supply, solar-generated energy, and a combined configuration. Solar irradiance sensors were utilized to collect input solar radiation data, which served as a critical parameter for numerical modeling and simulations. The set outdoor air temperature used in the analysis represents an average value calculated from data measured by environmental sensors at the location of the building during the monitored period. Key metrics included indoor air temperature, time to thermal stability, and heat loss relative to outdoor conditions. The combined electric and solar-powered system demonstrated thermal efficiency, improving indoor air temperature by up to 63.6% compared to an unheated room and achieving thermal stability within 22 h. Solar-only configuration showed moderate improvements. Heat loss analysis revealed a strong correlation with indoor–outdoor temperature differentials. Hybrid underfloor heating systems integrating PV panels significantly enhance indoor thermal comfort and energy efficiency. These findings support the adoption of renewable energy technologies in residential heating, contributing to sustainable energy transitions. Full article
Show Figures

Figure 1

22 pages, 5182 KB  
Article
A Novel TMR Cantilever-Based Bi-Directional Flow Sensor for Agricultural and Domestic Applications
by Anwar Ulla Khan and Ateyah Alzahrani
Sensors 2025, 25(18), 5915; https://doi.org/10.3390/s25185915 - 22 Sep 2025
Viewed by 334
Abstract
This article introduces a novel, cost-effective, noninvasive sensing mechanism for measuring water flow rate. It employs two tunneling magnetoresistance (TMR) sensors (analog and bi-polar), a magnet, and a stainless-steel cantilever. The TMR sensors are installed outside the insulating water pipe. A magnet is [...] Read more.
This article introduces a novel, cost-effective, noninvasive sensing mechanism for measuring water flow rate. It employs two tunneling magnetoresistance (TMR) sensors (analog and bi-polar), a magnet, and a stainless-steel cantilever. The TMR sensors are installed outside the insulating water pipe. A magnet is fixed at the free end of the cantilever and integrated into the pipe system. The cantilever’s deflection corresponds to the flow rate, with an analog TMR sensor measuring the bending angle. This bending angle, in either direction of the cantilever’s deflection, is captured through the analog voltage from the TMR sensor. The output from the analog TMR sensor is an analog voltage that directly reflects the strength of the magnetic field. An ESP32 microcontroller records the voltage from the analog TMR sensor, converts it to flow rates, and utilizes the bi-polar TMR sensor to ascertain the flow direction. A prototype sensor was developed and tested in a laboratory-scale setup to validate the effectiveness of the sensing mechanism. This prototype demonstrated a worst-case accuracy of 1.0% across flow rates of 0 to 1.5 m3/h for both the forward and reverse flow directions. The response and recovery times of the sensor are approximately 470 ms and 592 ms for forward and 487 ms and 625 ms for reverse direction flow. Also, hysteresis errors of 1.84% and 2.06% have been calculated for both flow directions. Notably, the sensing element does not contain any rotating components or require electrical connections to the cantilever for measurement. These attributes potentially lead to lower maintenance requirements and a longer lifespan for the sensor. Full article
Show Figures

Figure 1

12 pages, 581 KB  
Article
Cough-Induced Contraction Response Time and Strength of the Pelvic Floor Muscles Between Women with and Without Stress Urinary Incontinence
by Elora dos Santos Silva de Lima, Erica Feio Carneiro, Karina Moyano Amorim, César Ferreira Amorim, Adriano de Oliveira Andrade, Paulo Roberto Garcia Lucareli, Daniela Aparecida Biasotto-Gonzalez and Fabiano Politti
Sensors 2025, 25(18), 5914; https://doi.org/10.3390/s25185914 - 22 Sep 2025
Viewed by 585
Abstract
Anatomic and functional changes in the pelvic floor muscles (PFMs) have been associated with stress urinary incontinence (SUI). The aim of this study is to compare cough-induced contraction response time and PFM strength in women with and without SUI. This cross-sectional study evaluated [...] Read more.
Anatomic and functional changes in the pelvic floor muscles (PFMs) have been associated with stress urinary incontinence (SUI). The aim of this study is to compare cough-induced contraction response time and PFM strength in women with and without SUI. This cross-sectional study evaluated 40 women (20 with and 20 without SUI) aged 20 to 60 years. PFM strength was measured using a vaginal dynamometer. The cough signal was captured using an accelerometer, and activity of the right external oblique muscle was measured using surface electromyography. All signals were synchronized and recorded using the same signal acquisition module. Analysis of covariance (ANCOVA) with the Bonferroni post hoc test was used to compare the dynamometric data between groups (control and SUI). No significant differences were found between groups regarding variables related to PFM strength, but significant differences were found for activation time of the PFMs (F = 59.42, p < 0.0001, ηp2 = 0.76), activation time of the external oblique muscle (F = 6.55, p = 0.004, ηp2 = 0.26), and cough pulse time (F = 3.32, p = 0.04, ηp2 = 0.15). Women with stress urinary have a delayed cough-induced contraction response of the pelvic floor muscles, but no difference in the contraction force of these muscles was found in comparison to women without stress urinary incontinence. Full article
Show Figures

Figure 1

16 pages, 3751 KB  
Article
RAPSO: An Integrated PSO with Reinforcement Learning and an Adaptive Weight Strategy for the High-Precision Milling of Elastic Materials
by Qingxin Li, Peng Zeng, Qiankun Wu and Zijing Zhang
Sensors 2025, 25(18), 5913; https://doi.org/10.3390/s25185913 - 22 Sep 2025
Viewed by 356
Abstract
This study tackles the challenge of achieving high-precision robotic machining of elastic materials, where elastic recovery and overcutting often impair accuracy. To address this, a novel milling strategy, RAPSO, is introduced by combining an adaptive particle swarm optimization (APSO) algorithm with a reinforcement [...] Read more.
This study tackles the challenge of achieving high-precision robotic machining of elastic materials, where elastic recovery and overcutting often impair accuracy. To address this, a novel milling strategy, RAPSO, is introduced by combining an adaptive particle swarm optimization (APSO) algorithm with a reinforcement learning (RL)-based compensation mechanism. The method builds a material-specific milling model through residual error characterization, incorporates a dynamic inertia weight adjustment strategy into APSO for optimized toolpath generation, and integrates a Proximal Policy Optimization (PPO)-based RL module to refine trajectories iteratively. Experiments show that RAPSO reduces residual material by 33.51% compared with standard PSO and APSO methods, while offering faster convergence and greater stability. The proposed framework provides a practical solution for precision machining of elastic materials, offering improved accuracy, reduced post-processing requirements, and higher efficiency, while also contributing to the theoretical modeling of elastic recovery and advanced toolpath planning. Full article
(This article belongs to the Section Sensor Materials)
Show Figures

Figure 1

21 pages, 2347 KB  
Article
EAFormer: Edge-Aware Guided Adaptive Frequency-Navigator Network for Image Restoration
by Wenjie Xie, Dong Zhou, Wenshuai Zhang and Wenrui Wang
Sensors 2025, 25(18), 5912; https://doi.org/10.3390/s25185912 - 22 Sep 2025
Viewed by 351
Abstract
Although many deep learning-based image restoration networks have emerged in various image restoration tasks, most can only perform well in a specific type of restoration task and still face challenges in the general performance of image restoration. The fundamental reason for this problem [...] Read more.
Although many deep learning-based image restoration networks have emerged in various image restoration tasks, most can only perform well in a specific type of restoration task and still face challenges in the general performance of image restoration. The fundamental reason for this problem is that different types of degradation require different frequency features, and the image needs to be adaptively reconstructed according to the characteristics of input degradation. At the same time, we noticed that the previous image restoration network ignored the reconstruction of the edge contour details of the image, resulting in unclear contours of the restored image. Therefore, we proposed an edge-aware guided adaptive frequency navigation network, EAFormer, which extracts edge information in the image by applying different edge detection operators and reconstructs the edge contour details of the image more accurately during the restoration process. The adaptive frequency navigation perceives different frequency components in the image and interactively participates in the subsequent restoration process with high- and low-frequency feature information, better retaining the global structural information of the image and making the restored image more visually coherent and realistic. We verified the versatility of EAFormer in five classic image restoration tasks, and many experimental results also show that our model has advanced performance. Full article
(This article belongs to the Section Navigation and Positioning)
Show Figures

Figure 1

11 pages, 2157 KB  
Article
Feasibility of a Markerless Motion Capture System for Balance Function Assessment in Children with Cerebral Palsy
by Xiaoxia Yan, Nichola Wilson, Chengyan Sun and Yanxin Zhang
Sensors 2025, 25(18), 5911; https://doi.org/10.3390/s25185911 - 21 Sep 2025
Viewed by 415
Abstract
Children with cerebral palsy (CP) have impaired standing balance ability, caused by increased muscle tone, muscle weakness, and joint deformity. It is necessary to investigate standing balance for children with CP. Compared with postural stability assessment using force plates, OpenCap has the potential [...] Read more.
Children with cerebral palsy (CP) have impaired standing balance ability, caused by increased muscle tone, muscle weakness, and joint deformity. It is necessary to investigate standing balance for children with CP. Compared with postural stability assessment using force plates, OpenCap has the potential to be used utilized as a cost-effective standing balance assessment tool, providing details about the center of mass (CoM) and joint angles. This study aims to evaluate the feasibility of using OpenCap for standing balance assessment in children with CP by (i) examining the validity of OpenCap-based CoM parameters against force plate center of pressure (CoP) measures and (ii) exploring associations between joint angles and CoM displacement. Twenty-two children with CP completed standing balance trials on a force plate-based balance tester while two smartphones recorded synchronized videos for OpenCap processing. For the correlation between CoM parameters and CoP parameters, Pearson’s R values were from 0.39 to 0.94 between the two systems. After correcting the CoM parameters, the R2 values ranged from 0.98 to 1.00. Regarding the relationship between the joint angles and CoM, maximum and minimum sagittal angles in the ankle were corrected with CoM displacement along the x-axis. These findings suggest that OpenCap may be a potential, cost-effective tool for standing balance assessment in children with CP. Full article
(This article belongs to the Section Intelligent Sensors)
Show Figures

Figure 1

22 pages, 4786 KB  
Article
Multi-Signal Acquisition System for Continuous Blood Pressure Monitoring
by Naiwen Zhang, Yu Zhang, Jintao Chen, Shaoxuan Qiu, Jinting Ma, Lihai Tan and Guo Dan
Sensors 2025, 25(18), 5910; https://doi.org/10.3390/s25185910 - 21 Sep 2025
Viewed by 521
Abstract
Continuous blood pressure (BP) monitoring is essential for the early detection and prevention of cardiovascular diseases like hypertension. Recently, interest in continuous BP estimation systems and algorithms has grown. Various physiological signals reflect BP variations from different perspectives, and combining multiple signals can [...] Read more.
Continuous blood pressure (BP) monitoring is essential for the early detection and prevention of cardiovascular diseases like hypertension. Recently, interest in continuous BP estimation systems and algorithms has grown. Various physiological signals reflect BP variations from different perspectives, and combining multiple signals can enhance the accuracy of BP measurements. However, research integrating electrocardiogram (ECG), photoplethysmography (PPG), and impedance cardiography (ICG) signals for BP monitoring remains limited, with related technologies still in early development. A major challenge is the increased system complexity associated with acquiring multiple signals simultaneously, along with the difficulty of efficiently extracting and integrating key features for accurate BP estimation. To address this, we developed a BP monitoring system that can synchronously acquire and process ECG, PPG, and ICG signals. Optimizing the circuit design allowed ECG and ICG modules to share electrodes, reducing components and improving compactness. Using this system, we collected 400 min of signals from 40 healthy subjects, yielding 4390 records. Experiments were conducted to evaluate the system’s performance in BP estimation. The results demonstrated that combining pulse wave analysis features with the XGBoost model yielded the most accurate BP predictions. Specifically, the mean absolute error for systolic blood pressure was 3.76 ± 3.98 mmHg, and for diastolic blood pressure, it was 2.71 ± 2.57 mmHg, both of which achieved grade A performance under the BHS standard. These results are comparable to or better than existing studies based on multi-signal methods. These findings suggest that the proposed system offers an efficient and practical solution for BP monitoring. Full article
Show Figures

Figure 1

16 pages, 4189 KB  
Article
Experimental Study of Liquid and Gas Gate Valve Internal Leakage Testing Based on Ultrasonic Signal
by Tingwei Wang, Xinjia Ma, Shiqiang Zhang, Qiang Feng, Xiaomei Xiang and Hui Xia
Sensors 2025, 25(18), 5909; https://doi.org/10.3390/s25185909 - 21 Sep 2025
Viewed by 355
Abstract
This study presents an experimental analysis of high-pressure liquid and gas gate valve leakage under multiple operating conditions, based on the variation patterns of ultrasonic signals. Focusing on a multi-physics field analysis of gate valve internal leakage and corresponding experiments, this research illustrates [...] Read more.
This study presents an experimental analysis of high-pressure liquid and gas gate valve leakage under multiple operating conditions, based on the variation patterns of ultrasonic signals. Focusing on a multi-physics field analysis of gate valve internal leakage and corresponding experiments, this research illustrates the acoustic wave characteristics of gate valves across diverse working media, pressures, internal leakage defect sizes, and valve diameters. By drawing upon both fluid mechanics and acoustics theory, an analytical approach suited to high-pressure gate valve leakage issues is devised. Separate high-pressure gate valve leakage test platforms for liquid and gas environments were designed and constructed, enabling 126 groups of tests under varying conditions, which include one measurement per condition of the valve size, defect size, and pressure value. These experiments examine the quantitative correlation of internal leakage flow rates and ultrasonic signal measurements under different situations. In addition, the distinct behaviors and principles exhibited by high-pressure liquid gate valves and gas gate valves are compared. The findings provide theoretical and technical support for quantifying high-pressure gate valve leakage. The study analyzes the theoretical basis for the generation of ultrasonic signals from valve internal leakage, providing specific experimental data under various operating conditions. It explains the various observations during the experiments and their principles. The conclusions of this research have practical engineering value and provide important references for future studies. Full article
(This article belongs to the Section Industrial Sensors)
Show Figures

Figure 1

23 pages, 14935 KB  
Article
Robust Pedestrian Detection and Intrusion Judgment in Coal Yard Hazard Areas via 3D LiDAR-Based Deep Learning
by Anxin Zhao, Yekai Zhao and Qiuhong Zheng
Sensors 2025, 25(18), 5908; https://doi.org/10.3390/s25185908 - 21 Sep 2025
Viewed by 422
Abstract
Pedestrian intrusion in coal yard work areas is a major cause of accidents, posing challenges for the safe supervision of coal yards. Existing visual detection methods suffer under poor lighting and a lack of 3D data. To overcome these limitations, this study introduces [...] Read more.
Pedestrian intrusion in coal yard work areas is a major cause of accidents, posing challenges for the safe supervision of coal yards. Existing visual detection methods suffer under poor lighting and a lack of 3D data. To overcome these limitations, this study introduces a robust pedestrian intrusion detection method based on 3D LiDAR. Our approach consists of three main components. First, we propose a novel pedestrian detection network called EFT-RCNN. Based on Voxel-RCNN, this network introduces an EnhancedVFE module to improve spatial feature extraction, employs FocalConv to reconstruct the 3D backbone network for enhanced foreground–background distinction, and utilizes TeBEVPooling to optimize bird’s eye view (BEV) generation. Second, a precise 3D hazardous area is defined by combining a polygonal base surface, determined through on-site exploration, with height constraints. Finally, a point–region hierarchical judgment method is designed to calculate the spatial relationship between pedestrians and the hazardous area for graded warning. When evaluated on the public KITTI dataset, the EFT-RCNN network improved the average precision for pedestrian detection by 4.39% in 3D and 4.68% in BEV compared with the baseline, while maintaining a real-time processing speed of 28.56 FPS. In practical tests, the pedestrian detection accuracy reached 92.9%, with an average error in distance measurement of 0.054 m. The experimental results demonstrate that the proposed method effectively mitigates complex environmental interference, enables robust detection, and provides a reliable means for the proactive prevention of pedestrian intrusion accidents. Full article
Show Figures

Figure 1

18 pages, 4035 KB  
Article
Application of a Multi-Frequency Electromagnetic Method for Boundary Detection of Isolated Permafrost
by Yi Wu, Changlei Dai, Yunhu Shang, Lei Yang, Kai Gao and Wenzhao Xu
Sensors 2025, 25(18), 5907; https://doi.org/10.3390/s25185907 - 21 Sep 2025
Viewed by 363
Abstract
Isolated permafrost is widely distributed in freeze–thaw transition zones, characterized by blurred boundaries and strong spatial variability. Traditional methods such as drilling and electrical resistivity surveys are often limited in achieving efficient and continuous boundary identification. This study focuses on a typical isolated [...] Read more.
Isolated permafrost is widely distributed in freeze–thaw transition zones, characterized by blurred boundaries and strong spatial variability. Traditional methods such as drilling and electrical resistivity surveys are often limited in achieving efficient and continuous boundary identification. This study focuses on a typical isolated permafrost region in Northeast China and proposes a boundary detection strategy based on multi-frequency electromagnetic (EM) measurements using the GEM-2 sensor. By designing multiple frequency combinations and applying joint inversion, a boundary identification framework was developed and validated against borehole data. Results show that the multi-frequency joint inversion method improves the spatial identification accuracy of permafrost boundaries compared to traditional point-based techniques. In areas lacking boreholes, the method still demonstrates coherent boundary imaging and strong adaptability to geomorphological conditions. The multi-frequency joint inversion strategy significantly enhances imaging continuity and effectively captures electrical variations in complex freeze–thaw transition zones. Overall, this study establishes a complete non-invasive technical workflow—“acquisition–inversion–validation–imaging”—providing an efficient and scalable tool for engineering site selection, foundation design, and permafrost degradation monitoring. It also offers a methodological paradigm for electromagnetic frequency optimization and subsurface electrical boundary modeling. Full article
(This article belongs to the Section Electronic Sensors)
Show Figures

Figure 1

14 pages, 2211 KB  
Communication
Large-Area Nanostructure Fabrication with a 75 nm Half-Pitch Using Deep-UV Flat-Top Laser Interference Lithography
by Kexin Jiang, Mingliang Xie, Zhe Tang, Xiren Zhang and Dongxu Yang
Sensors 2025, 25(18), 5906; https://doi.org/10.3390/s25185906 - 21 Sep 2025
Viewed by 523
Abstract
Micro- and nanopatterning is crucial for advanced photonic, electronic, and sensing devices. Yet achieving large-area periodic nanostructures with a 75 nm half-pitch on low-cost laboratory systems remains difficult, because conventional near-ultraviolet laser interference lithography (LIL) suffers from Gaussian-beam non-uniformity and a narrow exposure [...] Read more.
Micro- and nanopatterning is crucial for advanced photonic, electronic, and sensing devices. Yet achieving large-area periodic nanostructures with a 75 nm half-pitch on low-cost laboratory systems remains difficult, because conventional near-ultraviolet laser interference lithography (LIL) suffers from Gaussian-beam non-uniformity and a narrow exposure latitude. Here, we report a cost-effective deep-ultraviolet (DUV) dual-beam LIL system based on a 266 nm laser and diffractive flat-top beam shaping, enabling large-area patterning of periodical nanostructures. At this wavelength, a moderate half-angle can be chosen to preserve a large beam-overlap region while still delivering 150 nm period (75 nm half-pitch) structures. By independently tuning the incident angle and beam uniformity, we pattern one-dimensional (1D) gratings and two-dimensional (2D) arrays over a Ø 1.0 cm field with critical-dimension variation < 5 nm (1σ), smooth edges, and near-vertical sidewalls. As a proof of concept, we transfer a 2D pattern into Si to create non-metal-coated nanodot arrays that serve as surface-enhanced Raman spectroscopy (SERS) substrates. The arrays deliver an average enhancement factor of ~1.12 × 104 with 11% intensity relative standard deviation (RSD) over 65 sampling points, a performance near the upper limit of all-dielectric SERS substrates. The proposed method overcomes the uneven hotspot distribution and complex fabrication procedures in conventional SERS substrates, enabling reliable and large-area chemical sensing. Compared to electron-beam lithography, the flat-top DUV-LIL approach offers orders-of-magnitude higher throughput at a fraction of the cost, while its centimeter-scale uniformity can be scaled to full wafers with larger beam-shaping optics. These attributes position the method as a versatile and economical route to large-area photonic metasurfaces and sensing devices. Full article
(This article belongs to the Section Nanosensors)
Show Figures

Figure 1

22 pages, 5746 KB  
Article
AGSK-Net: Adaptive Geometry-Aware Stereo-KANformer Network for Global and Local Unsupervised Stereo Matching
by Qianglong Feng, Xiaofeng Wang, Zhenglin Lu, Haiyu Wang, Tingfeng Qi and Tianyi Zhang
Sensors 2025, 25(18), 5905; https://doi.org/10.3390/s25185905 - 21 Sep 2025
Viewed by 462
Abstract
The performance of unsupervised stereo matching in complex regions such as weak textures and occlusions is constrained by the inherently local receptive fields of convolutional neural networks (CNNs), the absence of geometric priors, and the limited expressiveness of MLP in conventional ViTs. To [...] Read more.
The performance of unsupervised stereo matching in complex regions such as weak textures and occlusions is constrained by the inherently local receptive fields of convolutional neural networks (CNNs), the absence of geometric priors, and the limited expressiveness of MLP in conventional ViTs. To address these problems, we propose an Adaptive Geometry-aware Stereo-KANformer Network (AGSK-Net) for unsupervised stereo matching. Firstly, to resolve the conflict between the isotropic nature of traditional ViT and the epipolar geometry priors in stereo matching, we propose Adaptive Geometry-aware Multi-head Self-Attention (AG-MSA), which embeds epipolar priors via an adaptive hybrid structure of geometric modulation and penalty, enabling geometry-aware global context modeling. Secondly, we design Spatial Group-Rational KAN (SGR-KAN), which integrates the nonlinear capability of rational functions with the spatial awareness of deep convolutions, replacing the MLP with flexible, learnable rational functions to enhance the nonlinear expression ability of complex regions. Finally, we propose a Dynamic Candidate Gated Fusion (DCGF) module that employs dynamic dual-candidate states and spatially aware pre-enhancement to adaptively fuse global and local features across scales. Experiments demonstrate that AGSK-Net achieves state-of-the-art accuracy and generalizability on Scene Flow, KITTI 2012/2015, and Middlebury 2021. Full article
(This article belongs to the Special Issue Deep Learning Technology and Image Sensing: 2nd Edition)
Show Figures

Figure 1

23 pages, 5106 KB  
Article
Slot-Coupled Fed 256-Element Planar Microstrip Array with Beam Stability for K-Band Water Level Sensing
by Kuang-Hsuan Huang and Yen-Sheng Chen
Sensors 2025, 25(18), 5904; https://doi.org/10.3390/s25185904 - 21 Sep 2025
Viewed by 283
Abstract
Radar-based water-level monitoring requires antennas with narrow beams, high gain, and low sidelobes. Existing horn and series-fed microstrip arrays either lack compactness or suffer from frequency-dependent beam deviation that reduces sensing accuracy. This paper presents a 256-element slot-coupled planar microstrip array operating in [...] Read more.
Radar-based water-level monitoring requires antennas with narrow beams, high gain, and low sidelobes. Existing horn and series-fed microstrip arrays either lack compactness or suffer from frequency-dependent beam deviation that reduces sensing accuracy. This paper presents a 256-element slot-coupled planar microstrip array operating in the K-band for water-level radar. The array combines large-scale integration with slot-coupled feeding, which provides inherent 180° phase correction and stabilizes the main beam across frequency. The fabricated array has overall dimensions of 140 mm × 160 mm × 1.12 mm. Simulated results show a peak gain of 22.8 dBi with beamwidths of 5.2° (E-plane) and 4.2° (H-plane), while beam deviation remains within 0.5° across 25.9–27.0 GHz. In comparison, a series-fed array of identical aperture exhibits up to 7.5° deviation and only 15.8 dBi broadside gain. These results demonstrate that the proposed slot-coupled array provides a compact antenna solution meeting regulatory requirements and improving the accuracy of radar-based water-level monitoring systems. Full article
Show Figures

Figure 1

Previous Issue
Back to TopTop