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.

This paper presents a polyimide-based film bulk acoustic resonator (PI-FBAR) humidity sensor operating in resonant frequency and reflection coefficient S ₁₁ 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 S ₁₁ 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 S ₁₁ 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.

Multi-label electrocardiogram (ECG) classification is of great significance for the diagnosis of cardiovascular diseases, and it is also a challenging task because of the various of pathological patterns across different cardiac abnormalities. This paper analyzes the complex spatial-temporal variations information contained in the 12-lead ECG from a new perspective, and proposes an advanced deep neural network framework to accurately identify various multi-label ECG abnormalities. Firstly, the 12-lead ECG was modeled as 3-dimensional (3-D) spatial-temporal variations involving the intra-period, inter-period temporal dimensions, and cross-lead spatial dimension. Then, a 3-D spatial-temporal learning network (3D-STLNet) was carefully designed to extract the complex pathological features from the 3-D spatial-temporal variations. Secondly, the multi-head attention (MHA) mechanism was introduced into the proposed network to extract global temporal dependencies in ECG segments, which further improved the performance of the proposed network. By integrating a residual backbone network, a 3D-STLNet, and the MHA module, our proposed network allows end-to-end learning and prediction in a unified framework. The influence of several classic threshold selection strategies on the performance of multi-label ECG classification algorithm was also analyzed, which provides a reference for subsequent research on optimal threshold selection for multi-label ECG classification. Finally, our proposed network was evaluated on multiple large multi-label ECG public datasets, and the performance of our network outperforms that of current state-of-the-art networks, which demonstrates that our network has great competitiveness in identifying a wider range of multi-label ECG abnormalities.

Single-resonator-based (SRB) sensors have thrived in many sensing applications. However, they cannot meet the high-sensitivity requirement of future high-end markets such as ultra-small mass sensors and ultra-low accelerometers, and are vulnerable to environmental influences. It is fortunate that the integration of dual or multiple resonators into a sensor has become an effective way to solve such issues. Studies have shown that dual-resonator-based (DRB) and multiple-resonator-based (MRB) MEMS sensors have the ability to reject environmental influences, and their sensitivity is tens or hundreds of times that of SRB sensors. Hence, it is worth understanding the state-of-the-art technology behind DRB and MRB MEMS sensors to promote their application in future high-end markets.

Objective . The ECG is a standard diagnostic tool for identifying many arrhythmias. Accurate diagnosis and early intervention for arrhythmias are of great significance to the prevention and treatment of cardiovascular disease. Our objective is to develop an algorithm that can automatically identify 30 arrhythmias by using varying-dimensional ECG signals. Approach . In this paper, we firstly proposed a novel multi-scale 2D CNN that can effectively capture pathological information from small-scale to large-scale from ECG signals to identify 30 arrhythmias from 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead ECGs. Secondly, we explored the effects of varying convolution kernels sizes and branch subnetworks on the model’s performance for each arrhythmia. Thirdly, we introduced the weighted focal loss to alleviate the positive-negative class imbalance problem in the multi-label arrhythmias classification. Fourthly, we explored the utility of reduced-lead ECGs in detecting arrhythmias by comparing the performances of models on varying-dimensional ECGs. Main results . As a follow-up entry after the PhysioNet/Computing in Cardiology Challenge (2021), our proposed approach achieved the official test scores of 0.52, 0.47, 0.53, 0.51, and 0.50 for the 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead ECGs on the hidden test set (comparable to that of 6th, 11th, 4th, 5th, and 7th out of 39 teams in the Challenge). Significance . A multi-scale framework capable of detecting 30 arrhythmias from varying-dimensional ECGs was proposed in our work. We preliminarily verified that the multi-scale perception fields may be necessary to capture more comprehensive pathological information for arrhythmias detection. Besides, we also verified that the weighted focal loss may alleviate the positive–negative class imbalance and improve the model’s generalization performance on the cross-dataset. In addition, we observed that some reduced-lead models, such as the 4-lead and 3-lead models, can even achieve performance that is almost comparable to that of the 12-lead model. The excellent performance of our proposed framework demonstrates its great potential in detecting a wide range of arrhythmias.