A pooling convolution model for multi-classification of ECG and PCG signals.

Electrocardiogram (ECG) and phonocardiogram (PCG) signals are physiological signals generated throughout the cardiac cycle. The application of deep learning techniques to recognize ECG and PCG signals can greatly enhance the efficiency of cardiovascular disease detection. Therefore, we propose a series of straightforward and effective pooling convolutional models for the multi-classification of ECG and PCG signals. Initially, these signals undergo preprocessing. Subsequently, we design various structural blocks, including a stacked block (MCM) comprising convolutional layer and max-pooling layers, along with its variations, as well as a residual block (REC). By adjusting the number of structural blocks, these models can handle ECG and PCG data with different sampling rates. In the final tests, the models utilizing the MCM structural block achieved accuracies of 98.70 and 92.58% on the ECG and PCG fusion datasets, respectively. These accuracies surpass those of all networks utilizing its variations. Moreover, compared to the models employing the REC structural block, the accuracies are improved by 0.02 and 4.30%, respectively. Furthermore, this research has been validated through tests conducted on multiple ECG and PCG datasets, along with comparisons to other published literature. To further validate the generalizability of the model, an additional experiment involving the classification of a synchronized ECG-PCG dataset was conducted. This dataset is divided into seven different levels of fatigue based on the amount of exercise performed by each healthy subject during the testing process. The results indicate that the model using the MCM block also achieved the highest accuracy.

Boron nitride-enabled printing of a highly sensitive and flexible iontronic pressure sensing system for spatial mapping.

Recently, flexible iontronic pressure sensors (FIPSs) with higher sensitivities and wider sensing ranges than conventional capacitive sensors have been widely investigated. Due to the difficulty of fabricating the nanostructures that are commonly used on electrodes and ionic layers by screen printing techniques, strategies for fabricating such devices using these techniques to drive their mass production have rarely been reported. Herein, for the first time, we employed a 2-dimensional (2D) hexagonal boron nitride (h-BN) as both an additive and an ionic liquid reservoir in an ionic film, making the sensor printable and significantly improving its sensitivity and sensing range through screen printing. The engineered sensor exhibited high sensitivity (Smin> 261.4 kPa-1) and a broad sensing range (0.05-450 kPa), and it was capable of stable operation at a high pressure (400 kPa) for more than 5000 cycles. In addition, the integrated sensor array system allowed accurate monitoring of wrist pressure and showed great potential for health care systems. We believe that using h-BN as an additive in an ionic material for screen-printed FIPS could greatly inspire research on 2D materials for similar systems and other types of sensors. Hexagonal boron nitride (h-BN) was employed for the first time to make iontronic pressure sensor arrays with high sensitivity and a broad sensing range by screen printing.

A Pressure and Temperature Dual-Parameter Sensor Based on a Composite Material for Electronic Wearable Devices.

Wearable sensors integrating multiple functionalities are highly desirable in artificial wearable devices, which are of great significance in the field of biomedical research and for human-computer interactions. However, it is still a great challenge to simultaneously perceive multiple external stimuli such as pressure and temperature with one single sensor. Combining the piezoresistive effect with the negative temperature coefficient of resistance, in this paper, we report on a pressure-temperature dual-parameter sensor composed of a polydimethylsiloxane film, carbon nanotube sponge, and poly(3,4-ethylenedioxythiophene)-poly(styrenesulfonate). The proposed multifunctional sensor can stably monitor pressure signals with a high sensitivity of 16 kPa-1, has a range of up to 2.5 kPa, and also has a fast response time. Meanwhile, the sensor can also respond to temperature changes with an ultrahigh sensitivity rate of 0.84% °C-1 in the range of 20 °C to 80 °C. To validate the applicability of our sensor in practical environments, we conducted real-scene tests, which revealed its capability for monitoring = human motion signals while simultaneously sensing external temperature stimuli, reflecting its great application prospects for electronic wearable devices.

Double Fano Resonance and Independent Regulation Characteristics in a Rectangular-like Nanotetramer Metasurface Structure.

Fano resonance, which is based on a plasmonic metasurface, has many potential applications in various fields, such as biochemical sensors, slow light effect, and integrated optical circuits. In this study, a rectangular-like nanotetramer metasurface structure composed of four round-head nanorods was designed. The transmission spectrum, surface charge, and electrical field distributions of the proposed structure were simulated using the finite element method. A double Fano resonance profile was observed in the transmission spectrum. One of the Fano resonances was caused by the symmetry breaking and plasmon hybridization between the horizontal double rods, whereas the other resonance was due to the plasmonic modes' hybridization among four nanorods. These resonances could be independently tuned because of different formation mechanisms. The number of Fano resonances could be adjusted by changing the coupling distance between the horizontal and vertical rods. The results contributed to designing the highly sensitive sensors based on the plasmonic metasurface.

Refractive Index Sensor Based on the Fano Resonance in Metal-Insulator-Metal Waveguides Coupled with a Whistle-Shaped Cavity.

A plasmonic refractive index sensor based on surface plasmon polaritons (SPPs) that consist of metal-insulator-metal (MIM) waveguides and a whistle-shaped cavity is proposed. The transmission properties were simulated numerically by using the finite element method. The Fano resonance phenomenon can be observed in their transmission spectra, which is due to the coupling of SPPs between the transmission along the clockwise and anticlockwise directions. The refractive index-sensing properties based on the Fano resonance were investigated by changing the refractive index of the insulator of the MIM waveguide. Modulation of the structural parameters on the Fano resonance and the optics transmission properties of the coupled structure of two MIM waveguides with a whistle-shaped cavity were designed and evaluated. The results of this study will help in the design of new photonic devices and micro-sensors with high sensitivity, and can serve as a guide for future application of this structure.

Design and Fabrication of High-Frequency Piezoelectric Micromachined Ultrasonic Transducer Based on an AlN Thin Film.

A piezoelectric micromachined ultrasonic transducer (PMUT) is a microelectromechanical system (MEMS) device that can transmit and receive ultrasonic waves. Given its advantages of high-frequency ultrasound with good directionality and high resolution, PMUT can be used in application scenarios with low power supply, such as fingerprint recognition, nondestructive testing, and medical diagnosis. Here, a PMUT based on an aluminum nitride thin-film material is designed and fabricated. First, the eigenfrequencies of the PMUT are studied with multiphysics coupling simulation software, and the relationship between eigenfrequencies and vibration layer parameters is determined. The transmission performance of the PMUT is obtained via simulation. The PMUT device is fabricated in accordance with the designed simple MEMS processing process. The topography of the PMUT vibration layer is determined via scanning electron microscopy, and the resonant frequency of the PMUT device is 7.43 MHz. The electromechanical coupling coefficient is 2.21% via an LCR tester.

Automatic Classification Framework of Tongue Feature Based on Convolutional Neural Networks.

Tongue diagnosis is an important part of the diagnostic process in traditional Chinese medicine (TCM). It primarily relies on the expertise and experience of TCM practitioners in identifying tongue features, which are subjective and unstable. We proposed a tongue feature classification framework based on convolutional neural networks to reduce the differences in diagnoses among TCM practitioners. Initially, we used our self-designed instrument to capture 482 tongue photos and created 11 data sets based on different features. Then, the tongue segmentation task was completed using an upgraded facial landmark detection method and UNET. Finally, we used ResNet34 as the backbone to extract features from the tongue photos and classify them. Experimental results show that our framework has excellent results with an overall accuracy of over 86 percent and is particularly sensitive to the corresponding feature regions, and thus it could assist TCM practitioners in making more accurate diagnoses.

Enhancement of the Transmission Performance of Piezoelectric Micromachined Ultrasound Transducers by Vibration Mode Optimization.

Ultrasound is widely used in industry and the agricultural, biomedical, military, and other fields. As key components in ultrasonic applications, the characteristic parameters of ultrasonic transducers fundamentally determine the performance of ultrasonic systems. High-frequency ultrasonic transducers are small in size and require high precision, which puts forward higher requirements for sensor design, material selection, and processing methods. In this paper, a three-dimensional model of a high-frequency piezoelectric micromachined ultrasonic transducer (PMUT) is established based on the finite element method (FEM). This 3D model consists of a substrate, a silicon device layer, and a molybdenum-aluminum nitride-molybdenum (Mo-AlN-Mo) sandwich piezoelectric layer. The effect of the shape of the transducer's vibrating membrane on the transmission performance was studied. Through a discussion of the parametric scanning of the key dimensions of the diaphragms of the three structures, it was concluded that the fundamental resonance frequency of the hexagonal diaphragm was higher than that of the circle and the square under the same size. Compared with the circular diaphragm, the sensitivity of the square diaphragm increased by 8.5%, and the sensitivity of the hexagonal diaphragm increased by 10.7%. The maximum emission sound-pressure level of the hexagonal diaphragm was 6.6 times higher than that of the circular diaphragm. The finite element results show that the hexagonal diaphragm design has great advantages for improving the transmission performance of the high-frequency PMUT.

Design of a Novel Medical Acoustic Sensor Based on MEMS Bionic Fish Ear Structure.

High-performance medical acoustic sensors are essential in medical equipment and diagnosis. Commercially available medical acoustic sensors are capacitive and piezoelectric types. When they are used to detect heart sound signals, there is attenuation and distortion due to the sound transmission between different media. This paper proposes a new bionic acoustic sensor based on the fish ear structure. Through theoretical analysis and finite element simulation, the optimal parameters of the sensitive structure are determined. The sensor is fabricated using microelectromechanical systems (MEMS) technology, and is encapsulated in castor oil, which has an acoustic impedance close to the human body. An electroacoustic test platform is built to test the performance of the sensor. The results showed that the MEMS bionic sensor operated with a bandwidth of 20-2k Hz. Its linearity and frequency responses were better than the electret microphone. In addition, the sensor was tested for heart sound collection application to verify its effectiveness. The proposed sensor can be effectively used in clinical auscultation and has a high SNR.

An Optimal Design Method for Improving the Efficiency of Ultrasonic Wireless Power Transmission during Communication.

Due to the excellent directivity, strong penetrability, and no electromagnetic shielding effect, ultrasonic waves have good potential for wireless energy transmission and information transfer inside and outside of sealed metal devices. However, traditional ultrasonic based energy transmission methods usually result in considerable energy consumption because of the impedance mismatch during the impedance modulation of the communication. This paper presents an optimal design method for efficient energy transfer during ultrasonic communication. The channel equivalent circuit model is established by only using the acoustic-electric channel scattering parameters. According to the equivalent circuit model, the channel impedance matches with a weak mismatch state is performed during the communication. In this way, the impedance modulation effect is ensured with a lower decrease in the energy transmission efficiency. Finally, the simultaneous energy transmission and impedance modulation are carried out through the 11 mm thick 304 stainless steel plate. The transmission power is 37.86 W with a transmission efficiency of 45.75%, and the modulation rate is 10 Kbps. Compared with the traditional methods, our proposed energy transmission efficiency is increased by 17.62%. The results verify the proposed method's effectiveness and the high accuracy of the model. The proposed method has great engineering applications and broad prospects in condition monitoring of metallic environments.