Sensors

25 pages, 3956 KB

Open AccessReview

Multi-Sensor Monitoring, Intelligent Control, and Data Processing for Smart Greenhouse Environment Management

by Emmanuel Bicamumakuba, Md Nasim Reza, Hongbin Jin, Samsuzzaman, Kyu-Ho Lee and Sun-Ok Chung

Sensors 2025, 25(19), 6134; https://doi.org/10.3390/s25196134 - 3 Oct 2025

Management of smart greenhouses represents a transformative advancement in precision agriculture, enabling sustainable intensification of food production through the integration of multi-sensor networks, intelligent control, and sophisticated data filtering techniques. Unlike conventional greenhouses that rely on manual monitoring, smart greenhouses combine environmental sensors, [...] Read more.

Management of smart greenhouses represents a transformative advancement in precision agriculture, enabling sustainable intensification of food production through the integration of multi-sensor networks, intelligent control, and sophisticated data filtering techniques. Unlike conventional greenhouses that rely on manual monitoring, smart greenhouses combine environmental sensors, Internet of Things (IoT) platforms, and artificial intelligence (AI)-driven decision making to optimize microclimates, improve yields, and enhance resource efficiency. This review systematically investigates three key technological pillars, multi-sensor monitoring, intelligent control, and data filtering techniques, for smart greenhouse environment management. A structured literature screening of 114 peer-reviewed studies was conducted across major databases to ensure methodological rigor. The analysis compared sensor technologies such as temperature, humidity, carbon dioxide (CO₂), light, and energy to evaluate the control strategies such as IoT-based automation, fuzzy logic, model predictive control, and reinforcement learning, along with filtering methods like time- and frequency-domain, Kalman, AI-based, and hybrid models. Major findings revealed that multi-sensor integration enhanced precision and resilience but faced changes in calibration and interoperability. Intelligent control improved energy and water efficiency yet required robust datasets and computational resources. Advanced filtering strengthens data integrity but raises concerns of scalability and computational cost. The distinct contribution of this review was an integrated synthesis by linking technical performance to implementation feasibility, highlighting pathways towards affordable, scalable, and resilient smart greenhouse systems. Full article

(This article belongs to the Section Smart Agriculture)

► Show Figures

Figure 1

20 pages, 2227 KB

Open AccessArticle

Tuberculosis Detection from Cough Recordings Using Bag-of-Words Classifiers

by Irina Pavel and Iulian B. Ciocoiu

Sensors 2025, 25(19), 6133; https://doi.org/10.3390/s25196133 - 3 Oct 2025

Abstract

The paper proposes the use of Bag-of-Words classifiers for the reliable detection of tuberculosis infection from cough recordings. The effect of using both independent and combined distinct feature extraction procedures and encoding strategies is evaluated in terms of standard performance metrics such as [...] Read more.

The paper proposes the use of Bag-of-Words classifiers for the reliable detection of tuberculosis infection from cough recordings. The effect of using both independent and combined distinct feature extraction procedures and encoding strategies is evaluated in terms of standard performance metrics such as the Area Under Curve (AUC), accuracy, sensitivity, and F1-score. Experiments were conducted on two distinct large datasets, using both the original recordings and extended versions obtained by augmentation techniques. Performances were assessed by repeated k-fold cross-validation and by employing external datasets. An extensive ablation study revealed that the proposed approach yields up to 0.77 accuracy and 0.84 AUC values, comparing favorably against existing solutions and exhibiting robustness against various combinations of the setup parameters. Full article

(This article belongs to the Section Biomedical Sensors)

► Show Figures

Figure 1

17 pages, 2215 KB

Open AccessArticle

Fault Location of Generator Stator with Single-Phase High-Resistance Grounding Fault Based on Signal Injection

by Binghui Lei, Yifei Wang, Zongzhen Yang, Lijiang Ma, Xinzhi Yang, Yanxun Guo, Shuai Xu and Zhiping Cheng

Sensors 2025, 25(19), 6132; https://doi.org/10.3390/s25196132 - 3 Oct 2025

Abstract

This paper proposes a novel method for locating single-phase grounding faults in generator stator windings with high resistance, which are typically challenging to locate due to weak fault characteristics. The method utilizes an active voltage injection technique combined with traveling wave reflection analysis, [...] Read more.

This paper proposes a novel method for locating single-phase grounding faults in generator stator windings with high resistance, which are typically challenging to locate due to weak fault characteristics. The method utilizes an active voltage injection technique combined with traveling wave reflection analysis, singular value decomposition (SVD) denoising, and discrete wavelet transform (DWT). A DC voltage signal is then injected into the stator winding, and the voltage and current signals at both terminals are collected. These signals undergo denoising using SVD, followed by DWT, to identify the arrival time of the traveling waves. Fault location is determined based on the reflection and refraction of these waves within the winding. Simulation results demonstrate that this method achieves high accuracy in fault location, even with fault resistances up to 5000 Ω. The method offers a reliable and effective solution for locating high-resistance faults in generator stator windings without requiring winding parameters, demonstrating strong potential for practical applications. Full article

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

► Show Figures

Figure 1

11 pages, 2360 KB

Open AccessArticle

Temperature Hysteresis Calibration Method of MEMS Accelerometer

by Hak Ju Kim and Hyoung Kyoon Jung

Sensors 2025, 25(19), 6131; https://doi.org/10.3390/s25196131 - 3 Oct 2025

Abstract

Micro-electromechanical system (MEMS) sensors are widely used in various navigation applications because of their cost-effectiveness, low power consumption, and compact size. However, their performance is often degraded by temperature hysteresis, which arises from internal temperature gradients. This paper presents a calibration method that [...] Read more.

Micro-electromechanical system (MEMS) sensors are widely used in various navigation applications because of their cost-effectiveness, low power consumption, and compact size. However, their performance is often degraded by temperature hysteresis, which arises from internal temperature gradients. This paper presents a calibration method that corrects temperature hysteresis without requiring any additional hardware or modifications to the existing MEMS sensor design. By analyzing the correlation between the external temperature change rate and hysteresis errors, a mathematical calibration model is derived. The method is experimentally validated on MEMS accelerometers, with results showing an up to 63% reduction in hysteresis errors. We further evaluate bias repeatability, scale factor repeatability, nonlinearity, and Allan variance to assess the broader impacts of the calibration. Although minor trade-offs in noise characteristics are observed, the overall hysteresis performance is substantially improved. The proposed approach offers a practical and efficient solution for enhancing MEMS sensor accuracy in dynamic thermal environments. Full article

(This article belongs to the Section Navigation and Positioning)

► Show Figures

Figure 1

15 pages, 3332 KB

Open AccessArticle

YOLOv11-XRBS: Enhanced Identification of Small and Low-Detail Explosives in X-Ray Backscatter Images

by Baolu Yang, Zhe Yang, Xin Wang, Baozhong Mu, Jie Xu and Hong Li

Sensors 2025, 25(19), 6130; https://doi.org/10.3390/s25196130 - 3 Oct 2025

Abstract

Identifying concealed explosives in X-ray backscatter (XRBS) imagery remains a critical challenge, primarily due to low image contrasts, cluttered backgrounds, small object sizes, and limited structural details. To address these limitations, we propose YOLOv11-XRBS, an enhanced detection framework tailored to the characteristics of [...] Read more.

Identifying concealed explosives in X-ray backscatter (XRBS) imagery remains a critical challenge, primarily due to low image contrasts, cluttered backgrounds, small object sizes, and limited structural details. To address these limitations, we propose YOLOv11-XRBS, an enhanced detection framework tailored to the characteristics of XRBS images. A dedicated dataset (SBCXray) comprising over 10,000 annotated images of simulated explosive scenarios under varied concealment conditions was constructed to support training and evaluation. The proposed framework introduces three targeted improvements: (1) adaptive architectural refinement to enhance multi-scale feature representation and suppress background interference, (2) a Size-Aware Focal Loss (SaFL) strategy to improve the detection of small and weak-feature objects, and (3) a recomposed loss function with scale-adaptive weighting to achieve more accurate bounding box localization. The experiments demonstrated that YOLOv11-XRBS achieves better performance compared to both existing YOLO variants and classical detection models such as Faster R-CNN, SSD512, RetinaNet, DETR, and VGGNet, achieving a mean average precision (mAP) of 94.8%. These results confirm the robustness and practicality of the proposed framework, highlighting its potential deployment in XRBS-based security inspection systems. Full article

(This article belongs to the Special Issue Advanced Spectroscopy-Based Sensors and Spectral Analysis Technology)

► Show Figures

Figure 1

23 pages, 4721 KB

Open AccessArticle

Performance Analysis of Keypoints Detection and Description Algorithms for Stereo Vision Based Odometry

by Sebastian Budzan, Roman Wyżgolik and Michał Lysko

Sensors 2025, 25(19), 6129; https://doi.org/10.3390/s25196129 - 3 Oct 2025

Abstract

This paper presents a comprehensive evaluation of keypoint detection and description algorithms for stereo vision-based odometry in dynamic environments. Five widely used methods—FAST, GFTT, ORB, BRISK, and KAZE—were analyzed in terms of detection accuracy, robustness to image distortions, computational efficiency, and suitability for [...] Read more.

This paper presents a comprehensive evaluation of keypoint detection and description algorithms for stereo vision-based odometry in dynamic environments. Five widely used methods—FAST, GFTT, ORB, BRISK, and KAZE—were analyzed in terms of detection accuracy, robustness to image distortions, computational efficiency, and suitability for embedded systems. Using the KITTI dataset, the study assessed the influence of image resolution, noise, blur, and contrast variations on keypoint performance. The matching quality between stereo image pairs and across consecutive frames was also examined, with particular attention to drift—cumulative trajectory error—during motion estimation. The results show that while FAST and ORB detect the highest number of keypoints, GFTT offers the best balance between matching quality and processing time. KAZE provides high robustness but at the cost of computational load. The findings highlight the trade-offs between speed, accuracy, and resilience to environmental changes, offering practical guidance for selecting keypoint algorithms in real-time stereo visual odometry systems. The study concludes that GFTT is the most suitable method for trajectory estimation in dynamic, real-world conditions. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

17 pages, 10273 KB

Open AccessArticle

Deep Learning-Based Approach for Automatic Defect Detection in Complex Structures Using PAUT Data

by Kseniia Barshok, Jung-In Choi and Jaesun Lee

Sensors 2025, 25(19), 6128; https://doi.org/10.3390/s25196128 - 3 Oct 2025

Abstract

This paper presents a comprehensive study on automated defect detection in complex structures using phased array ultrasonic testing data, focusing on both traditional signal processing and advanced deep learning methods. As a non-AI baseline, the well-known signal-to-noise ratio algorithm was improved by introducing [...] Read more.

This paper presents a comprehensive study on automated defect detection in complex structures using phased array ultrasonic testing data, focusing on both traditional signal processing and advanced deep learning methods. As a non-AI baseline, the well-known signal-to-noise ratio algorithm was improved by introducing automatic depth gate calculation using derivative analysis and eliminated the need for manual parameter tuning. Even though this method demonstrates robust flaw indication, it faces difficulties for automatic defect detection in highly noisy data or in cases with large pore zones. Considering this, multiple DL architectures—including fully connected networks, convolutional neural networks, and a novel Convolutional Attention Temporal Transformer for Sequences—are developed and trained on diverse datasets comprising simulated CIVA data and real-world data files from welded and composite specimens. Experimental results show that while the FCN architecture is limited in its ability to model dependencies, the CNN achieves a strong performance with a test accuracy of 94.9%, effectively capturing local features from PAUT signals. The CATT-S model, which integrates a convolutional feature extractor with a self-attention mechanism, consistently outperforms the other baselines by effectively modeling both fine-grained signal morphology and long-range inter-beam dependencies. Achieving a remarkable accuracy of 99.4% and a strong F1-score of 0.905 on experimental data, this integrated approach demonstrates significant practical potential for improving the reliability and efficiency of NDT in complex, heterogeneous materials. Full article

(This article belongs to the Special Issue AI-Powered RF Sensing and Signal Intelligence: Advances in Detection and Classification Techniques)

► Show Figures

Figure 1

33 pages, 5950 KB

Open AccessArticle

Fault Point Search with Obstacle Avoidance for Machinery Diagnostic Robots Using Hierarchical Fuzzy Logic Control

by Rui Mu, Ryojun Ikeura, Hongtao Xue, Chengxiang Zhao and Peng Chen

Sensors 2025, 25(19), 6127; https://doi.org/10.3390/s25196127 - 3 Oct 2025

Abstract

Higher requirements have been placed on fault detection for continuously operating machines in modern factories. Manual inspection faces challenges related to timeliness, leading to the emergence of autonomous diagnostic robots. To overcome the safety limitations of existing diagnostic robots in factory environments, a [...] Read more.

Higher requirements have been placed on fault detection for continuously operating machines in modern factories. Manual inspection faces challenges related to timeliness, leading to the emergence of autonomous diagnostic robots. To overcome the safety limitations of existing diagnostic robots in factory environments, a hierarchical fuzzy logic-based navigation and obstacle avoidance algorithm is proposed in this study. The algorithm is constructed based on zero-order Takagi–Sugeno type fuzzy control, comprising subfunctions for navigation, static obstacle avoidance, and dynamic obstacle avoidance. Coordinated navigation and equipment protection are achieved by jointly considering the information of the fault point and surrounding equipment. The concept of a dynamic safety boundary is introduced, wherein the normalized breached level is used to replace the traditional distance-based input. In the inference process for dynamic obstacle avoidance, the relative speed direction is additionally considered. A Mamdani-type fuzzy inference system is employed to infer the necessity of obstacle avoidance and determine the priority target for avoidance, thereby enabling multi-objective planning. Simulation results demonstrate that the proposed algorithm can guide the diagnostic robot to within 30 cm of the fault point while ensuring collision avoidance with both equipment and obstacles, enhancing the completeness and safety of the fault point searching process. Full article

(This article belongs to the Special Issue Feature Papers in Fault Diagnosis & Sensors 2025)

► Show Figures

Figure 1

26 pages, 14595 KB

Open AccessArticle

Practical Application of Passive Air-Coupled Ultrasonic Acoustic Sensors for Wheel Crack Detection

by Aashish Shaju, Nikhil Kumar, Giovanni Mantovani, Steve Southward and Mehdi Ahmadian

Sensors 2025, 25(19), 6126; https://doi.org/10.3390/s25196126 - 3 Oct 2025

Abstract

Undetected cracks in railroad wheels pose significant safety and economic risks, while current inspection methods are limited by cost, coverage, or contact requirements. This study explores the use of passive, air-coupled ultrasonic acoustic (UA) sensors for detecting wheel damage on stationary or moving [...] Read more.

Undetected cracks in railroad wheels pose significant safety and economic risks, while current inspection methods are limited by cost, coverage, or contact requirements. This study explores the use of passive, air-coupled ultrasonic acoustic (UA) sensors for detecting wheel damage on stationary or moving wheels. Two controlled datasets of wheelsets, one with clear damage and another with early, service-induced defects, were tested using hammer impacts. An automated system identified high-energy bursts and extracted features in both time and frequency domains, such as decay rate, spectral centroid, and entropy. The results demonstrate the effectiveness of UAE (ultrasonic acoustic emission) techniques through Kernel Density Estimation (KDE) visualization, hypothesis testing with effect sizes, and Receiver Operating Characteristic (ROC) analysis. The decay rate consistently proved to be the most effective discriminator, achieving near-perfect classification of severely damaged wheels and maintaining meaningful separation for early defects. Spectral features provided additional information but were less decisive. The frequency spectrum characteristics were effective across both axial and radial sensor orientations, with ultrasonic frequencies (20–80 kHz) offering higher spectral fidelity than sonic frequencies (1–20 kHz). This work establishes a validated “ground-truth” signature essential for developing a practical wayside detection system. The findings guide a targeted engineering approach to physically isolate this known signature from ambient noise and develop advanced models for reliable in-motion detection. Full article

(This article belongs to the Special Issue Sensing and Imaging for Defect Detection: 2nd Edition)

► Show Figures

Figure 1

2 pages, 131 KB

Open AccessCorrection

Correction: Okey et al. BoostedEnML: Efficient Technique for Detecting Cyberattacks in IoT Systems Using Boosted Ensemble Machine Learning. Sensors 2022, 22, 7409

by Ogobuchi Daniel Okey, Siti Sarah Maidin, Pablo Adasme, Renata Lopes Rosa, Muhammad Saadi, Dick Carrillo Melgarejo and Demóstenes Zegarra Rodríguez

Sensors 2025, 25(19), 6125; https://doi.org/10.3390/s25196125 - 3 Oct 2025

Abstract

There was an error in the original publication [...] Full article

(This article belongs to the Section Communications)

28 pages, 7501 KB

Open AccessArticle

Multi-Step Apparent Temperature Prediction in Broiler Houses Using a Hybrid SE-TCN–Transformer Model with Kalman Filtering

by Pengshen Zheng, Wanchao Zhang, Bin Gao, Yali Ma and Changxi Chen

Sensors 2025, 25(19), 6124; https://doi.org/10.3390/s25196124 - 3 Oct 2025

Abstract

In intensive broiler production, rapid environmental fluctuations can induce heat stress, adversely affecting flock welfare and productivity. Apparent temperature (AT), integrating temperature, humidity, and wind speed, provides a comprehensive thermal index, guiding predictive climate control. This study develops a multi-step AT forecasting model [...] Read more.

In intensive broiler production, rapid environmental fluctuations can induce heat stress, adversely affecting flock welfare and productivity. Apparent temperature (AT), integrating temperature, humidity, and wind speed, provides a comprehensive thermal index, guiding predictive climate control. This study develops a multi-step AT forecasting model based on a hybrid SE-TCN–Transformer architecture enhanced with Kalman filtering. The temporal convolutional network with SE attention extracts short-term local trends, the Transformer captures long-range dependencies, and Kalman smoothing reduces prediction noise, collectively improving robustness and accuracy. The model was trained on multi-source time-series data from a commercial broiler house and evaluated for 5, 15, and 30 min horizons against LSTM, GRU, Autoformer, and Informer benchmarks. Results indicate that the proposed model achieves substantially lower prediction errors and higher determination coefficients. By combining multi-variable feature integration, local–global temporal modeling, and dynamic smoothing, the model offers a precise and reliable tool for intelligent ventilation control and heat stress management. These findings provide both scientific insight into multi-step thermal environment prediction and practical guidance for optimizing broiler welfare and production performance. Full article

(This article belongs to the Section Smart Agriculture)

16 pages, 6701 KB

Open AccessArticle

Novel Fabry-Pérot Filter Structures for High-Performance Multispectral Imaging with a Broadband from the Visible to the Near-Infrared

by Bo Gao, Tianxin Wang, Lu Chen, Shuai Wang, Chenxi Li, Fajun Xiao, Yanyan Liu and Weixing Yu

Sensors 2025, 25(19), 6123; https://doi.org/10.3390/s25196123 - 3 Oct 2025

Abstract

The integration of a pixelated Fabry–Pérot filter array onto the image sensor enables on-chip snapshot multispectral imaging, significantly reducing the size and weight of conventional spectral imaging equipment. However, a traditional Fabry–Pérot cavity, based on metallic or dielectric layers, exhibits a narrow bandwidth, [...] Read more.

The integration of a pixelated Fabry–Pérot filter array onto the image sensor enables on-chip snapshot multispectral imaging, significantly reducing the size and weight of conventional spectral imaging equipment. However, a traditional Fabry–Pérot cavity, based on metallic or dielectric layers, exhibits a narrow bandwidth, which restricts their utility in broader applications. In this work, we propose novel Fabry–Pérot filter structures that employ dielectric thin films for phase modulation, enabling single-peak filtering across a broad operational wavelength range from 400 nm to 1100 nm. The proposed structures are easy to fabricate and compatible with complementary metal-oxide-semiconductor (CMOS) image sensors. Moreover, the structures show low sensitivity to oblique incident angles of up to 30° with minimal wavelength shifts. This advanced Fabry–Pérot filter design provides a promising pathway for expanding the operational wavelength of snapshot spectral imaging systems, thereby potentially extending their application across numerous related fields. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

42 pages, 3952 KB

Open AccessArticle

An Explainable Markov Chain–Machine Learning Sequential-Aware Anomaly Detection Framework for Industrial IoT Systems Based on OPC UA

by Youness Ghazi, Mohamed Tabaa, Mohamed Ennaji and Ghita Zaz

Sensors 2025, 25(19), 6122; https://doi.org/10.3390/s25196122 - 3 Oct 2025

Abstract

Stealth attacks targeting industrial control systems (ICS) exploit subtle sequences of malicious actions, making them difficult to detect with conventional methods. The OPC Unified Architecture (OPC UA) protocol—now widely adopted in SCADA/ICS environments—enhances OT–IT integration but simultaneously increases the exposure of critical infrastructures [...] Read more.

Stealth attacks targeting industrial control systems (ICS) exploit subtle sequences of malicious actions, making them difficult to detect with conventional methods. The OPC Unified Architecture (OPC UA) protocol—now widely adopted in SCADA/ICS environments—enhances OT–IT integration but simultaneously increases the exposure of critical infrastructures to sophisticated cyberattacks. Traditional detection approaches, which rely on instantaneous traffic features and static models, neglect the sequential dimension that is essential for uncovering such gradual intrusions. To address this limitation, we propose a hybrid sequential anomaly detection pipeline that combines Markov chain modeling to capture temporal dependencies with machine learning algorithms for anomaly detection. The pipeline is further augmented by explainability through SHapley Additive exPlanations (SHAP) and causal inference using the PC algorithm. Experimental evaluation on an OPC UA dataset simulating Man-In-The-Middle (MITM) and denial-of-service (DoS) attacks demonstrates that incorporating a second-order sequential memory significantly improves detection: F1-score increases by +2.27%, precision by +2.33%, and recall by +3.02%. SHAP analysis identifies the most influential features and transitions, while the causal graph highlights deviations from the system’s normal structure under attack, thereby providing interpretable insights into the root causes of anomalies. Full article

(This article belongs to the Special Issue Trustworthy and Secure Internet of Things and Cyber–Physical Systems)

20 pages, 74841 KB

Open AccessArticle

Autonomous Concrete Crack Monitoring Using a Mobile Robot with a 2-DoF Manipulator and Stereo Vision Sensors

by Seola Yang, Daeik Jang, Jonghyeok Kim and Haemin Jeon

Sensors 2025, 25(19), 6121; https://doi.org/10.3390/s25196121 - 3 Oct 2025

Abstract

Crack monitoring in concrete structures is essential to maintaining structural integrity. Therefore, this paper proposes a mobile ground robot equipped with a 2-DoF manipulator and stereo vision sensors for autonomous crack monitoring and mapping. To facilitate crack detection over large areas, a 2-DoF [...] Read more.

Crack monitoring in concrete structures is essential to maintaining structural integrity. Therefore, this paper proposes a mobile ground robot equipped with a 2-DoF manipulator and stereo vision sensors for autonomous crack monitoring and mapping. To facilitate crack detection over large areas, a 2-DoF motorized manipulator providing linear and rotational motions, with a stereo vision sensor mounted on the end effector, was deployed. In combination with a manual rotation plate, this configuration enhances accessibility and expands the field of view for crack monitoring. Another stereo vision sensor, mounted at the front of the robot, was used to acquire point cloud data of the surrounding environment, enabling tasks such as SLAM (simultaneous localization and mapping), path planning and following, and obstacle avoidance. Cracks are detected and segmented using the deep learning algorithms YOLO (You Only Look Once) v6-s and SFNet (Semantic Flow Network), respectively. To enhance the performance of crack segmentation, synthetic image generation and preprocessing techniques, including cropping and scaling, were applied. The dimensions of cracks are calculated using point clouds filtered with the median absolute deviation method. To validate the performance of the proposed crack-monitoring and mapping method with the robot system, indoor experimental tests were performed. The experimental results confirmed that, in cases of divided imaging, the crack propagation direction was predicted, enabling robotic manipulation and division-point calculation. Subsequently, total crack length and width were calculated by combining reconstructed 3D point clouds from multiple frames, with a maximum relative error of 1%. Full article

(This article belongs to the Special Issue Emerging Sensors and AI-Driven Innovations in Infrastructure Health Monitoring)

► Show Figures

Figure 1

31 pages, 1950 KB

Open AccessArticle

Subspace Complexity Reduction in Direction-of-Arrival Estimation via the RASA Algorithm

by Belan Bapir-Bakr, Haitham Kareem-Ali, Sandra Gutiérrez-Serrano, Nerea del-Rey-Maestre and Carlos Hernández-Fernández

Sensors 2025, 25(19), 6120; https://doi.org/10.3390/s25196120 - 3 Oct 2025

Abstract

The complexity and scale of contemporary datasets are increasing, making the need for reliable and effective subspace processing more pressing. In array signal processing, the quality of the projection matrix and the structure of the noise subspace have a significant impact on the [...] Read more.

The complexity and scale of contemporary datasets are increasing, making the need for reliable and effective subspace processing more pressing. In array signal processing, the quality of the projection matrix and the structure of the noise subspace have a significant impact on the Direction of Arrival (DoA) estimation accuracy. In this study, the limits of typical subspace sampling approaches are emphasized, especially when source coherence, restricted snapshots, or low Signal-to-Noise Ratio (SNR) are present. Traditional DoA estimate strategies are revisited. To overcome these problems, a selective subspace refinement-based enhanced dimensionality reduction technique is proposed. Using a correlation measure based on the

ℓ_{2}

-norm, the suggested strategy minimizes the projection subspace by finding and keeping just the noise subspace’s least correlated columns. Adaptively choosing the first, last, and least dependent inner eigenvectors allows the method to maintain excellent angular resolution and estimation accuracy while drastically reducing computational complexity by up to

75 %

. This correlation-aware subspace design enhances the final pseudo-spectrum’s robustness, numerical stability, and orthogonality. The suggested method provides a scalable and effective solution for high-resolution DoA estimation in data-intensive signal environments, as demonstrated by experimental results that show it beats traditional methods in terms of accuracy and execution time. Full article

(This article belongs to the Special Issue Detection, Recognition and Identification in the Radar Applications)

19 pages, 3076 KB

Open AccessArticle

Air Pollutant Traceability Based on Federated Learning of Edge Intelligent Perception Agents

by Jinping Xue, Xin Hu, Qiang Liu, Congbo Yin, Peitao Ni and Xinyu Bo

Sensors 2025, 25(19), 6119; https://doi.org/10.3390/s25196119 - 3 Oct 2025

Abstract

Tracing the source of air pollution presents a significant challenge, especially in densely populated urban areas, because of the unpredictable and complex nature of aerodynamics. To address this issue, intelligent lamp posts have been developed with smart sensors and edge computing capabilities. These [...] Read more.

Tracing the source of air pollution presents a significant challenge, especially in densely populated urban areas, because of the unpredictable and complex nature of aerodynamics. To address this issue, intelligent lamp posts have been developed with smart sensors and edge computing capabilities. These lamp posts serve as nodes in the EIPA (Edge Intelligent Perception Agent) network within urban campuses. These lamp posts aim to track air pollutants by employing a tracking algorithm that utilizes big data learning and Gaussian diffusion models. This approach focuses on monitoring the quality of urban air and identifying pollution sources, rather than relying solely on traditional CFD simulations for air pollution dispersion. The algorithm comprises three primary components: (1) the Federated Learning framework built on the EIPA system; (2) the LSTM model implemented on the edge nodes of the EIPA system; and (3) a genetic algorithm utilized for optimizing the model parameters. By using CFD simulations in a simulated city park, training data on air dynamic movements is gathered. The usefulness of the method for tracing air pollutants based on federated learning of edge intelligent perception agents is demonstrated by the outcomes of algorithm training. Experimental results show that, compared to the traditional genetic algorithm (GA) and LSTM + genetic algorithm, the proposed FL + LSTM + GA method significantly improves the pollution source positioning accuracy to 99.5% and reduces the average absolute error (MAE) of Gaussian model parameter estimation to 0.20. Full article

(This article belongs to the Section Intelligent Sensors)

► Show Figures

Figure 1

25 pages, 737 KB

Open AccessSystematic Review

A Systematic Literature Review on the Implementation and Challenges of Zero Trust Architecture Across Domains

by Sadaf Mushtaq, Muhammad Mohsin and Muhammad Mujahid Mushtaq

Sensors 2025, 25(19), 6118; https://doi.org/10.3390/s25196118 - 3 Oct 2025

Abstract

The Zero Trust Architecture (ZTA) model has emerged as a foundational cybersecurity paradigm that eliminates implicit trust and enforces continuous verification across users, devices, and networks. This study presents a systematic literature review of 74 peer-reviewed articles published between 2016 and 2025, spanning [...] Read more.

The Zero Trust Architecture (ZTA) model has emerged as a foundational cybersecurity paradigm that eliminates implicit trust and enforces continuous verification across users, devices, and networks. This study presents a systematic literature review of 74 peer-reviewed articles published between 2016 and 2025, spanning domains such as cloud computing (24 studies), Internet of Things (11), healthcare (7), enterprise and remote work systems (6), industrial and supply chain networks (5), mobile networks (5), artificial intelligence and machine learning (5), blockchain (4), big data and edge computing (3), and other emerging contexts (4). The analysis shows that authentication, authorization, and access control are the most consistently implemented ZTA components, whereas auditing, orchestration, and environmental perception remain underexplored. Across domains, the main challenges include scalability limitations, insufficient lightweight cryptographic solutions for resource-constrained systems, weak orchestration mechanisms, and limited alignment with regulatory frameworks such as GDPR and HIPAA. Cross-domain comparisons reveal that cloud and enterprise systems demonstrate relatively mature implementations, while IoT, blockchain, and big data deployments face persistent performance and compliance barriers. Overall, the findings highlight both the progress and the gaps in ZTA adoption, underscoring the need for lightweight cryptography, context-aware trust engines, automated orchestration, and regulatory integration. This review provides a roadmap for advancing ZTA research and practice, offering implications for researchers, industry practitioners, and policymakers seeking to enhance cybersecurity resilience. Full article

(This article belongs to the Special Issue Advanced Wireless Sensor Network Deployment in Smart Cities, Industry 4.0, and Agriculture 4.0 (2nd Edition))

► Show Figures

Figure 1

23 pages, 7554 KB

Open AccessArticle

A*-TEB: An Improved A* Algorithm Based on the TEB Strategy for Multi-Robot Motion Planning

by Xu Li, Tuanjie Li, Yan Zhang, Yulin Zhang, Ziang Li, Lixiang Ban and Kecheng Sun

Sensors 2025, 25(19), 6117; https://doi.org/10.3390/s25196117 - 3 Oct 2025

Abstract

Multi-robot motion planning (MRMP) requires each robot to possess strong local planning capabilities while maintaining global consistency. However, existing research often fails to address both global and local planning simultaneously, resulting in conflicts in real-time path execution. The A* algorithm is widely used [...] Read more.

Multi-robot motion planning (MRMP) requires each robot to possess strong local planning capabilities while maintaining global consistency. However, existing research often fails to address both global and local planning simultaneously, resulting in conflicts in real-time path execution. The A* algorithm is widely used for global path planning due to its adaptability and search efficiency, while the Timed Elastic Band (TEB) algorithm excels in local trajectory optimization and real-time dynamic obstacle avoidance. This paper presents a novel motion planning framework integrating an improved A* algorithm with an enhanced TEB strategy to address both levels of planning collaboratively. The proposed improvements include the introduction of steering costs and dynamic weights into the A* algorithm to enhance path smoothness and efficiency, and a hierarchical obstacle treatment in TEB for improved local avoidance. Simulation and real-world experiments conducted with ROS confirmed the feasibility and effectiveness of the method. Compared to the traditional A* algorithm, the proposed framework reduces the average path length by 5.2%, shortens completion time by 11.5%, and decreases inflection points by 66.7%, demonstrating superior performance for multi-robot systems in dynamic environments. Full article

(This article belongs to the Special Issue Advances in Mobile Robot Perceptions, Planning, Control and Learning: 2nd Edition)

► Show Figures

Figure 1

27 pages, 1651 KB

Open AccessArticle

Real-Time Heartbeat Classification on Distributed Edge Devices: A Performance and Resource Utilization Study

by Eko Sakti Pramukantoro, Kasyful Amron, Putri Annisa Kamila and Viera Wardhani

Sensors 2025, 25(19), 6116; https://doi.org/10.3390/s25196116 - 3 Oct 2025

Abstract

Early detection is crucial for preventing heart disease. Advances in health technology, particularly wearable devices for automated heartbeat detection and machine learning, can enhance early diagnosis efforts. However, previous studies on heartbeat classification inference systems have primarily relied on batch processing, which introduces [...] Read more.

Early detection is crucial for preventing heart disease. Advances in health technology, particularly wearable devices for automated heartbeat detection and machine learning, can enhance early diagnosis efforts. However, previous studies on heartbeat classification inference systems have primarily relied on batch processing, which introduces delays. To address this limitation, a real-time system utilizing stream processing with a distributed computing architecture is needed for continuous, immediate, and scalable data analysis. Real-time ECG inference is particularly crucial for immediate heartbeat classification, as human heartbeats occur with durations between 0.6 and 1 s, requiring inference times significantly below this threshold for effective real-time processing. This study implements a real-time heartbeat classification inference system using distributed stream processing with LSTM-512, LSTM-256, and FCN models, incorporating RR-interval, morphology, and wavelet features. The system is developed as a distributed web-based application using the Flask framework with distributed backend processing, integrating Polar H10 sensors via Bluetooth and Web Bluetooth API in JavaScript. The implementation consists of a frontend interface, distributed backend services, and coordinated inference processing. The frontend handles sensor pairing and manages real-time streaming for continuous ECG data transmission. The backend processes incoming ECG streams, performing preprocessing and model inference. Performance evaluations demonstrate that LSTM-based heartbeat classification can achieve real-time performance on distributed edge devices by carefully selecting features and models. Wavelet-based features with an LSTM-Sequential architecture deliver optimal results, achieving 99% accuracy with balanced precision-recall metrics and an inference time of 0.12 s—well below the 0.6–1 s heartbeat duration requirement. Resource analysis on Jetson Orin devices reveals that Wavelet-FCN models offer exceptional efficiency with 24.75% CPU usage, minimal GPU utilization (0.34%), and 293 MB memory consumption. The distributed architecture’s dynamic load balancing ensures resilience under varying workloads, enabling effective horizontal scaling. Full article

(This article belongs to the Special Issue Advanced Sensors for Human Health Management)

Journal Description

Sensors

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI