IF 4 3区综合性期刊

Sensors Pub Date : 2026-10-04 DOI: 10.3390/s26196292

Hyeongmuk Kang, Giseo Park, Sungmin Kim

{"title":"Development of an Autonomous Mobile Robot System Capable of Tracking Workers in a Factory Environment.","authors":"Hyeongmuk Kang, Giseo Park, Sungmin Kim","doi":"10.3390/s26196292","DOIUrl":"10.3390/s26196292","url":null,"abstract":"An autonomous mobile robot (AMR) that follows a worker can reduce the physical burden on the worker, but stable navigation remains difficult in the narrow and cluttered spaces of a factory, where the conventional dynamic window approach (DWA) tends to prefer high linear velocities and therefore turns with a large radius. This paper proposes a worker-following navigation system with three specific elements: a unique ArUco marker whose pose, obtained by solving the perspective-n-point problem, is transformed into the map frame to define the goal point; an A* search whose evaluation function includes the costmap cost, followed by waypoint pruning and cubic B-spline refinement of the resulting path; and an improved DWA that adds a corner-aware term regulating the linear velocity according to the heading change expected over the prediction horizon. The system is implemented on an AMR equipped with a 3-D light detection and ranging (LiDAR) and a camera, and is evaluated in a demonstration factory through two scenarios of 30 trials each. The proposed algorithm completes all 60 trials without a collision, whereas Nav2 and the fast marching method (FMM)-DWA record 22 and 17 collisions, respectively. The experimental results demonstrate that path-geometry-aware velocity control improves navigation stability and reduces collision risk in complex factory environments.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"26 19","pages":""},"PeriodicalIF":4.0,"publicationDate":"2026-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13667468/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149196307","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

Execution Velocity as a Task Constraint Modulates Motor Variability and Movement Complexity in Dynamic Resistance Exercise. 执行速度作为任务约束调节动态阻力运动中的运动变异性和运动复杂性。

IF 4 3区综合性期刊

Sensors Pub Date : 2026-10-04 DOI: 10.3390/s26196286

Miguel López-Fernández, Fernando García-Aguilar, Carla Caballero, Francisco J Moreno, Rafael Sabido

{"title":"Execution Velocity as a Task Constraint Modulates Motor Variability and Movement Complexity in Dynamic Resistance Exercise.","authors":"Miguel López-Fernández, Fernando García-Aguilar, Carla Caballero, Francisco J Moreno, Rafael Sabido","doi":"10.3390/s26196286","DOIUrl":"10.3390/s26196286","url":null,"abstract":"Execution velocity is a key constraint in resistance exercise, yet its influence on motor variability and movement complexity remains poorly understood. This study examined how different execution velocities modulate the magnitude and temporal structure of motor variability during a dynamic resistance task. Seventy-two resistance-trained participants performed parallel back squats at 50% of one-repetition maximum under three velocity conditions: preferred velocity, slow velocity, and maximal intended velocity. Acceleration signals were recorded using an inertial measurement unit placed at the lumbar region, while ground reaction force was obtained from a force platform. The magnitude of variability was quantified using standard deviation, whereas movement complexity was assessed through Fuzzy Entropy and Detrended Fluctuation Analysis. Repeated-measures ANOVAs revealed significant effects of execution velocity on standard deviation and Fuzzy Entropy in both measurement systems, with effect sizes of η2p = 0.937 and 0.738, respectively, for the IMU, and η2p = 0.882 and 0.712, respectively, for the force platform. Maximal velocity increased the magnitude of variability, whereas slow velocity produced higher complexity values, particularly for Fuzzy Entropy. Detrended Fluctuation Analysis showed a significant effect only in force-platform data (η2p = 0.182). These findings indicate that execution velocity modulates motor variability in distinct ways: faster executions amplify mechanical fluctuations, whereas slower executions increase the temporal complexity of the movement pattern. Therefore, velocity should be considered not only as a mechanical or physiological training variable, but also as a task constraint capable of shaping the organization of motor behavior during resistance exercise.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"26 19","pages":""},"PeriodicalIF":4.0,"publicationDate":"2026-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13667598/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149196597","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

An Artificial Intelligence Framework for Detection of Leukemia with Comparison Between Segmented and Non-Segmented Images. 基于分割与未分割图像比较的白血病检测人工智能框架。

IF 4 3区综合性期刊

Sensors Pub Date : 2026-10-04 DOI: 10.3390/s26196290

Rula Abdallat, Osama Al-Bataineh, Ali Mohammad Alqudah, Ausilah Alfraihat

{"title":"An Artificial Intelligence Framework for Detection of Leukemia with Comparison Between Segmented and Non-Segmented Images.","authors":"Rula Abdallat, Osama Al-Bataineh, Ali Mohammad Alqudah, Ausilah Alfraihat","doi":"10.3390/s26196290","DOIUrl":"10.3390/s26196290","url":null,"abstract":"Background: Accurate classification of Acute Lymphoblastic Leukemia (ALL) subtypes from peripheral blood smear (PBS) images using deep learning may support automated image-based analysis of this blood malignancy.Methods: We developed a custom lightweight Convolutional Neural Network (CNN) to classify white blood cells into four subtypes: Benign, Early Pre-B ALL, Pre-B ALL, and Pro-B ALL. We assessed performance using accuracy, ROC curves, and explainability techniques, including upsampled feature map activations, occlusion sensitivity, and SHAP-style explanation overlays, comparing original (Non-segmented) and HSV-Segmented images. To mitigate patient-level data leakage without explicit patient identifiers, we further used unsupervised K-means clustering of HSV color histograms to group 3256 images into 89 \"proxy-patient\" clusters. Consequently, we implemented rigorous subject-level grouped 5-fold cross-validation and Hold-Out protocols alongside standard image-level evaluations.Results: Under standard image-level evaluation, the model achieved 98.8% accuracy on non-segmented images and 91.3% on segmented images. Crucially, this performance advantage was maintained under strict subject-level cross-validation (97.9% vs. 89.7%), confirming the robustness of the findings against data leakage. Explainability visualizations demonstrated that HSV segmentation discarded vital contextual morphological cues, increasing confusion between closely related subtypes.Conclusions: A lightweight CNN can accurately classify ALL subtypes directly from raw PBS images. The evaluated HSV segmentation degraded performance by removing contextual information. This study underscores the necessity of subject-level evaluation in medical imaging and indicates that mandatory preprocessing should be empirically justified rather than assumed beneficial.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"26 19","pages":""},"PeriodicalIF":4.0,"publicationDate":"2026-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13667586/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149196468","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

Optical Smart-Wheel Sensing of Tire Deformation for Tire State and Load Estimation. 基于光学智能车轮的轮胎变形传感技术，用于轮胎状态和载荷估计。

IF 4 3区综合性期刊

Sensors Pub Date : 2026-10-03 DOI: 10.3390/s26196284

Halil Yahya Yeşilyurt, Özgen Akalın

{"title":"Optical Smart-Wheel Sensing of Tire Deformation for Tire State and Load Estimation.","authors":"Halil Yahya Yeşilyurt, Özgen Akalın","doi":"10.3390/s26196284","DOIUrl":"10.3390/s26196284","url":null,"abstract":"Tire-road interaction is increasingly important for situational awareness in autonomous vehicles and advanced driver-assistance systems, as tire deformation contains information that is related to both vehicle kinematics and tire forces. Optical sensing offers a direct means of observing this interaction with minimal influence on tire dynamics. In this study, an optical smart-wheel prototype was developed using a single high-speed camera rotating with the wheel and observing a circular-marker grid applied to the tire's inner liner. Camera calibration and distance-dependent imaging tests were used to support geometric correction and pixel-to-length conversion, after which the system was evaluated using static and on-road dynamic tests. Static drum calibration established a relationship between the diagonal-distance metric and vertical wheel load (R2 = 0.9992; RMSE = 33.37 N). Initial vehicle-level multi-point validation over 30 static conditions and loads up to approximately 3.92 kN yielded a prediction R2 of 0.9933 and an RMSE of 91.05 N. Dynamic tests revealed increasing longitudinal and lateral deformation with increasing maneuver speed and decreasing inflation pressure, together with direction-dependent lateral responses consistent with wheel-load transfer. Across the cases included in the cycle-variation analysis, the coefficients of variation ranged from 1.88% to 5.10% for longitudinal amplitude and from 6.08% to 19.98% for lateral peak deformation. These results demonstrate sensitivity to operating conditions and indicate a potential association between lateral deformation and slip angle, rather than constituting direct tire-force or slip-angle estimation. The proposed metric-based approach provides a promising lower-complexity alternative to full-field stereo-based deformation measurement for future real-time tire-state sensing and investigation of force-related deformation indicators.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"26 19","pages":""},"PeriodicalIF":4.0,"publicationDate":"2026-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13667706/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149196614","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

Securing AI-Driven Systems for Environmental Sustainability in IoT Applications: A Lightweight Message-Authentication Scheme Against Telemetry Poisoning. 保护物联网应用中环境可持续性的人工智能驱动系统：一种针对遥测中毒的轻量级消息认证方案。

IF 4 3区综合性期刊

Sensors Pub Date : 2026-10-03 DOI: 10.3390/s26196276

Aala Oqab Alsalem

{"title":"Securing AI-Driven Systems for Environmental Sustainability in IoT Applications: A Lightweight Message-Authentication Scheme Against Telemetry Poisoning.","authors":"Aala Oqab Alsalem","doi":"10.3390/s26196276","DOIUrl":"10.3390/s26196276","url":null,"abstract":"Machine-learning models for environmental monitoring are only as trustworthy as the field measurements that train them, yet raw or custom LoRa telemetry links-unlike a correctly configured LoRaWAN network-carry no application-layer authentication, letting any in-range transmitter inject fabricated readings and poison the training pipeline. We propose a lightweight, unidirectional, encryption-free scheme in which each message carries an HMAC-SHA-256 tag over the device identifier, a timestamp, a monotonic counter, and the sensor payload; the server accepts a message only if its tag verifies and its counter exceeds a durable, transactionally updated high-water mark, giving origin authentication, tamper evidence, and duplicate or stale rejection without encryption. For an ESP32-S3/Heltec reference implementation, device-server-reference HMAC agreement was confirmed on a published test vector, with zero false accepts or rejects across a 25,000-message four-class adversarial test; both checks ran in a host-side reference implementation of the device's algorithm, not on physical ESP32-S3 hardware. A ten-seed illustrative poisoning study on two public environmental datasets shows a value-based defence can increase PM2.5 forecast RMSE by up to about 104% by discarding genuine extremes, whereas our scheme holds the clean baseline exactly, since forged rows are rejected before training. The tag grows an example message from 34 to 99 bytes (about 2.9×) and roughly doubles airtime (about 2.2×); per-message CPU time and energy are not quantified here. Under independent per-device keys and rate limits, partial key compromise bounds admitted forged traffic to the compromised devices' share of total traffic.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"26 19","pages":""},"PeriodicalIF":4.0,"publicationDate":"2026-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13667637/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149196643","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 Comprehensive Review on Self-Powered Wearable Photonic Sensors: Materials, Photophysics, and System Integration. 自供电可穿戴光子传感器综述：材料、光物理和系统集成。

IF 4 3区综合性期刊

Sensors Pub Date : 2026-10-03 DOI: 10.3390/s26196277

Nikolay L Kazanskiy, Nikita V Golovastikov, Svetlana N Khonina

{"title":"A Comprehensive Review on Self-Powered Wearable Photonic Sensors: Materials, Photophysics, and System Integration.","authors":"Nikolay L Kazanskiy, Nikita V Golovastikov, Svetlana N Khonina","doi":"10.3390/s26196277","DOIUrl":"10.3390/s26196277","url":null,"abstract":"Self-powered wearable photonic sensors enable energy-autonomous operation by integrating optical sensing, energy harvesting, and signal transduction within a unified platform. These systems exploit photophysical mechanisms such as photovoltaic, photogating, and triboelectric effects to convert ambient or body-derived energy into electrical signals while simultaneously performing sensing. Advances in hybrid semiconductors, two-dimensional materials, and nanocomposites have significantly improved light absorption, carrier transport, and mechanical compliance, enabling integration into flexible and textile-based wearable formats. Device architectures have evolved from simple junctions to heterostructured and tandem configurations that enhance spectral selectivity and energy utilization under variable illumination. However, reliable operation under low-intensity and dynamically changing conditions remains a key challenge, particularly in balancing sensing performance with energy autonomy. This review analyzes the interplay between materials, photophysical mechanisms, device architectures, and system-level design, with emphasis on energy harvesting-sensing co-optimization. Challenges related to mechanical stability, signal reliability, and real-world deployment are discussed, alongside emerging solutions based on adaptive photonic systems and intelligent data processing. These insights provide a framework for next-generation wearable photonic platforms for healthcare, environmental monitoring, and human-machine interfaces.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"26 19","pages":""},"PeriodicalIF":4.0,"publicationDate":"2026-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13667529/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149196258","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

Mitigating Spatio-Temporal Forgetting in Federated Continual Learning with Dynamic-Domain Clients. 动态域客户端联合持续学习中的时空遗忘。

IF 4 3区综合性期刊

Sensors Pub Date : 2026-10-03 DOI: 10.3390/s26196273

Dairao He, Ji Wang, Weidong Bao

{"title":"Mitigating Spatio-Temporal Forgetting in Federated Continual Learning with Dynamic-Domain Clients.","authors":"Dairao He, Ji Wang, Weidong Bao","doi":"10.3390/s26196273","DOIUrl":"10.3390/s26196273","url":null,"abstract":"Distributed sensing systems increasingly rely on geographically distributed devices that collect data under different operating conditions. Federated continual learning (FCL) enables a global model to be trained across distributed sensing clients whose local data evolve over time, while preserving previously acquired knowledge. Existing FCL studies have mainly addressed continual task evolution or class-based client heterogeneity, while federated domain-incremental learning has investigated adaptation to changing domains under a shared label space. Less attention has been paid to scenarios where continual task evolution and domain-shifted client participation occur simultaneously, leading to coupled temporal and spatial interference. In this paper, we study a dynamic-domain federated continual learning setting, where new clients share the same label space with source clients but introduce shifted feature distributions during training. This setting reveals a challenging form of spatio-temporal catastrophic forgetting: the model must learn evolving class-incremental tasks while preventing new-domain knowledge injection from degrading source-domain performance. To address this problem, we propose STP-FCL, a coordinated client-server framework. On the client side, STP-FCL preserves historical task semantics and source-domain discriminative structures through source-aware prototype-space optimization, reducing representation drift under evolving tasks and domains. On the server side, STP-FCL designs domain-projected aggregation to remove conflicting components from new-domain updates and adaptively control their fusion weight. Experiments under dynamic-domain federated continual learning scenarios show that STP-FCL achieves stronger source-domain knowledge retention and higher mixed-domain accuracy than representative baselines, with a trade-off in target-domain accuracy.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"26 19","pages":""},"PeriodicalIF":4.0,"publicationDate":"2026-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13667711/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149195963","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

Event-Based Bidirectional People Counting Using a Spatiotemporal Neural Network and a Single 77 GHz MIMO FMCW Radar. 基于时空神经网络和单77ghz MIMO FMCW雷达的基于事件的双向人员计数。

IF 4 3区综合性期刊

Sensors Pub Date : 2026-10-03 DOI: 10.3390/s26196270

Anna Ślesicka, Adam Kawalec, Błażej Ślesicki

{"title":"Event-Based Bidirectional People Counting Using a Spatiotemporal Neural Network and a Single 77 GHz MIMO FMCW Radar.","authors":"Anna Ślesicka, Adam Kawalec, Błażej Ślesicki","doi":"10.3390/s26196270","DOIUrl":"10.3390/s26196270","url":null,"abstract":"Accurate bidirectional people counting at room entrances is essential for reliable occupancy estimation, yet radar-based methods remain challenged when reflections from multiple individuals temporarily merge or when people move simultaneously in opposite directions. This study presents a hybrid event-based method for bidirectional people counting using a single 77 GHz multiple-input multiple-output frequency-modulated continuous-wave radar. Unlike conventional tracking-based approaches, the proposed method treats a complete doorway passage as one event and does not require continuous individual trajectories or frame-to-frame data association. Each event is represented as a sequence of three-dimensional point clouds with radial velocity information. A PointNet encoder extracts frame-level spatial representations, a bidirectional gated recurrent unit models their temporal evolution, and an attention mechanism emphasizes the most informative event phases. Separate output heads estimate the numbers of entering and exiting individuals, while an auxiliary head identifies the event type. Predictions are accepted using explicit confidence and geometric-consistency criteria. The primary dataset comprised 550 labeled events and an additional 100 events recorded in five continuous sequences. In the held-out test session, entry- and exit-count accuracies were 95.5% and 94.5%, respectively, while joint entry-exit count accuracy reached 92.7%. The mean absolute error in occupancy change was 0.06 person per event, and the mean absolute occupancy error across the continuous sequences was 0.10 person. The proposed method exceeded geometric rules and density-based clustering combined with tracking in joint count accuracy by 37.2 and 24.5 percentage points, respectively. On an independent laboratory dataset comprising 100 events, the model achieved a joint count accuracy of 91.0% without retraining, fine-tuning, or parameter adaptation, providing preliminary evidence of cross-environment generalization.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"26 19","pages":""},"PeriodicalIF":4.0,"publicationDate":"2026-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13667633/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149196555","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

Applications of Machine Learning in Automotive Engineering: Editorial to the Special Issue. 机器学习在汽车工程中的应用：特刊编辑。

IF 4 3区综合性期刊

Sensors Pub Date : 2026-10-03 DOI: 10.3390/s26196283

Hwan-Sik Yoon

引用次数: 0

Bayesian Variational Neural Architecture Search for Lightweight Weld Seam Feature Point Detection in Laser Vision Systems. 基于贝叶斯变分神经结构的轻型激光视觉焊缝特征点检测。

IF 4 3区综合性期刊

Sensors Pub Date : 2026-10-03 DOI: 10.3390/s26196282

Wenjia Mou, Yulin Wang, Chunyuan Liu, Yanbiao Zou

{"title":"Bayesian Variational Neural Architecture Search for Lightweight Weld Seam Feature Point Detection in Laser Vision Systems.","authors":"Wenjia Mou, Yulin Wang, Chunyuan Liu, Yanbiao Zou","doi":"10.3390/s26196282","DOIUrl":"10.3390/s26196282","url":null,"abstract":"In laser vision-based robotic welding, the seam feature point must be located, under strong arc-light and spatter interference, in every frame acquired while the weld is being made, so that the torch can be steered in real time; the detector must therefore keep pace with the camera on the modest processor of an industrial controller. Conventional deep learning models encounter structural redundancy and high computational latency under this constraint. To address these limitations, this paper proposes a lightweight object detection model, whose box-center output is mapped to the weld seam feature point, optimized via Bayesian variational neural architecture search (BayeNAS), in which architecture parameters are modeled as Gaussian distributions and updated through natural-gradient variational inference. A novel dual-selection optimization strategy is introduced to jointly search for optimal candidate operators and network topology branches, achieving an explicit balance between model complexity and hardware latency. Furthermore, an in-search channel pruning strategy is incorporated to compress the search space and prevent the combinatorial growth of the channel configuration space. Comparative analysis and real-world welding experiments demonstrate that the proposed model achieves a high processing speed of 78 frames per second (FPS) on a legacy central processing unit (CPU)-above the 60 fps acquisition rate of the sensor-while maintaining a mean positioning error within 0.15 mm on the measurement plane. These results demonstrate that the proposed model achieves detection accuracy comparable to heavyweight detectors while offering an order-of-magnitude advantage in inference speed and model size, validating its suitability for low-cost industrial deployment.","PeriodicalId":21698,"journal":{"name":"Sensors","volume":"26 19","pages":""},"PeriodicalIF":4.0,"publicationDate":"2026-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13667476/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149196289","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