Previous Issue
Volume 26, May-2
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
8.2
3.5
Journals
Sensors
Volume 26
Issue 11
sensors-logo

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Sensors, Volume 26, Issue 11 (June-1 2026) – 29 articles

  • 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
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
27 pages, 6872 KB  
Article
Capacitive Insect Sensing Under a Single Dual-Arc Geometry: A Laboratory Benchmark of Four CDC Architectures
by Sen-Miao Chen, Yu-Bing Huang, Jen-Cheng Wang and Joe-Air Jiang
Sensors 2026, 26(11), 3306; https://doi.org/10.3390/s26113306 (registering DOI) - 22 May 2026
Abstract
Capacitive sensing offers a low-power, non-optical route for automated insect monitoring, but architecture-level benchmarking under shared geometry remains limited. Rather than presenting a general framework, this study proposed a configuration-specific laboratory benchmark comparing four sigma-delta and charge-transfers in a 6 mm dual-arc conduit [...] Read more.
Capacitive sensing offers a low-power, non-optical route for automated insect monitoring, but architecture-level benchmarking under shared geometry remains limited. Rather than presenting a general framework, this study proposed a configuration-specific laboratory benchmark comparing four sigma-delta and charge-transfers in a 6 mm dual-arc conduit at 25 °C, targeting six adult terrestrial arthropod species spanning a 25-fold range of the body cross-sectional area. Static measurements showed a strong linear relationship between ΔC_static and body cross-sectional area (17.96 fF/mm2, r = 0.995), supporting first-pass conduit sizing and detectability screening. In contrast, transit amplitudes were not monotonic with body size because posture, motion, and gap occupancy affected waveform shape. Under chamber conditions, static sensitivity degraded by less than 3.2% across all architectures from RH 40% to 80%. However, under the deployment-oriented noise model, SNR_FR degradation was substantially higher for charge-transfer devices (64.8–66.8%) than for Σ–Δ devices (≤35.5%), because the composite noise floor amplifies the effect of humidity-induced baseline drift. These results generated a conduit-specific reference dataset for preliminary capacitance-to-digital converter (CDC) selection within the tested 6 mm dual-arc geometry. In addition, the experimental validation focused on laboratory baseline noise characterization, long-term drift, and trap-integrated testing in temperature-controlled environments and natural-locomotion trials, providing critical information on configuration-specific architectures and body-size-scaling reference. This study serves as an initial step toward real-world capacitive insect sensing. Future studies will investigate additional conduit geometries and insect species to improve the robustness of the proposed framework. Full article
(This article belongs to the Section Smart Agriculture)
►▼ Show Figures

Figure 1

19 pages, 5072 KB  
Article
MDCL-DETR: Multi-Domain Enhancement and Cross-Layer Feature Fusion for Small Object Detection
by Tianran Hao, Xiao Zhang and Bing Zhou
Sensors 2026, 26(11), 3305; https://doi.org/10.3390/s26113305 (registering DOI) - 22 May 2026
Abstract
Small object detection in uncrewed aerial vehicle (UAV) imagery is hindered by limited pixels, insufficient detailed information, and strong background interference, leading to weak feature representation and poor contextual modeling. To address these issues, we propose a multi-domain enhancement and cross-layer feature fusion [...] Read more.
Small object detection in uncrewed aerial vehicle (UAV) imagery is hindered by limited pixels, insufficient detailed information, and strong background interference, leading to weak feature representation and poor contextual modeling. To address these issues, we propose a multi-domain enhancement and cross-layer feature fusion detection Transformer (MDCL-DETR) with progressive feature processing. First, a multi-domain enhancement module (MDEM) based on CSP (cross stage partial) structure is proposed, which fuses spatial and frequency-domain features in a lightweight manner to enhance object detail and global structures while effectively distinguishing object features from background interference. Second, a cross-layer feature extraction module (CLEM) is introduced to aggregate multi-scale features across layers, alleviate information loss caused by downsampling, and preserve spatial details of small objects while integrating high-level contextual semantics. Meanwhile, a gated Mamba fusion module (GMFM) is proposed, which adopts the Mamba architecture for long-range dependency modeling of multi-scale features and integrates a gating mechanism to realize the dynamic weighted fusion of local details and global context, further improving feature discriminability and global modeling capability. Finally, a fine-grained enhancement module (FGEM) is designed, which leverages feature reorganization and adaptive feature extraction to reinforce and compensate fine-grained features. Extensive experimental results validate the effectiveness and generalization of the proposed method, achieving mAP50 scores of 54.1% and 56.2% on the VisDrone2019 and AI-TOD datasets. Full article
(This article belongs to the Section Sensing and Imaging)
20 pages, 1656 KB  
Article
Design and Evaluation of a Flexible Substrate-Based Microstrip Sensor for Partial Discharge Detection in High-Voltage Equipment
by Shuhao Dong and Xiao Hu
Sensors 2026, 26(11), 3304; https://doi.org/10.3390/s26113304 (registering DOI) - 22 May 2026
Abstract
Partial discharge (PD) detection effectively identifies insulation defects in power equipment. Radio frequency (RF) methods for PD detection offer promising advantages due to their non-invasive measurement capability and ability to locate discharge sources. However, microstrip antennas used as RF sensors for PD detection [...] Read more.
Partial discharge (PD) detection effectively identifies insulation defects in power equipment. Radio frequency (RF) methods for PD detection offer promising advantages due to their non-invasive measurement capability and ability to locate discharge sources. However, microstrip antennas used as RF sensors for PD detection suffer from narrow bandwidth and limited installation flexibility. To address these limitations, this paper presents a novel flexible microstrip antenna design. By incorporating a partial ground plane and oblique-cut meandering techniques and optimizing the structural parameters using an improved whale optimization algorithm (I-WOA), the operating bandwidth is expanded from 0.612–0.625 GHz to 0.346–2.0 GHz, while the overall size is reduced to 75.3% of its original dimensions. The antenna’s performance was validated through GTEM cell measurements and PD calibration pulse tests, confirming its suitability for RF detection of PD in power equipment such as transformers and cable joints. Notably, when the antenna was conformally wrapped around a cable joint, the response amplitude increased by 14%. This study contributes to the development of a low-cost, broadband, and flexibly installable RF sensor for partial discharge detection. Full article
(This article belongs to the Special Issue Feature Papers in Fault Diagnosis & Sensors 2026)
27 pages, 2285 KB  
Article
Human Motion Segmentation via Spatiotemporally Dual-Constrained Density Estimation with Commodity Wi-Fi Device
by Xu Wang, Linghua Zhang and Feng Shu
Sensors 2026, 26(11), 3303; https://doi.org/10.3390/s26113303 (registering DOI) - 22 May 2026
Abstract
In ubiquitous Wi-Fi sensing, human motion interval segmentation is crucial for applications ranging from basic intrusion detection to advanced activity understanding. Existing methods often treat the Channel State Information (CSI) primarily as time series, overlooking its rich information in the spatial and frequency [...] Read more.
In ubiquitous Wi-Fi sensing, human motion interval segmentation is crucial for applications ranging from basic intrusion detection to advanced activity understanding. Existing methods often treat the Channel State Information (CSI) primarily as time series, overlooking its rich information in the spatial and frequency domains. To address this, we propose a training-free motion segmentation method that exploits the spatiotemporal features of CSI. We first analyze the discriminative spatial distributions of the CSI Ratio on the complex plane and construct a spatiotemporally dual-constrained local density estimator to characterize motion-induced perturbations. To overcome subcarrier selection challenges, we introduce a packet-level asymmetric truncation-based fusion algorithm, which yields a feature representation with a pronounced bimodal histogram. This enables the automatic determination of the optimal segmentation threshold based on the distribution characteristics of the truncated density image. Experiments in typical indoor environments demonstrate that the proposed method achieves high accuracy in both motion event detection and interval localization. Full article
(This article belongs to the Section Sensor Networks)
23 pages, 3576 KB  
Article
3D Pose Estimation Using Virtual Projection Based on 3D Reconstructed Model
by Jung-Woo Kim, Sol Lee, Byung-Seo Park, Hak-Bum Lee, Dong-Ho Kang and Young-Ho Seo
Sensors 2026, 26(11), 3302; https://doi.org/10.3390/s26113302 (registering DOI) - 22 May 2026
Abstract
In this paper, we estimate and refine 3D human pose using the 3D point cloud or mesh model reconstructed from RGB-D cameras or volumetric capture systems. We first reconstruct the 3D model using the multi-view cameras to estimate a highly accurate skeleton. To [...] Read more.
In this paper, we estimate and refine 3D human pose using the 3D point cloud or mesh model reconstructed from RGB-D cameras or volumetric capture systems. We first reconstruct the 3D model using the multi-view cameras to estimate a highly accurate skeleton. To obtain a 2D skeleton with low error, the reconstructed 3D model is projected to four virtual planes after decidi ng the direction of the 3D model. Four 2D skeletons are estimated from four images projected in the virtual plane. Afterward, the refinement process selects candidate joints based on the distribution of local vertices and the DBSCAN algorithm. It applies a sphere fitting to ensure that the final joints are located within the body volume. The joints are combined at the intersection through the back-projection of the joints, including those in the 2D skeleton on the virtual plane. The joints in the intersection are refined using the spatial distribution of the 3D information. Through the proposed method, we estimated a stable and geometrically consistent 3D human pose from reconstructed volumetric data. Using models with ground truth, we calculated the MPJPE between the skeletons of the proposed and the ground truth. The 3D pose estimation was evaluated through a visual assessment of the captured image, and the results were quantitatively compared with the 3D joint positions acquired by the motion capture device. Full article
(This article belongs to the Section Sensing and Imaging)
►▼ Show Figures

Figure 1

21 pages, 1878 KB  
Article
Improving IoT Cybersecurity Performance with Lifecycle-Motivated Bit-Manipulation Compiler Optimizations
by Alexia Budiul and Ciprian Pungilă
Sensors 2026, 26(11), 3301; https://doi.org/10.3390/s26113301 (registering DOI) - 22 May 2026
Abstract
Implementing cryptographic primitives on resource-constrained IoT devices involves tight latency, code-size, and energy budgets. This work proposes a general LLVM backend instruction-selection strategy that recognizes single-bit update idioms—typically expressed as LOAD–-(AND/OR)–-STORE sequences in SHA-256 and similar bit-oriented code—and lowers them to the most [...] Read more.
Implementing cryptographic primitives on resource-constrained IoT devices involves tight latency, code-size, and energy budgets. This work proposes a general LLVM backend instruction-selection strategy that recognizes single-bit update idioms—typically expressed as LOAD–-(AND/OR)–-STORE sequences in SHA-256 and similar bit-oriented code—and lowers them to the most efficient target-specific bit-manipulation primitive when legality and cost conditions are met. As a concrete instantiation, we implement the strategy for the Renesas RL78/G23 ISA by rewriting eligible patterns into SET1/CLR1 instructions when the constant mask targets exactly one bit. We evaluate the resulting backend on an RL78/G23 platform using cycle counts and code size (bytes) across SHA-256-driven workloads motivated by firmware integrity checking, Merkle-tree hashing, HMAC-based authentication, password-based key derivation (PBKDF2), and chunk-level update validation. The observed cycle reductions are also converted to absolute time across the device’s supported on-chip oscillator frequencies to quantify latency impact under different clocking modes. The experimental validation in this work is limited to the RL78/G23 backend implementation. The underlying instruction-selection idea may be adaptable to other RL78-family devices or to other embedded architectures that provide equivalent single-bit set/clear or bitfield operations; however, such adaptations require target-specific legality checks, cost modeling, and separate experimental validation. Full article
(This article belongs to the Section Internet of Things)
►▼ Show Figures

Figure 1

25 pages, 1348 KB  
Article
An Adaptive Octile JPS and Fuzzy-DWA Fused Path Planning Algorithm for Indoor Home Environments
by Wei Li, Zhuoda Jia, Dawen Sun, Deng Han, Zhenyang Qin and Qianjin Liu
Sensors 2026, 26(11), 3300; https://doi.org/10.3390/s26113300 - 22 May 2026
Abstract
Home indoor environments are characterized by alternating open spaces and obstacle-cluttered regions, which pose critical challenges to the autonomous navigation of home service robots. Existing hybrid path planning algorithms generally suffer from three core limitations: low global search efficiency, weak global-local planning coordination, [...] Read more.
Home indoor environments are characterized by alternating open spaces and obstacle-cluttered regions, which pose critical challenges to the autonomous navigation of home service robots. Existing hybrid path planning algorithms generally suffer from three core limitations: low global search efficiency, weak global-local planning coordination, and poor dynamic scene adaptability. To tackle these issues, this paper presents a novel hierarchical path planning framework combining an enhanced Jump Point Search (JPS) and a fuzzy-optimized Dynamic Window Approach (DWA). In the global planning layer, an adaptive Octile heuristic JPS based on local obstacle density is designed to reduce redundant node expansion and accelerate global path search, with a bounded suboptimality guarantee. To bridge global and local planning, a look-ahead distance-based dynamic waypoint selection strategy is developed to match the optimal waypoint in real time according to the robot’s motion state and environmental complexity, enabling seamless coordination between global path guidance and local trajectory generation. In the local planning layer, a fuzzy logic controller is introduced to dynamically tune the weights of the DWA trajectory evaluation function, which significantly improves the robot’s dynamic obstacle avoidance capability and motion smoothness. Comparative simulation experiments verify that the proposed method not only outperforms the conventional hybrid path planning algorithm, reducing expanded nodes by 68.09% and global planning time by 52.94%, while improving dynamic obstacle avoidance success rate by 31.43% and overall navigation efficiency by 23.95%, it also achieves better comprehensive navigation performance than the widely adopted PSO-DWA comparison algorithm. The proposed framework shows superior comprehensive performance and is well suited for the indoor autonomous navigation of home service robots. Full article
(This article belongs to the Special Issue Autonomous Navigation for Intelligent Robots: Perception, Planning, and Control)
18 pages, 3534 KB  
Article
Risk-Aware Resource Allocation Strategy for Target Tracking in a Cognitive Radar Network
by Ji Ye Lee and Jongho Park
Sensors 2026, 26(11), 3299; https://doi.org/10.3390/s26113299 - 22 May 2026
Abstract
Cognitive radar has been developed to use feedback from its operating environment, obtained from a beam, to make resource allocation decisions by solving optimization problems. Previous works focused on target tracking accuracy by designing an evaluation metric for an optimization problem. However, in [...] Read more.
Cognitive radar has been developed to use feedback from its operating environment, obtained from a beam, to make resource allocation decisions by solving optimization problems. Previous works focused on target tracking accuracy by designing an evaluation metric for an optimization problem. However, in practical real-world scenarios, both the target tracking performance of cognitive radar and its operational perspective should be considered. In this study, the usage of an operational risk score in the allocation of radar resources is proposed for a cognitive radar framework. Resource allocation regarding radar dwell time is considered to reflect the operational significance of the target’s priority level. The dwell time allocation problem is solved through Second-Order Cone Programming (SOCP). Numerical simulations are performed to verify the effectiveness of the proposed framework. The results show that the proposed SOCP-based algorithm achieves comparable operational risk estimation performance to conventional methods while using fewer time resources, thereby improving overall resource efficiency in resource-constrained environments. Full article
(This article belongs to the Special Issue Innovative Sensor Systems and Applications: Enabling Navigation, Perception, and Decision-Making Across Domains)
23 pages, 3212 KB  
Article
Crash-Test Curve Anomaly Detection via Multi-View Context Augmentation
by Chang Zhou, Boqin Zhang, Zhao Liu and Ping Zhu
Sensors 2026, 26(11), 3298; https://doi.org/10.3390/s26113298 - 22 May 2026
Abstract
In automotive crash testing, trustworthy crash-test curves are essential for reliable crashworthiness assessment, yet automated anomaly detection is difficult due to limited labeled abnormal cases, event-level data scarcity, and distribution shifts across vehicle models and sensor configurations. This paper proposes MVCA-AD (Multi-View Context [...] Read more.
In automotive crash testing, trustworthy crash-test curves are essential for reliable crashworthiness assessment, yet automated anomaly detection is difficult due to limited labeled abnormal cases, event-level data scarcity, and distribution shifts across vehicle models and sensor configurations. This paper proposes MVCA-AD (Multi-View Context Augmentation for Anomaly Detection) for single-channel crash-test curves. MVCA-AD generates multiple context-rich views using deterministic time- and frequency-domain transformations to amplify subtle anomalous patterns under limited labeled supervision. A trend-aware modulation module and cross-view attention fuse these views to improve sensitivity to critical segments such as impact spikes and gradual transitions while remaining robust to noise. Experiments on three subsets derived from physical full-scale crash tests show that MVCA-AD improves Precision, Recall, F1-score, and area under the ROC curve (AUC) over strong baselines and achieves stable performance under event-level grouped evaluation across heterogeneous head and B-pillar crash-test signals. The proposed approach supports crash-test data quality control by automatically identifying abnormal curves for downstream crashworthiness assessment workflows. Full article
(This article belongs to the Section Fault Diagnosis & Sensors)
19 pages, 4794 KB  
Article
Comparative Measurement Accuracy Analysis of an Optical Medium Voltage Transducer Pre- and Post-Lightning Impulse Testing
by Grzegorz Fusiek and Pawel Niewczas
Sensors 2026, 26(11), 3297; https://doi.org/10.3390/s26113297 - 22 May 2026
Abstract
This paper reports on the performance of an optical voltage transducer (MVT) module after undergoing lightning impulse withstand tests. The device was designed to monitor the output voltage of a dedicated capacitive voltage divider (CVD) to facilitate a voltage sensor dedicated for 132-kV [...] Read more.
This paper reports on the performance of an optical voltage transducer (MVT) module after undergoing lightning impulse withstand tests. The device was designed to monitor the output voltage of a dedicated capacitive voltage divider (CVD) to facilitate a voltage sensor dedicated for 132-kV high voltage (HV) networks. Hard piezoelectric transducer (PZT) and fiber Bragg grating (FBG) technologies were combined in the module to serve as a voltage-to-strain-to-wavelength converter. The FBG peak wavelength shifts were calibrated against the input voltage to provide precise measurements of the network voltage. The module was subjected to lightning impulse withstand tests as per the requirements of the IEC 60044-7 and IEC 60060-1 standards, and the impact of the lightning impulses on the performance of the MVT module was evaluated based on the accuracy tests performed before and after the lightning impulse tests. The experimental results demonstrated that the MVT module successfully withstood the lightning impulse tests without any disruptive discharges or voltage collapses. The performance of the module was not affected by the lightning impulse tests within the practical constraints of the reference measuring equipment: its amplitude and phase errors remained within the original limits of ±0.1% and ±0.1° at 80–120% of the rated voltage, and below ±4% and ±2° at 2% of the rated voltage, respectively. Full article
(This article belongs to the Special Issue Optical Sensors for Industrial Applications: 2nd Edition)
22 pages, 3515 KB  
Article
Prediction of Spectral Parameters in Er3+, Dy3+ and Nd3+ Doped Oxide Glasses via cGAN-Enhanced Hybrid Modeling
by Liumiao Xie, Hengxin Yang and Xiangfu Wang
Sensors 2026, 26(11), 3296; https://doi.org/10.3390/s26113296 - 22 May 2026
Abstract
The Judd–Ofelt (J–O) intensity parameters and oscillator strengths are key to understanding the optical transition properties of rare-earth-doped glasses. However, the scarcity of experimental samples and the complex nonlinear relationship between composition and spectral properties pose significant challenges to accurate predictions. To address [...] Read more.
The Judd–Ofelt (J–O) intensity parameters and oscillator strengths are key to understanding the optical transition properties of rare-earth-doped glasses. However, the scarcity of experimental samples and the complex nonlinear relationship between composition and spectral properties pose significant challenges to accurate predictions. To address this, we propose a generalizable framework that integrates conditional generative adversarial network (cGAN)-based data augmentation with an attention-embedded artificial neural network (ANN)–support vector regression (SVR) hybrid model. The cGAN generates physically plausible virtual samples to enrich data distribution and enhance generalization in sparse compositional regions. The attention mechanism in the ANN identifies critical compositional features, which are then leveraged by SVR for robust regression of parameter trends. The framework demonstrates high predictive accuracy for Er3+-doped glasses, achieving R2 values above 0.93 for Ω2, Ω4, and Ω6, and exhibits strong generalization performance on independent Dy3+- and Nd3+-doped datasets without task-specific retraining, confirming its practical applicability across multiple rare-earth ions. The model maintains consistency across diverse glass host systems (tellurite, borate, phosphate, silicate/germanate, heavy-metal oxide), and the attention analysis reveals feature importance aligned with established glass chemistry principles. Demonstrated on Er3+, Dy3+, and Nd3+, with potential for a broader range of rare-earth ions through transfer learning and future dataset extensions, this approach offers a data-driven, physics-informed tool for the targeted design of rare-earth optical materials in next-generation optical sensors. Full article
(This article belongs to the Section Optical Sensors)
26 pages, 1185 KB  
Article
Delay Correction Method Based on VLF Timing Signal Phase Variation Model
by Xinze Ma, Wenhe Yan, Zhaopeng Hu, Jiangbin Yuan, Yu Hua and Shifeng Li
Sensors 2026, 26(11), 3295; https://doi.org/10.3390/s26113295 - 22 May 2026
Abstract
Positioning, navigation, and timing (PNT) services require stable time transfer, but satellite-based PNT signals are vulnerable to interference, attenuation, and limited availability in constrained environments. Very-low-frequency (VLF) signals propagate over long distances in the Earth–ionosphere waveguide and can serve as a terrestrial complement [...] Read more.
Positioning, navigation, and timing (PNT) services require stable time transfer, but satellite-based PNT signals are vulnerable to interference, attenuation, and limited availability in constrained environments. Very-low-frequency (VLF) signals propagate over long distances in the Earth–ionosphere waveguide and can serve as a terrestrial complement to satellite-based timing systems. Their timing performance, however, is affected by propagation-delay variation, especially the diurnal component associated with changes in the effective ionospheric reflection height. This study presents a propagation-delay correction method for VLF timing signals based on a phase-variation model. The total delay error is separated into primary path delay, secondary propagation delay, and residual random error. The primary delay is calculated from the transmitter–receiver path, while the periodic secondary delay is corrected using the predicted phase variation. Historical Alpha observations recorded at Chongqing and Guilin were used to evaluate the correction performance. The results show that the corrected standard deviation is reduced to 2.0054–2.2500 μs for the Chongqing paths and 2.7987–4.4792 μs for the Guilin paths. The corrected root mean square error (RMSE) ranges from 2.1316 μs to 4.5641 μs across the six Alpha propagation paths. These results indicate that the proposed method can suppress the main diurnal propagation-delay component in the selected historical Alpha datasets, although further validation with contemporary and multi-season VLF observations is still needed. Full article
(This article belongs to the Section Navigation and Positioning)
25 pages, 912 KB  
Article
Flow-Guided Mimicry Covert Communication over Learned Legitimate OFDM Signal Manifolds
by Qi Feng, Junyi Zhang, Mingdi Li and Li Chen
Sensors 2026, 26(11), 3294; https://doi.org/10.3390/s26113294 - 22 May 2026
Abstract
Classical covert wireless communication is commonly formulated under a noise-only null hypothesis, in which a warden detects the presence of a transmission. In shared-spectrum settings with persistent legitimate traffic, however, a warden may already observe legitimate traffic and may therefore test whether an [...] Read more.
Classical covert wireless communication is commonly formulated under a noise-only null hypothesis, in which a warden detects the presence of a transmission. In shared-spectrum settings with persistent legitimate traffic, however, a warden may already observe legitimate traffic and may therefore test whether an observation is statistically consistent with a legitimate signal class. Motivated by this regime, this paper studies mimicry covert communication in the post-demodulation OFDM resource-grid domain. A normalizing flow is trained on legitimate IEEE 802.11a NonHT-Data resource-grid observations, and covert bits are embedded by shared-key latent sign modulation, whose inner coordinatewise sign-flip rule preserves the standard Gaussian prior and thus the learned legitimate distribution under the ideal flow model. To improve message recovery under observation-domain perturbations, the framework further combines this inner embedding with a two-stage, two-state robustness-aware coordinate selector and a CRC-Polar outer code with reliability-weighted soft decoding. Experiments show that the coded design substantially improves message recovery over an uncoded repeated-sign baseline while keeping Willie-side discriminability low under both classifier-based and flow-density typicality tests. The study focuses on the learned post-demodulation resource-grid observation domain and leaves full over-the-air RF-chain validation for future work. Full article
(This article belongs to the Special Issue Integrated AI and Communication for 6G)
38 pages, 12868 KB  
Article
A Digital Twin Framework for Structural Health Monitoring of Existing Large-Span Bridges
by Minh Quang Tran, Hélder S. Sousa, José C. Matos, Son N. Dang and Huan X. Nguyen
Sensors 2026, 26(11), 3293; https://doi.org/10.3390/s26113293 - 22 May 2026
Abstract
Large-span bridges are critical components of transportation networks. Environmental variability, material degradation, and cumulative fatigue continuously affect their long-term performance. Digital Twin (DT) technology has emerged as a promising paradigm for integrating sensing, modeling, and data analytics. Most existing DT implementations in civil [...] Read more.
Large-span bridges are critical components of transportation networks. Environmental variability, material degradation, and cumulative fatigue continuously affect their long-term performance. Digital Twin (DT) technology has emerged as a promising paradigm for integrating sensing, modeling, and data analytics. Most existing DT implementations in civil infrastructure rely on dense sensor networks, assume near-complete observability, and primarily serve as passive visualization or diagnostic tools, limiting their scalability and practical applicability. This paper proposes a DT framework specifically designed for the monitoring and management of existing large-span bridges under sparse sensing conditions. The framework adopts an information-centric perspective in which limited physical measurements are complemented by full-field state reconstruction through the integration of physics-based modeling, data-driven learning, and uncertainty-aware inference. A synchronized reference configuration, termed State 0, is introduced as the initial basis for tracking structural changes over time, while allowing conditional re-baselining through a Dynamic State 0 (DS0) when verified reassessment justifies it. On this basis, the proposed DT is formulated as an adaptive and decision-oriented cyber–physical system that supports optimization-based recommendations for sensing, inspection, and maintenance planning. Full article
(This article belongs to the Special Issue Advanced Sensors in Nondestructive Testing and Structural Health Monitoring: 2nd Edition)
►▼ Show Figures

Figure 1

22 pages, 1555 KB  
Article
Physics-Informed Modified Kolmogorov–Arnold Network for CO Concentration Prediction in Gob Areas of Coal Spontaneous Combustion
by Zhuoqing Li, Jie Hou, Longqiang Han and Xiaodong Wang
Sensors 2026, 26(11), 3292; https://doi.org/10.3390/s26113292 - 22 May 2026
Abstract
Coal spontaneous combustion in gob areas is a major disaster endangering safe production in underground coal mines, and accurate prediction of carbon monoxide (CO), the core signature gas of coal oxidation, is critical for early warning and targeted prevention of mine fire disasters. [...] Read more.
Coal spontaneous combustion in gob areas is a major disaster endangering safe production in underground coal mines, and accurate prediction of carbon monoxide (CO), the core signature gas of coal oxidation, is critical for early warning and targeted prevention of mine fire disasters. However, CO concentration in gob areas is governed by complex gas–solid thermal–chemical multi-field coupling, presenting strong nonlinear characteristics. Traditional numerical methods suffer from prohibitive computational cost, purely data-driven models have inherent black-box defects, and conventional Physics-Informed Neural Networks (PINNs) require explicit full governing equations, which are hard to establish for such complex systems. This paper first proposes a Physics-Informed Modified Kolmogorov–Arnold Network (PIM-KAN), which deeply integrates domain physical knowledge with KAN architecture via a physics encoding layer, a residual-modified KAN layer, a multi-physics attention mechanism, and a multi-term physical consistency constraint framework. Experiments on 3125 real coal mine field samples show that the PIM-KAN achieves R2 = 0.9965 and RMSE = 0.9290 ppm, reducing RMSE by 19.5% compared with MLP, and outperforming all baseline models. Ablation studies confirm the significant contribution of each innovation module, and attention weight analysis is highly consistent with Arrhenius reaction kinetics, verifying its superior prediction accuracy, physical consistency and intrinsic interpretability. Full article
(This article belongs to the Special Issue Smart Sensors for Real-Time Mining Hazard Detection)
16 pages, 12756 KB  
Article
Field Performance and Calibration Strategies for Low-Cost Capacitive Soil Moisture Sensors
by Glenn Strypsteen, Magnus Persson, Mykola Miroshnychenko and Nikola Rakonjac
Sensors 2026, 26(11), 3291; https://doi.org/10.3390/s26113291 - 22 May 2026
Abstract
Low-cost capacitive (LCC) soil moisture sensors have considerable potential for precision agriculture due to their low cost, low energy consumption, and suitability for IoT-based systems. However, their field performance and the transferability of laboratory calibration to field conditions remain insufficiently documented. The objective [...] Read more.
Low-cost capacitive (LCC) soil moisture sensors have considerable potential for precision agriculture due to their low cost, low energy consumption, and suitability for IoT-based systems. However, their field performance and the transferability of laboratory calibration to field conditions remain insufficiently documented. The objective of this study was to evaluate the field performance of LCC sensors calibrated in the laboratory and to assess practical calibration strategies for field application. Laboratory calibration was performed for eight soil types, and field performance was evaluated in four experiments under different soil and climatic conditions. The sensors showed high accuracy under laboratory conditions, with RMSE values of 0.002–0.022 m3/m3 for soil-specific calibration, but substantially larger errors when laboratory-derived calibrations were applied directly in the field (RMSE 0.055–0.191 m3/m3). Soil-specific field calibration gave the highest accuracy (RMSE 0.005–0.036 m3/m3), whereas a simplified one-point calibration also improved performance considerably (RMSE 0.006–0.078 m3/m3) while requiring much less effort. Sensor performance declined at high water contents and under saline conditions. The results show that low-cost capacitive sensors can be used for reliable field soil moisture monitoring. Full article
(This article belongs to the Section Intelligent Sensors)
►▼ Show Figures

Figure 1

28 pages, 7538 KB  
Article
Quantifying the Impact of Headlamp Light Distribution on Automotive Camera Perception: Establishing a New Primary Design Parameter
by David Hoffmann, Julian Lerch, Korbinian Kunst, Nikolai Kreß and Tran Quoc Khanh
Sensors 2026, 26(11), 3290; https://doi.org/10.3390/s26113290 - 22 May 2026
Abstract
Perception-oriented evaluation of automotive headlamps still relies mainly on human-vision photometric criteria, although forward-facing cameras are increasingly safety-critical sensing elements for night driving. This paper benchmarks 16 measured production headlamp light distributions with a simulation chain that combines headlamp spectra and beam patterns, [...] Read more.
Perception-oriented evaluation of automotive headlamps still relies mainly on human-vision photometric criteria, although forward-facing cameras are increasingly safety-critical sensing elements for night driving. This paper benchmarks 16 measured production headlamp light distributions with a simulation chain that combines headlamp spectra and beam patterns, diffuse scene reflection, an imaging-transfer model, and an EMVA-based camera model. The quantitative chain maps scene radiance to sensor-domain signal-to-noise ratio, derives task-specific required signal-to-noise curves from a six-network object-recognition ensemble, and aggregates local threshold satisfaction as region-of-interest coverage across three target reflectances and five driving speeds using WLTP moving-time weights. For the baseline RGB camera, WLTP-weighted coverage ranges from 18.95% to 53.48% across the evaluated light distributions, corresponding to a factor of 2.82 between the weakest and strongest distribution. The camera-parameter sweeps show that favorable beam placement can deliver comparable benchmark coverage with roughly 60% smaller pixel pitch than the weakest distribution, corresponding to an 84% reduction in pixel area, or at materially shorter exposure times. The WLTP-weighted coverage score correlates positively with the established Headlamp Safety Performance Rating, with Pearson r=0.68 for the RGB configuration, indicating partial alignment between human-centric and camera-centric illumination needs while confirming that the metrics are not interchangeable. The results identify headlamp light distribution as a primary design parameter for nighttime camera perception and provide a quantitative basis for co-design of automotive lighting and camera-based systems. Full article
(This article belongs to the Section Intelligent Sensors)
16 pages, 27588 KB  
Article
Non-Contact IOP Estimation Based on Corneal Stress Birefringence: Experimental and Computational Validation
by Haoyuan Li, Yinda Li, Zhenhua Guo and Yong Zhang
Sensors 2026, 26(11), 3289; https://doi.org/10.3390/s26113289 - 22 May 2026
Abstract
Accurate intraocular pressure (IOP) assessment is essential for glaucoma diagnosis and follow-up. Conventional contact tonometry (e.g., Goldmann and rebound devices) remains widely used, but its accuracy is affected by operator dependence, alignment errors, and patient discomfort. We present a non-contact IOP estimation framework [...] Read more.
Accurate intraocular pressure (IOP) assessment is essential for glaucoma diagnosis and follow-up. Conventional contact tonometry (e.g., Goldmann and rebound devices) remains widely used, but its accuracy is affected by operator dependence, alignment errors, and patient discomfort. We present a non-contact IOP estimation framework based on corneal stress birefringence and full-field fringe inversion. Ex vivo porcine corneas were imaged under controlled pressure loading from 15 to 20 mmHg, and a coupled stress-optic/shell mechanics model was used to generate pressure-indexed synthetic fringe fields for inverse fitting. In the 15–18 mmHg range, more than 75% of the estimates were within plus or minus 1 mmHg of the reference pressure; performance declined at 19–20 mmHg, consistent with a stronger nonlinear biomechanical response and reduced fringe separability. Defect experiments further showed that local stiffness loss caused both near-defect distortion and far-field stress redistribution, supporting the need for full-field rather than point-wise analysis. These results indicate that stress-birefringence imaging is a promising route toward non-contact, region-sensitive IOP assessment. Full article
(This article belongs to the Section Optical Sensors)
►▼ Show Figures

Figure 1

26 pages, 6128 KB  
Article
Reliability-Guided Adaptive Feature Fusion Network for Noise-Robust Bearing Fault Diagnosis
by Song Yang, Mei Liu, Yukang Chen, Jianfeng Zhang, Peng Wang and Pengfei Luo
Sensors 2026, 26(11), 3288; https://doi.org/10.3390/s26113288 - 22 May 2026
Abstract
Cross-noise fault diagnosis remains challenging due to the mismatch between training and testing noise conditions, which degrades feature reliability and model generalization. To address this issue, this paper proposes a reliability-guided adaptive feature fusion framework (RGAF-Net). The method focuses on sample-wise adaptive feature [...] Read more.
Cross-noise fault diagnosis remains challenging due to the mismatch between training and testing noise conditions, which degrades feature reliability and model generalization. To address this issue, this paper proposes a reliability-guided adaptive feature fusion framework (RGAF-Net). The method focuses on sample-wise adaptive feature fusion, where the enhanced wide first-layer convolutional neural network(WDCNN) backbone is employed to improve multi-scale feature extraction under noisy environments. In addition, a dual-path architecture is introduced to provide complementary representations, including globally robust structural representations and locally detail-sensitive structural responses. Furthermore, a lightweight reliability estimation module is designed to characterize the signal degradation tendency under noisy conditions of each input sample, based on which a sample-wise routing mechanism dynamically adjusts feature contributions during feature fusion. Experiments on two public bearing datasets (PU and JNU) under cross-noise settings demonstrate that the proposed method achieves improved performance compared with representative approaches, particularly under severe noise conditions. For example, on the JNU dataset at −10 dB, the proposed method improves the Macro-F1 score by over 19 percentage points compared with the baseline WDCNN. Ablation studies and visualization analyses further demonstrate the effectiveness and adaptive fusion behavior of the proposed framework. The results indicate that the proposed method provides an effective solution for robust fault diagnosis under noise mismatch scenarios. Full article
(This article belongs to the Section Fault Diagnosis & Sensors)
36 pages, 34951 KB  
Article
Evaluating the ESP32-S3 for Wi-Fi Penetration Testing Through the Development of Deauther32 and HackHeld32
by Stefan Kremser and Kalman Graffi
Sensors 2026, 26(11), 3287; https://doi.org/10.3390/s26113287 (registering DOI) - 22 May 2026
Abstract
Wi-Fi security analysis and testing tools are vital to ensure the safety of wireless networks. Specialised hardware and software are needed to examine the underlying technology that connects our devices wirelessly. This article explores the feasibility of utilising the ESP32-S3 microcontroller as the [...] Read more.
Wi-Fi security analysis and testing tools are vital to ensure the safety of wireless networks. Specialised hardware and software are needed to examine the underlying technology that connects our devices wirelessly. This article explores the feasibility of utilising the ESP32-S3 microcontroller as the basis for a low-cost, open-source, portable Wi-Fi penetration testing tool. By developing and evaluating the Deauther32 firmware, the project demonstrates key functionalities such as capturing and injecting frames to execute common Wi-Fi attacks, like beacon flooding and deauthentication. The developed HackHeld32 design complements the firmware by offering a compact and extendable handheld device, making the tool standalone and portable. These prototypes build upon previous work, the ESP8266 Deauther and the HackHeld Vega, by introducing significant improvements in functionality, usability, and hardware capabilities. This establishes a strong foundation for future development by demonstrating the potential of microcontroller-based solutions. These tools bridge the gap between accessibility for beginners and functionality for professionals by offering a cost-effective and portable solution for Wi-Fi security testing and beyond. Full article
(This article belongs to the Special Issue Security and Privacy Challenges in IoT-Driven Smart Environments)
►▼ Show Figures

Graphical abstract

11 pages, 11473 KB  
Article
Fast Hydrogen Detection via Optical Fibers Coated with Metal Hydride Thin Films
by André D. Santos, Miguel A. S. Almeida, João P. Mendes, José M. M. M. de Almeida and Luís C. C. Coelho
Sensors 2026, 26(11), 3285; https://doi.org/10.3390/s26113285 - 22 May 2026
Abstract
Detection of leaks in hydrogen (H2) infrastructure is required on a large scale to enable a safe widespread use of this clean energy source. Sensing solutions must be low-cost, use scalable fabrication methods and allow multiplexed detection while providing reliable safety [...] Read more.
Detection of leaks in hydrogen (H2) infrastructure is required on a large scale to enable a safe widespread use of this clean energy source. Sensing solutions must be low-cost, use scalable fabrication methods and allow multiplexed detection while providing reliable safety alarms as fast as possible. Optical methods can make this possible while avoiding the risk of ignition due to electronics at the point of detection. Metal hydride-based micro-mirror configurations benefit from a simple interrogation scheme, as long as the sensitive element can produce a large optical response. Magnesium thin films undergo a drastic variation of properties when hydrogenated, making them suitable for this application. In this work, a micro-mirror device using single-mode fibers capable of detecting the presence of H2 with a loading t10 and t90 of 1.2 and 3.0 s, respectively, is demonstrated. A complete interrogation unit was developed, presenting a solution suited for widespread deployment using industry-standard optical components and equipment. Full article
(This article belongs to the Special Issue Recent Advances in Fiber Optic Sensor Technology)
►▼ Show Figures

Graphical abstract

18 pages, 5071 KB  
Article
Infrared Gas Detection Method Based on Non-Solid Characteristics and Spatiotemporal Information
by Xin Zhang and Shiwei Xu
Sensors 2026, 26(11), 3284; https://doi.org/10.3390/s26113284 - 22 May 2026
Abstract
Infrared imaging technology has been widely adopted for industrial gas leak detection due to its capability for large field-of-view, long-range, and dynamic monitoring. However, in practical applications, natural object interference within the scene, together with the blurred contours and low contrast of infrared [...] Read more.
Infrared imaging technology has been widely adopted for industrial gas leak detection due to its capability for large field-of-view, long-range, and dynamic monitoring. However, in practical applications, natural object interference within the scene, together with the blurred contours and low contrast of infrared images, severely degrades the performance of gas detection and leakage region segmentation. To address these challenges, this paper proposes a gas leak detection method that integrates gas characteristics with spatiotemporal information. Specifically, the non-solid characteristics of gas are incorporated to constrain the foreground extraction process of the Gaussian Mixture Model (GMM), thereby suppressing interfering moving objects. Furthermore, by exploiting the spatiotemporal information in infrared image sequences, a multi-scale cross-attention fusion model is designed to fuse multi-scale and global feature representations, improving the accuracy of foreground detection. Finally, density-based clustering is employed to achieve complete segmentation of gas regions with irregular shapes. Experimental results demonstrate that the proposed method effectively suppresses interference from solid objects, accurately detects gas leakage, and successfully segments the diffusion regions. Compared with existing approaches, the proposed method shows significant advantages and provides a valuable reference for research on infrared imaging-based gas leak detection. Full article
(This article belongs to the Special Issue AI-Based Sensing and Imaging Applications)
►▼ Show Figures

Figure 1

22 pages, 6338 KB  
Article
Lightweight Visual Detection and Dynamic Tracking for Pigeon Egg Inspection in Caged Pigeon Farming
by Qianhui Li, Yufan Cheng, Jingcheng Xi, Zhenghang He, Qingqing Ye, Chang Zhu, Rui Kang and Longshen Liu
Sensors 2026, 26(11), 3283; https://doi.org/10.3390/s26113283 - 22 May 2026
Abstract
Manual inspection in large-scale pigeon farms is inefficient and often misses critical targets. In addition, recognition results are difficult to link to physical cage locations in real time. Here, we develop an intelligent inspection and localization system that integrates an improved lightweight YOLO [...] Read more.
Manual inspection in large-scale pigeon farms is inefficient and often misses critical targets. In addition, recognition results are difficult to link to physical cage locations in real time. Here, we develop an intelligent inspection and localization system that integrates an improved lightweight YOLO model with QR-code-based tracking. QR codes are deployed along the inspection route as spatial anchors. Base detection models are combined with the ByteTrack algorithm to establish a dynamic mapping among video frames, cage numbers and detected targets. To improve the detection of small pigeon eggs caused by interference from metal cage meshes, we further design a lightweight YOLO-PEDI (Pigeon Egg Detection Inspection) model. Ghost modules replace standard convolutions to reduce computational cost. CBAM is introduced to enhance feature extraction in complex backgrounds. The newly designed model enables simultaneous identification of egg number and egg condition, including normal and broken eggs. The proposed method achieves an mAP50 of 98.1%, with only 1.53 million parameters and an inference time of 0.8 ms. Field tests show a cumulative egg-counting accuracy of 80.0% and a broken egg detection rate of 98.0%. These results demonstrate the potential of the proposed system for intelligent inspection in pigeon farming and provide a practical route towards precise traceability and digital production management. Full article
(This article belongs to the Special Issue Sensing Technology and Computer Vision for Precision Agriculture and Smart Farming: 2nd Edition)
►▼ Show Figures

Figure 1

15 pages, 7182 KB  
Article
In Vitro Repeatability and Inter-Device Agreement of Higher-Order Aberration Measurements in Scleral Lenses Using Two Hartmann–Shack Metrology Devices
by Francesco Viviano, Marco Iovino, Rute J. Macedo-de-Araújo and José Manuel González-Meijome
Sensors 2026, 26(11), 3282; https://doi.org/10.3390/s26113282 - 22 May 2026
Abstract
Scleral lenses (SLs) are increasingly incorporating complex optical designs, including front surface eccentricity (FSE) optimisation and wavefront-guided (WFG) corrections, to address residual higher-order aberrations (HOAs) in eyes with irregular corneas. Accurate in vitro optical verification of these surfaces relies on Hartmann–Shack (HS) metrology [...] Read more.
Scleral lenses (SLs) are increasingly incorporating complex optical designs, including front surface eccentricity (FSE) optimisation and wavefront-guided (WFG) corrections, to address residual higher-order aberrations (HOAs) in eyes with irregular corneas. Accurate in vitro optical verification of these surfaces relies on Hartmann–Shack (HS) metrology systems, yet commercially available devices differ substantially in lenslet array spatial sampling density, raising questions about their interchangeability for quality control purposes. This study evaluated the repeatability and inter-device agreement of HOA measurements in SLs obtained with two HS metrology systems with substantially different spatial sampling resolution. Sixteen SLs (four symmetric spherical, four spherical with toric periphery, four symmetric aspherical, four aspherical with toric periphery) were measured three times each using the SHSOphthalmic Cito (54 × 54 lenslet array) and SHSInspect Prio (157 × 157 lenslet array). Sphere (D) and Zernike coefficients from third to fifth radial orders were extracted for three aperture diameters (3.00, 5.00, and 7.00 mm) and analysed as root-mean-square (RMS) values by radial order and as Total HOA RMS. Both devices demonstrated excellent within-device repeatability for Sphere, RMS4, and Total HOA RMS (ICC: 0.994–1.000, CV ≤ 4%), while RMS3 and RMS5 showed moderate repeatability (ICC: 0.591–0.964, CV: 7–21%). Inter-device agreement was excellent at 5.00 and 7.00 mm (ICC: 0.950–1.000, mean bias < 0.006 μm), with a significant difference only for RMS3 at 7.00 mm aperture (p = 0.034). At 3.00 mm, significant systematic bias was detected for RMS4 (bias = −0.00102 μm, p < 0.001) and Total HOA RMS (bias = −0.00092 μm, p < 0.001), with the Cito underestimating values relative to the Prio. FSE design did not significantly influence inter-device differences. HS spatial sampling density influences HOA measurement accuracy in SLs at small apertures, and standardised high-resolution metrology protocols are essential to ensure accurate HOA characterisation. Full article
(This article belongs to the Section Optical Sensors)
►▼ Show Figures

Figure 1

19 pages, 24088 KB  
Article
LC-HR2FNet: High-Resolution Early-Level Fusion-Based LiDAR-Camera Network for Accurate Road Segmentation Autonomous Driving
by Lele Wang, Ming Li and Peng Zhang
Sensors 2026, 26(11), 3281; https://doi.org/10.3390/s26113281 - 22 May 2026
Abstract
Accurate road segmentation is a core perceptual technology for autonomous driving, but faces two challenges: (1) ambiguous road boundaries caused by insufficient modeling of contextual information relationships in CNN-based networks and (2) inadequate LiDAR-camera fusion due to modality gaps between heterogeneous sensors. To [...] Read more.
Accurate road segmentation is a core perceptual technology for autonomous driving, but faces two challenges: (1) ambiguous road boundaries caused by insufficient modeling of contextual information relationships in CNN-based networks and (2) inadequate LiDAR-camera fusion due to modality gaps between heterogeneous sensors. To mitigate these limitations, this paper proposes a novel approach, named LiDAR-Camera High-Resolution Feature Fusion Network (LC-HR2FNet), a multi-cross-stage fusion model designed for road segmentation. Firstly, a new type of pseudo-LiDAR-Image representation is generated via an early-level fusion strategy and data complementation. Sparse point clouds are transformed into dense LiDAR-Image data and then concatenated with RGB channel maps to form complementary multi-modal data inputs. Subsequently, a modified HRNet backbone integrated with cross-stage feature fusion is constructed to strengthen information interaction across different branches and enhance the modeling of contextual relationships. Additionally, a dilated feature collection model is designed to collect multi-scale confidence scores for pixel-wise class determination. Experiments on the KITTI road benchmark demonstrate that the proposed method achieves a MaxF of 97.39% on UMM_ROAD and an average of 96.28% across all urban scenarios, demonstrating superior performance and robustness. Full article
(This article belongs to the Section Vehicular Sensing)
►▼ Show Figures

Figure 1

30 pages, 4499 KB  
Article
Gap Measurement Method for Railway Switch Machines Based on the Fusion of Deep Vision and Geometric Features
by Wenxuan Zhi, Qingsheng Feng, Shuai Xiao, Xilong He, Haowei Liu, Yiyang Zou and Hong Li
Sensors 2026, 26(11), 3280; https://doi.org/10.3390/s26113280 (registering DOI) - 22 May 2026
Abstract
The gap dimension of a railway switch machine is a critical physical quantity for determining the locking status of railway turnouts. Under operating conditions characterized by heavy oil contamination, complex illumination, and equipment vibration, existing visual measurement methods often struggle to maintain stability [...] Read more.
The gap dimension of a railway switch machine is a critical physical quantity for determining the locking status of railway turnouts. Under operating conditions characterized by heavy oil contamination, complex illumination, and equipment vibration, existing visual measurement methods often struggle to maintain stability and achieve sub-pixel precision. To address this issue, this paper proposes a gap measurement method based on the fusion of vision and geometric features (G-VFM). The method first utilizes a confidence-aware optimized YOLOv8 model to achieve robust localization of the gap region. Subsequently, an improved multi-channel U-Net is employed to extract soft-edge probability maps, based on which a 20-dimensional structured geometric descriptor is constructed. Finally, visual semantic features and geometric priors are fused for regression through an R34-Fusion two-stream residual network, and systematic errors are corrected using a weighted Huber loss combined with a piecewise linear calibration strategy. Test results on a constructed field dataset show that the proposed method achieves a Mean Absolute Error (MAE) of 0.0076 mm and a maximum error of 0.0193 mm. It achieves a 100% pass rate under an industrial tolerance of 0.02 mm, with an end-to-end inference time of 52.23 ms (~19.15 FPS), balancing both precision and efficiency. Further tests on illumination degradation, noise interference, and cross-batch evaluations indicate that the method maintains relatively stable performance across various complex scenarios. However, performance decreases significantly under extremely low-light conditions, suggesting that actual deployment may require integration with active lighting or multi-sensor fusion to ensure system reliability across all working conditions. Overall, this method achieves high-precision gap measurement under current experimental conditions and provides a feasible solution for vision-based switch machine status monitoring. Full article
(This article belongs to the Special Issue Advanced Sensing Technologies for Sustainable and Resilient Railway Infrastructures)
►▼ Show Figures

Figure 1

13 pages, 2254 KB  
Article
Development of a Screen-Printable Liquid Metal Ink on PDMS Substrates Toward Flexible Conductive Electronics
by Mengwen Guo, Shengming Jin, Sanhu Liu and Fang Wang
Sensors 2026, 26(11), 3279; https://doi.org/10.3390/s26113279 - 22 May 2026
Abstract
In this study, poly(vinylpyrrolidone) (PVP)-modified liquid metal (LM) particles were formulated into a mixed-solvent system comprising ethanol (EtOH), 1,2-propanediol (1,2-PG), and a trace amount of N,N-dimethylformamide (DMF). This design addresses the instability, poor wetting/adhesion on polydimethylsiloxane (PDMS), and limited rheological tunability of conventional [...] Read more.
In this study, poly(vinylpyrrolidone) (PVP)-modified liquid metal (LM) particles were formulated into a mixed-solvent system comprising ethanol (EtOH), 1,2-propanediol (1,2-PG), and a trace amount of N,N-dimethylformamide (DMF). This design addresses the instability, poor wetting/adhesion on polydimethylsiloxane (PDMS), and limited rheological tunability of conventional LM inks for screen printing. By regulating solvent evaporation during drying, the system enables coordinated control over wettability, viscosity, shear-thinning behavior, and drying-induced film formation. At an LM:PVP weight ratio of 20:1, the contact angle on PDMS decreased from 115° to 17.8°. The ink exhibited pronounced shear-thinning characteristics with tunable viscosity in the range of 1000–3000 cP, meeting the screen-printing requirements of facile mesh passage and rapid setting. Following laser activation, the printed conductive patterns demonstrated stable electrical performance, with a resistance drift of less than 1% after 14 days of storage and a ΔR/R0 of less than 1% after 3000 bending cycles at a bending diameter of 1 cm. Furthermore, a resistance drift of less than 3% was observed after 1000 stretching cycles at 30% strain. This study proposes a viable materials and processing strategy for the reliable screen printing of LM:PVP ink on PDMS substrates toward flexible conductive electronics. The motion-monitoring test is presented only as a preliminary proof-of-concept demonstration of motion-induced electrical resistance response, rather than as a sensor performance evaluation. Full article
(This article belongs to the Section Sensor Materials)
►▼ Show Figures

Figure 1

12 pages, 571 KB  
Article
Can Locomotor Performance Predict the Final Result of a Football Match? A Machine Learning Approach
by Julen Castellano, Aitor Pinedo-Jauregi, Roberto Lopez del Campo, Ricardo Resta and Jesús Cámara
Sensors 2026, 26(11), 3278; https://doi.org/10.3390/s26113278 - 22 May 2026
Abstract
The aim of this study was to predict the match outcome using locomotor-performance-related data from teams in both Spanish professional leagues. All matches from the first and second Spanish divisions (LaLiga and LaLiga2, respectively) across two consecutive seasons were used. The locomotor variables [...] Read more.
The aim of this study was to predict the match outcome using locomotor-performance-related data from teams in both Spanish professional leagues. All matches from the first and second Spanish divisions (LaLiga and LaLiga2, respectively) across two consecutive seasons were used. The locomotor variables were as follows: total distance (TD) and distance covered at >21 km·h−1 (HSR), distinguishing between different game moments (in-possession, out-of-possession, and ball stopping). Match outcomes (win/lose) were predicted using a LASSO-regularized logistic regression based on standardized locomotor variables. Model performance was evaluated through accuracy, precision, recall, F1-scores, and AUC–ROC, demonstrating strong discriminative capacity and balanced classification across outcomes. The LASSO-regularized logistic regression model achieved strong predictive accuracy (76.8%) and balanced classification performance (F1 = 0.77; AUC = 0.85). TDnoPosmin, TD21posmin, TD21min, and TDoffmin emerged as key positive predictors of victory, whereas TD21noPosmin, TDmin, and TDposmin were negatively associated with winning. LASSO regularization confirmed the stability and robustness of these predictors, indicating limited overfitting and consistency. Match outcomes were accurately predicted from locomotor variables, with high-intensity activity out of possession emerging as the key determinant of success. Match success was primarily linked to high-intensity activity during the defensive phase, highlighting the need for further research on these critical phases of play. Full article
(This article belongs to the Special Issue Sensor-Based Methods for Kinematics, Kinetics, and Physiology in Motion: Applications and Metrological Characterization)
►▼ Show Figures

Figure 1

2 pages, 246 KB  
Correction
Correction: Liu, X.; Lin, Y. YOLO-GW: Quickly and Accurately Detecting Pedestrians in a Foggy Traffic Environment. Sensors 2023, 23, 5539
by Xinchao Liu and Yier Lin
Sensors 2026, 26(11), 3277; https://doi.org/10.3390/s26113277 - 22 May 2026
Abstract
In the original publication [...] Full article
(This article belongs to the Section Environmental Sensing)
►▼ Show Figures

Figure 7

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-29
Previous Issue
Back to TopTop