IEEE Open Journal of Instrumentation and Measurement最新文献

{"title":"Postprocessing Time-Alignment Method of Power Angular Delay Profile for Automated mmWave WPAN Channel Sounding","authors":"Hiroaki Endo;Yusuke Koda;Norichika Ohmi;Hiroshi Harada","doi":"10.1109/OJIM.2026.3676164","DOIUrl":"https://doi.org/10.1109/OJIM.2026.3676164","url":null,"abstract":"Accurate propagation channel measurements and modeling—encompassing both angular and delay characteristics—are fundamental to the design of millimeter wave (mmWave) communication systems. Accordingly, steerable directional antennas and strict time-synchronization are commonly employed to capture power angle delay profiles (PADPs) that share synchronized standard time axes. However, time synchronization requires labor-intensive management to ensure clock synchronization during or after measurements, which hinders the construction of massive propagation channel databases. Thus, this study aimed to develop a streamlined channel sounding system by fully automating the PADP acquisition flow. First, an automated data-driven postprocessing method is proposed to reconstruct a time-synchronized PADP from an unsynchronized PADP, thereby discarding the requirement for managing clock synchronization. This approach is well-suited for simple channel sounding setups in mmWave wireless personal area network (WPAN) scenarios. The proposed method was evaluated through raytracing simulations tailored to WPAN systems with a comprehensive analysis of the impact of various measurement parameters. Simulation results demonstrated that the method achieved a time-alignment error of less than 1 ns in over 99% of cases across various receiver (Rx) locations and Rx antenna rotation angles in noise-free environments. Moreover, a real-world experimental evaluation revealed that the time-aligned PADP obtained using the proposed method reached an alignment root-mean-square error (RMSE) below 1 ns. These findings strongly demonstrate the feasibility of the proposed method for channel sounding in mmWave WPAN systems.","PeriodicalId":100630,"journal":{"name":"IEEE Open Journal of Instrumentation and Measurement","volume":"5 ","pages":"1-14"},"PeriodicalIF":1.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11449231","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147696197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ANEP: Adaptive Newton Ego Planner for Multiwaypoint UAV Trajectory Optimization in Constrained Environments","authors":"Tiancheng Liu;Ling Bai;David Zou;Zheng Liu","doi":"10.1109/OJIM.2026.3693424","DOIUrl":"https://doi.org/10.1109/OJIM.2026.3693424","url":null,"abstract":"Roof gutters are highly susceptible to the accumulation of debris, such as fallen leaves, which can block drain outlets and pose a significant threat to the structural integrity of a building. Traditional high-altitude cleaning methods primarily rely on manual operations with ropes, ladders, and extended tools. These methods are not only inherently dangerous but also inefficient, making them inadequate for building maintenance. The use of drones offers a promising solution for high-altitude cleaning. However, drones still face significant technical challenges in ensuring precise arrival at target points after detecting debris while simultaneously navigating multipoint obstacle avoidance during flight. In particular, autonomous roof gutter cleaning requires robust multistage trajectory planning in a cluttered environment, where the state estimation and waypoint accuracy can be degraded by the noises and inaccuracies from sensing and Global Navigation Satellite System (GNSS). This article presents an Adaptive Newton Ego Planner (ANEP) framework for multiwaypoint trajectory optimization under constrained environments. The proposed ANEP integrates a novel adaptive Newton–Raphson-based optimizer (ANRBO) to enhance exploration and prevent premature convergence during online trajectory refinement. The optimizer leverages Newton–Raphson search rules (NRSRs) and a trap avoidance operator (TAO), while an online dynamic adaptation mechanism enables the efficient multipoint exploration and real-time trajectory optimization. In this article, we focus on trajectory planning and optimization. Perception, e.g., debris detection, and cleaning actuation were not evaluated in this simulation study. Experimental results demonstrate that the proposed trajectory planning method improves multistage flight missions by generating smoother trajectories, lower trajectory errors, and a higher mission completion rate. These results suggest that ANEP can serve as an effective trajectory planning component for unmanned aerial vehicle (UAV)-based roof gutter maintenance scenarios.","PeriodicalId":100630,"journal":{"name":"IEEE Open Journal of Instrumentation and Measurement","volume":"5 ","pages":"8500111-8500111"},"PeriodicalIF":1.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11533592","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148236201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Proof-of-Concept Dual-Energy X-Ray Discrimination of Glass and Poly(methyl methacrylate) Enabled by Carbon Nanotube Cold Cathode","authors":"Jiaqi Wang;Fred Sun;Wentao Gao;John T. W. Yeow","doi":"10.1109/OJIM.2026.3706153","DOIUrl":"https://doi.org/10.1109/OJIM.2026.3706153","url":null,"abstract":"This article presents a proof-of-concept study on a quantitative dual-energy X-ray material discrimination system enabled by a high-stability carbon nanotube (CNT) cold cathode triode. Traditional thermionic X-ray sources suffer from thermal drift and long stabilization times, which compromise precision of energy sensitive measurements. In contrast, our CNT field emission source is evidenced by a 505-h stress test of the cathode chip at 10 mA emission current, and the dual-energy (DE) imaging experiments themselves were conducted at 1 mA within this validated stability envelope. We propose a robust material decomposition framework that integrates automated K-means clustering and a lower order polynomial beam hardening correction. Experimental results using borosilicate glass and poly(methyl methacrylate) (PMMA) standards demonstrate that the system can accurately decouple material types and absolute thickness. The proposed correction algorithm reduced the path-length-dependent thickness reconstruction error from approximately 15% to below 3%, achieving a thickness measurement precision with an in-sample mean absolute error of 0.04 mm and a maximum absolute error of 0.06 mm. These results validate the potential of CNT cold cathode instrumentation for high-precision industrial inspection and medical diagnostics.","PeriodicalId":100630,"journal":{"name":"IEEE Open Journal of Instrumentation and Measurement","volume":"5 ","pages":"6000209-6000209"},"PeriodicalIF":2.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11574722","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148442369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Measurement as Modeling: The Bayesian Bridge Between Artificial Intelligence and Metrological Traceability","authors":"Ignacio Lira","doi":"10.1109/OJIM.2026.3699771","DOIUrl":"https://doi.org/10.1109/OJIM.2026.3699771","url":null,"abstract":"The rapid integration of artificial intelligence (AI) into instrumentation has created a paradox: while AI-driven “soft sensors” offer unprecedented predictive power, they frequently fail to meet the fundamental requirements of metrological traceability. Measurement is not merely data acquisition; it is a model-based process that constructs a bridge between empirical reality and information. Current AI methods—often functioning as “opaque models”—emphasize scalability at the expense of metrological rigor. They typically lack the explicit structural models needed to validate this bridge, which risks noncompliance with the Guide to the Expression of Uncertainty in Measurement (GUM). This article proposes that the solution lies not in forcing AI into the linear constraints of classical propagation, but in fully embracing the Bayesian approach of GUM Supplement 1. We argue that the training phase of a machine-learning algorithm is metrologically equivalent to a massive Type B evaluation and must be treated as such across the model lifecycle—including data curation, training, validation, deployment, and recalibration—so that uncertainty statements remain current and defensible. By addressing the errors-in-variables (EiV) imperative and reinterpreting neural-network weights and true inputs as random variables with probability density functions (pdfs), and by using practical Bayesian surrogates (for example, Bayesian neural networks (BNNs), ensembles and Monte Carlo dropout, or diffusion-based input posteriors), we establish a framework that disentangles aleatoric from epistemic uncertainties. In doing so, we restore the epistemic link essential for traceability in the digital age.","PeriodicalId":100630,"journal":{"name":"IEEE Open Journal of Instrumentation and Measurement","volume":"5 ","pages":"1000106-1000106"},"PeriodicalIF":2.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11550185","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148433221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Algorithmic Optimization of Star-Mesh Quantized Hall Resistance Networks for Bridge Sensitivity","authors":"Gretchen B. Ferguson;Albert F. Rigosi;Dominick S. Scaletta;David B. Newell;Dean G. Jarrett","doi":"10.1109/OJIM.2026.3709475","DOIUrl":"https://doi.org/10.1109/OJIM.2026.3709475","url":null,"abstract":"Contemporary advances in electrical metrology include the understanding and development of star-mesh transformations and their applicability to the access of very high quantized resistances. These pursuits seek to drastically reduce the traceability chain for global calibrations, as demonstrated by a recent exemplary 1 G<inline-formula> <tex-math>$Omega $ </tex-math></inline-formula> star-mesh graphene quantized Hall array resistance standard (QHARS) using a dual-source bridge. Such studies revealed that there are limitations to many symmetrically iterated star-mesh devices, mainly due to single elements experiencing high enough current that its QHE breaks down, as well as general decreased bridge sensitivity. These two issues may be overcome by modifying the star-mesh designs to include a sufficient number of Hall elements at the first and last branches of the QHARS. In this work, new designs that give consideration to quantum Hall breakdown currents and bridge measurement performances were analyzed using the LTspice circuit simulator replicating the behavior of star-mesh devices in the quantized state. Several improved QHARS device designs for the outputs of 1 and 10 G<inline-formula> <tex-math>$Omega $ </tex-math></inline-formula> are reported, with most device output resistances falling within <inline-formula> <tex-math>$500~mu Omega $ </tex-math></inline-formula>/<inline-formula> <tex-math>$Omega $ </tex-math></inline-formula> of nominal.","PeriodicalId":100630,"journal":{"name":"IEEE Open Journal of Instrumentation and Measurement","volume":"5 ","pages":"1500108-1500108"},"PeriodicalIF":2.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11594103","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148507867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"JFET-Input Ultralow-Noise Amplifier for Low-Frequency Noise Measurements","authors":"Graziella Scandurra;Emanuele Cardillo;Luigi Ferro;Gino Giusi;Carmine Ciofi","doi":"10.1109/OJIM.2026.3720851","DOIUrl":"https://doi.org/10.1109/OJIM.2026.3720851","url":null,"abstract":"Low-frequency noise measurements are essential for the characterization of electronic devices, sensors, and materials, as they provide insight into physical mechanisms, device quality, and long-term stability. The accuracy of such measurements is fundamentally limited by the noise performance of the front-end instrumentation. We propose a topology for the realization of JFET-input voltage amplifiers that allows for obtaining equivalent input voltage noise (EIVN) levels lower than 3 nV/<inline-formula> <tex-math>$surd $ </tex-math></inline-formula>Hz at 100 mHz and below 1 nV/<inline-formula> <tex-math>$surd $ </tex-math></inline-formula>Hz at frequencies above 1 Hz. The proposed design allows for the DC connection of a biased device under test (DUT) to the amplifier input without the need for an input AC coupling filter that may result in a reduction of the input impedance, introduction of excess noise, and very long transients. The rejection of the DC component across the DUT, with a bandpass extending down below 100 mHz, is obtained by resorting to internal filters with low-resistance values and supercapacitors, which are characterized by intrinsically low noise. Tests were performed on a prototype employing the IF3602 discrete JFET pair by InterFET. However, other JFETs can be used since, as discussed in this work, the proposed topology allows for easily tailoring specific performance parameters, such as different compromises in terms of DC input range, required low-frequency noise level, and overall bandwidth. Experimental results demonstrate state-of-the-art noise performance. A comparison with amplifiers reported in the literature shows that, to the best of the authors’ knowledge, the proposed solution achieves the lowest background noise reported for JFET-input amplifiers in the frequency range below 10 Hz.","PeriodicalId":100630,"journal":{"name":"IEEE Open Journal of Instrumentation and Measurement","volume":"5 ","pages":"2000110-2000110"},"PeriodicalIF":2.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11643847","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148781337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Measurement Variability in Iron-Loss-Based Magnetic Bolt Axial Force Evaluation","authors":"Kota Toyoshima;Wenxu Sun;Hisafumi Asaue;Tomoki Shiotani;Masanori Hashimoto;Ryo Shirai","doi":"10.1109/OJIM.2026.3742015","DOIUrl":"https://doi.org/10.1109/OJIM.2026.3742015","url":null,"abstract":"Iron-loss-based magnetic methods are promising for bolt axial force evaluation. How-ever, their practical reliability can be limited by measurement variability caused by probe installation and specimen-dependent differences. This article evaluates such variability using M22 high-strength bolted joints through a series of experiments addressing probe holding conditions, probe reattachment, measurement-face differences, and specimen-to-specimen variation. Experimental results showed that probe fixation reduced the standard deviation of the iron-loss-related index from 0.490 to 0.059 W, while repeated probe reattachment resulted in a standard deviation of 0.199 W. Face-to-face variation remained nonnegligible, with standard deviations of 0.305 W on the bolt-head side and 0.363 W on the nut side. For the fully tightened and zero-axial-force conditions, the differences between the group means were 0.211 and 0.342 W on the bolt-head and nut sides, respectively. These differences were comparable to the magnitude of the observed measurement variability, indicating that the axial-force-dependent response can be obscured by face-to-face and specimen-to-specimen variations even between the two extreme conditions examined. These results provide a variability-oriented basis for improving the practical reliability of iron-loss-based bolt axial force measurement, particularly through further reduction of variability associated with probe installation, measurement faces, and specimen differences.","PeriodicalId":100630,"journal":{"name":"IEEE Open Journal of Instrumentation and Measurement","volume":"5 ","pages":"6000611-6000611"},"PeriodicalIF":2.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11733684","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149249435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Early Leak Recognition and Classification in Two-Phase Flow Systems Based on Machine Learning Using Dynamic Pressure Signals","authors":"Alamera Nouran Alquennah;Hicham Ferroudji;Mohammad Azizur Rahman;Ali Ghrayeb;Haitham Abu-Rub;Abinash Barooah","doi":"10.1109/OJIM.2026.3706192","DOIUrl":"https://doi.org/10.1109/OJIM.2026.3706192","url":null,"abstract":"Gas–liquid two-phase flows in oil and gas pipelines exhibit highly nonlinear, transient, and regime-dependent behavior, which poses substantial challenges for reliable monitoring and fault detection. Accurate leakage identification in such systems is critical for operational safety, environmental protection, and asset integrity; however, conventional physics-based and empirical methods often struggle under dynamic multiphase conditions. While machine learning (ML) techniques have demonstrated strong performance in flow regime identification and pattern recognition, their application to leakage detection in multiphase pipelines, particularly under offshore operating conditions, remains limited, with most existing studies focusing on single-phase systems. This article proposes a pressure-based artificial intelligence framework combined with a sliding-window feature extraction strategy for leakage detection and classification in gas–liquid two-phase pipelines. The methodology targets three operational scenarios: no leakage, single-point leakage, and multiple leakage points. Statistical features are extracted from windowed pressure measurements to capture transient flow behavior, and multiple data-driven classifiers are evaluated under both low-frequency experimental data and high-frequency numerical simulation data. The approach is designed to enhance robustness against flow regime fluctuations, reduce false alarms, and improve discrimination between leakage scenarios. The results demonstrate that cascaded ML models are well suited for low-frequency measurement systems, while neural network (NN) models exhibit high performance under high-frequency sampling, achieving online inference times of less than 1 s on a low-cost embedded platform. Overall, this study offers actionable guidance for the design and implementation of intelligent leakage monitoring systems, supporting early fault detection and improved integrity management in offshore oil and gas operations.","PeriodicalId":100630,"journal":{"name":"IEEE Open Journal of Instrumentation and Measurement","volume":"5 ","pages":"2500314-2500314"},"PeriodicalIF":2.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11586180","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148626206","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cycle-Patching and Domain-Balance With Tracking for Phonocardiogram Classification","authors":"Ebrahim A. Nehary;Sreeraman Rajan","doi":"10.1109/OJIM.2026.3738176","DOIUrl":"https://doi.org/10.1109/OJIM.2026.3738176","url":null,"abstract":"Phonocardiograms (PCGs) can be intelligently processed to diagnose heart valve-related diseases earlier than their symptoms manifest using advanced deep learning models trained using large datasets of heart sound measurements. As large sets of measurements (data) cannot be obtained using a single type of sensor or acquired from a particular measurement site on the chest of a subject or in a strictly controlled environment, the resulting datasets are nonhomogeneous. Even though training is done on a heart cycle basis, a record consisting of several continuous heart cycles is given a single class label, normal or abnormal, and each cycle then inherits this label. Inherited class labels may be incorrect when measurements are obtained from subjects having early stages of valvular diseases. Training with heterogeneous measurements, along with possible wrong labels, has been ignored in the literature. This article proposes constructing tensors from multiple cycles to mitigate the effects of noisy labels (NLs) and using domain-balanced training with a tracking method to ensure that all measurements contribute to model training and address heterogeneity. Vertical and horizontal patching are proposed to extract meaningful features from the constructed input tensors before feeding them into a focal modulation transformer and then fusing features for final classification through a majority voting process. Comprehensive experiments demonstrate that the proposed method achieves average score improvements of 19%, 3%, and 5% over centralized training, domain-balanced training, and the closest state-of-the-art method, respectively. These results demonstrate the effectiveness of the proposed approach for improving binary classification performance under data heterogeneity and noisy-label conditions. The source code is available at <uri>https://github.com/EbrahimAli1989/cycle-patching-pcg-classification.git</uri>","PeriodicalId":100630,"journal":{"name":"IEEE Open Journal of Instrumentation and Measurement","volume":"5 ","pages":"4000313-4000313"},"PeriodicalIF":2.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11727578","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149133543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Experimental Analysis of Short Acquisition Windows in Low-Latency Embedded Power Quality Disturbance Classification","authors":"Jonatan A. Medina-Molina;Enrique Reyes-Archundia;Marco V. Chávez-Báez;José A. Gutiérrez-Ignecch;Javier A. Rodríguez-Herrejón;Juan C. Olivares-Rojas;Néstor F. Guerrero-RodrÍguez","doi":"10.1109/OJIM.2026.3742002","DOIUrl":"https://doi.org/10.1109/OJIM.2026.3742002","url":null,"abstract":"The growth of distributed energy systems, renewable energy sources, and power electronic equipment has affected power quality. The use of low-latency algorithms is crucial in smart meters for the rapid detection of power quality disturbances (PQDs); however, reducing the acquisition window to enable faster responses may reduce classification accuracy due to limited signal information. This article presents an experimental analysis of short acquisition windows for embedded PQD classification. The performance of the proposed approach is evaluated across acquisition windows ranging from 200 to 50 ms under both noiseless and noisy conditions. The method employs the discrete wavelet transform (DWT) for feature extraction, combined with decision tree (DT) and support vector machine (SVM) classifiers. The experimental validation is carried out using a real-time setup that includes a waveform generator, a Piccolo C2000-based acquisition system, and a Raspberry Pi 4 (RPI4) for processing. The results show that classification accuracy decreases as the acquisition window is reduced. Nevertheless, the DWT <inline-formula> <tex-math>$textit {+}$ </tex-math></inline-formula> SVM configuration exhibits more robust behavior, maintaining accuracy between 94.67% and 98.56% over a 50-ms acquisition window, with an execution time of 1.53 ms, whereas DT shows a more pronounced degradation under the same conditions. These results allow identifying the tradeoff between latency and classification accuracy and provide useful insights for the design of real-time PQD monitoring systems implemented on embedded platforms.","PeriodicalId":100630,"journal":{"name":"IEEE Open Journal of Instrumentation and Measurement","volume":"5 ","pages":"3000309-3000309"},"PeriodicalIF":2.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11733720","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149249431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}