Search Results (345)

Surface electromyography (sEMG) is widely used for neuromuscular assessment, but the high cost of commercial systems limits accessibility in sports and rehabilitation settings. This study validated a low-cost open-source sEMG device (OLI) against a commercial field reference (SHI) during dynamic and isometric knee extensions in 36 healthy adults. Three preprocessing pipelines were tested for OLI signals: RAW, global root mean square (RMS), and cycle-centered RMS. Waveform similarity was assessed using the coefficient of multiple correlation (CMC), retaining repetitions with CMC ≥ 0.80. For valid repetitions, a calibration model (SHI = a + b × OLI) and Bland–Altman analysis were applied to min–max normalized RMS and area-under-the-curve (AUC) metrics. The global RMS pipeline showed the best overall performance, retaining 81.9% of repetitions with high shape similarity (CMC = 0.92 ± 0.04). It exhibited minimal bias in RMS (−0.69; 95% CI −1.11 to −0.27), limits of agreement of approximately ±10 normalized units, and a moderate-to-high correlation (r = 0.73; 95% CI 0.69–0.77). The calibration slope (b = 0.16; 95% CI 0.15–0.17) showed moderate within-session consistency (ICC(2,1) = 0.45). These findings indicate that, with appropriate preprocessing, the open-source system provides practically acceptable agreement with a commercial reference for characterizing relative muscle activation patterns, supporting its use in applied sports and rehabilitation contexts. Full article

Remote photoplethysmography (rPPG) enables non-contact acquisition of human physiological parameters using ordinary cameras, and has been widely applied in medical monitoring, human–computer interaction, and health management. However, most existing studies focus on estimating specific physiological metrics, such as heart rate and heart rate variability, while paying insufficient attention to reconstructing the underlying rPPG waveform. In addition, publicly available datasets typically record facial videos accompanied by fingertip PPG signals as reference labels. Since fingertip PPG waveforms differ substantially from the true photoplethysmography (PPG) signals obtained from the face, deep learning models trained on such datasets often struggle to recover high-quality rPPG waveforms. To address this issue, we collected a new dataset consisting of palm-region videos paired with wrist-based PPG signals as reference labels, and experimentally validated its effectiveness for training neural network models aimed at rPPG waveform reconstruction. Furthermore, we propose a generative adversarial network (GAN)-based pulse-wave synthesis framework that produces high-quality rPPG waveforms by denoising the mean green-channel signal. By incorporating time-domain peak-aware loss, frequency-domain loss, and adversarial loss, our method achieves promising performance, with an RMSE (Root Mean Square Error) of 0.102, an MAPE (Mean Absolute Percentage Error) of 0.028, a Pearson correlation of 0.987, and a cosine similarity of 0.989. These results demonstrate the capability of the proposed approach to reconstruct high-fidelity rPPG waveforms with improved morphological accuracy compared to noisy raw rPPG signals, rather than directly validating health monitoring performance. This study presents a high-quality rPPG waveform reconstruction approach from both data and model perspectives, providing a reliable foundation for subsequent physiological signal analysis, waveform-based studies, and potential health-related applications. Full article

Cardiovascular disease is the leading cause of morbidity and mortality worldwide, with ischemic and structural heart diseases being key contributors. While the 12-lead electrocardiogram (ECG) is a common low-cost diagnostic test, its interpretation is limited by human variability. Through machine learning with large diverse ECG data sets and artificial intelligence (AI) algorithms, ECG analysis can be automated for pattern recognition with higher accuracy. AI-augmented ECG algorithms have been demonstrated to be able to detect myocardial infarction with high accuracy and reduce door-to-balloon coronary intervention times. Similar models can be utilized to detect subtle ECG waveforms suggestive of current or future asymptomatic left ventricular dysfunction, aortic stenosis, and hypertrophic cardiomyopathy. Despite these promising results, there is concern for generalizability and bias or errors in training data. As AI systems evolve to multimodal integration, AI-augmented ECG has the potential to redefine cardiovascular diagnostics and enable earlier detection, risk stratification, and precision-guided interventions. Full article

This study evaluates the morphological performance of the CardioBAN wearable electrocardiogram (ECG) device by comparing its beat-level waveform accuracy against a clinically certified reference system (GE Vivid E9). A cycle-by-cycle Dynamic Time Warping (DTW) analysis was employed to assess beat-level waveform similarity between both devices in 17 healthy participants under controlled conditions. Each cardiac cycle from CardioBAN was aligned to its reference counterpart, enabling a fine-grained comparison of waveform shape. The resulting DTW distances (mean 0.493 ± 0.166) demonstrated overall high morphological agreement, with lower values occurring in recordings with stable beat morphology and higher values primarily reflecting normal variability related to minor motion artifacts or electrode–skin impedance fluctuations. A complementary Bland–Altman analysis of point-wise amplitude differences after DTW alignment showed minimal bias (0.079) and narrow limits of agreement (−0.897–1.055), confirming strong amplitude concordance between systems. These findings indicate that the CardioBAN wearable reliably reproduces key ECG morphological features under controlled, short-term recording conditions. Further studies encompassing ambulatory environments and clinical populations are needed to evaluate its suitability for real-world and pathological scenarios. Full article

Burrs are a significant machining defect affecting the quality of precision parts, and tool eccentricity may substantially influence milling burrs. Using AISI 304 stainless steel as the workpiece material, a three-dimensional thermo-mechanical coupled model for slot milling was constructed based on an explicit dynamics model. Combining the Johnson–Cook (J-C) constitutive model with the J-C shear failure criterion, simulations were conducted to obtain burr dimensions, cutting temperature distributions, and cutting force waveforms under different tool eccentricity directions and magnitudes. Results: As the eccentricity increases, the temperature of the top burr rises, and both the width of the top burr and the thickness of the exit side burr significantly increase. Under simulated conditions, the width of the top burr in down milling side increased by up to 70%. The burr dimensions under different eccentricity directions can differ by approximately 40%. Groove milling experiments revealed similar burr shapes between experimental and simulated results. Furthermore, the simulated cutting force waveforms aligned with those in the literature, indicating the reliability of the simulation outcomes. Based on these findings, it can be concluded that tool eccentricity significantly affects the dimensions of top burrs and exit side burrs. The width of top burrs and the thickness of exit side burrs are positively correlated with the tool eccentricity distance, while exit bottom burrs remain unaffected by eccentricity. These research results provide valuable reference for burr suppression in practical machining operations. Full article

In this study, we investigate the role of film thickness in modulating the properties of Cu films deposited on BaTiO₃ ceramic substrates using direct current magnetron sputtering (DCMS) and high-power pulsed magnetron sputtering (HiPIMS). While HiPIMS is known for producing dense films, and the thickness-dependent properties of sputtered Cu films are well-documented, this work uniquely explores the synergistic interplay between deposition technique and thickness on BaTiO₃ ceramic substrates, revealing novel insights into stress evolution and property optimization for advanced microelectronic and coating applications. Cu films of 300 nm, 1000 nm, and 1700 nm were systematically compared for their microstructures, surface morphologies, and electrical and mechanical properties, elucidating the critical role of thickness in densification, stress state, and overall performance. The results indicate that the target current and voltage waveforms of HiPIMS are similar to square waves, and the ionization rate is significantly higher than that of DCMS. Still, the deposition rate at the same power of 180 W is only 44.6% of that of DCMS. The films obtained by both processes present a strong (111) orientation; the crystallite size of the DCMS film grows with increasing thickness, while the HiPIMS film shows increasing and then decreasing, and its residual stress is overall lower than that of DCMS. In terms of surface morphology, DCMS films appeared porous and rough, whereas HiPIMS films were denser and smoother. In terms of properties, the resistivity of HiPIMS films is significantly lower than that of DCMS, especially at 1000 nm thickness. The binding force is also better than that of DCMS, especially at thicknesses less than 1000 nm, which is mainly attributed to the compressive stresses introduced by the energetic ion bombardment at the early deposition stage. These findings provide new mechanistic insights into thickness-dependent stress and property modulation, offering a reference for tailoring high-performance Cu films through process optimization. Full article

The cross-correlation algorithm, widely used for transit-time determination in ultrasonic gas flowmeters, becomes susceptible to significant errors under high flow rates. Fluid disturbances and noise distort ultrasonic waveforms, causing cycle-skipping errors that result in large, integer-period miscalculations of time-of-flight. To overcome these limitations, this study introduces a novel similarity-symmetry method. First, a similarity-based technique is proposed that exploits the stable rising-edge profile of the signal envelope, which remains consistent across flow rates, to accurately pinpoint the arrival time and mitigate cycle-skipping. Second, for multi-path flowmeters, the inherent physical symmetry between upstream and downstream transit times in each channel provides a basis for cross-validation. Any significant asymmetry flags potential cycle-skip events for correction. By integrating these two principles, our hybrid method enhances robustness. Experimental results on a six-path gas flowmeter rig demonstrate that the proposed approach reduces average flow rate errors by 75% compared to the standard cross-correlation method and maintains the maximum relative error below 1% when the flow rate is above 71.78 m³/h. This work provides a reliable solution for high-precision gas flow measurement in demanding conditions, with direct relevance to applications such as natural gas custody transfer and industrial process control where measurement accuracy is critical. Full article

Background and Objectives: Intraoperative hypotension (IOH) is of great importance in preventing diseases such as postoperative myocardial infarction, acute kidney injury, and mortality. This study aimed to develop and validate machine learning and deep learning models that predict IOH using both biosignals and personalized clinical information for each patient. Materials and Methods: In this retrospective observational study, we used the VitalDB open dataset, which included intraoperative biosignals and clinical information from 6388 patients who underwent non-cardiac surgery between June 2016 and August 2017 at Seoul National University Hospital, Seoul, South Korea. The predictive performances of models trained with four waveforms (arterial blood pressure, electrocardiography, photoplethysmography, and capnography) and clinical information were evaluated and compared at time points at 5 min before the hypotensive event. To predict hypotensive events during surgery, we developed two predictive models: machine learning and deep learning. In total, 2611 patients were enrolled in this retrospective study. Machine and deep learning algorithms were developed and validated using raw waveforms and clinical information as inputs. Results: Gradient boosting machine showed predicted IOH with an AUROC and accuracy of 0.94 (0.93–0.95) and 0.88 (0.86–0.89). A hybrid CNN-RNN model also showed similar performance with an AUROC and accuracy of 0.94 (0.93–0.95) and 0.88 (0.87–0.89). Conclusions: This study developed and validated machine and deep learning models to predict IOH using waveform data and covariate values. In the future, we anticipate that the results of our study will contribute to predicting IOH in real time in the operating room and reducing the occurrence of IOH. Full article

The aramid honeycomb composite material plays an important role in industry. Defects of this material seriously influence its performance. However, conventional detecting tools such as X-ray or computer tomography (CT) imaging, ultrasonic testing, and visual inspection are not able to meet the requirements of fast, safe, and high resolution at the same time. In this study, we numerically use rapid terahertz time−domain spectroscopy (THz-TDS) to identify defects in the aramid paper composite structure effectively. Simulation results demonstrate that THz-TDS technology enables the non-destructive reflection imaging of layered defects in glass fiber covering and glue layers as supporting components within the composite structure, with a spatial resolution of 0.5 mm and a depth range exceeding 10 mm. During the study, the finite difference time domain (FDTD) simulation with a real pulse waveform is achieved, and the defect position can be recognized by the anomaly in the reflection profile when compared with the waveform reflected by non-defect samples. At the same time, it is found that the defect identification ability is obviously affected by the incident position. The numerical research illustrates that the detectable defect is as thick as 0.1 mm and has a diameter of 1 mm. The results will offer valuable guides to the real application of THz-TDS systems in the detection of a similar structure. Full article

High-impedance fault (HIF) feeder detection in resonant-grounded active distribution systems remains a challenging issue. In practice, fault currents are typically weak, and the integration of distributed generation (DG) often distorts fault signatures, significantly limiting the effectiveness of existing detection techniques. This paper presents a novel HIF feeder detection method based on the fusion of zero-sequence current (ZSC) cross-correlation polarity analysis and harmonic wavebody similarity matching. Firstly, the HIF mechanism is examined, and the impact of DG on ZSC behavior is characterized, revealing polarity differences among feeders. To suppress high-frequency interference, variational mode decomposition (VMD) is employed to extract low-frequency components indicative of ZSC polarity, which are then subjected to cross-correlation analysis and used as the primary detection indicator. When ZSCs are heavily distorted due to DG, harmonic wavebody similarity serves as a supplementary detection feature. A comprehensive detection criterion is subsequently formulated by combining both analyses. Simulation and experimental results demonstrate that under HIF conditions, the proposed method is robust against variations in fault location, fault type, and noise interference, and can accurately identify the faulty feeder. Moreover, it remains effective for arc grounding, grass grounding, and pond grounding scenarios, highlighting its strong practical applicability. Full article

As a key form of deep foundation in civil engineering, the concrete pouring quality of cast-in-place piles directly determines the integrity and long-term bearing performance of the pile body. Accurate monitoring of the pouring interface is critical to preventing defects such as mud inclusion and pile breakage. To address the limitations of existing monitoring methods for concrete pouring interfaces, this paper proposes a full-pulse acoustic monitoring method for the concrete pouring interface of cast-in-place piles. Firstly, by constructing a hardware system platform consisting of “multi-level in-borehole sound sources + interface acoustic wave sensors + orifice full-pulse receivers + ground processors”, differential capture of signals propagating at different depths is achieved through multi-frequency excitation. Subsequently, a waveform data processing method is proposed to realize denoising, enhancement, and frequency discrimination of different signals, and a target feature recognition model that integrates cross-correlation functions and signal similarity analysis is established. Finally, by leveraging the differential characteristics of measurement signals at different depths, a near-field measurement mode and a far-field measurement mode are developed, thereby establishing a calculation model for the elevation position of the pouring interface under different scenarios. Meanwhile, the feasibility of the proposed method is verified through practical engineering cases. The results indicate that the proposed full pulse acoustic monitoring method can achieve non-destructive, real-time, and high-precision monitoring of the pouring interface, providing an effective technical approach for quality control in pile foundation construction and exhibiting broad application prospects. Full article

In patients with respiratory failure, mechanical ventilation aims to balance respiratory muscle loading and gas exchange. The interplay between the ventilator and the respiratory muscles is an increasingly recognized factor in tailoring ventilatory support. Surface electromyography (sEMG) offers a non-invasive modality to monitor the respiratory muscles. The sEMG signal, however, requires elaborate processing, which is limitedly standardized and documented. This paper presents the Respiratory Surface Electromyography (ReSurfEMG) package, an open-source Python package for respiratory sEMG analysis developed to address these challenges. ReSurfEMG integrates denoising, feature extraction, and quality assessment in one dedicated library. The effects of over- and under-filtering were compared to ReSurfEMG default settings regarding waveform duration, time-to-peak, amplitude, electrical time product (ETP), pseudo-slope, pseudo-signal-to-noise ratio (SNR), area under the baseline (AUB), and bell-curve error. Under-filtering increased amplitudes (+21%) and ETPs (+10%). Over-filtering smoothed sEMG waveforms, reducing amplitude (−58%), ETP (−39%), and pseudo-slope (−49%), while waveform duration and time-to-peak increased. Default ReSurfEMG settings provided the highest SNRs with similar or lower AUBs and bell-curve errors. The ReSurfEMG library integrates advanced methods dedicated to respiratory sEMG analysis. Systematic assessment using ReSurfEMG showed that signal processing settings affect sEMG features. ReSurfEMG enables reproducible signal processing, facilitating the standardization of respiratory sEMG analysis. Full article

Accurate classification between magnetizing inrush currents and internal faults is essential for reliable transformer protection and stable power system operation. Because their transient waveforms are so similar, conventional differential protection and harmonic restraint techniques often fail under dynamic conditions. This study presents a two-stage classification model that combines a self-organizing map (SOM) and a convolutional neural network (CNN) to enhance robustness and accuracy in distinguishing between inrush currents and internal faults in power transformers. In the first stage, an unsupervised SOM identifies topologically structured event clusters without the need for labeled data or predefined thresholds. Seven features are extracted from differential current signals to form fixed-length input vectors. These vectors are projected onto a two-dimensional SOM grid to capture inrush and fault distributions. In the second stage, the SOM’s activation maps are converted to grayscale images and classified by a CNN, thereby merging the interpretability of clustering with the performance of deep learning. Simulation data from a 154 kV MATLAB/Simulink transformer model includes inrush, internal fault, and overlapping events. Results show that after one cycle following fault inception, the proposed method improves accuracy (AC), precision (PR), recall (RC), and F1-score (F1s) by up to 3% compared with a conventional CNN model, demonstrating its suitability for real-time transformer protection. Full article

Fish species’ biological vocalizations serve as essential acoustic signatures for passive acoustic monitoring (PAM) and ecological assessments. However, limited availability of high-quality acoustic recordings, particularly for region-specific species like the brown croaker (Miichthys miiuy), hampers data-driven bioacoustic methodology development. In this study, we present a framework for reconstructing brown croaker vocalizations by integrating fk14 wavelet synthesis, PSO-based parameter optimization (with an objective combining correlation and normalized MSE), and deep learning-based validation. Sensitivity analysis using a normalized Bartlett processor identified delay and scale (length) as the most critical parameters, defining valid ranges that maintained waveform similarity above 98%. The reconstructed signals matched measured calls in both time and frequency domains, replicating single-pulse morphology, inter-pulse interval (IPI) distributions, and energy spectral density. Validation with a ResNet-18-based Siamese network produced near-unity cosine similarity (~0.9996) between measured and reconstructed signals. Statistical analyses (95% confidence intervals; residual errors) confirmed faithful preservation of SPL values and minor, biologically plausible IPI variations. Under noisy conditions, similarity decreased as SNR dropped, indicating that environmental noise affects reconstruction fidelity. These results demonstrate that the proposed framework can reliably generate acoustically realistic and morphologically consistent fish vocalizations, even under data-limited scenarios. The methodology holds promise for dataset augmentation, PAM applications, and species-specific call simulation. Future work will extend this framework by using reconstructed signals to train generative models (e.g., GANs, WaveNet), enabling scalable synthesis and supporting real-time adaptive modeling in field monitoring. Full article

Electroencephalography signal generation remains a challenging task due to its non-stationarity, multi-scale oscillations, and strong spatiotemporal coupling. Conventional generative models, including VAEs and GAN variants such as DCGAN, WGAN, and WGAN-GP, often yield blurred waveforms, unstable spectral distributions, or lack semantic controllability, limiting their effectiveness in emotion-related applications. To address these challenges, this research proposes a Transformer-based conditional variational autoencoder–generative adversarial network (Trans-cVAE-GAN) that combines Transformer-driven temporal modeling, label-conditioned latent inference, and adversarial learning. A multi-dimensional structural loss further constrains generation by preserving temporal correlation, frequency-domain consistency, and statistical distribution. Experiments on three SEED-family datasets—SEED, SEED-FRA, and SEED-GER—demonstrate high similarity to real EEG, with representative mean ± SD correlations of Pearson ≈ 0.84 ± 0.08/0.74 ± 0.12/0.84 ± 0.07 and Spearman ≈ 0.82 ± 0.07/0.72 ± 0.12/0.83 ± 0.08, together with low spectral divergence (KL ≈ 0.39 ± 0.15/0.41 ± 0.20/0.37 ± 0.18). Comparative analyses show consistent gains over classical GAN baselines, while ablations verify the indispensable roles of the Transformer encoder, label conditioning, and cVAE module. In downstream emotion recognition, augmentation with generated EEG raises accuracy from 86.9% to 91.8% on SEED (with analogous gains on SEED-FRA and SEED-GER), underscoring enhanced generalization and robustness. These results confirm that the proposed approach simultaneously ensures fidelity, stability, and controllability across cohorts, offering a scalable solution for affective computing and brain–computer interface applications. Full article