IF 3.5 3区综合性期刊

Sensors Pub Date : 2025-09-19 DOI: 10.3390/s25185852

Zeev Fradkin, Maxim Piscklich, Moshe Zohar, Mark Auslender

{"title":"Numerical Study of Incidence Angle-Tuned, Guided-Mode Resonant, Metasurfaces-Based Sensors for Glucose and Blood-Related Analytes Detection.","authors":"Zeev Fradkin, Maxim Piscklich, Moshe Zohar, Mark Auslender","doi":"10.3390/s25185852","DOIUrl":"10.3390/s25185852","url":null,"abstract":"In optical one-dimensional grating-on-layer planar structures, an optical resonance occurs when the incident light wave becomes phase-matched to a leaky waveguide mode excited in the layer underneath the grating by an appropriate tuning of the grating periodicity. Changing the refractive indices of the grating's constituents, and/or thickness, changes the resonance frequency. In the case of a two-dimensional grating atop such a smooth layer, a similar and also cavity-mode resonance can occur. This idea has straightforward usage in diverse optical sensor applications. In this study, a novel guided-mode resonance sensor design for detecting glucose and hemoglobin in minute concentrations at a wide range of incidence angles is presented. In this design, materials of the grating, such as a polymer and cesium-lead halide with a perovskite crystal structure, are examined, which will allow flexible, low-cost fabrication by soft-lithography/imprint-lithography methods. The sensitivity, figure of merit, and quality factor are reported for one- and two-dimensional grating structures. The simulations performed are based on rigorous coupled-wave analysis. Optical resonance quality factor of ∼5·105 is achieved at oblique incidence for a structure comprising a one-dimensional grating etched in a poly-vinylidene chloride layer atop a silicon nitride waveguide layer on a substrate. Record values of the above-noted characteristics are achieved with a synergetic interplay of the materials, structural dimensions, incidence angle, polarization, and grating geometry.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"25 18","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12473734/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145178307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cross-Scanner Harmonization of AI/DL Accelerated Quantitative Bi-Parametric Prostate MRI. AI/DL加速定量双参数前列腺MRI的交叉扫描仪协调。

IF 3.5 3区综合性期刊

Sensors Pub Date : 2025-09-19 DOI: 10.3390/s25185858

Dariya Malyarenko, Scott D Swanson, Jacob Richardson, Suzan Lowe, James O'Connor, Yun Jiang, Reve Chahine, Shane A Wells, Thomas L Chenevert

{"title":"Cross-Scanner Harmonization of AI/DL Accelerated Quantitative Bi-Parametric Prostate MRI.","authors":"Dariya Malyarenko, Scott D Swanson, Jacob Richardson, Suzan Lowe, James O'Connor, Yun Jiang, Reve Chahine, Shane A Wells, Thomas L Chenevert","doi":"10.3390/s25185858","DOIUrl":"10.3390/s25185858","url":null,"abstract":"Clinical application of AI/DL-aided acquisitions for quantitative bi-parametric (q-bp)MRI requires validation and harmonization across vendor platforms. An AI/DL-accelerated q-bpMRI, including 5-echo T2 and 4-b-value apparent diffusion coefficient (ADC) mapping, was implemented on two 3T clinical scanners by two vendors alongside the qualitative standard-of-care (SOC) MRI protocols for six patients with biopsy-confirmed prostate cancer (PCa). AI/DL versus SOC bpMRI image quality was compared for MR-visible PCa lesions on a 4-point Likert-like scale. Quantitative validation and protocol bias assessment were performed using a multiparametric phantom with reference T2 and diffusion kurtosis values mimicking prostate tissue ranges. Six-minute q-bpMRI achieved acceptable diagnostic quality comparable to the SOC. Better SNR was observed for DL/AI versus SOC ADC with method-dependent distortion susceptibility and resolution enhancement. The measured biases were unaffected by AI/DL reconstruction and related to acquisition protocol parameters: constant for spin-echo T2 (-7 ms to +5 ms) and ADC (4b-fit: -0.37 µm2/ms and 2b-fit: -0.19 µm2/ms), while nonlinear for echo-planar T2 (-37 ms to +14 ms). Measured phantom ADC bias dependence on b-value range was consistent with that observed for PCa lesions. Bias correction harmonized lesion T2 and ADC values across different AI/DL-aided q-bpMRI acquisitions. The developed workflow enables harmonization of AI/DL-accelerated quantitative T2 and ADC mapping in multi-vendor clinical settings.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"25 18","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12473519/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145178149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

3D-Printed Wearable Sensors for the Identification of Shoulder Movement Planes. 用于肩部运动平面识别的3d打印可穿戴传感器。

IF 3.5 3区综合性期刊

Sensors Pub Date : 2025-09-19 DOI: 10.3390/s25185853

Alfredo Dimo, Umile Giuseppe Longo, Pieter D'Hooghe, Alessandro de Sire, Rocco Papalia, Emiliano Schena, Daniela Lo Presti

{"title":"3D-Printed Wearable Sensors for the Identification of Shoulder Movement Planes.","authors":"Alfredo Dimo, Umile Giuseppe Longo, Pieter D'Hooghe, Alessandro de Sire, Rocco Papalia, Emiliano Schena, Daniela Lo Presti","doi":"10.3390/s25185853","DOIUrl":"10.3390/s25185853","url":null,"abstract":"Rotator cuff injuries are a leading cause of shoulder disability, directly impacting joint mobility and overall quality of life. Effective recovery in these patients depends not only on surgical intervention, when necessary, but also on accurate and continuous monitoring of joint movements during rehabilitation, especially across multiple anatomical planes. Traditional tools, such as clinical assessments or motion capture systems, are often subjective or expensive and impractical for routine use. In this context, wearable devices are emerging as a viable alternative, offering the ability to collect real-time, non-invasive, and repeatable data, both in clinical and home settings. This study presents innovative wearable sensors, developed through 3D printing and integrated with fiber Bragg grating technology, designed to detect the shoulder's planes of motion (sagittal, scapular, and frontal) during flexion-extension movements. Two wearable sensors made of thermoplastic polyurethane (TPU 85A and 95A) were fabricated and subjected to metrological characterization, including strain and temperature sensitivity, hysteresis error, and tear resistance, and tested on eight healthy volunteers. The results demonstrated high discriminative ability, with sensitivity values up to 0.76 nm/mε and low hysteresis errors. The proposed system represents a promising, cost-effective, and customizable solution for motion monitoring during shoulder rehabilitation.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"25 18","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12473567/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145177997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Secure and Decentralized Hybrid Multi-Face Recognition for IoT Applications. 物联网应用的安全和分散混合多人脸识别。

IF 3.5 3区综合性期刊

Sensors Pub Date : 2025-09-19 DOI: 10.3390/s25185880

Erëza Abdullahu, Holger Wache, Marco Piangerelli

{"title":"Secure and Decentralized Hybrid Multi-Face Recognition for IoT Applications.","authors":"Erëza Abdullahu, Holger Wache, Marco Piangerelli","doi":"10.3390/s25185880","DOIUrl":"10.3390/s25185880","url":null,"abstract":"The proliferation of smart environments and Internet of Things (IoT) applications has intensified the demand for efficient, privacy-preserving multi-face recognition systems. Conventional centralized systems suffer from latency, scalability, and security vulnerabilities. This paper presents a practical hybrid multi-face recognition framework designed for decentralized IoT deployments. Our approach leverages a pre-trained Convolutional Neural Network (VGG16) for robust feature extraction and a Support Vector Machine (SVM) for lightweight classification, enabling real-time recognition on resource-constrained devices such as IoT cameras and Raspberry Pi boards. The purpose of this work is to demonstrate the feasibility and effectiveness of a lightweight hybrid system for decentralized multi-face recognition, specifically tailored to the constraints and requirements of IoT applications. The system is validated on a custom dataset of 20 subjects collected under varied lighting conditions and facial expressions, achieving an average accuracy exceeding 95% while simultaneously recognizing multiple faces. Experimental results demonstrate the system's potential for real-world applications in surveillance, access control, and smart home environments. The proposed architecture minimizes computational load, reduces dependency on centralized servers, and enhances privacy, offering a promising step toward scalable edge AI solutions.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"25 18","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12473792/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145178329","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

TFP-YOLO: Obstacle and Traffic Sign Detection for Assisting Visually Impaired Pedestrians. TFP-YOLO：辅助视障行人的障碍物和交通标志检测。

IF 3.5 3区综合性期刊

Sensors Pub Date : 2025-09-19 DOI: 10.3390/s25185879

Zhiwei Zheng, Jin Cheng, Fanghua Jin

{"title":"TFP-YOLO: Obstacle and Traffic Sign Detection for Assisting Visually Impaired Pedestrians.","authors":"Zhiwei Zheng, Jin Cheng, Fanghua Jin","doi":"10.3390/s25185879","DOIUrl":"10.3390/s25185879","url":null,"abstract":"With the increasing demand for intelligent mobility assistance among the visually impaired, machine guide dogs based on computer vision have emerged as an effective alternative to traditional guide dogs, owing to their flexible deployment and scalability. To enhance their visual perception capabilities in complex urban environments, this paper proposes an improved YOLOv8-based detection algorithm, termed TFP-YOLO, designed to recognize traffic signs such as traffic lights and crosswalks, as well as small obstacle objects including pedestrians and bicycles, thereby improving the target detection performance of machine guide dogs in complex road scenarios. The proposed algorithm incorporates a Triplet Attention mechanism into the backbone network to strengthen the perception of key regions, and integrates a Triple Feature Encoding (TFE) module to achieve collaborative extraction of both local and global features. Additionally, a P2 detection head is introduced to improve the accuracy of small object detection, particularly for traffic lights. Furthermore, the WIoU loss function is adopted to enhance training stability and the model's generalization capability. Experimental results demonstrate that the proposed algorithm achieves a detection accuracy of 93.9% and a precision of 90.2%, while reducing the number of parameters by 17.2%. These improvements significantly enhance the perception performance of machine guide dogs in identifying traffic information and obstacles, providing strong technical support for subsequent path planning and embedded deployment, and demonstrating considerable practical application value.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"25 18","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12473299/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145178342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Hybrid Deep Learning Framework for Fault Diagnosis in Milling Machines. 铣床故障诊断的混合深度学习框架。

IF 3.5 3区综合性期刊

Sensors Pub Date : 2025-09-19 DOI: 10.3390/s25185866

Muhammad Farooq Siddique, Wasim Zaman, Muhammad Umar, Jae-Young Kim, Jong-Myon Kim

{"title":"A Hybrid Deep Learning Framework for Fault Diagnosis in Milling Machines.","authors":"Muhammad Farooq Siddique, Wasim Zaman, Muhammad Umar, Jae-Young Kim, Jong-Myon Kim","doi":"10.3390/s25185866","DOIUrl":"10.3390/s25185866","url":null,"abstract":"This paper presents a hybrid fault-diagnosis framework for milling cutting tools designed to address three persistent challenges in industrial monitoring: noisy vibration signals, limited fault labels, and variability across operating conditions. The framework begins by removing baseline drift from raw signals to improve the signal-to-noise ratio. Logarithmic continuous wavelet scalograms are then constructed to provide precise time-frequency localization and reveal fault-related harmonics. To enhance feature clarity, a Canny edge operator is applied, suppressing minor artifacts and reducing intra-class variation so that key diagnostic structures are emphasized. Feature representation is obtained through a dual-branch encoder, where one pathway captures localized patterns while the other preserves long-range dependencies, resulting in compact and discriminative fault descriptors. These descriptors are integrated by an ensemble decision mechanism that assigns validation-guided weights to individual learners, ensuring reliable fault identification, improved robustness under noise, and stable performance across diverse operating conditions. Experimental validation on real-world cutting tool data demonstrates an accuracy of 99.78%, strong resilience to environmental noise, and consistent diagnostic performance under variable conditions. The framework remains lightweight, scalable, and readily deployable, providing a practical solution for high-precision tool fault diagnosis in data-constrained industrial environments.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"25 18","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12473162/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145178054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AI-Assisted Dynamic Port and Waveform Switching for Enhancing UL Coverage in 5G NR. ai辅助的动态端口和波形切换增强5G NR的UL覆盖。

IF 3.5 3区综合性期刊

Sensors Pub Date : 2025-09-19 DOI: 10.3390/s25185875

Alejandro Villena-Rodríguez, Francisco J Martín-Vega, Gerardo Gómez, Mari Carmen Aguayo-Torres, José Outes-Carnero, F Yak Ng-Molina, Juan Ramiro-Moreno

{"title":"AI-Assisted Dynamic Port and Waveform Switching for Enhancing UL Coverage in 5G NR.","authors":"Alejandro Villena-Rodríguez, Francisco J Martín-Vega, Gerardo Gómez, Mari Carmen Aguayo-Torres, José Outes-Carnero, F Yak Ng-Molina, Juan Ramiro-Moreno","doi":"10.3390/s25185875","DOIUrl":"10.3390/s25185875","url":null,"abstract":"The uplink of 5G networks allows selecting the transmit waveform between cyclic prefix orthogonal frequency division multiplexing (CP-OFDM) and discrete Fourier transform spread OFDM (DFT-S-OFDM) to cope with the diverse operational conditions of the power amplifiers (PAs) in different user equipment (UEs). CP-OFDM leads to higher throughput when the PAs are operating in their linear region, which is mostly the case for cell-interior users, whereas DFT-S-OFDM is more appealing when PAs are exhibiting non-linear behavior, which is associated with cell-edge users. Therefore, existing waveform selection solutions rely on predefined signal-to-noise ratio (SNR) thresholds that are computed offline. However, the varying user and channel dynamics, as well as their interactions with power control, require an adaptable threshold selection mechanism. In this paper, we propose an intelligent waveform-switching mechanism based on deep reinforcement learning (DRL) that learns optimal switching thresholds for the current operational conditions. In this proposal, a learning agent aims at maximizing a function built using available throughput percentiles in real networks. Said percentiles are weighted so as to improve the cell-edge users' service without dramatically reducing the cell average. Aggregated measurements of signal-to-noise ratio (SNR) and timing advance (TA), available in real networks, are used in the procedure. In addition, the solution accounts for the switching cost, which is related to the interruption of the communication after every switch due to implementation issues, which has not been considered in existing solutions. Results show that our proposed scheme achieves remarkable gains in terms of throughput for cell-edge users without degrading the average throughput.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"25 18","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12473732/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145178156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fault Recovery Through Online Adaptation of Boolean Network Robots. 基于布尔网络机器人在线自适应的故障恢复。

IF 3.5 3区综合性期刊

Sensors Pub Date : 2025-09-19 DOI: 10.3390/s25185849

Paolo Baldini, Michele Braccini, Andrea Roli

引用次数: 0

CIRS: A Multi-Agent Machine Learning Framework for Real-Time Accident Detection and Emergency Response. 实时事故检测和应急响应的多智能体机器学习框架。

IF 3.5 3区综合性期刊

Sensors Pub Date : 2025-09-19 DOI: 10.3390/s25185845

Sadaf Ayesha, Aqsa Aslam, Muhammad Hassan Zaheer, Muhammad Burhan Khan

{"title":"CIRS: A Multi-Agent Machine Learning Framework for Real-Time Accident Detection and Emergency Response.","authors":"Sadaf Ayesha, Aqsa Aslam, Muhammad Hassan Zaheer, Muhammad Burhan Khan","doi":"10.3390/s25185845","DOIUrl":"10.3390/s25185845","url":null,"abstract":"Road traffic accidents remain a leading cause of fatalities worldwide, and the consequences are considerably worsened by delayed detection and emergency response. Although several machine learning-based approaches have been proposed, accident detection systems are not widely deployed, and most existing solutions fail to handle the growing complexity of modern traffic environments. This study introduces Collaborative Intelligence for Road Safety (CIRS), a novel, multi-agent, machine-learning-based framework designed for real-time accident detection, semantic scene understanding, and coordinated emergency response. Each agent in CIRS is designed for a distinct role perception, classification, description, localization, and decision-making, working collaboratively to enhance situational awareness and response efficiency. These agents integrate advanced models: YOLOv11 for high-accuracy accident detection and VideoLLaMA3 for contextual-rich scene description. CIRS bridges the gap between low-level visual analysis and high-level situational awareness. Extensive evaluation on a custom dataset comprising (5200 accident, 4800 nonaccident) frames demonstrates the effectiveness of the proposed approach. YOLOv11 achieves a top-1 accuracy of 86.5% and a perfect top-5 accuracy of 100%, ensuring reliable real-time detection. VideoLLaMA3 outperforms other vision-language models with superior factual accuracy and fewer hallucinations, generating strong results in the metrics of BLEU (0.0755), METEOR (0.2258), and ROUGE-L (0.3625). The decentralized multi-agent architecture of CIRS enables scalability, reduced latency, and the timely dispatch of emergency services while minimizing false positives.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"25 18","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12473270/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145178127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-Domain CoP Feature Analysis of Functional Mobility for Parkinson's Disease Detection Using Wearable Pressure Insoles. 基于可穿戴压力鞋垫的帕金森病检测功能活动的多域CoP特征分析

IF 3.5 3区综合性期刊

Sensors Pub Date : 2025-09-19 DOI: 10.3390/s25185859

Thathsara Nanayakkara, H M K K M B Herath, Hadi Sedigh Malekroodi, Nuwan Madusanka, Myunggi Yi, Byeong-Il Lee

{"title":"Multi-Domain CoP Feature Analysis of Functional Mobility for Parkinson's Disease Detection Using Wearable Pressure Insoles.","authors":"Thathsara Nanayakkara, H M K K M B Herath, Hadi Sedigh Malekroodi, Nuwan Madusanka, Myunggi Yi, Byeong-Il Lee","doi":"10.3390/s25185859","DOIUrl":"10.3390/s25185859","url":null,"abstract":"Parkinson's disease (PD) impairs balance and gait through neuromotor dysfunction, yet conventional assessments often overlook subtle postural deficits during dynamic tasks. This study evaluated the diagnostic utility of center-of-pressure (CoP) features captured by pressure-sensing insoles during the Timed Up and Go (TUG) test. Using 39 PD and 38 control participants from the recently released open-access WearGait-PD dataset, the authors extracted 144 CoP features spanning positional, dynamic, frequency, and stochastic domains, including per-foot averages and asymmetry indices. Two scenarios were analyzed: the complete TUG and its 3 m walking segment. Model development followed a fixed protocol with a single participant-level 80/20 split; sequential forward selection with five-fold cross-validation optimized the number of features within the training set. Five classifiers were evaluated: SVM-RBF, logistic regression (LR), random forest (RF), k-nearest neighbors (k-NN), and Gaussian naïve Bayes (NB). LR performed best on the held-out test set (accuracy = 0.875, precision = 1.000, recall = 0.750, F1 = 0.857, ROC-AUC = 0.921) using a 23-feature subset. RF and SVM-RBF each achieved 0.812 accuracy. In contrast, applying the identical pipeline to the 3 m walking segment yielded lower performance (best model: k-NN, accuracy = 0.688, F1 = 0.615, ROC-AUC = 0.734), indicating that the multi-phase TUG task captures PD-related balance deficits more effectively than straight walking. All four feature families contributed to classification performance. Dynamic and frequency-domain descriptors, often appearing in both average and asymmetry form, were most consistently selected. These features provided robust magnitude indicators and offered complementary insights into reduced control complexity in PD.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"25 18","pages":""},"PeriodicalIF":3.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12473803/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145178236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sensors最新文献