Long-term Monitoring Applications Research Articles

Enhancing data sparsity in spectral signals using wavelet decomposition for improved compression and storage efficiency

Wavelet decomposition (WD) is integrated into the Compressive Sensing (CS) model to enhance data sparsity. This approach aims to ensure efficiency and quality in the received data after compression and reconstruction processes. The proposed WD-CS model is developed for reflected spectra signals from Fiber Bragg Gratings-based extensometers, which were subjected to induced deflections simulating the underground soil movement. WD decomposes the input signal before compressive measurement, followed by transferring and storing the compressed data in the cloud. The spectral data were reconstructed using Orthogonal Matching Pursuit (OMP) followed by wavelet reconstruction. The impact of wavelet decomposition on the quality of compression and reconstruction is assessed and compared against that of the standard CS model. The findings indicate that the WD-CS model can improve data sparsity by a factor of three and compressibility by a factor of ten without degenerating the reconstructed data quality. The error in the Bragg wavelength shift of the reconstructed spectra is minimal extracted using Pseudo-high Resolution Interrogation (PHRI) method. The proposed WD-CS model is useful in improving data compression for FBG spectra as well as storage efficiency, which make it potentially applicable in FBG-based sensor networks for long-term structural health monitoring applications.

ECG signal quality in intermittent long-term dry electrode recordings with controlled motion artifacts.

Wearable long-term monitoring applications are becoming more and more popular in both the consumer and the medical market. In wearable ECG monitoring, the data quality depends on the properties of the electrodes and on how they interface with the skin. Dry electrodes do not require any action from the user. They usually do not irritate the skin, and they provide sufficiently high-quality data for ECG monitoring purposes during low-intensity user activity. We investigated prospective motion artifact-resistant dry electrode materials for wearable ECG monitoring. The tested materials were (1) porous: conductive polymer, conductive silver fabric; and (2) solid: stainless steel, silver, and platinum. ECG was acquired from test subjects in a 10-min continuous settling test and in a 48-h intermittent long-term test. In the settling test, the electrodes were stationary, whereas both stationary and controlled motion artifact tests were included in the long-term test. The signal-to-noise ratio (SNR) was used as the figure of merit to quantify the results. Skin-electrode interface impedance was measured to quantify its effect on the ECG, as well as to leverage the dry electrode ECG amplifier design. The SNR of all electrode types increased during the settling test. In the long-term test, the SNR was generally elevated further. The introduction of electrode movement reduced the SNR markedly. Solid electrodes had a higher SNR and lower skin-electrode impedance than porous electrodes. In the stationary testing, stainless steel showed the highest SNR, followed by platinum, silver, conductive polymer, and conductive fabric. In the movement testing, the order was platinum, stainless steel, silver, conductive polymer, and conductive fabric.

Development of data anomaly classification for structural health monitoring based on iterative trimmed loss minimization and human-in-the-loop learning

Huge amounts of data can be generated during long-term monitoring performed by structural health monitoring (SHM) and structural integrity management applications. Monitoring data can be corrupted, and the presence of abnormal data can distort information during signal processing, extract incorrect characteristics during system identification, produce false conclusions during damage detection, and ultimately lead to misjudgment of structural conditions during diagnosis and prognosis. Therefore, developing effective techniques to autonomously detect and classify anomalies becomes necessary and significant. Generally, conventional physics-based strategies can be straightforward, but their performance highly depends on prior knowledge of measurement. Recently, data-driven methods leveraging machine learning (ML) have been used to directly handle the task. This study proposes an ML-based classifier and improves it by incorporating the human-in-the-loop (HITL) learning. The classifier is built on a shallow neural network with high performance to address potential online or real-time applications for long-term monitoring. First, a field monitoring dataset is introduced, and various anomalies are defined to investigate the effectiveness. To further enhance the performance of the proposed classifier, the mislabels in the monitoring dataset are examined, and a correction technique is performed. Additionally, HITL ML is developed to overcome the disadvantages of the conventional correction technique. As a result, the proposed procedure can improve both the classifier and the field dataset, and the proposed classifier can now function as a fundamental component in achieving a continuous and autonomous SHM system.

Time-Series Cross-Radiometric Calibration and Validation of GF-6/WFV Using Multi-Site

The GaoFen6 (GF-6) satellite, equipped with a wide full-swath (WFV) sensor, offers high spatial resolution and extensive coverage, making it widely utilized in agricultural and forestry classification, land resource monitoring, and other fields. Accurate on-orbit radiometric calibration of GF-6/WFV is crucial for these quantitative applications. Currently, the absolute radiometric calibration of GF-6/WFV relies primarily on vicarious calibration conducted by the China Center for Resources Satellite Data and Application (CRESDA). However, annual vicarious calibration may not adequately capture the radiometric performance of GF-6/WFV due to performance degradation. Therefore, increasing the frequency of on-orbit radiometric calibration throughout the lifetime of GF-6/WFV is essential. This study proposes a method for conducting long-term cross-radiometric calibrations of GF-6/WFV by taking the multispectral imager (MSI) onboard the Sentinel-2 satellite as a reliable reference sensor and the sites from RadCalNet as reference ground targets. Firstly, we conducted 62 on-orbit cross-radiometric calibrations of GF-6/WFV since its launch by tracking with the Sentinel-2/MSI sensor after correcting the discrepancy spectrum and solar zenith angle. Then, validation of cross-radiometric calibration results against RadCalNet products indicated an average absolute relative error between 3.55% and 4.64%. Cross-validation with additional reference sensors, including Landsat-8/OLI and MODIS, confirmed the reliability of calibration, demonstrating relative differences from GF-6/WFV of less than 5%. Furthermore, the overall uncertainty of the cross-radiometric calibration was estimated to be from 4.08% to 4.89%. Finally, trend analysis of the time-series radiometric performance was also conducted and revealed an annual degradation rate ranging from 0.57% to 2.31%. This degradation affects surface reflectance retrieval, introducing a bias of approximately 0.0073 to 0.0084. Our findings highlight the operational effectiveness of the proposed method in achieving long-time-series on-orbit radiometric calibration and degradation monitoring of GF-6/WFV. The study also demonstrates that the radiometric performance of GF-6/WFV is relatively stable and suitable for further quantitative applications, especially for long-term monitoring applications.

The ENCEVIS algorithm in the EMU and the factors affecting its performance: Our experience

The study's purpose was to assess the seizure detection performance of ENCEVIS 1.7, identify factors that may influence algorithm performance, and explore its potential for implementation and application in long-term video EEG monitoring units. The study included video-EEG recordings containing at least one epileptic seizure. Forty-three recordings, encompassing 112 seizures, were included in the analysis. True positive, false negative, and false positive seizure detections were defined. Factors that may influence algorithm performance were studied. ENCEVIS demonstrated an overall sensitivity of 71.2%, significantly higher (75.1%) in focal compared to generalized seizures (62%). Ictal patterns rhythmicity (rhythmic 59.4 %, arrhythmic 41.7 %), seizure duration (<10 sec 6.3 %, >60 sec. 63.9 % (p < 0.05)) and patient age (<18 years 39.5 %, >18 years 58.1 % (P < 0.05)) influenced ENCEVIS sensitivity. The coexistence of extracerebral signal changes did not influence sensitivity. ENCEVIS with 79.1% accuracy annotates at least one seizure in those recordings containing epileptic seizures. ENCEVIS seizure detection performance was reasonable for generalized/focal to bilateral tonic-clonic seizures and seizures with temporal lobe onset. Rhythmic ictal patterns, longer seizure duration, and adult age positively influenced algorithm performance. ENCEVIS can be a valuable tool for identifying recordings containing seizures and can potentially reduce the workload of neurophysiologists.

Long-term monitoring of a masonry arch bridge to evaluate scour effects

Evaluating the scour effects on masonry arch bridges is of utmost importance to ensure the continued operational safety of those infrastructures. Even if numerical and laboratory studies have demonstrated the possibility of detecting scour-induced effects by measuring the structural response of masonry bridges, there is a lack of long-term monitoring applications on real structures. Within this context, the paper presents selected results obtained during two years of continuous monitoring of a historical masonry arch bridge to evaluate scour-induced effects. Firstly, on-site inspections of the bridge revealed severe foundation erosion and extensive documentary research was carried out to identify the depth of the foundation level. Subsequently, a monitoring system was installed in the bridge, including several MEMS-based tiltmeters, 1 echosounder, 1 hydrometer and 1 weather station. The correlation between measured rotations and environmental parameters is investigated and a linear regression model is used to minimize/remove temperature-induced effects. The residual errors between measured and predicted rotations highlighted the occurrence of various anomalies.

Review of low-cost light sources and miniaturized designs in photoacoustic microscopy.

Photoacoustic microscopy (PAM) is a promising imaging technique to provide structural, functional, and molecular information for preclinical and clinical studies. However, expensive and bulky lasers and motorized stages have limited the broad applications of conventional PAM systems. A recent trend is to use low-cost light sources and miniaturized designs to develop a compact PAM system and expand its applications from benchtop to bedside. We provide (1)an overview of PAM systems and their limitations, (2)a comprehensive review of PAM systems with low-cost light sources and their applications, (3)a comprehensive review of PAM systems with miniaturized and handheld scanning designs, and (4)perspective applications and a summary of the cost-effective and miniaturized PAM systems. Papers published before July 2023 in the area of using low-cost light sources and miniaturized designs in PAM were reviewed. They were categorized into two main parts: (1)low-cost light sources and (2)miniaturized or handheld designs. The first part was classified into two subtypes: pulsed laser diode and continuous-wave laser diode. The second part was also classified into two subtypes: galvanometer scanner and micro-electro-mechanical system scanner. Significant progress has been made in the development of PAM systems based on low-cost and compact light sources as well as miniaturized and handheld designs. The review highlights the potential of these advancements to revolutionize PAM technology, making it more accessible and practical for various applications in preclinical studies, clinical practice, and long-term monitoring.

Novel flexible hydrogels based on carboxymethyl guar gum and polyacrylic acid for ultra-highly sensitive and reliable strain and pressure sensors

To realize on stable and real-time monitoring of human activities, novel hydrogels using polyacrylic acid (PAA) and carboxymethyl guar gum (CMGG) were fabricated as wearable and flexible strain or pressure sensors in the presence of lignosulfonate (LS) and Al3+. Based on the co-existence of metal coordination bonds, hydrogen bonds and ionic interaction in this system, the obtained hydrogels exhibited desirable mechanical properties with good self-recovery ability. The hydrogels displayed good self-adhesion behavior and an ultra-high tensile sensitivity (gauge factor (GF) = 24.30), therefore, they could precisely detect human joints movements such as elbow, wrist, and finger bending as well as tiny movements and external stimuli such as swallowing, smile, frown, pulse, speaking, writing, and even the falling of different liquid drops. Additionally, the hydrogels showed excellent self-healing ability with the healing efficiency as high as 100 % after 30 h. Most importantly, the healed hydrogel could perform the same sensing performance as before. Based on these distinguished characteristics, this hydrogel represents great potentials in wearable and flexible sensors for long-term and stable health monitoring application.

A low-power neutron and gamma-ray detector for environmental radiation monitoring using CLYC scintillator

This paper describes a low-power neutron and gamma-ray detector based on a CLYC scintillator enriched with 96% 6Li for environmental radiation monitoring. The detector is designed in compliance with the IP66 standard having water and dust release capability. The power consumption of the detector is 3.5 W, and the operating temperature is from -15° to +40°. The energy response range for gamma rays is 40 keV to 3 MeV, while the energy resolution of the detector is 4.8% (662 keV). A standard figure of merit (FOM) is used to evaluate neutron-gamma discrimination, achieving a value of 3.42. The mixed neutron-gamma environment was simulated at the Back-n neutron beam of the China Spallation Neutron Source (CSNS). The test results show that the detector can detect the changes in the gamma dose and neutron count rates when the beam is turned on and off in real-time. The proposed detector is suitable for the application of long-term environmental radiation monitoring for nuclear facilities or buildings housing radioactive sources.

Self-sensing study of stress in low-doped carbon fiber reinforced hydraulic concrete

As an intrinsically self-sensing material, carbon fibre concrete has promising applications in structural health monitoring. Investigating the long-term stability of carbon fibre concrete in terms of resistivity changes under the influence of factors such as ageing effects and environmental conditions can help assess its feasibility for long-term monitoring applications. In this paper, the specimens were designed based on the variables of carbon fibre admixture (0.05 vol%, 0.08 vol%, 0.1 vol%) and carbon fibre length (3 mm, 6 mm, 9 mm, 12 mm), and the DC four-electrode method was used to study the self-sensing of low admixture carbon fibre reinforced hydraulic concrete containing coarse aggregate (5–20 mm) under long age (180d) in order to analyze the resistivity change law when it was loaded under long age condition. The results show that the fraction of resistivity change during loading (in compression and flexure) is low for all specimens in the long-age condition, but the resistivity change is consistent with its internal change. Uniaxial compressive cyclic loading in the elastic phase, each specimen exhibits a piezoresistivity under each loading cycle, while the material's own resistance under bending loading increases irreversibly as the loading progresses. In addition, for the flexural toughness evaluation test of fibre concrete, an adjustable deflection test device is designed based on existing codes, which can effectively solve the drawback of the existing bracket for fixing the deflection test instrument in the span, which needs to know the type of instrument in advance and then reserve the through-holes that can be clamped to the instrument.

Feature Selection, Construction, and Validation of a Lightweight Model for Foot Function Assessment During Gait With In-Shoe Motion Sensors

Identifying and monitoring overpronation and oversupination in the long term during activities of daily living is essential for people’s ambulatory health. Using an in-shoe motion sensor (IMS) with power-saving functions is a potential solution. In this study, we challenged the development of an estimation model of foot function using the foot center of pressure excursion index (CPEI) as an index via linear multivariate regression, which is sufficiently light for this type of IMS. Data collected from 65 and 17 participants were involved in model construction and validation, respectively. We validated ten scenarios simulating daily living activities, including walking on different surfaces, using different shoes, with or without carrying a bag, and indoors and outdoors. We applied statistic parametric mapping (SPM) to determine significant predictors and performed our original feature selection algorithm, leave-one-subject-out LASSO, to compress the volume of the predictors. We successfully discovered significant sex-specific predictors for foot function estimation from foot motion and constructed large effect-sized sex-specific foot function estimation models that achieved high-precision CPEI estimation. In the validation, the model successfully estimated a maximum of 99.0% and 100.0% males’ and females’ data under the same experimental conditions with the training data and 92.8–100.0% and 85.8–100.0% data in different scenarios. The constructed models are effective and possible to provide applications for long-term foot function monitoring by using an IMS.

Electrospun Nanofibers Hybrid Wrinkled Micropyramidal Architectures for Elastic Self-Powered Tactile and Motion Sensors.

Conformable, sensitive, long-lasting, external power supplies-free multifunctional electronics are highly desired for personal healthcare monitoring and artificial intelligence. Herein, we report a series of stretchable, skin-like, self-powered tactile and motion sensors based on single-electrode mode triboelectric nanogenerators. The triboelectric sensors were composed of ultraelastic polyacrylamide (PAAm)/(polyvinyl pyrrolidone) PVP/(calcium chloride) CaCl2 conductive hydrogels and surface-modified silicon rubber thin films. The significant enhancement of electrospun polyvinylidene fluoride (PVDF) nanofiber-modified hierarchically wrinkled micropyramidal architectures for the friction layer was studied. The mechanism of the enhanced output performance of the electrospun PVDF nanofibers and the single-side/double-side wrinkled micropyramidal architectures-based sensors has been discussed in detail. The as-prepared devices exhibited excellent sensitivity of a maximum of 20.1 V/N (or 8.03 V/kPa) as tactile sensors to recognize a wide range of forces from 0.1 N to 30 N at low frequencies. In addition, multiple human motion monitoring was demonstrated, such as knee, finger, wrist, and neck movement and voice recognition. This work shows great potential for skin-like epidermal electronics in long-term medical monitoring and intelligent robot applications.

Landslide Monitoring along the Dadu River in Sichuan Based on Sentinel-1 Multi-Temporal InSAR

The Dadu River travels in the mountainous areas of southwestern China, one of regions with the most hazards that has long suffered from frequent geohazards. The early identification of landslides in this region is urgently needed, especially after the recent Luding earthquake (MS 6.8). While conventional ground-based monitoring techniques are limited by the complex terrain conditions in these alpine valley regions, space interferometric synthetic aperture radar (InSAR) provides an incomparable advantage in obtaining surface deformation with high precision and over a wide area, which is very useful for long-term and slow geohazard monitoring. In this study, more than 500 Sentinel-1 SAR images with four frames acquired during 2017~2022 were collected to detect the hidden landslide regions from the Jinchuan to Ebian Section along the Dadu River, based on joint-scatterer InSAR (JS-InSAR) and small baseline subset (SBAS) techniques. The results showed that our method could be successfully applied for landslide monitoring in complex mountainous regions. Furthermore, 143 potential landslide regions spreading over an 800 km area along the Dadu River were extracted by integrating the deformation measurements and optical images. Our study can provide a reference for large-scale geological hazard surveys in mountainous areas, and the InSAR technique will be encouraged for the local government in future long-term monitoring applications in the Dadu River Basin.

Strain-induced conductive network and memory effect of maximum strain in liquid metal hierarchical structure

Liquid metals based on gallium have attracted considerable attention for flexible electronics, thanks to their excellent combination of stretchability and conductivity. Nevertheless, the degradations of electrical properties under deformation and effective tune of electrical resistance like a rheostat remain problems to be solved. Herein, a hierarchical structure of liquid metal particles is prepared by the combination of oxidation process and two-step physical vapor deposition. Owing to the rupture of particles, the electromechanical response allows resistance to irreversibly decrease in response to increased tensile strains and remain constant during strain release. Furthermore, the rupture level of core–shell structural particle can be controlled by the applied strain, resulting in strain-induced electrical properties. Notable characteristics include memory effect of maximum strain. As long as the strain is smaller than the maximum strain experienced previously, the strain-induced conductive network maintains nearly constant resistances to cyclic deformations (R/R0 < 1% above 1000 cycles). Finally, only based on the resistance before and after deformation, a class of devices is developed specifically for measuring and memorizing the maximum strain. The batteryless operation feature allows the device promising applications in long-term monitoring.

Low Power IoT based Implementation ECG &amp; Health Monitoring System.

The demand for efficient and cost-effective health monitoring systems is increasing rapidly due to the growing aging population and rising health concerns. In this context, the Low Power IoT-Based Implementation ECG &amp; Health Monitoring System proposed in this project is a significant step forward. The system incorporates the MAX30100 sensor and ESP32 to monitor and track the user's electrocardiogram (ECG) signals and various other health parameters, such as heart rate, blood oxygen levels, and temperature. The proposed system is highly reliable, accurate, and portable, making it an ideal choice for health monitoring applications.&#x0D; The MAX30100 sensor is a low-cost, highly sensitive optical sensor that measures blood oxygen levels and heart rate through the fingertip. The ESP32 is a low-power, high-performance microcontroller with built-in Wi-Fi and Bluetooth capabilities, enabling the proposed system to be connected to the internet and transmit data wirelessly. In addition, the system features an inbuilt LCD that displays the readings and a Telegram bot that provides real-time remote monitoring of the user's health data.&#x0D; The proposed system's power consumption is incredibly low, making it suitable for long-term health monitoring applications. Moreover, the system's low-power consumption also ensures extended battery life, making it highly efficient and cost-effective.&#x0D; Overall, the proposed Low Power IoT-Based Implementation ECG &amp; Health Monitoring System offers a highly reliable and efficient solution for health monitoring applications. The combination of the MAX30100 sensor and ESP32 microcontroller provides highly accurate measurements, and the system's low-power consumption ensures extended battery life. The Telegram bot and inbuilt LCD offer real-time monitoring capabilities, making it an ideal choice for remote health monitoring applications.

Accuracy and repeatability of the Microsoft Azure Kinect for clinical measurement of motor function.

Quantitative assessment of motor function is increasingly applied in fall risk stratification, diagnosis, and disease monitoring of neuro-geriatric disorders of balance and gait. Its broad application, however, demands for low-cost and easy to use solutions that facilitate high-quality assessment outside laboratory settings. In this study, we validated in 30 healthy adults (12 female, age: 32.5 [22 - 62] years) the performance and accuracy of the latest generation of the Microsoft RGB-D camera, i.e., Azure Kinect (AK), in tracking body motion and providing estimates of clinical measures that characterise static posture, postural transitions, and locomotor function. The accuracy and repeatability of AK recordings was validated with a clinical reference standard multi-camera motion capture system (Qualisys) and compared to its predecessor Kinect version 2 (K2). Motion signal quality was evaluated by Pearson's correlation and signal-to-noise ratios while the accuracy of estimated clinical parameters was described by absolute and relative agreement based on intraclass correlation coefficients. The accuracy of AK-based body motion signals was moderate to excellent (RMSE 89 to 20 mm) and depended on the dimension of motion (highest for anterior-posterior dimension), the body region (highest for wrists and elbows, lowest for ankles and feet), and the specific motor task (highest for stand up and sit down, lowest for quiet standing). Most derived clinical parameters showed good to excellent accuracy (r .84 to .99) and repeatability (ICC(1,1) .55 to .94). The overall performance and limitations of body tracking by AK were comparable to its predecessor K2 in a cohort of young healthy adults. The observed accuracy and repeatability of AK-based evaluation of motor function indicate the potential for a broad application of high-quality and long-term monitoring of balance and gait in different non-specialised environments such as medical practices, nursing homes or community centres.

Atrial Fibrillation Monitoring Based on Noncontact Capacitive ECG Using an Integrated Microhumidity Fabric Electrode-Sheet Sensing Scheme

This study designed a novel noncontact capacitive Electrocardiogram (cECG) system for long-term atrial fibrillation (AF) monitoring. Unlike conventional ECG monitoring, the proposed system can record ECG signals without touching a subject’s skin, avoiding the problem of skin allergy by using wet electrodes. The main contributions of this study include the two aspects. Firstly, a noncontact electrode based on a micro-humidity fabric structure is proposed, which can improve the noncontact cECG signal quality. Secondly, based on the proposed electrode, the possibility of its application in long-term AF monitoring was investigated. The micro-humidity fabric electrode can improve the micro-humidity of the skin-electrode interface and the noncontact cECG signal quality. This humidity is low and can hardly be felt by the human body, which can also ensure comfort. The experimental results show that compared with the conventional noncontact fabric electrode, the skin-electrode impedance decreases from 104.1±58.1 MΩ (when using the electrode without the micro-humidity structure) at 0.5 Hz to 2.8±1.79 MΩ (with the micro-humidity structure). In the long-term cECG recording experiment, the system has high consistency with the reference equipment. The RR interval correlation coefficient is 0.998, and the maximum error ≤ 18 ms. For the validation of AF monitoring, a designed AF analysis algorithm is integrated into the noncontact cECG system, including effective signal screening and AF recognition algorithm based on RR interval and SVM, with an average accuracy of 98.57% on the wearable database. The algorithm is verified on 3 healthy people and 1 PAF patient using the noncontact cECG system with an average accuracy of 98.12%, showing that our system has the potential for long-term AF monitoring.

An Adaptive Energy Efficient MAC Protocol for RF Energy Harvesting WBANs

Continuous and remote health monitoring medical applications with heterogeneous requirements can be realized through wireless body area networks (WBANs). Energy harvesting is adopted to enable low-power health applications and long-term monitoring without battery replacement, which have drawn significant interest recently. Because energy harvesting WBANs are obviously different from battery-powered ones, network protocols should be designed accordingly to improve network performance. In this article, an efficient cross-layer media access control protocol is proposed for radio frequency powered energy harvesting WBANs. We redesigned the superframe structure, which can be rescheduled by the coordinator dynamically. A time switching (TS) strategy is used when sensors harvest energy from radio frequency signals broadcast by the coordinator, and a transmission power adjustment scheme is proposed for sensors based on the energy harvesting efficiency and the network environment. Energy efficiency can be effectively improved that more packets can be uploaded using limited energy. The length of the energy harvesting period is determined by the coordinator to balance the channel resources and energy requirements of sensors and further improve the network performance. Numerical simulation results show that our protocol can provide superior system performance for long-term periodic health monitoring applications.

Adhesive free, conformable and washable carbon nanotube fabric electrodes for biosensing

AbstractSkin-mounted wearable electronics are attractive for continuous health monitoring and human-machine interfacing. The commonly used pre-gelled rigid and bulky electrodes cause discomfort and are unsuitable for continuous long-term monitoring applications. Here, we design carbon nanotubes (CNTs)-based electrodes that can be fabricated using different textile manufacturing processes. We propose woven and braided electrode design using CNTs wrapped textile yarns which are highly conformable to skin and measure a high-fidelity electrocardiography (ECG) signal. The skin-electrode impedance analysis revealed size-dependent behavior. To demonstrate outstanding wearability, we designed a seamless knit electrode that can be worn as a bracelet. The designed CNT-based dry electrodes demonstrated record high signal-to-noise ratios and were very stable against motion artifacts. The durability test of the electrodes exhibited robustness to laundering and practicality for reusable and sustainable applications.

A novel approach to automatic sleep stage classification using forehead electrophysiological signals

BackgroundSleep stage scoring is very important for the effective diagnosis and intervention of sleep disorders. However, the current automatic sleep staging methods generally have the problems of poor model generalization ability and non-portable acquisition equipment. MethodIn this paper, we propose a novel automatic sleep scoring system based on forehead electrophysiological signals that is more effective and convenient than other systems. We extract 3 channel signals from the forehead, named forehead electroencephalogram 1 (Fh1), forehead electroencephalogram 2 (Fh2), and forehead center electrooculogram (Fhz). Spectral features, statistical features, and entropy features are extracted using the discrete wavelet transform (DWT) method. Light gradient boosting machine (LGB), random forest (RF), and support vector machine (SVM) are employed to classify four stages: awake, light sleep (LS), deep sleep (DS), and rapid eye movement (REM). ResultThe performance of the proposed method is validated using databases of the Sleep-EDFX and our Own-data, which include polysomnograms (PSGs) and forehead signals of 28 subjects. The overall classification accuracy of using the combination of Fh1, Fh2, and Fhz can reach up to 90.25% accuracy with a kappa coefficient of 0.857. ConclusionsThe proposed method could provide state-of-art multichannel sleep stage scoring performance with higher portability. This will facilitate the application of long-term monitoring of sleep quality in the future.