Search

Chronic Obstructive Pulmonary Disease (COPD), as the third leading cause of death worldwide, is a major global health issue. The early detection and grading of COPD are pivotal for effective treatment. Traditional spirometry tests, requiring considerable physical effort and strict adherence to quality standards, pose challenges in COPD diagnosis. Volumetric capnography (VCap), which can be performed during natural breathing without requiring additional compliance, presents a promising alternative tool. In this study, the dataset comprised 279 subjects with normal pulmonary function and 148 patients diagnosed with COPD. We introduced a novel quantitative analysis method for VCap. Volumetric capnograms were converted into two-dimensional grayscale images through the application of Gramian Angular Field (GAF) transformation. Subsequently, a multi-scale convolutional neural network, CapnoNet, was conducted to extract features and facilitate classification. To improve CapnoNet's performance, two data augmentation techniques were implemented. The proposed model exhibited a detection accuracy for COPD of 95.83%, with precision, recall, and F1 measures of 95.21%, 95.70%, and 95.45%, respectively. In the task of grading the severity of COPD, the model attained an accuracy of 96.36%, complemented by precision, recall, and F1 scores of 88.49%, 89.99%, and 89.15%, respectively. This work provides a new perspective for the quantitative analysis of volumetric capnography and demonstrates the strong performance of the proposed CapnoNet in the diagnosis and grading of COPD. It offers direction and an effective solution for the clinical application of capnography. [ABSTRACT FROM AUTHOR]

Dementia‐associated disorders cause damage to the brains of patients and bring huge burdens to individuals and families. Electroencephalogram (EEG) monitoring is friendly to patients on account of low cost, non‐invasion, and objective. Event‐related potential (ERP) is a component of EEG that has huge potential to evaluate the cognitive function of the brain. In this study, we recorded the ERP from patients with dementia and healthy people, then proposed an ERP‐based deep learning method to realize dementia recognition via the model Dementia‐Unet (D‐Unet). To improve the performance of the model, on the base of the decoder and the primary classifier, we added new structures including a symmetric decoder and two auxiliary outputs. One of the auxiliary outputs was input reconstruction, and the other one was aimed at working like the primary classifier with the same task. The results of the experiment of four‐fold cross‐validation demonstrated the two auxiliary outputs improved the performance of the model effectively. When compared with some other machine learning methods and deep learning methods, our model obtained the best performance with an accuracy of 0.815, a precision of 0.829, a recall of 0.797, and an f1‐score of 0.812. Besides, we put up a complex training strategy with all outputs involved, but a simple testing strategy with only a primary classifier working to keep high performance but cut down the complexity burden during testing. [ABSTRACT FROM AUTHOR]

The pneumotachograph (PNT), a commonly used flowmeter in pulmonary function diagnostic equipment, is the required frequency calibration to maintain high accuracy. Aiming to simplify calibration steps, we developed a fast calibration system with a commercially available 3L syringe to provide a real output flow waveform. The acquisition of the real output flow waveform is based on the reliable measurement of in-cylinder pressure and the real-time detection of plunger speed. To improve the calibration accuracy, the tapping position for measuring in-cylinder pressure was optimized by CFD dynamic-mesh updating technique. The plunger speed was obtained by tracking the handle of the plunger with a smart terminal. Then, the real output flow was corrected using a compensation model equation. The calibration system was verified by the pulmonary waveform generator that the accuracy satisfied the requirements for respiratory flow measurement according to ATS standardization. The experimental results suggest that the developed method promises the fast calibration of PNT. [ABSTRACT FROM AUTHOR]

An airborne anemometer, which monitors wind on the basis of Meteorological Multi-rotor UAVs (Unmanned Aerial Vehicles), is important for the prevention of catastrophe. However, its performance will be affected by the self-excited air turbulence generated by UAV rotors. In this paper, for the purpose of the correction of an error, we developed a method for the elimination of the influence of air turbulence on wind speed measurement. The corresponding correction model is obtained according to the CFD (Computational Fluid Dynamics) simulation of a six-rotor UAV which is carried out with the sliding grid method and the S-A turbulence model. Then, the model is applied to the developed prototype by adding the angle of attack compensation model of the airborne anemometer. It is shown by the actual application that the airborne anemometer can maintain the original measurement accuracy at different ascent speeds. [ABSTRACT FROM AUTHOR]

Pulse wave velocity (PWV) measured at a specific artery location is called local PWV, which provides the elastic characteristics of arteries and indicates the degree of arterial stiffness. However, the large and cumbersome ultrasound probes require an appropriate sensor position and pressure maintenance, introducing usability constraints. In this paper, we developed a light (0.5 g) and thin (400 μ m) flexible ultrasound array by encapsulating 1–3 composite piezoelectric transducers with a silicone elastomer. It can capture the distension waveforms of four arterial positions with a spacing of 10 mm and calculate the local PWV by multi-point fitting. This is illustrated by in vivo experiments, where the local PWV value of five normal subjects ranged from 3.07 to 4.82 m/s, in agreement with earlier studies. The beat-to-beat coefficient of variation (CV) is 12.0% ± 3.5%, showing high reliability. High reproducibility is shown by the results of two groups of independent measurements of three subjects (the error between the mean values is less than 0.3 m/s). These properties of the developed flexible ultrasound array enable the bandage-like application of local PWV monitoring to skin surfaces. [ABSTRACT FROM AUTHOR]

Emotion recognition is receiving significant attention in research on health care and Human-Computer Interaction (HCI). Due to the high correlation with emotion and the capability to affect deceptive external expressions such as voices and faces, Electroencephalogram (EEG) based emotion recognition methods have been globally accepted and widely applied. Recently, great improvements have been made in the development of machine learning for EEG-based emotion detection. However, there are still some major disadvantages in previous studies. Firstly, traditional machine learning methods require extracting features manually which is time-consuming and rely heavily on human experts. Secondly, to improve the model accuracies, many researchers used user-dependent models that lack generalization and universality. Moreover, there is still room for improvement in the recognition accuracies in most studies. Therefore, to overcome these shortcomings, an EEG-based novel deep neural network is proposed for emotion classification in this article. The proposed 2D CNN uses two convolutional kernels of different sizes to extract emotion-related features along both the time direction and the spatial direction. To verify the feasibility of the proposed model, the pubic emotion dataset DEAP is used in experiments. The results show accuracies of up to 99.99% and 99.98 for arousal and valence binary classification, respectively, which are encouraging for research and applications in the emotion recognition field. [ABSTRACT FROM AUTHOR]

Respiration monitoring is vital for human health assessment. Humidity sensing is a promising way to establish a relationship between human respiration and electrical signal. This paper presents a polyimide-based film bulk acoustic resonator (PI-FBAR) humidity sensor operating in resonant frequency and reflection coefficient S11 dual-parameter with high sensitivity and stability, and it is applied in real-time human respiration monitoring for the first time. Both these two parameters can be used to sense different breathing conditions, such as normal breathing and deep breathing, and breathing with different rates such as normal breathing, slow breathing, apnea, and fast breathing. Experimental results also indicate that the proposed humidity sensor has potential applications in predicting the fitness of individual and in the medical field for detecting body fluids loss and daily water intake warning. The respiratory rates measured by our proposed PI-FBAR humidity sensor operating in frequency mode and S11 mode have Pearson correlation of up to 0.975 and 0.982 with that measured by the clinical monitor, respectively. Bland–Altman method analysis results further revealed that both S11 and frequency response are in good agreement with clinical monitor. The proposed sensor combines the advantages of non-invasiveness, high sensitivity and high stability, and it has great potential in human health monitoring. [ABSTRACT FROM AUTHOR]

Objective: Pulmonary function parameters play a pivotal role in the assessment of respiratory diseases. However, the accuracy of the existing methods for the prediction of pulmonary function parameters is low. This study proposes a combination algorithm to improve the accuracy of pulmonary function parameter prediction. Methods: We first established a system to collect volumetric capnography and then processed the data with a combination algorithm to predict pulmonary function parameters. The algorithm consists of three main parts: a medical feature regression structure consisting of support vector machines (SVM) and extreme gradient boosting (XGBoost) algorithms, a sequence feature regression structure consisting of one-dimensional convolutional neural network (1D-CNN), and an error correction structure using improved K-nearest neighbor (KNN) algorithm. Results: The root mean square error (RMSE) of the pulmonary function parameters predicted by the combination algorithm was less than 0.39L and the R2 was found to be greater than 0.85 through a ten-fold cross-validation experiment. Conclusion: Compared with the existing methods for predicting pulmonary function parameters, the present algorithm can achieve a higher accuracy rate. At the same time, this algorithm uses specific processing structures for different features, and the interpretability of the algorithm is ensured while mining the feature depth information. [ABSTRACT FROM AUTHOR]

This paper presents a polyimide-based film bulk acoustic resonator (PI-FBAR) humidity sensor operating in resonant frequency and reflection coefficient S11 dual-mode. Models and experiments showed that those two modes are governed by different mechanisms, of which the former is based on the modulation of the humidity on the Young’s modulus of PI, while the latter is based on the modulation of the humidity on dynamic resistance. In the full-scale relative humidity (RH) testing range (20%-80%), the resonant mode achieved a sensitivity of 29.93 kHz/%RH (28.56 ppm/%RH) with ultra-high linearity (${R}^{2}=0.9993$), and the humidity hysteresis error is only about 1.32% RH. For the S11 response, an ultra-high average humidity sensitivity of 0.044dB/%RH (2095ppm/%RH) was achieved, and the sensitivity at 20% low relative humidity reached 0.075dB/%RH (3571ppm/%RH), which is more than 2 orders of magnitude higher than that of the resonant frequency response. And the limit of detection (LOD) for the humidity response of S11 is 0.035% RH, which is half lower than that of the resonant mode. Thus, we can choose a more appropriate sensing mode according to particular application or combine these two mechanisms in one test to expand the sensor competences by taking advantages of each method. In addition, as both of the two modes have high sensitivity to humidity and temperature, we deduced a method to calibrate the temperature for the humidity sensing. Based on this dual-mode mechanism, we can further achieve either temperature-calibrated humidity sensing or dual-variable sensing of humidity and temperature with more accurate sensing results. [ABSTRACT FROM AUTHOR]

Geographic location of nodes is very useful for a sensor network. A novel and practical Radio Frequency (RF)-based localization algorithm called Kcdlocation has been presented for some specific sensor network topologies, such as the grid and linear types. The Kcdlocation algorithm is adapted to those wireless sensor networks deployed with known coordinate database. It examines the ordered sequence of neighboring unknown nodes relative to some anchor nodes so that they are ranked to compute the location of unknown nodes by wireless localization measurements. After the task of distinguishing neighboring unknown nodes is completed through the ranging technology, the correct position for each sensor node would be identified. The localization scalability and fault tolerant performance of this algorithm have been evaluated from the perspective of practicability. Its performances for the real circumstance are verified through different experiments with several RF channels and deployment parameters. The node localization accuracy of Kcdlocation in a 5 * 4 grid network reaches 100% in a flat open square.

Today, excessive psychological stress has become a universal threat to humans. That stress can heavily affect work and study when a person repeatedly is exposed to high stress. If that exposure is long enough, it can even cause cardiovascular disease and cancer. Therefore, both monitoring and managing of stress is imperative to reduce the bad outcomes from excessive psychological stress. Conventional monitoring methods firstly extract the characteristics of the RR interval of an electrocardiogram (ECG) from a time domain and a frequency domain, then use machine learning models, like SVM, random forest, and decision tree, to distinguish the level of that stress. The biggest limitation of using these methods is that at least one minute of ECG data and other signals are indispensable to ensure the high accuracy of the results. This will greatly affect the real-time application of the models. To satisfy real-time detection of stress with high accuracy, we proposed a framework based on deep learning technology. The proposed monitoring framework is based on convolutional neural networks (CNN) and bidirectional long short-term memory (BiLSTM). To evaluate the performance of this network, we conducted the experiments applying conventional methods. The data for the 34 subjects were collected on the server platform created by the group at the Institute of Psychology of the Chinese Academy of Sciences and our group. The accuracy of the proposed framework was up to 0.865 on three levels of stress using a 10 s ECG signal, a 0.228 improvement compared with conventional methods. Therefore, our proposed framework is more suitable for real-time applications [ABSTRACT FROM AUTHOR]

To satisfy the need to accurately monitor emotional stress, this paper explores the effectiveness of the attention mechanism based on the deep learning model CNN (Convolutional Neural Networks)-BiLSTM (Bi-directional Long Short-Term Memory) As different attention mechanisms can cause the framework to focus on different positions of the feature map, this discussion adds attention mechanisms to the CNN layer and the BiLSTM layer separately, and to both the CNN layer and BiLSTM layer simultaneously to generate different CNN–BiLSTM networks with attention mechanisms. ECG (electrocardiogram) data from 34 subjects were collected on the server platform created by the Institute of Psychology of the Chinese Academy of Science and the researches. It verifies that the average accuracy of CNN–BiLSTM is up to 0.865 without any attention mechanism, while the highest average accuracy of 0.868 is achieved using the CNN–attention–based BiLSTM. [ABSTRACT FROM AUTHOR]

A high-precision humidity response time measurement has been urgently needed for the fast response humidity sensor in some special situations, for instance, when the quadcopter performs the meteorological observations in the atmospheric boundary layer, the relative humidity changes drastically as it flies into the cloud. So it is essential to gain the accurate response time for these sensors. However, owing to the uncontrollable errors, the conventional methods are difficult to carry out an accurate measurement. Herein, for meeting the requirements above, we designed an accurate measurement method based on a type of switchable chamber and a humidity generator. Among, the chamber was designed through surface molecular dynamics analysis and verified by experiments. It is proved that the switchable chamber with the hydrophobic surface and low water molecule content, combined with the surface to volume ratio S/V = 0.2 can achieve the realistic humidity response time of the sensor. For a commercial sensor (SHT20) at 25 °C, the time corresponding to the 63% and 90% complete responses are 7 s and 49 s measured in this way, which is extraordinarily improved than those traditional ways (51 s and 140 s). As a result, this measurement method could gain the accurate response time for the special situation applications. [ABSTRACT FROM AUTHOR]

• A novel thermodynamic control model was established. • Adding additional compensation function solved the problem of temperature gradient. • A chip-level oven-controlled sensor system was designed and implemented. • Oven-controlled system improved performance of silicon piezoresistive sensors. High precision is an important indicator for the silicon piezoresistive pressure sensor, which is deeply affected by the ambient temperature. This paper presented a chip-level oven-controlled system to operate the silicon piezoresistive pressure sensor at a constant temperature. However, the changes in ambient temperature still affect the temperature of the silicon piezoresistive pressure sensor due to the non-coplanar temperature control and the direct heat transfer between the piezoresistance on the surface of the pressure sensor and the environment. In order to decrease the effects and further improve the accuracy of the silicon piezoresistive sensor, a compensation function was introduced in the designed system. In addition, the oven-controlled structure fabricated by the MEMS process and the silicon piezoresistive pressure sensor were implemented at the chip level, which further reduced power consumption. The feasibility of the design was verified by the results of the thermodynamic model and COMSOL Multiphysics simulation analysis. Test results showed that when the pressure ranged from 100 hPa to 1100 hPa, the designed system performed a maximum measurement error no more than ±0.2 hPa from −45 °C to 45 °C. After compensation, the accuracy, sensitivity temperature coefficient, offset temperature coefficient of the silicon piezoresistive pressure sensor can reach 0.02% FS, 1.081 × 10−5/°C, 2.22 × 10−4% FS/°C respectively. [ABSTRACT FROM AUTHOR]

In this study, the authors present an alternative method for poor accuracy of piezoresistive meteorology pressure sensing in low‐temperature environment (down to −45°C) by incorporating external thermodynamic control. In order to use the designed sensor in such a low‐temperature environment, the microelectromechanical systems (MEMS) chip itself has to be kept at 50°C, which is the most common used highest working temperature in meteorology field. The heat compensation is achieved by a pulse‐width modulation controlled heating resistor based on proportional–integral–derivative algorithm. The precision of thermal control was obtained at 50 ± 0.5°C during the bench test. The simulation results from COMSOL software are consisted with lumped element model analysis. Under the condition of environmental temperature down to −45°C, system achieved a maximum absolute error within ±0.5 hPa after pressure calibration. [ABSTRACT FROM AUTHOR]

In this paper, a wind energy harvester, which can be used as building skin, is developed. In order to overcome the defects of traditional wind energy harvester, such as expensive and crisp, the developed harvester is designed as a circular silicon plate with several symmetrically distributed rectangular cavities which were covered with ZnO (Zinc oxide) thin film. It is verified whether the designed harvester can function in turbulence flow by theoretical analysis and finite element analysis. The acoustic measurement illustrated that the output of designed device is linear to the frequency. And, the wind fluid experiments suggested that the thin film can vibrate under a low wind velocity 1 m/s and is easy to vibrate in wind turbulence. The maximum output power density is 23.39nW/cm 2 with a maximum open circuit output voltage 2.81 V. All of characteristics of designed harvester enable that it can be used as the building skin to harvest wind energy. [ABSTRACT FROM AUTHOR]

A dynamic heterogeneous and multihop (DHMH) wireless health monitoring system (WHMS) as a three-tier semi-self-organizing health monitoring network was presented. From bottom to top, the first tire of the network is the mobile data acquisition layer (DAL), the second tire of the network is the data transporting layer (DTL), and the third tire of the network is the data collection layer (DCL). A RF power control based topology management mechanism is proposed to balance the network load and to improve the network throughput. A lightweight hierarchical routing protocol (LHRP) was designed to reduce the transmission delay and improve the network throughput. For the mobile DAL nodes, the seamless mobile access mechanism (SMAM) was designed to ensure the low packet loss ratio. To evaluate the network performance, the end-to-end delay, the averaged reception ratio, and the network throughput of the DHMH were tested and the results proved that the network performance of the DHMH was improved. [ABSTRACT FROM AUTHOR]

Cachexia denotes a complex metabolic syndrome featuring severe loss of weight, fatigue and anorexia. In total, 50-80% of patients suffering from advanced cancer are diagnosed with cancer cachexia, which contributes to 40% of cancer-associated mortalities. MicroRNAs (miRNAs) are non-coding RNAs capable of regulating gene expression. Dysregulated miRNA expression has been observed in muscle tissue, adipose tissue and blood samples from patients with cancer cachexia compared with that of samples from patients with cancer without cachexia or healthy controls. In addition, miRNAs promote and maintain the malignant state of systemic inflammation, while inflammation contributes to cancer cachexia. The present review discusses the role of miRNAs in the progression of cancer cachexia, and assess their diagnostic value and potential therapeutic value. [ABSTRACT FROM AUTHOR]