Previous Issue
Volume 25, September-1
 
 
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 25
Issue 18
sensors-logo

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Sensors, Volume 25, Issue 18 (September-2 2025) – 22 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:
18 pages, 3745 KB  
Article
Photogrammetric and LiDAR Scanning with iPhone 13 Pro: Accuracy, Precision and Field Application on Hazelnut Trees
by Elèna Grobler and Giuseppe Celano
Sensors 2025, 25(18), 5629; https://doi.org/10.3390/s25185629 (registering DOI) - 9 Sep 2025
Abstract
Accurate estimation of tree structural and morphological parameters is essential in precision fruit farming, supporting optimised irrigation management, biomass estimation and carbon stock assessment. While traditional field-based measurements remain widely used, they are often time-consuming and subject to operator-induced errors. In recent years, [...] Read more.
Accurate estimation of tree structural and morphological parameters is essential in precision fruit farming, supporting optimised irrigation management, biomass estimation and carbon stock assessment. While traditional field-based measurements remain widely used, they are often time-consuming and subject to operator-induced errors. In recent years, Terrestrial Laser Scanning (TLS) and UAV-based photogrammetry have been successfully employed to generate high-resolution 3D reconstructions of plants; however, their cost and operational constraints limit their scalability in routine field applications. This study investigates the performances of a low-cost, consumer-grade device—the iPhone 13 Pro equipped with an integrated LiDAR sensor and RGB camera—for 3D scanning of fruit tree structures. Cylindrical targets with known geometric dimensions were scanned using both the LiDAR and photogrammetric (Photo) modes of the Polycam© application, with accuracy and precision assessed by comparing extracted measurements to reference values. Field applicability was also tested on hazelnut trees, assessing height, stem diameter and leaf area: the Photo mode delivered the highest accuracy (systematic error of 0.007 m and R2 = 0.99) and strong agreement with manual leaf measurements (R2 = 0.93). These results demonstrate that smartphone-based 3D scanning can provide a practical, low-cost approach for structural characterisation in fruit orchards, supporting more efficient crop monitoring. Full article
(This article belongs to the Special Issue Advances in Sensor Technologies and Measurement Techniques for Smart Agri-Food)
►▼ Show Figures

Figure 1

13 pages, 2827 KB  
Article
Predictive Modelling of Exam Outcomes Using Stress-Aware Learning from Wearable Biosignals
by Sham Lalwani and Saideh Ferdowsi
Sensors 2025, 25(18), 5628; https://doi.org/10.3390/s25185628 - 9 Sep 2025
Abstract
This study investigates the feasibility of using wearable technology and machine learning algorithms to predict academic performance based on physiological signals. It also examines the correlation between stress levels, reflected in the collected physiological data, and academic outcomes. To this aim, six key [...] Read more.
This study investigates the feasibility of using wearable technology and machine learning algorithms to predict academic performance based on physiological signals. It also examines the correlation between stress levels, reflected in the collected physiological data, and academic outcomes. To this aim, six key physiological signals, including skin conductance, heart rate, skin temperature, electrodermal activity, blood volume pulse, inter-beat interval, and accelerometer were recorded during three examination sessions using a wearable device. A novel pipeline, comprising data preprocessing and feature engineering, is proposed to prepare the collected data for training machine learning algorithms. We evaluated five machine learning models, including Random Forest, Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost), Categorical Boosted (CatBoost), and Gradient-Boosting Machine (GBM), to predict the exam outcomes. The Synthetic Minority Oversampling Technique (SMOTE), followed by hyperparameter tuning and dimensionality reduction, are implemented to optimise model performance and address issues like class imbalance and overfitting. The results obtained by our study demonstrate that physiological signals can effectively predict stress and its impact on academic performance, offering potential for real-time monitoring systems that support student well-being and academic success. Full article
(This article belongs to the Special Issue Biomedical Imaging, Sensing and Signal Processing)
►▼ Show Figures

Figure 1

17 pages, 4513 KB  
Article
Spectral Demodulation of Mixed-Linewidth FBG Sensor Networks Using Cloud-Based Deep Learning for Land Monitoring
by Michael Augustine Arockiyadoss, Cheng-Kai Yao, Pei-Chung Liu, Pradeep Kumar, Siva Kumar Nagi, Amare Mulatie Dehnaw and Peng-Chun Peng
Sensors 2025, 25(18), 5627; https://doi.org/10.3390/s25185627 - 9 Sep 2025
Abstract
Fiber Bragg grating (FBG) sensing systems face significant challenges in resolving overlapping spectral signatures when multiple sensors operate within limited wavelength ranges, severely limiting sensor density and network scalability. This study introduces a novel Transformer-based neural network architecture that effectively resolves spectral overlap [...] Read more.
Fiber Bragg grating (FBG) sensing systems face significant challenges in resolving overlapping spectral signatures when multiple sensors operate within limited wavelength ranges, severely limiting sensor density and network scalability. This study introduces a novel Transformer-based neural network architecture that effectively resolves spectral overlap in both uniform and mixed-linewidth FBG sensor arrays, operating under bidirectional drift. The system uniquely combines dual-linewidth configurations with reflection and transmission mode fusion to enhance demodulation accuracy and sensing capacity. By integrating cloud computing, the model enables scalable deployment and near-real-time inference even in large-scale monitoring environments. The proposed approach supports self-healing functionality through dynamic switching between spectral modes during fiber breaks and enhances resilience against spectral congestion. Comprehensive evaluation across twelve drift scenarios demonstrates exceptional demodulation performance under severe spectral overlap conditions that challenge conventional peak-finding algorithms. This breakthrough establishes a new paradigm for high-density, distributed FBG sensing networks applicable to land monitoring, soil stability assessment, groundwater detection, maritime surveillance, and smart agriculture. Full article
(This article belongs to the Special Issue Advancing Land Monitoring through Synergistic Harmonization of Optical, Radar and Lidar Satellite Technologies)
►▼ Show Figures

Figure 1

17 pages, 8532 KB  
Article
An Effective Two-Step Procedure Allowing the Retrieval of the Non-Redundant Spherical Near-Field Samples from the 3-D Mispositioned Ones
by Francesco D'Agostino, Flaminio Ferrara, Claudio Gennarelli, Rocco Guerriero, Massimo Migliozzi and Luigi Pascarella
Sensors 2025, 25(18), 5626; https://doi.org/10.3390/s25185626 - 9 Sep 2025
Abstract
In this article, a novel procedure is developed to properly handle the 3-D mispositioning of the scanning probe in the near-field to far-field (NFtFF) transformations with spherical scanning for quasi-planar antennas under test, which make use of a non-redundant (NR) number of samples. [...] Read more.
In this article, a novel procedure is developed to properly handle the 3-D mispositioning of the scanning probe in the near-field to far-field (NFtFF) transformations with spherical scanning for quasi-planar antennas under test, which make use of a non-redundant (NR) number of samples. It proceeds through two stages. In the former, a phase correction technique, named spherical wave correction, is applied to compensate for the phase shifts of the collected NF samples, which do not belong to the measurement sphere, due to mechanical defects of the arc, or inaccuracy of the robotic arm employed in the considered NF facility driving the probe. Once the phase shifts have been compensated, the recovered NF samples belong to the set spherical surface, but their positions differ from those prescribed by the adopted NR representation, because of an imprecise control and/or inaccuracy of the positioning system. Thus, the resulting sampling arrangement is affected by 2-D mispositioning errors. Accordingly, an iterative procedure is used in the latter step to restore the NF samples at their exact locations from those determined at the first step. Once the correct sampling arrangement has been retrieved from the 3-D mispositioned one, an optimal sampling interpolation formula is employed to obtain the massive input NF data necessary for the classical spherical NFtFF transformation technique. Numerical results, showing the precision of the NF and FF reconstructions, assessed the efficacy of the developed procedure. Full article
(This article belongs to the Special Issue Recent Advances in Antenna Measurement Techniques)
►▼ Show Figures

Figure 1

20 pages, 947 KB  
Article
Rapid Identification of Dendrobium Species Using Near-Infrared Hyperspectral Imaging Technology
by Kaixuan Li, Yijun Guo, Haosheng Zhong, Yiqi Jin, Bin Li, Huimin Fang, Lijian Yao and Chao Zhao
Sensors 2025, 25(18), 5625; https://doi.org/10.3390/s25185625 - 9 Sep 2025
Abstract
Dendrobium officinale is a valuable Chinese medicinal herb, but distinguishing it from other Dendrobium species after processing is challenging, leading to low classification accuracy and time-consuming analysis. This study proposes a rapid classification model based on near-infrared hyperspectral imaging (NIR-HSI), incorporating data preprocessing [...] Read more.
Dendrobium officinale is a valuable Chinese medicinal herb, but distinguishing it from other Dendrobium species after processing is challenging, leading to low classification accuracy and time-consuming analysis. This study proposes a rapid classification model based on near-infrared hyperspectral imaging (NIR-HSI), incorporating data preprocessing and feature wavelength selection. Five Dendrobium species—D. officinale, D. aphyllum, D. chrysanthum, D. fimbriatum, and D. thyrsiflorum—were used. Spectral preprocessing techniques like normalization and smoothing were applied, and Support Vector Machine (SVM) models were constructed. Normalization improved both accuracy and stability, with the full-spectrum Normalize-SVM model achieving 97% accuracy for calibration and 88% for prediction. D. chrysotoxum performed best, with all metrics reaching 100%, while D. aphyllum had poor classification (40% recall and 51.74% F1 score). To improve efficiency and performance, feature wavelength selection was performed using Competitive Adaptive Reweighted Sampling (CARS) and Successive Projections Algorithm (SPA). The CARS-Normalize-SVM model yielded the best results: 98% accuracy for calibration and 96% for prediction, improving by 1% and 8%, respectively. D. aphyllum’s classification also improved significantly, with a 100% recall rate and 95.24% F1 score. These findings highlight hyperspectral imaging’s potential for rapid Dendrobium species identification, supporting future quality control and market supervision. Full article
(This article belongs to the Special Issue Recent Advances in Spectroscopic Sensing and Sensor Engineering)
18 pages, 1355 KB  
Article
Sit-and-Reach Pose Detection Based on Self-Train Method and Ghost-ST-GCN
by Shuheng Jiang, Haihua Cui and Liyuan Jin
Sensors 2025, 25(18), 5624; https://doi.org/10.3390/s25185624 - 9 Sep 2025
Abstract
The sit-and-reach test is a common stretching exercise suitable for adolescents, aimed at improving joint flexibility and somatic neural control, and has become a mandatory item in China’s student physical fitness assessments. However, many students tend to perform incorrect postures during their practice, [...] Read more.
The sit-and-reach test is a common stretching exercise suitable for adolescents, aimed at improving joint flexibility and somatic neural control, and has become a mandatory item in China’s student physical fitness assessments. However, many students tend to perform incorrect postures during their practice, which may lead to sports injuries such as muscle strains if sustained over time. To address this issue, this paper proposes a Ghost-ST-GCN model for judging the correctness of the sit-and-reach pose. The model first requires detecting seven body keypoints. Leveraging a publicly available labeled keypoint dataset and unlabeled sit-and-reach videos, these keypoints are acquired through the proposed self-train method using the BlazePose network. Subsequently, the keypoints are fed into the Ghost-ST-GCN model, which consists of nine stacked GCN-TCN blocks. Critically, each GCN-TCN layer is embedded with a ghost layer to enhance efficiency. Finally, a classification layer determines the movement’s correctness. Experimental results demonstrate that the self-train method significantly improves the annotation accuracy of the seven keypoints; the integration of ghost layers streamlines the overall detection model; and the system achieves an action detection accuracy of 85.20% for the sit-and-reach exercise, with a response latency of less than 1 s. This approach is highly suitable for guiding adolescents to standardize their movements during independent sit-and-reach practice. Full article
(This article belongs to the Special Issue AI-Based Automated Recognition and Detection in Healthcare)
43 pages, 1198 KB  
Article
An Overview of Phase-Locked Loop: From Fundamentals to the Frontier
by Thi Viet Ha Nguyen and Cong-Kha Pham
Sensors 2025, 25(18), 5623; https://doi.org/10.3390/s25185623 - 9 Sep 2025
Abstract
Phase-Locked Loops (PLLs) are fundamental building blocks in modern electronic systems, enabling precise frequency synthesis, signal synchronization, and clock generation. This paper provides a comprehensive system-level analysis of PLLs, covering their fundamental operation, key architectures, performance considerations, and applications in emerging technologies. Additionally, [...] Read more.
Phase-Locked Loops (PLLs) are fundamental building blocks in modern electronic systems, enabling precise frequency synthesis, signal synchronization, and clock generation. This paper provides a comprehensive system-level analysis of PLLs, covering their fundamental operation, key architectures, performance considerations, and applications in emerging technologies. Additionally, this paper discusses current challenges and future trends in PLL design, including low-power optimization, noise reduction, and integration with machine learning techniques. Full article
(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2025)
14 pages, 1140 KB  
Article
Design Considerations for a 120 GHz MIMO Sparse Radar Array Based on SISO Integrated Circuits
by Luigi Ferro, Changzhi Li and Emanuele Cardillo
Sensors 2025, 25(18), 5622; https://doi.org/10.3390/s25185622 - 9 Sep 2025
Abstract
This study aims to illustrate the main aspects of designing a modular 120 GHz Multiple-Input Multiple-Output (MIMO) sparse radar array (SRA) composed of multiple Single-Input Single-Output (SISO) Integrated Circuits (ICs). Although the scientific literature reports on 120 GHz integrated circuit prototypes, to the [...] Read more.
This study aims to illustrate the main aspects of designing a modular 120 GHz Multiple-Input Multiple-Output (MIMO) sparse radar array (SRA) composed of multiple Single-Input Single-Output (SISO) Integrated Circuits (ICs). Although the scientific literature reports on 120 GHz integrated circuit prototypes, to the authors’ best knowledge, there are no commercial MIMO radars composed of multiple SISO ICs operating in the D-band spectrum. The design involves many challenges; indeed, the necessity to combine multiple chips with fixed dimensions and the presence of transmitting and receiving antennas on chips add many constraints for the antenna placement and, consequently, for the virtual array design. As an example, the minimum distance between the antennas must be at least equal to the chip width, which is in turn higher than half a wavelength and renders the array into a sparse configuration, thus raising many concerns regarding fixing the optimum inter-chip distance. Thus, this contribution can be considered as pioneering, being focused on the emerging concept of designing D-band MIMO radars by exploiting a modular approach. Full article
(This article belongs to the Special Issue Microwave/MM-Wave Components for Communications and Sensors)
27 pages, 4114 KB  
Article
Arrhythmia Classification with Single-Channel Features Extracted from “A Large-Scale 12-Lead ECG Database for Arrhythmia Study”
by Monica Fira, Liviu Goraș, Lucian Fira, Radu Florin Popa and Hariton-Nicolae Costin
Sensors 2025, 25(18), 5621; https://doi.org/10.3390/s25185621 - 9 Sep 2025
Abstract
This study assesses how classical and modern features extracted from a single ECG lead (II) influence automated arrhythmia classification. Using the Large Scale 12-Lead Electrocardiogram Database for Arrhythmia Study and MATLAB®, we compared traditional morphological measures (e.g., QRS duration, QT interval, [...] Read more.
This study assesses how classical and modern features extracted from a single ECG lead (II) influence automated arrhythmia classification. Using the Large Scale 12-Lead Electrocardiogram Database for Arrhythmia Study and MATLAB®, we compared traditional morphological measures (e.g., QRS duration, QT interval, atrial/ventricular rates) with advanced time-, frequency-, and nonlinear-domain descriptors. The method classifies ECGs into four or eight categories using 15–39 features, either automatically selected or combined. In the eight-class task, 29–39 features yielded 69% accuracy; in the four-class task, 15 MRMR-selected features achieved 94.2% accuracy. A key strength is efficiency: relying on a single lead reduces preprocessing, storage, and classification time by a factor of ~12 compared with 12-lead approaches. These findings show that advanced descriptors from a single lead can match multi-lead performance, enabling practical, scalable clinical applications. Full article
(This article belongs to the Special Issue Advances in E-health, Biomedical Sensing, Biosensing Applications)
24 pages, 5241 KB  
Article
CogMamba: Multi-Task Driver Cognitive Load and Physiological Non-Contact Estimation with Multimodal Facial Features
by Yicheng Xie and Bin Guo
Sensors 2025, 25(18), 5620; https://doi.org/10.3390/s25185620 - 9 Sep 2025
Abstract
The cognitive load of drivers directly affects the safety and practicality of advanced driving assistant systems, especially in autonomous driving scenarios where drivers need to quickly take control of the vehicle after performing non-driving-related tasks (NDRTs). However, existing driver cognitive load detection methods [...] Read more.
The cognitive load of drivers directly affects the safety and practicality of advanced driving assistant systems, especially in autonomous driving scenarios where drivers need to quickly take control of the vehicle after performing non-driving-related tasks (NDRTs). However, existing driver cognitive load detection methods have shortcomings such as the inability to deploy invasive detection equipment inside vehicles and limitations to eye movement detection, which restrict their practical application. To achieve more efficient and practical cognitive load detection, this study proposes a multi-task non-contact cognitive load and physiological state estimation model based on RGB video, named CogMamba. The model utilizes multimodal features extracted from facial video and introduces the Mamba architecture to efficiently capture local and global temporal dependencies, thereby further jointly estimating cognitive load, heart rate (HR), and respiratory rate (RR). Experimental results demonstrate that CogMamba exhibits superior performance on two public datasets and shows excellent robustness under the cross-dataset generalization test. This study provides insights for non-contact driver state monitoring in real-world driving scenarios. Full article
(This article belongs to the Section Physical Sensors)
►▼ Show Figures

Figure 1

32 pages, 6726 KB  
Article
Synergy of Information in Multimodal Internet of Things Systems—Discovering the Impact of Daily Behaviour Routines on Physical Activity Level
by Mohsen Shirali, Zahra Ahmadi, Jose Luis Bayo-Monton, Zoe Valero-Ramon and Carlos Fernandez-Llatas
Sensors 2025, 25(18), 5619; https://doi.org/10.3390/s25185619 - 9 Sep 2025
Abstract
Background and Objective: The intricate connection between daily behaviours and health necessitates robust monitoring, particularly with the advent of Internet of Things (IoT) systems. This study introduces an innovative approach that exploits the synergy of information from various IoT sources to assess the [...] Read more.
Background and Objective: The intricate connection between daily behaviours and health necessitates robust monitoring, particularly with the advent of Internet of Things (IoT) systems. This study introduces an innovative approach that exploits the synergy of information from various IoT sources to assess the alignment of behavioural routines with health guidelines. The goal is to improve the readability of behaviour models and provide actionable insights for healthcare professionals. Method: We integrate data from ambient sensors, smartphones, and wearable devices to acquire daily behavioural routines by employing process mining (PM) techniques to generate interpretable behaviour models. These routines are grouped according to compliance with health guidelines, and a clustering method is used to identify similarities in behaviours and key characteristics within each cluster. Results: Applied to an elderly care case study, our approach categorised days into three physical activity levels (Insufficient, Sufficient, Desirable) based on daily step thresholds. The integration of multi-source data revealed behavioural variations not detectable through single-source monitoring. We demonstrated that the proposed visualisations in calendar and timeline views aid health experts in understanding patient behaviours, enabling longitudinal monitoring and clearer interpretation of behavioural trends and precise interventions. Notably, the approach facilitates early detection of behaviour changes during contextual events (e.g., COVID-19 lockdown and Ramadan), which are available in our dataset. Conclusions: By enhancing interpretability and linking behaviour to health guidelines, this work signifies a promising path for behavioural analysis and discovering variations to empower smart healthcare, offering insights into patient health, personalised interventions, and healthier routines through continuous monitoring with IoT-driven data analysis. Full article
(This article belongs to the Special Issue IoT and Sensor Technologies for Healthcare)
31 pages, 8125 KB  
Review
Toward Field Deployment: Tackling the Energy Challenge in Environmental Sensors
by Valentin Daniel Paccoia, Francesco Bonacci, Giacomo Clementi, Francesco Cottone, Igor Neri and Maurizio Mattarelli
Sensors 2025, 25(18), 5618; https://doi.org/10.3390/s25185618 - 9 Sep 2025
Abstract
The need for sustainable and long-term environmental monitoring has driven the development of energy-autonomous sensors, which either operate passively or integrate energy harvesting (EH) solutions. In many applications, the energy cost of data transmission is a critical factor in autonomous sensing systems. To [...] Read more.
The need for sustainable and long-term environmental monitoring has driven the development of energy-autonomous sensors, which either operate passively or integrate energy harvesting (EH) solutions. In many applications, the energy cost of data transmission is a critical factor in autonomous sensing systems. To address this challenge, optical passive sensors, which exploit changes in reflectivity to monitor physical parameters, offer self-sustained operation without requiring an external power source. Similarly, RF-based passive sensors, both chipless and with minimal circuitry, enable wireless monitoring with low power consumption. When more energy is available, EH techniques can be combined with active optical sensors. Infrared laser-based CO2 sensors, as well as drone-mounted optical systems, demonstrate how EH can power precise environmental measurements. Beyond optics, other sensing modalities also benefit from EH, further expanding the range of self-powered environmental monitoring technologies. This review discusses the trade-offs between passive and EH-assisted sensing strategies, with a focus on optical implementations. The outlook highlights emerging solutions to enhance sensor autonomy while minimizing the energy cost of data transmission, paving the way for sustainable and scalable environmental monitoring. Full article
(This article belongs to the Special Issue Feature Review Papers in Optical Sensors)
►▼ Show Figures

Figure 1

40 pages, 7228 KB  
Article
Guidance for Interactive Visual Analysis in Multivariate Time Series Preprocessing
by Flor de Luz Palomino Valdivia and Herwin Alayn Huillcen Baca
Sensors 2025, 25(18), 5617; https://doi.org/10.3390/s25185617 - 9 Sep 2025
Abstract
Multivariate time series analysis presents significant challenges due to its dynamism, heterogeneity, and scalability. Given this, preprocessing is considered a crucial step to ensure analytical quality. However, this phase falls solely on the user without system support, resulting in wasted time, subjective decision-making, [...] Read more.
Multivariate time series analysis presents significant challenges due to its dynamism, heterogeneity, and scalability. Given this, preprocessing is considered a crucial step to ensure analytical quality. However, this phase falls solely on the user without system support, resulting in wasted time, subjective decision-making, and cognitive overload, and is prone to errors that affect the quality of the results. This situation reflects the lack of interactive visual analysis approaches that effectively integrate preprocessing with guidance mechanisms. The main objective of this work was to design and develop a guidance system for interactive visual analysis in multivariate time series preprocessing, allowing users to understand, evaluate, and adapt their decisions in this critical phase of the analytical workflow. To this end, we propose a new guide-based approach that incorporates recommendations, explainability, and interactive visualization. This approach is embodied in the GUIAVisWeb tool, which organizes a workflow through tasks, subtasks, and preprocessing algorithms; recommends appropriate components through consensus validation and predictive evaluation; and explains the justification for each recommendation through visual representations. The proposal was evaluated in two dimensions: (i) quality of the guidance, with an average score of 6.19 on the Likert scale (1–7), and (ii) explainability of the algorithm recommendations, with an average score of 5.56 on the Likert scale (1–6). In addition, a case study was developed with air quality data that demonstrated the functionality of the tool and its ability to support more informed, transparent, and effective preprocessing decisions. Full article
(This article belongs to the Section Intelligent Sensors)
►▼ Show Figures

Figure 1

12 pages, 2022 KB  
Article
Cor-Esc-25: A Low-Cost Prototype for Monitoring Brace Adherence and Pressure in Adolescent Idiopathic Scoliosis
by Pablo Ulldemolins, Pedro Rubio, Jorge Morales, Silvia Pérez, Jose Luis Bas, Paloma Bas, Mario Lamas, Jose María Baydal, Miquel Bovea, Carlos María Atienza and Teresa Bas
Sensors 2025, 25(18), 5616; https://doi.org/10.3390/s25185616 - 9 Sep 2025
Abstract
The treatment of adolescent idiopathic scoliosis (AIS) requires the use of orthopedic braces. However, few current designs provide real-time monitoring or inform clinicians about the precise adjustment of therapeutic pressure. The objective of this study is to develop a low-cost open-system prototype capable [...] Read more.
The treatment of adolescent idiopathic scoliosis (AIS) requires the use of orthopedic braces. However, few current designs provide real-time monitoring or inform clinicians about the precise adjustment of therapeutic pressure. The objective of this study is to develop a low-cost open-system prototype capable of providing future researchers with objective information regarding brace adherence and adjustment. For adherence evaluation, a market study was conducted to identify temperature-measuring devices and a custom system was developed to measure adjustment. Cor-Esc-25 was developed to monitor brace adherence using a non-invasive temperature sensor which connects via Bluetooth to the parents’ smartphone, which runs an app that uploads the data to an online platform accessible to clinicians. In addition, a custom-designed pressure sensing device was created. This system uses three patches connected to an acquisition board and are installed on the brace each time the patient visits the clinic. It connects to a customized application where clinicians can view all the information. Cor-Esc-25 represents a first step toward the creation of personalized consultations, where AIS treatment monitoring is based on objective criteria that consider both adherence and brace adjustment. Its design allows for easy integration into clinical settings, thereby improving the ability of researchers and clinicians to assess the effectiveness of brace treatment. Full article
(This article belongs to the Section Biosensors)
►▼ Show Figures

Figure 1

24 pages, 6054 KB  
Article
Construction of a High-Precision Underwater 3D Reconstruction System Based on Line Laser
by Hongyang Xu, Yongqing Zeng, Mingyu Qiu and Xiaoping Wang
Sensors 2025, 25(18), 5615; https://doi.org/10.3390/s25185615 - 9 Sep 2025
Abstract
This study presents a high-precision underwater 3D reconstruction system based on rotating laser scanning. The system adopts a modeling framework that combines air-based camera calibration with refraction compensation. A five-stage image preprocessing pipeline, followed by an adaptive locally weighted centroid (ALWC) algorithm, is [...] Read more.
This study presents a high-precision underwater 3D reconstruction system based on rotating laser scanning. The system adopts a modeling framework that combines air-based camera calibration with refraction compensation. A five-stage image preprocessing pipeline, followed by an adaptive locally weighted centroid (ALWC) algorithm, is employed to extract the laser stripe centerline with high accuracy. In addition, a synchronized feature extraction-based joint calibration method is introduced to simultaneously calibrate the light plane and the rotation axis. Resolution evaluation experiments demonstrate that the system achieves a spatial resolution of better than 0.6 mm in clear water at a distance of 1 m, and approximately 0.8 mm in turbid water conditions of 6 Nephelometric Turbidity Units (NTU), thereby verifying its reconstruction accuracy and robustness under varying water clarity. Full article
(This article belongs to the Section Optical Sensors)
►▼ Show Figures

Figure 1

14 pages, 970 KB  
Article
NeuroSkin®: AI-Driven Wearable Functional Electrical Stimulation for Post-Stroke Gait Recovery—A Multicenter Feasibility Study
by Amine Metani, Lana Popović-Maneski, Perrine Seguin and Julie Di Marco
Sensors 2025, 25(18), 5614; https://doi.org/10.3390/s25185614 - 9 Sep 2025
Abstract
(1) Background: Functional Electrical Stimulation (FES) is a recognized method for post-stroke gait rehabilitation but remains underutilized due to workflow complexity and the need for manual configuration. NeuroSkin®, a wearable FES system integrating AI-driven stimulation and sensor-based gait monitoring, was developed [...] Read more.
(1) Background: Functional Electrical Stimulation (FES) is a recognized method for post-stroke gait rehabilitation but remains underutilized due to workflow complexity and the need for manual configuration. NeuroSkin®, a wearable FES system integrating AI-driven stimulation and sensor-based gait monitoring, was developed to streamline clinical use by automating phase-specific, multi-muscle stimulation. (2) Methods: This retrospective multicenter feasibility study evaluated the integration of NeuroSkin® into routine inpatient rehabilitation. Fifteen subacute stroke patients across seven centers underwent 10 to 20 FES-assisted gait training sessions. Standardized assessments (10MWT, 6MWT, TUG, NFAC) were performed pre- and post-intervention. Therapists completed the System Usability Scale (SUS) questionnaire. (3) Results: All outcomes showed statistically significant improvement: walking speed and endurance increased by 70% and 171% respectively, TUG time decreased by 39%, and ambulation level improved by three NFAC categories. No adverse events were reported, and usability was rated as excellent (mean SUS score: 84.6). (4) Conclusions: NeuroSkin® was safely and effectively implemented in diverse clinical settings, demonstrating strong usability and promising functional benefits. These findings support the need for prospective controlled trials to confirm its clinical efficacy and broader applicability in stroke rehabilitation. Full article
(This article belongs to the Special Issue Sensors and Wearables for Rehabilitation)
►▼ Show Figures

Figure 1

21 pages, 873 KB  
Article
MBSCL-Net: Multi-Branch Spectral Network and Contrastive Learning for Next-Point-of-Interest Recommendation
by Sucheng Wang, Jinlai Zhang and Tao Zeng
Sensors 2025, 25(18), 5613; https://doi.org/10.3390/s25185613 - 9 Sep 2025
Abstract
Next-point-of-interest (POI) recommendation aims to model user preferences based on historical information to predict future mobility behavior, which has significant application value in fields such as urban planning, traffic management, and optimizing business decisions. However, existing methods often overlook the differences in location, [...] Read more.
Next-point-of-interest (POI) recommendation aims to model user preferences based on historical information to predict future mobility behavior, which has significant application value in fields such as urban planning, traffic management, and optimizing business decisions. However, existing methods often overlook the differences in location, time, and category information features, fail to fully utilize information from various modalities, and lack effective solutions for addressing users’ incidental behavior. Additionally, existing methods are somewhat lacking in capturing users’ personalized preferences. To address these issues, we propose a new method called Multi-Branch Spectral Network with Contrastive Learning (MBSCL-Net) for next-POI recommendation. We use a multihead attention mechanism to separately capture the distinct features of location, time, and category information, and then fuse the captured features to effectively integrate cross-modal features, avoid feature confusion, and achieve effective modeling of multi-modal information. We propose converting the time-domain information of user check-ins into frequency-domain information through Fourier transformation, directly enhancing the low-frequency signals of users’ periodic behavior and suppressing occasional high-frequency noise, thereby greatly alleviating noise interference caused by the introduction of too much information. Additionally, we introduced contrastive learning loss to distinguish user behavior patterns and better model personalized preferences. Extensive experiments on two real-world datasets demonstrate that MBSCL-Net outperforms state-of-the-art (SOTA) methods. Full article
(This article belongs to the Section Intelligent Sensors)
►▼ Show Figures

Figure 1

28 pages, 7302 KB  
Article
A Prototype of a Lightweight Structural Health Monitoring System Based on Edge Computing
by Yinhao Wang, Zhiyi Tang, Guangcai Qian, Wei Xu, Xiaomin Huang and Hao Fang
Sensors 2025, 25(18), 5612; https://doi.org/10.3390/s25185612 - 9 Sep 2025
Abstract
Bridge Structural Health Monitoring (BSHM) is vital for assessing structural integrity and operational safety. Traditional wired systems are limited by high installation costs and complexity, while existing wireless systems still face issues with cost, synchronization, and reliability. Moreover, cloud-based methods for extreme event [...] Read more.
Bridge Structural Health Monitoring (BSHM) is vital for assessing structural integrity and operational safety. Traditional wired systems are limited by high installation costs and complexity, while existing wireless systems still face issues with cost, synchronization, and reliability. Moreover, cloud-based methods for extreme event detection struggle to meet real-time and bandwidth constraints in edge environments. To address these challenges, this study proposes a lightweight wireless BSHM system based on edge computing, enabling local data acquisition and real-time intelligent detection of extreme events. The system consists of wireless sensor nodes for front-end acceleration data collection and an intelligent hub for data storage, visualization, and earthquake recognition. Acceleration data are converted into time–frequency images to train a MobileNetV2-based model. With model quantization and Neural Processing Unit (NPU) acceleration, efficient on-device inference is achieved. Experiments on a laboratory steel bridge verify the system’s high acquisition accuracy, precise clock synchronization, and strong anti-interference performance. Compared with inference on a general-purpose ARM CPU running the unquantized model, the quantized model deployed on the NPU achieves a 26× speedup in inference, a 35% reduction in power consumption, and less than 1% accuracy loss. This solution provides a cost-effective, reliable BSHM framework for small-to-medium-sized bridges, offering local intelligence and rapid response with strong potential for real-world applications. Full article
(This article belongs to the Section Fault Diagnosis & Sensors)
►▼ Show Figures

Figure 1

25 pages, 5128 KB  
Article
Non-Uniform Deployment of LWSN for Automated Railway Track Fastener Maintenance Robot and GA-LEACH Optimization
by Yanni Shen and Jianjun Meng
Sensors 2025, 25(18), 5611; https://doi.org/10.3390/s25185611 - 9 Sep 2025
Abstract
WSNs are an important component of the Internet of Things (IoT), and the research on their routing protocols has always been a hot topic in academia. However, in ARTFMRs’ collaborative operation along railway lines, there are common problems such as energy holes, high [...] Read more.
WSNs are an important component of the Internet of Things (IoT), and the research on their routing protocols has always been a hot topic in academia. However, in ARTFMRs’ collaborative operation along railway lines, there are common problems such as energy holes, high latency, and uneven energy consumption in LWSNs. To address these issues, this paper proposes a genetic algorithm-optimized energy-aware routing protocol (GAECRPQ). Firstly, a non-uniform deployment strategy of three-line isosceles triangles is constructed to enhance coverage and balance node distribution. Secondly, an energy–distance adaptive weighting mechanism based on a genetic algorithm is introduced for cluster head (CH) selection to reduce energy consumption in hotspots and extend the network lifetime. Finally, a task-aware TDMA dynamic time slot allocation method is proposed, which incorporates the real-time task status of ARTFMRs into communication scheduling to achieve priority transmission under latency constraints. The simulation results show, that compared with six unequal clustering protocols—EADUC, EAUCA, EBUC, EEUC, LEACH, and LEACH-C—the three-line isosceles triangle deployment has a wider coverage area, and the GAECRPQ protocol increases the network lifetime by 7.4%, the lifetime by 40%, and reduces the average latency by 55.77%, 53.07%, 47.61%, 39.87%, 52.08%, and 50.48%, respectively. This verifies that GAECRPQ has good performance in terms of network lifetime and energy utilization efficiency, providing a practical solution for the collaborative operation of ARTFMRs in railway maintenance scenarios. Full article
(This article belongs to the Section Sensors and Robotics)
►▼ Show Figures

Figure 1

24 pages, 6133 KB  
Article
A Smart System for Continuous Sitting Posture Monitoring, Assessment, and Personalized Feedback
by David Faith Odesola, Janusz Kulon, Shiny Verghese, Adam Partlow and Colin Gibson
Sensors 2025, 25(18), 5610; https://doi.org/10.3390/s25185610 - 9 Sep 2025
Abstract
Prolonged sitting and the adoption of unhealthy sitting postures have been a common issue generally seen among many adults and the working population in recent years. This alone has contributed to the alarming rise of various health issues, such as musculoskeletal disorders and [...] Read more.
Prolonged sitting and the adoption of unhealthy sitting postures have been a common issue generally seen among many adults and the working population in recent years. This alone has contributed to the alarming rise of various health issues, such as musculoskeletal disorders and a range of long-term health conditions. Hence, this study proposes the development of a novel smart-sensing chair system designed to analyze and provide actionable insights to help encourage better postural habits and promote well-being. The proposed system was equipped with two 32 × 32 pressure sensor mats, which were integrated into an office chair to facilitate the collection of postural data. Unlike traditional approaches that rely on generalized datasets collected from multiple healthy participants to train machine learning models, this study adopts a user-tailored methodology—collecting data from a single individual to account for their unique physiological characteristics and musculoskeletal conditions. The dataset was trained using five different machine learning models—Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Convolutional Neural Networks (CNN)—to classify 19 distinct sitting postures. Overall, CNN achieved the highest accuracy, with 98.29%. To facilitate user engagement and support long-term behavior change, we developed SitWell—an intelligent postural feedback platform comprising both mobile and web applications. The platform’s core features include sitting posture classification, posture duration analytics, and sitting quality assessment. Additionally, the platform integrates OpenAI’s GPT-4o Large Language Model (LLM) to deliver personalized insights and recommendations based on users’ historical posture data. Full article
(This article belongs to the Special Issue Advanced Non-Invasive Sensors: Methods and Applications—2nd Edition)
►▼ Show Figures

Figure 1

16 pages, 2632 KB  
Article
A Wavelet-Based Elevation Angle Selection Method for Soil Moisture Retrieval Using GNSS-IR
by Xilong Kou, Yan Zhou, Qian Chen, Haigang Pang and Bo Sun
Sensors 2025, 25(18), 5609; https://doi.org/10.3390/s25185609 - 9 Sep 2025
Abstract
Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) technology has emerged as a research hotspot in the remote sensing field in recent years due to its advantages of low cost and high precision for soil moisture monitoring. Addressing the issue that fixed elevation angle [...] Read more.
Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) technology has emerged as a research hotspot in the remote sensing field in recent years due to its advantages of low cost and high precision for soil moisture monitoring. Addressing the issue that fixed elevation angle intervals struggle to adapt to the varying signal characteristics of different satellites, this paper proposes an adaptive elevation angle interval selection method based on wavelet transform. This method utilizes wavelet transform to analyze the time-frequency characteristics of the residual Signal-to-Noise Ratio (SNR) signal, calculates the ratio sequence of the main frequency component strength to the noise component strength, and sets a threshold to automatically determine the retrieval elevation angle interval for each satellite, thereby improving the accuracy of feature parameter extraction. The results show the following: ① Compared to traditional fixed elevation angle intervals (5–20° and 5–30°), the proposed method significantly enhances soil moisture retrieval accuracy. ② For the averaged phase feature parameters calculated within the algorithm-selected intervals for all satellites, the R2 and RMSE are 0.925 and 0.55%, respectively, representing improvements of 3.1% and 14.2% compared to the original results. ③ For signals from low-quality reflection zones, R2 increased from 0.728 to 0.839 (a 13.2% improvement), while RMSE decreased from 1.045 to 0.806 (a 22.9% reduction). This method effectively adapts to the quality attenuation characteristics of satellite signals across different reflection zones, providing an optimized elevation angle interval selection strategy for GNSS-IR soil moisture retrieval. Full article
(This article belongs to the Section Smart Agriculture)
►▼ Show Figures

Figure 1

23 pages, 2646 KB  
Article
Model-Reconstructed RBFNN-DOB for FJR Trajectory Control with External Disturbances
by Tianmeng Li, Caiwen Ma, Yanbing Liang, Fan Wang and Zhou Ji
Sensors 2025, 25(18), 5608; https://doi.org/10.3390/s25185608 - 9 Sep 2025
Abstract
Parameter uncertainties and fluctuating disturbances have posed significant challenges to the smooth and precise control of Flexible Joint Robots (FJRs) in industrial environments. To mitigate such disturbances, Disturbance Observers (DOBs) are commonly employed; however, the model uncertainties inherent in FJR systems make accurate [...] Read more.
Parameter uncertainties and fluctuating disturbances have posed significant challenges to the smooth and precise control of Flexible Joint Robots (FJRs) in industrial environments. To mitigate such disturbances, Disturbance Observers (DOBs) are commonly employed; however, the model uncertainties inherent in FJR systems make accurate dynamic modeling challenging, and the efficacy of DOBs hinges heavily on the accuracy of the dynamic model, which limits their applicability to FJR control. This paper presents a hybrid RBFNN-based Disturbance Observer (RBFNNDOB) state feedback controller for FJRs. By combining a nominal model-based DOB with an RBFNN, this method effectively addresses the unknown dynamics of FJRs while simultaneously compensating for external time-varying disturbances. In this framework, an adaptive neural network weight update law is formulated using Lyapunov stability theory. This enables the RBFNN to selectively estimate the unmodeled uncertainties in FJR dynamics, thereby minimizing computational redundancy in model estimation while allowing dynamic compensation for residual uncertainties beyond the nominal model and DOB estimation errors—ultimately enhancing computational efficiency and achieving robust compensation for rapidly changing disturbances. The boundedness of the tracking error is proven using the Lyapunov approach, and experimental validation is conducted on the FJR system to confirm the efficacy of the proposed control method. Full article
(This article belongs to the Section Sensors and Robotics)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-22
Previous Issue
Back to TopTop