Search Results (54)

At SAE Level 2 automation, the human driver retains full supervisory responsibility, making unobtrusive monitoring relevant for maintaining supervision under real-world driving conditions. Driver monitoring systems capable of operating robustly under such conditions are therefore essential, but wearable-based personalized approaches remain underexplored, particularly when the target labels are derived from experimental scenarios. This study presents a real-world SAE Level 2 on-road acquisition campaign and evaluates a target-driver intra-subject classification approach using non-intrusive wrist-derived signals. Physiological and motion data recorded with the Empatica E4 wristband, including blood volume pulse, electrodermal activity, heart rate, skin temperature, and triaxial wrist acceleration, were converted into image representations and processed with a frozen ResNet-50 feature extractor, principal component analysis, and a supervised classifier. The labels were scenario-derived operational driver-state classes defined from experimental phases and scenario groups. Personalization was assessed via a Leave-One-Experience-Out protocol on the target driver. Classification accuracy was 50% under external-user-only training, 54% under mixed target/external-user training, and 60% under target-driver-only training, with the target-driver-only configuration yielding the highest mean performance in the evaluated setting. For the low-demand baseline class, the one-vs.-rest classifier achieved 88.4% accuracy and an F1-score of 70%. These results provide initial evidence of the feasibility of personalized wrist-worn classification of scenario-derived operational driver-state classes under the real-world automated driving conditions evaluated in this study. Full article

Reflective-mode photoplethysmography (PPG) potentially enables non-invasive physiological monitoring of heart rate and Peripheral Oxygen Saturation (SpO₂) from virtually any anatomical body site, but its performances are strongly affected by several parameters such as local perfusion, skin temperature, and microvascular bed and tissue optical properties. This study systematically evaluates the quality of reflective-mode PPG signals acquired at the finger, wrist, ear, nose, temple, upper lip, and lower lip, using two commercial PPG sensors. PPG signal quality was quantified via Skewness, Kurtosis, Perfusion Index, and Shannon entropy. Heart rate (HR) and pulse transit time (PTT) were also computed. Skewness and Perfusion Index were the most informative quality indices, revealing the finger as the site with the best signal quality and the wrist as the most challenging location. Several facial regions—including the lips, nose, and temple—showed signal quality comparable to the finger. HR estimation was most accurate using the GREEN wavelength, with the lower lip achieving the lowest error, followed by the upper lip and finger. PTT values reflected physiological differences in pulse propagation, being longest at the finger and wrist and shortest at the lips. These findings highlight the potential of non-conventional anatomical sites as alternatives to the finger and wrist for reflective-mode PPG acquisition. Full article

Numerous studies have shown that remote monitoring of heart failure patients can reduce hospital readmission rates and mortality. This dataset includes multimodal physiological and inertial signals (acceleration and angular velocity data) recorded with PerHeart—a remote health monitoring platform intended for heart failure patients. In the pilot, which took place in Poland, 27 participants’ health was monitored for one month using the platform with commercially available devices (blood pressure meters, pulse oximeters, bathroom scales, thermometers, and glucometers), resulting in over four thousand physiological measurements. Eight adults were additionally monitored for gait and activity analysis using custom wrist sensors with inertial measurement units, yielding 2536 h of movement data collected over 204 days with almost 690,000 steps detected. Full article

Flexible piezoresistive sensors are often vulnerable to modal ambiguity and bending-induced drift, both of which can obscure true pressure and strain signals under practical operation. Here, we address these limitations by suppressing bending sensitivity at the device level and disambiguating tactile modes at the algorithmic level. We propose and fabricate a Ti₃C₂T_x/graphene oxide (GO) sandwich sensor in which the conductive network is positioned near the neutral axis, thereby ensuring that bending induces negligible axial strain in the active layer. In contrast, out-of-plane pressing enlarges microcontacts, while in-plane stretching disrupts percolation pathways. We develop a composite-beam model to quantify neutral-axis alignment and the resultant bending immunity, realize the device via a straightforward casting process, and systematically characterize its electromechanical response under bending, pressing, nail pressing, and stretching. To further reduce modal ambiguity and improve tactile recognition, a lightweight one-dimensional convolutional neural network (1D-CNN) was introduced to classify temporal resistance signals from the sensor. Experimental results showed that the 1D-CNN achieved a high classification accuracy of 98.52% under flat-state training and testing conditions, and maintained 96.67% accuracy when evaluated on bending-state samples, demonstrating strong robustness against bending-induced interference. Together, the neutral-axis device architecture and the learning-based inference pipeline deliver high sensitivity to pressing and stretching while markedly suppressing the response to bending, thereby enabling wrist-worn pulse monitoring, soft-robotic joint sensing, and plantar pressure insoles. Full article

Flexible piezoelectric materials demonstrate broad application potential in wearable health monitoring, human–machine interaction, and biosensing. However, the piezoelectric response of pure PVDF-TrFE is limited and insufficient to meet the requirements for highly sensitive sensing. In this study, ZnO/PVDF-TrFE composite films with varying ZnO doping contents (3–11 wt%) were fabricated and systematically characterized in terms of their structural, thermal, and electrical properties. The results indicate that ZnO significantly promotes the formation of the polar β-phase in PVDF-TrFE, with the maximum β-phase content (F_β = 24.76%) and optimal piezoelectric performance achieved at 9 wt% ZnO doping. Devices based on this optimal composition exhibited stable ultrasonic transmission and reception capabilities under high-frequency pulse excitation, enabling sensitive detection of minor static pressure variations (e.g., contact pressure) through changes in ultrasonic echo signals, thereby realizing wearable conformity monitoring. Moreover, a sensor designed with a three-channel flexible substrate successfully captured human wrist pulse signals with high accuracy, demonstrating the practical utility and reliability of the device in flexible bio-electronic sensing applications. 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

This study describes the developed special prototype of a wearable measuring device based on a photoplethysmography (PPG) sensor. It contains also a humidity sensor and a thermometer to measure skin moisture and temperature, and a force-sensitive (FSR) element to sense a contact pressure between the measuring probe and the skin surface. All parts of the multi-sensor are shielded, to be applicable in a weak magnetic field environment. After the basic sensor’s functionality verification inside the magnetic resonance imaging tomograph, a set of experiments was performed. Comparative measurements by an oximeter confirm good correspondence with heart rate values determined from PPG (HR_PPG) and FSR (HR_FSR) signals—the mean absolute error lies below 0.5 min⁻¹ for both types. The sensing of PPG signals on wrists was realized for Normal, Dry, and Wet skin. In comparison with normal skin conditions, drying decreases the PPG signal range by 7% and the systolic pulse width by 8%, while moistening increases the signal ripple by 3% and decreases the correlation between HR_PPG and HR_FSR values by 5%. The detailed analysis per hand and gender types yields differences between male and female subjects, while the results for left and right hands differ less. Full article

The article describes a system for monitoring the vital parameters of evacuated individuals, integrating three key functionalities: pulse detection, verification of wristband contact with the skin, and motion recognition. For pulse detection, the system employs the MAX30102 optical sensor and a signal processing algorithm presented in the study. The algorithm is based on spectral analysis using the Fast Fourier Transform (FFT) and incorporates a nonparametric estimator of the probability density function (PDF) in the form of Kernel Density Estimation (KDE). This developed real-time algorithm enables reliable assessment of vital parameters of evacuated individuals. The wristband contact with the skin is verified by measuring the brightness of backscattered light and the temperature of the wrist. Motion detection is achieved using the MPU-9250 inertial module, which analyzes acceleration across three axes. This allows the system to distinguish between states of rest and physical activity, which is crucial for accurately interpreting vital parameters during evacuation. The experimental studies, which were performed on a representative group of individuals, confirmed the correctness of the developed algorithm. The system ensures reliable monitoring of vital parameters by combining precise pulse detection, skin contact verification, and motion analysis. The classifier achieves nearly 95% accuracy and an F₁-score of 0.9465, which indicates its high quality. This level of effectiveness can be considered fully satisfactory for evacuation monitoring systems. Full article

We present a hermetically sealed capacitive microelectromechanical system (MEMS) strain sensor designed for arterial pulse waveform extraction using the strain plethysmography (SPG) modality. The MEMS strain sensor features a small form factor of 3.3 mm × 3.3 mm × 1 mm, leverages a nano-gap fabrication process to improve the sensitivity, and uses a differential sensing mechanism to improve the linearity and remove the common mode drift. The MEMS strain sensor is interfaced with an application-specific integrated circuit (ASIC) to form a compact strain sensing system. This system exhibits a high strain sensitivity of 316 aF/µε, a gauge factor (GF) of 35, and a strain sensing resolution of 1.26 µε, while maintaining a linear range exceeding 700 µε. SPG signals have been reliably captured at both the fingertip and wrist using the MEMS strain sensor with high signal quality, preserving various photoplethysmography (PPG) features. Experimental results demonstrate that heart rate (HR) and heart rate variability (HRV) can be estimated from the SPG signal collected at the fingertip and wrist using the sensor with an accuracy of over 99%. Pulse arrival time (PAT) and pulse transit time (PTT) have been successfully extracted using the sensor together with a MEMS seismometer, showcasing its potential for ambulatory BP monitoring (ABPM) application. Full article

Background: Heart rate (HR) is a critical biomarker that provides insights into overall health, stress levels, and the autonomic nervous system. Pulse wave signals contain valuable information about the cardiovascular system and heart status. However, signal acquisition in wearables poses challenges, particularly when using electrical sensors, due to factors like the distance from the heart, body movement, and suboptimal electrode placement. Methods: Electrical bioimpedance (EBI) measurements using bipolar and tetrapolar electrode systems were employed for pulse wave signal acquisition from the wrist in both perpendicular and distal configurations. Signal preprocessing techniques, including baseline removal via Hankel matrix methods, normalization, cross-correlation, and peak detection, were applied to improve signal quality. This study describes the combination of sensor-level signal acquisition and processing for accurate wearable HR estimation. Results: The bipolar system was shown to produce larger $\Delta Z\left(t\right)$, while the tetrapolar system demonstrated higher sensitivity. Distal placement of the electrodes yielded greater $\Delta Z\left(t\right)$ (up to 0.231 $\Omega$) when targeting both wrist arteries. Bandpass filtering resulted in a better signal-to-noise ratio (SNR), achieving 3.6 dB for the best bipolar setup and 4.8 dB for the tetrapolar setup, compared to 2.6 and 3.3 dB SNR, respectively, with the Savitzky–Golay filter. The custom HR estimation algorithm presented in this paper demonstrated improved accuracy over a reference method, achieving an average error of 1.8 beats per minute for the best bipolar setup, with a mean absolute percentage error (MAPE) of 8%. Conclusions: The analysis supports the feasibility of using bipolar electrode setups on the wrist and highlights the importance of electrode positioning relative to the arteries. The proposed signal processing method, featuring a preprocessing pipeline and HR estimation algorithm, provides a proof-of-concept demonstration for HR estimation from EBI signals acquired at the wrist. Full article

A fiber Bragg grating (FBG) pulse and systolic blood pressure (SBP) measurement system based on the edge-filtering method is proposed. The edge filter is the Mach–Zehnder interferometer (MZI) fabricated by two fiber couplers with a linear slope of 52.45 dBm/nm. The developed system consists of a broadband light source, an edge filter, fiber Bragg gratings (FBGs), a coarse wavelength-division multiplexer (CWDM), and signal-processing circuits based on a field-programmable gate array (FPGA). It can simultaneously measure pulse pulsations of the radial artery in the wrist at three positions: Cun, Guan and Chi. The SBP can be calculated based on the pulse transit time (PTT) principle. The measurement results compared to a standard blood pressure monitor showed the mean absolute error (MAE) and standard deviation (STD) of the SBP were 0.93 ± 3.13 mmHg. The system meets the requirements of the Association for the Advancement of Medical Instrumentation (AAMI) equipment standards. The proposed system can achieve continuous real-time measurement of pulse and SBP and has the advantages of fast detection speed, stable performance, and no compression sensation for subjects. The system has important application value in the fields of human health monitoring and medical device development. Full article

The demand for self-powered, flexible, and wearable electronic devices has been increasing in recent years for physiological and biomedical applications in real-time detection due to their higher flexibility and stretchability. This work fabricated a highly sensitive, self-powered wearable microdevice with Poly-Vinylidene Fluoride-Tetra Fluoroethylene (PVDF-TrFE) nano-fibers using an electrospinning technique. The dielectric response of the polymer was improved by incorporating the reduced-graphene-oxide (rGO) multi-walled carbon nano-tubes (MWCNTs) through doping. The dielectric behavior and piezoelectric effect were improved through the stretching and orientation of polymeric chains. The outermost layer was attained by chemical vapor deposition (CVD) of conductive polymer poly (3,4-ethylenedioxythiophene) to enhance the electrical conductivity and sensitivity. The hetero-structured nano-composite comprises PVDF-TrFE doped with rGO-MWCNTs over poly (3,4-ethylenedioxythiophene) (PEDOT), forming continuous self-assembly. The piezoelectric pressure sensor is capable of detecting human physiological vital signs. The pressure sensor exhibits a high-pressure sensitivity of 19.09 kPa⁻¹, over a sensing range of 1.0 Pa to 25 kPa, and excellent cycling stability of 10,000 cycles. The study reveals that the piezoelectric pressure sensor has superior sensing performance and is capable of monitoring human vital signs, including heartbeat and wrist pulse, masticatory movement, voice recognition, and eye blinking signals. The research work demonstrates that the device could potentially eliminate metallic sensors and be used for early disease diagnosis in biomedical and personal healthcare applications. Full article

Inertial signals are the most widely used signals in human activity recognition (HAR) applications, and extensive research has been performed on developing HAR classifiers using accelerometer and gyroscope data. This study aimed to investigate the potential enhancement of HAR models through the fusion of biological signals with inertial signals. The classification of eight common low-, medium-, and high-intensity activities was assessed using machine learning (ML) algorithms, trained on accelerometer (ACC), blood volume pulse (BVP), and electrodermal activity (EDA) data obtained from a wrist-worn sensor. Two types of ML algorithms were employed: a random forest (RF) trained on features; and a pre-trained deep learning (DL) network (ResNet-18) trained on spectrogram images. Evaluation was conducted on both individual activities and more generalized activity groups, based on similar intensity. Results indicated that RF classifiers outperformed corresponding DL classifiers at both individual and grouped levels. However, the fusion of EDA and BVP signals with ACC data improved DL classifier performance compared to a baseline DL model with ACC-only data. The best performance was achieved by a classifier trained on a combination of ACC, EDA, and BVP images, yielding F1-scores of 69 and 87 for individual and grouped activity classifications, respectively. For DL models trained with additional biological signals, almost all individual activity classifications showed improvement (p-value < 0.05). In grouped activity classifications, DL model performance was enhanced for low- and medium-intensity activities. Exploring the classification of two specific activities, ascending/descending stairs and cycling, revealed significantly improved results using a DL model trained on combined ACC, BVP, and EDA spectrogram images (p-value < 0.05). Full article

Arterial stiffness has been proved to be an important parameter in the evaluation of cardiovascular diseases, and Pulse Wave Velocity (PWV) is a strong indicator of arterial stiffness. Compared to regional PWV (PWV among different arteries), local PWV (PWV within a single artery) outstands in providing higher precision in indicating arterial properties, as regional PWVs are highly affected by multiple parameters, e.g., variations in blood vessel lengths due to individual differences, and multiple reflection effects on the pulse waveform. However, local PWV is less-developed due to its high dependency on the temporal resolution in synchronized signals with usually low signal-to-noise ratios. This paper presents a method for the noninvasive simultaneous measurement of two local PWVs in both left and right radial arteries based on the Fiber Bragg Grating (FBG) technique via correlation analysis of the pulse pairs at the fossa cubitalis and at the wrist. Based on the measurements of five male volunteers at the ages of 19 to 21 years old, the average left radial PWV ranged from 9.44 m/s to 12.35 m/s and the average right radial PWV ranged from 11.50 m/s to 14.83 m/s. What is worth mentioning is that a stable difference between the left and right radial PWVs was observed for each volunteer, ranging from 2.27 m/s to 3.04 m/s. This method enables the dynamic analysis of local PWVs and analysis of their features among different arteries, which will benefit the diagnosis of early-stage arterial stiffening and may bring more insights into the diagnosis of cardiovascular diseases. Full article

There has been a significant shift in research focus in recent years toward laser-induced graphene (LIG), which is a high-performance material with immense potential for use in energy storage, ultrahydrophobic water applications, and electronic devices. In particular, LIG has demonstrated considerable potential in the field of high-precision human motion posture capture using flexible sensing materials. In this study, we investigated the surface morphology evolution and performance of LIG formed by varying the laser energy accumulation times. Further, to capture human motion posture, we evaluated the performance of highly accurate flexible wearable sensors based on LIG. The experimental results showed that the sensors prepared using LIG exhibited exceptional flexibility and mechanical performance when the laser energy accumulation was optimized three times. They exhibited remarkable attributes, such as high sensitivity (~41.4), a low detection limit (0.05%), a rapid time response (response time of ~150 ms; relaxation time of ~100 ms), and excellent response stability even after 2000 s at a strain of 1.0% or 8.0%. These findings unequivocally show that flexible wearable sensors based on LIG have significant potential for capturing human motion posture, wrist pulse rates, and eye blinking patterns. Moreover, the sensors can capture various physiological signals for pilots to provide real-time capturing. Full article