Micromachines

Research

Jump to: Review

12 pages, 1289 KiB

Open AccessArticle

An Arrhythmia Classification Model Based on Vision Transformer with Deformable Attention

by Yanfang Dong, Miao Zhang, Lishen Qiu, Lirong Wang and Yong Yu

Micromachines 2023, 14(6), 1155; https://doi.org/10.3390/mi14061155 - 30 May 2023

Cited by 11 | Viewed by 3272

Abstract

The electrocardiogram (ECG) is a highly effective non-invasive tool for monitoring heart activity and diagnosing cardiovascular diseases (CVDs). Automatic detection of arrhythmia based on ECG plays a critical role in the early prevention and diagnosis of CVDs. In recent years, numerous studies have [...] Read more.

The electrocardiogram (ECG) is a highly effective non-invasive tool for monitoring heart activity and diagnosing cardiovascular diseases (CVDs). Automatic detection of arrhythmia based on ECG plays a critical role in the early prevention and diagnosis of CVDs. In recent years, numerous studies have focused on using deep learning methods to address arrhythmia classification problems. However, the transformer-based neural network in current research still has a limited performance in detecting arrhythmias for the multi-lead ECG. In this study, we propose an end-to-end multi-label arrhythmia classification model for the 12-lead ECG with varied-length recordings. Our model, called CNN-DVIT, is based on a combination of convolutional neural networks (CNNs) with depthwise separable convolution, and a vision transformer structure with deformable attention. Specifically, we introduce the spatial pyramid pooling layer to accept varied-length ECG signals. Experimental results show that our model achieved an F1 score of 82.9% in CPSC-2018. Notably, our CNN-DVIT outperforms the latest transformer-based ECG classification algorithms. Furthermore, ablation experiments reveal that the deformable multi-head attention and depthwise separable convolution are both efficient in extracting features from multi-lead ECG signals for diagnosis. The CNN-DVIT achieved good performance for the automatic arrhythmia detection of ECG signals. This indicates that our research can assist doctors in clinical ECG analysis, providing important support for the diagnosis of arrhythmia and contributing to the development of computer-aided diagnosis technology. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

11 pages, 3305 KiB

Open AccessArticle

Simple Immunosensor Based on Carboxyl-Functionalized Multi-Walled Carbon Nanotubes @ Antimony-Doped Tin Oxide Composite Membrane for Aflatoxin B₁ Detection

by Guanglei Chu, Zengning Liu, Yanyan Zhang, Yemin Guo, Xia Sun and Ming Li

Micromachines 2023, 14(5), 996; https://doi.org/10.3390/mi14050996 - 3 May 2023

Cited by 1 | Viewed by 1760

Abstract

This paper presents a novel nano-material composite membrane for detecting aflatoxin B₁ (AFB₁). The membrane is based on carboxyl-functionalized multi-walled carbon nanotubes (MWCNTs-COOH) @ antimony-doped tin oxide (ATO)-chitosan (CS). To prepare the immunosensor, MWCNTs-COOH were dissolved in the CS solution, [...] Read more.

This paper presents a novel nano-material composite membrane for detecting aflatoxin B₁ (AFB₁). The membrane is based on carboxyl-functionalized multi-walled carbon nanotubes (MWCNTs-COOH) @ antimony-doped tin oxide (ATO)-chitosan (CS). To prepare the immunosensor, MWCNTs-COOH were dissolved in the CS solution, but some MWCNTs-COOH formed aggregates due to the intertwining of carbon nanotubes, blocking some pores. ATO was added to the solution containing MWCNTs-COOH, and the gaps were filled by adsorbing hydroxide radicals to form a more uniform film. This greatly increased the specific surface area of the formed film, resulting in a nano-composite film that was modified on screen-printed electrodes (SPCEs). The immunosensor was then constructed by immobilizing anti-AFB₁ antibodies (Ab) and bovine serum albumin (BSA) on an SPCE successively. The assembly process and effect of the immunosensor were characterized using scanning electron microscopy (SEM), differential pulse voltammetry (DPV), and cyclic voltammetry (CV). Under optimized conditions, the prepared immunosensor exhibited a low detection limit of 0.033 ng/mL with a linear range of 1 × 10⁻³–1 × 10³ ng/mL. The immunosensor demonstrated good selectivity, reproducibility, and stability. In summary, the results suggest that the MWCNTs-COOH@ATO-CS composite membrane can be used as an effective immunosensor for detecting AFB₁. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

9 pages, 720 KiB

Open AccessArticle

Dynamic Image Difficulty-Aware DNN Pruning

by Vasileios Pentsos, Ourania Spantidi and Iraklis Anagnostopoulos

Micromachines 2023, 14(5), 908; https://doi.org/10.3390/mi14050908 - 23 Apr 2023

Cited by 2 | Viewed by 1320

Abstract

Deep Neural Networks (DNNs) have achieved impressive performance in various image recognition tasks, but their large model sizes make them challenging to deploy on resource-constrained devices. In this paper, we propose a dynamic DNN pruning approach that takes into account the difficulty of [...] Read more.

Deep Neural Networks (DNNs) have achieved impressive performance in various image recognition tasks, but their large model sizes make them challenging to deploy on resource-constrained devices. In this paper, we propose a dynamic DNN pruning approach that takes into account the difficulty of the incoming images during inference. To evaluate the effectiveness of our method, we conducted experiments on the ImageNet dataset on several state-of-art DNNs. Our results show that the proposed approach reduces the model size and amount of DNN operations without the need to retrain or fine-tune the pruned model. Overall, our method provides a promising direction for designing efficient frameworks for lightweight DNN models that can adapt to the varying complexity of input images. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

16 pages, 3016 KiB

Open AccessArticle

A Multi-Parameter Fusion Method for Cuffless Continuous Blood Pressure Estimation Based on Electrocardiogram and Photoplethysmogram

by Gang Ma, Jie Zhang, Jing Liu, Lirong Wang and Yong Yu

Micromachines 2023, 14(4), 804; https://doi.org/10.3390/mi14040804 - 31 Mar 2023

Cited by 2 | Viewed by 1890

Abstract

Blood pressure (BP) is an essential physiological indicator to identify and determine health status. Compared with the isolated BP measurement conducted by traditional cuff approaches, cuffless BP monitoring can reflect the dynamic changes in BP values and is more helpful to evaluate the [...] Read more.

Blood pressure (BP) is an essential physiological indicator to identify and determine health status. Compared with the isolated BP measurement conducted by traditional cuff approaches, cuffless BP monitoring can reflect the dynamic changes in BP values and is more helpful to evaluate the effectiveness of BP control. In this paper, we designed a wearable device for continuous physiological signal acquisition. Based on the collected electrocardiogram (ECG) and photoplethysmogram (PPG), we proposed a multi-parameter fusion method for noninvasive BP estimation. An amount of 25 features were extracted from processed waveforms and Gaussian copula mutual information (MI) was introduced to reduce feature redundancy. After feature selection, random forest (RF) was trained to realize systolic BP (SBP) and diastolic BP (DBP) estimation. Moreover, we used the records in public MIMIC-III as the training set and private data as the testing set to avoid data leakage. The mean absolute error (MAE) and standard deviation (STD) for SBP and DBP were reduced from 9.12 ± 9.83 mmHg and 8.31 ± 9.23 mmHg to 7.93 ± 9.12 mmHg and 7.63 ± 8.61 mmHg by feature selection. After calibration, the MAE was further reduced to 5.21 mmHg and 4.15 mmHg. The result showed that MI has great potential in feature selection during BP prediction and the proposed multi-parameter fusion method can be used for long-term BP monitoring. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

12 pages, 4085 KiB

Open AccessFeature PaperEditor’s ChoiceArticle

Heterogeneous Multi-Material Flexible Piezoresistive Sensor with High Sensitivity and Wide Measurement Range

by Tingting Yu, Yebo Tao, Yali Wu, Dongguang Zhang, Jiayi Yang and Gang Ge

Micromachines 2023, 14(4), 716; https://doi.org/10.3390/mi14040716 - 23 Mar 2023

Cited by 7 | Viewed by 1925

Abstract

Flexible piezoresistive sensors (FPSs) have the advantages of compact structure, convenient signal acquisition and fast dynamic response; they are widely used in motion detection, wearable electronic devices and electronic skins. FPSs accomplish the measurement of stresses through piezoresistive material (PM). However, FPSs based [...] Read more.

Flexible piezoresistive sensors (FPSs) have the advantages of compact structure, convenient signal acquisition and fast dynamic response; they are widely used in motion detection, wearable electronic devices and electronic skins. FPSs accomplish the measurement of stresses through piezoresistive material (PM). However, FPSs based on a single PM cannot achieve high sensitivity and wide measurement range simultaneously. To solve this problem, a heterogeneous multi-material flexible piezoresistive sensor (HMFPS) with high sensitivity and a wide measurement range is proposed. The HMFPS consists of a graphene foam (GF), a PDMS layer and an interdigital electrode. Among them, the GF serves as a sensing layer, providing high sensitivity, and the PDMS serves as a supporting layer, providing a large measurement range. The influence and principle of the heterogeneous multi-material (HM) on the piezoresistivity were investigated by comparing the three HMFPS with different sizes. The HM proved to be an effective way to produce flexible sensors with high sensitivity and a wide measurement range. The HMFPS-10 has a sensitivity of 0.695 kPa⁻¹, a measurement range of 0–14,122 kPa, fast response/recovery (83 ms and 166 ms) and excellent stability (2000 cycles). In addition, the potential application of the HMFPS-10 in human motion monitoring was demonstrated. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

12 pages, 3900 KiB

Open AccessArticle

Multifunctional Nanoplatform Based on Sunitinib for Synergistic Phototherapy and Molecular Targeted Therapy of Hepatocellular Carcinoma

by Wenjing Xu, Meng Yang, Xuanlong Du, Hao Peng, Yue Yang, Jitao Wang and Yewei Zhang

Micromachines 2023, 14(3), 613; https://doi.org/10.3390/mi14030613 - 7 Mar 2023

Cited by 1 | Viewed by 1926

Abstract

Hepatocellular carcinoma (HCC) is a tumor that poses a serious threat to human health, with an extremely low five-year survival rate due to its difficulty in early diagnosis and insensitivity to radiotherapy and chemotherapy. To improve the therapeutic efficiency of HCC, we developed [...] Read more.

Hepatocellular carcinoma (HCC) is a tumor that poses a serious threat to human health, with an extremely low five-year survival rate due to its difficulty in early diagnosis and insensitivity to radiotherapy and chemotherapy. To improve the therapeutic efficiency of HCC, we developed a novel multifunctional nanoplatform (SCF NPs) with an amphiphilic polymer (Ce6-PEG2000-FA) and a multitarget tyrosine kinase inhibitor sunitinib. SCF NPs showed superior therapeutical efficiency for HCC due to the synergetic effect of molecular targeted therapy and phototherapy. The Ce6-PEG2000-FA not only serves as a nanocarrier with excellent biocompatibility but also can act as a therapeutic reagent for photothermal therapy (PTT) and photodynamic therapy (PDT). Furthermore, the folic acid group of Ce6-PEG2000-FA enhanced the active targeting performance of SCF NPs. As a multitargeted tyrosine kinase inhibitor, sunitinib in SCF NPs can play a role in molecular targeted therapies, including tumor growth inhibition and anti-angiogenesis. In vivo experiments, SCF NPs showed multimode imaging capabilities, which can be used for tumorous diagnosis and intraoperative navigation. Meanwhile, SCF NPs showed outstanding synergetic tumor inhibition ability. Tumors of SCF NPs group with laser radiation were eradicated without any recrudescence after 14 days of treatment. Such theranostic nanoparticles offer a novel therapeutic tactic for HCC. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

13 pages, 9802 KiB

Open AccessArticle

Development of an Assessment Model for the Effect of the Replacement of Minimal Artificial Ossicles on Hearing in the Inner Ear

by Junyi Liang, Jiakun Wang, Wenjuan Yao and Mianzhi Wang

Micromachines 2023, 14(2), 483; https://doi.org/10.3390/mi14020483 - 19 Feb 2023

Cited by 1 | Viewed by 1780

Abstract

Due to ethical issues and the nature of the ear, it is difficult to directly perform experimental measurements on living body elements of the human ear. Therefore, a numerical model has been developed to effectively assess the effect of the replacement of artificial [...] Read more.

Due to ethical issues and the nature of the ear, it is difficult to directly perform experimental measurements on living body elements of the human ear. Therefore, a numerical model has been developed to effectively assess the effect of the replacement of artificial ossicles on hearing in the inner ear. A healthy volunteer’s right ear was scanned to obtain CT data, which were digitalized through the use of a self-compiling program and coalescent Patran-Nastran software to establish a 3D numerical model of the whole ear, and a frequency response of a healthy human ear was analyzed. The vibration characteristics of the basilar membrane (BM) after total ossicular replacement prosthesis (TORP) implantation were then analyzed. The results show that although the sound conduction function of the middle ear was restored after replacement of the TORP, the sensory sound function of the inner ear was affected. In the low frequency and medium frequency range, hearing loss was 5.2~10.7%. Meanwhile, in the middle–high frequency range, the replacement of a middle ear TORP in response to high sound pressure produced a high acoustic stimulation effect in the inner ear, making the inner ear structures susceptible to fatigue and more prone to fatigue damage compared to the structures in healthy individuals. This developed model is able to assess the effects of surgical operation on the entire hearing system. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

24 pages, 5247 KiB

Open AccessArticle

Architecture Optimization of a Non-Linear Autoregressive Neural Networks for Mackey-Glass Time Series Prediction Using Discrete Mycorrhiza Optimization Algorithm

by Hector Carreon-Ortiz, Fevrier Valdez, Patricia Melin and Oscar Castillo

Micromachines 2023, 14(1), 149; https://doi.org/10.3390/mi14010149 - 6 Jan 2023

Cited by 5 | Viewed by 1978

Abstract

Recurrent Neural Networks (RNN) are basically used for applications with time series and sequential data and are currently being used in embedded devices. However, one of their drawbacks is that RNNs have a high computational cost and require the use of a significant [...] Read more.

Recurrent Neural Networks (RNN) are basically used for applications with time series and sequential data and are currently being used in embedded devices. However, one of their drawbacks is that RNNs have a high computational cost and require the use of a significant amount of memory space. Therefore, computer equipment with a large processing capacity and memory is required. In this article, we experiment with Nonlinear Autoregressive Neural Networks (NARNN), which are a type of RNN, and we use the Discrete Mycorrhizal Optimization Algorithm (DMOA) in the optimization of the NARNN architecture. We used the Mackey-Glass chaotic time series (MG) to test the proposed approach, and very good results were obtained. In addition, some comparisons were made with other methods that used the MG and other types of Neural Networks such as Backpropagation and ANFIS, also obtaining good results. The proposed algorithm can be applied to robots, microsystems, sensors, devices, MEMS, microfluidics, piezoelectricity, motors, biosensors, 3D printing, etc. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

12 pages, 4442 KiB

Open AccessArticle

A 7.6-nW 1-kS/s 10-Bit SAR ADC for Biomedical Applications

by Yunfeng Hu, Bin Tang, Lexing Hu, Haibo Liang, Bin Li, Zhaohui Wu and Xiaojia Liu

Micromachines 2022, 13(12), 2110; https://doi.org/10.3390/mi13122110 - 29 Nov 2022

Viewed by 1741

Abstract

This paper presents a 10-bit successive approximation register analog-to-digital converter with energy-efficient low-complexity switching scheme, automatic ON/OFF comparator and automatic ON/OFF SAR logic for biomedical applications. The energy-efficient switching scheme achieves an average digital-to-analog converter switching energy of 63.56 CV_ref², [...] Read more.

This paper presents a 10-bit successive approximation register analog-to-digital converter with energy-efficient low-complexity switching scheme, automatic ON/OFF comparator and automatic ON/OFF SAR logic for biomedical applications. The energy-efficient switching scheme achieves an average digital-to-analog converter switching energy of 63.56 CV_ref², achieving a reduction of 95.34% compared with the conventional capacitor switching scheme for CDACs. With the switching scheme, the ADC can lower the dependency on the accuracy of V_cm and complexity of DAC control logic and DAC driver circuit. Moreover, dynamic circuits and automatic ON/OFF technology are used to reduce power consumption of comparator and SAR logic. The prototype is designed and fabricated in a 180 nm CMOS with a core size of 500 μm × 300 μm (0.15 mm²). It consumes 7.6 nW at 1 kS/s sampling rate and 1.8-V supply with an achieved signal-to-noise-and distortion ratio of 45.90 dB and a resulting figure of merit of 51.7 fJ/conv.-step. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

19 pages, 11726 KiB

Open AccessArticle

Holographic Microwave Image Classification Using a Convolutional Neural Network

by Lulu Wang

Micromachines 2022, 13(12), 2049; https://doi.org/10.3390/mi13122049 - 23 Nov 2022

Cited by 5 | Viewed by 1934

Abstract

Holographic microwave imaging (HMI) has been proposed for early breast cancer diagnosis. Automatically classifying benign and malignant tumors in microwave images is challenging. Convolutional neural networks (CNN) have demonstrated excellent image classification and tumor detection performance. This study investigates the feasibility of using [...] Read more.

Holographic microwave imaging (HMI) has been proposed for early breast cancer diagnosis. Automatically classifying benign and malignant tumors in microwave images is challenging. Convolutional neural networks (CNN) have demonstrated excellent image classification and tumor detection performance. This study investigates the feasibility of using the CNN architecture to identify and classify HMI images. A modified AlexNet with transfer learning was investigated to automatically identify, classify, and quantify four and five different HMI breast images. Various pre-trained networks, including ResNet18, GoogLeNet, ResNet101, VGG19, ResNet50, DenseNet201, SqueezeNet, Inception v3, AlexNet, and Inception-ResNet-v2, were investigated to evaluate the proposed network. The proposed network achieved high classification accuracy using small training datasets (966 images) and fast training times. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

11 pages, 2557 KiB

Open AccessArticle

Cyclic Voltammetric-Paper-Based Genosensor for Detection of the Target DNA of Zika Virus

by Anirudh Bishoyi, Md. Anish Alam, Mohd. Rahil Hasan, Manika Khanuja, Roberto Pilloton and Jagriti Narang

Micromachines 2022, 13(12), 2037; https://doi.org/10.3390/mi13122037 - 22 Nov 2022

Cited by 12 | Viewed by 2462

Abstract

Zika virus (ZIKV), a positive-sense single-stranded RNA virus, has been declared as the cause of a ‘worldwide public health emergency’ by the WHO since the year 2016. In cases of acute infections, it has been found to cause Guillain–Barre syndrome and microcephaly. Considering [...] Read more.

Zika virus (ZIKV), a positive-sense single-stranded RNA virus, has been declared as the cause of a ‘worldwide public health emergency’ by the WHO since the year 2016. In cases of acute infections, it has been found to cause Guillain–Barre syndrome and microcephaly. Considering the tropical occurrence of the infections, and the absence of any proper treatments, accurate and timely diagnosis is the only way to control this infectious disease. Currently, there are many diagnostic methods under investigation by the scientific community, but they have some major limitations, such as high cost, low specificity, and poor sensitivity. To overcome these limitations, we have presented a low-cost, simple-to-operate, and portable diagnosis system for its detection by utilizing silver nanoparticles. silver nanoparticles were synthesized via chemical methods and characterization was confirmed by UV/TEM and XRD. The paper platform was synthesized using a graphene-based conductive ink, methylene blue as the redox indicator, and a portable potentiostat to perform the cyclic voltammetry to ensure true point-of-care availability for patients in remote areas. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

15 pages, 4934 KiB

Open AccessArticle

Dental Lesion Segmentation Using an Improved ICNet Network with Attention

by Tian Ma, Xinlei Zhou, Jiayi Yang, Boyang Meng, Jiali Qian, Jiehui Zhang and Gang Ge

Micromachines 2022, 13(11), 1920; https://doi.org/10.3390/mi13111920 - 7 Nov 2022

Cited by 5 | Viewed by 1892

Abstract

Precise segmentation of tooth lesions is critical to creation of an intelligent tooth lesion detection system. As a solution to the problem that tooth lesions are similar to normal tooth tissues and difficult to segment, an improved segmentation method of the image cascade [...] Read more.

Precise segmentation of tooth lesions is critical to creation of an intelligent tooth lesion detection system. As a solution to the problem that tooth lesions are similar to normal tooth tissues and difficult to segment, an improved segmentation method of the image cascade network (ICNet) network is proposed to segment various lesion types, such as calculus, gingivitis, and tartar. First, the ICNet network model is used to achieve real-time segmentation of lesions. Second, the Convolutional Block Attention Module (CBAM) is integrated into the ICNet network structure, and large-size convolutions in the spatial attention module are replaced with layered dilated convolutions to enhance the relevant features while suppressing useless features and solve the problem of inaccurate lesion segmentations. Finally, part of the convolution in the network model is replaced with an asymmetric convolution to reduce the calculations added by the attention module. Experimental results show that compared with Fully Convolutional Networks (FCN), U-Net, SegNet, and other segmentation algorithms, our method has a significant improvement in the segmentation effect, and the image processing frequency is higher, which satisfies the real-time requirements of tooth lesion segmentation accuracy. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

13 pages, 2436 KiB

Open AccessArticle

Airline Point-of-Care System on Seat Belt for Hybrid Physiological Signal Monitoring

by Xiaoqiang Ji, Zhi Rao, Wei Zhang, Chang Liu, Zimo Wang, Shuo Zhang, Butian Zhang, Menglei Hu, Peyman Servati and Xiao Xiao

Micromachines 2022, 13(11), 1880; https://doi.org/10.3390/mi13111880 - 1 Nov 2022

Cited by 7 | Viewed by 2509

Abstract

With a focus on disease prevention and health promotion, a reactive and disease-centric healthcare system is revolutionized to a point-of-care model by the application of wearable devices. The convenience and low cost made it possible for long-term monitoring of health problems in long-distance [...] Read more.

With a focus on disease prevention and health promotion, a reactive and disease-centric healthcare system is revolutionized to a point-of-care model by the application of wearable devices. The convenience and low cost made it possible for long-term monitoring of health problems in long-distance traveling such as flights. While most of the existing health monitoring systems on aircrafts are limited for pilots, point-of-care systems provide choices for passengers to enjoy healthcare at the same level. Here in this paper, an airline point-of-care system containing hybrid electrocardiogram (ECG), breathing, and motion signals detection is proposed. At the same time, we propose the diagnosis of sleep apnea-hypopnea syndrome (SAHS) on flights as an application of this system to satisfy the inevitable demands for sleeping on long-haul flights. The hardware design includes ECG electrodes, flexible piezoelectric belts, and a control box, which enables the system to detect the original data of ECG, breathing, and motion signals. By processing these data with interval extraction-based feature selection method, the signals would be characterized and then provided for the long short-term memory recurrent neural network (LSTM-RNN) to classify the SAHS. Compared with other machine learning methods, our model shows high accuracy up to 84–85% with the lowest overfit problem, which proves its potential application in other related fields. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

13 pages, 1722 KiB

Open AccessArticle

Performance Analysis of Electromyogram Signal Compression Sampling in a Wireless Body Area Network

by Liangyu Zhang, Junxin Chen, Chenfei Ma, Xiufang Liu and Lisheng Xu

Micromachines 2022, 13(10), 1748; https://doi.org/10.3390/mi13101748 - 15 Oct 2022

Cited by 3 | Viewed by 1600

Abstract

The rapid growth in demand for portable and intelligent hardware has caused tremendous pressure on signal sampling, transfer, and storage resources. As an emerging signal acquisition technology, compressed sensing (CS) has promising application prospects in low-cost wireless sensor networks. To achieve reduced energy [...] Read more.

The rapid growth in demand for portable and intelligent hardware has caused tremendous pressure on signal sampling, transfer, and storage resources. As an emerging signal acquisition technology, compressed sensing (CS) has promising application prospects in low-cost wireless sensor networks. To achieve reduced energy consumption and maintain a longer acquisition duration for high sample rate electromyogram (EMG) signals, this paper comprehensively analyzes the compressed sensing method using EMG. A fair comparison is carried out on the performances of 52 ordinary wavelet sparse bases and five widely applied reconstruction algorithms at different compression levels. The experimental results show that the db2 wavelet basis can sparse EMG signals so that the compressed EMG signals are reconstructed properly, thanks to its low percentage root mean square distortion (PRD) values at most compression ratios. In addition, the basis pursuit (BP) reconstruction algorithm can provide a more efficient reconstruction process and better reconstruction performance by comparison. The experiment records and comparative analysis screen out the suitable sparse bases and reconstruction algorithms for EMG signals, acting as prior experiments for further practical applications and also a benchmark for future academic research. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

12 pages, 2554 KiB

Open AccessFeature PaperEditor’s ChoiceArticle

Evaluating and Visualizing the Contribution of ECG Characteristic Waveforms for PPG-Based Blood Pressure Estimation

by Gang Ma, Yuhang Chen, Wenliang Zhu, Lesong Zheng, Hui Tang, Yong Yu and Lirong Wang

Micromachines 2022, 13(9), 1438; https://doi.org/10.3390/mi13091438 - 31 Aug 2022

Cited by 3 | Viewed by 2452

Abstract

Non-invasive continuous blood pressure monitoring is of great significance for the preventing, diagnosing, and treating of cardiovascular diseases (CVDs). Studies have demonstrated that photoplethysmogram (PPG) and electrocardiogram (ECG) signals can effectively and continuously predict blood pressure (BP). However, most of the BP estimation [...] Read more.

Non-invasive continuous blood pressure monitoring is of great significance for the preventing, diagnosing, and treating of cardiovascular diseases (CVDs). Studies have demonstrated that photoplethysmogram (PPG) and electrocardiogram (ECG) signals can effectively and continuously predict blood pressure (BP). However, most of the BP estimation models focus on the waveform features of the PPG signal, while the peak value of R-wave in ECG is only used as a time reference, and few references investigated the ECG waveforms. This paper aims to evaluate the influence of three characteristic waveforms in ECG on the improvement of BP estimation. PPG is the primary signal, and five input combinations are formed by adding ECG, P wave, QRS complex, T wave, and none. We employ five common convolutional neural networks (CNN) to validate the consistency of the contribution. Meanwhile, with the visualization of Gradient-weighted class activation mapping (Grad-CAM), we generate the heat maps and further visualize the distribution of CNN’s attention to each waveform of PPG and ECG. The heat maps show that networks pay more attention to the QRS complex and T wave. In the comparison results, the QRS complex and T wave have more contribution to minimizing errors than P wave. By separately adding P wave, QRS complex, and T wave, the average MAE of these networks reaches 7.87 mmHg, 6.57 mmHg, and 6.21 mmHg for systolic blood pressure (SBP), and 4.27 mmHg, 3.65 mmHg, and 3.73 mmHg, respectively, for diastolic blood pressure (DBP). The results of the experiment show that QRS complex and T wave deserves more attention and feature extraction like PPG waveform features in the continuous BP estimation. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

19 pages, 3638 KiB

Open AccessArticle

Human Motion Pattern Recognition and Feature Extraction: An Approach Using Multi-Information Fusion

by Xin Li, Jinkang Liu, Yijing Huang, Donghao Wang and Yang Miao

Micromachines 2022, 13(8), 1205; https://doi.org/10.3390/mi13081205 - 29 Jul 2022

Cited by 15 | Viewed by 2678

Abstract

An exoskeleton is a kind of intelligent wearable device with bioelectronics and biomechanics. To realize its effective assistance to the human body, an exoskeleton needs to recognize the real time movement pattern of the human body in order to make corresponding movements at [...] Read more.

An exoskeleton is a kind of intelligent wearable device with bioelectronics and biomechanics. To realize its effective assistance to the human body, an exoskeleton needs to recognize the real time movement pattern of the human body in order to make corresponding movements at the right time. However, it is of great difficulty for an exoskeleton to fully identify human motion patterns, which are mainly manifested as incomplete acquisition of lower limb motion information, poor feature extraction ability, and complicated steps. Aiming at the above consideration, the motion mechanisms of human lower limbs have been analyzed in this paper, and a set of wearable bioelectronics devices are introduced based on an electromyography (EMG) sensor and inertial measurement unit (IMU), which help to obtain biological and kinematic information of the lower limb. Then, the Dual Stream convolutional neural network (CNN)-ReliefF was presented to extract features from the fusion sensors’ data, which were input into four different classifiers to obtain the recognition accuracy of human motion patterns. Compared with a single sensor (EMG or IMU) and single stream CNN or manual designed feature extraction methods, the feature extraction based on Dual Stream CNN-ReliefF shows better performance in terms of visualization performance and recognition accuracy. This method was used to extract features from EMG and IMU data of six subjects and input these features into four different classifiers. The motion pattern recognition accuracy of each subject under the four classifiers is above 97%, with the highest average recognition accuracy reaching 99.12%. It can be concluded that the wearable bioelectronics device and Dual Stream CNN-ReliefF feature extraction method proposed in this paper enhanced an exoskeleton’s ability to capture human movement patterns, thus providing optimal assistance to the human body at the appropriate time. Therefore, it can provide a novel approach for improving the human-machine interaction of exoskeletons. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

11 pages, 2600 KiB

Open AccessFeature PaperEditor’s ChoiceArticle

A Novel Fluidic Platform for Semi-Automated Cell Culture into Multiwell-like Bioreactors

by Francesca Maria Orecchio, Vito Tommaso, Tommaso Santaniello, Sara Castiglioni, Federico Pezzotta, Andrea Monti, Francesco Butera, Jeanette Anne Marie Maier and Paolo Milani

Micromachines 2022, 13(7), 994; https://doi.org/10.3390/mi13070994 - 24 Jun 2022

Cited by 1 | Viewed by 2865

Abstract

In this work, we developed and characterized a novel fluidic platform that enables long-term in vitro cell culture in a semi-automated fashion. The system is constituted by a control unit provided with a piezoelectric pump, miniaturized valves, and a microfluidic network for management [...] Read more.

In this work, we developed and characterized a novel fluidic platform that enables long-term in vitro cell culture in a semi-automated fashion. The system is constituted by a control unit provided with a piezoelectric pump, miniaturized valves, and a microfluidic network for management and fine control of reagents’ flow, connected to a disposable polymeric culture unit resembling the traditional multiwell-like design. As a proof of principle, Human Umbilical Vein Endothelial Cells (HUVEC) and Human Mesenchymal Stem Cells (hMSC) were seeded and cultured into the cell culture unit. The proliferation rate of HUVEC and the osteogenic differentiation of hMSC were assessed and compared to standard culture in Petri dishes. The results obtained demonstrated that our approach is suitable to perform semi-automated cell culture protocols, minimizing the contribution of human operators and allowing the standardization and reproducibility of the procedures. We believe that the proposed system constitutes a promising solution for the realization of user-friendly automated control systems that will favor the standardization of cell culture processes for cell factories, drug testing, and biomedical research. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

15 pages, 4448 KiB

Open AccessArticle

Screw Analysis, Modeling and Experiment on the Mechanics of Tibia Orthopedic with the Ilizarov External Fixator

by Peng Su, Sikai Wang, Yuliang Lai, Qinran Zhang and Leiyu Zhang

Micromachines 2022, 13(6), 932; https://doi.org/10.3390/mi13060932 - 11 Jun 2022

Cited by 5 | Viewed by 4674

Abstract

The Ilizarov external fixator plays an important role in the correction of complex malformed limbs. Our purpose in this work was to reveal the transmission of adjustable forces between the external fixator and the broken bone, and express the stress distribution at the [...] Read more.

The Ilizarov external fixator plays an important role in the correction of complex malformed limbs. Our purpose in this work was to reveal the transmission of adjustable forces between the external fixator and the broken bone, and express the stress distribution at the end of the broken bone during the orthopedic treatment. Firstly, the screw model of the fixator was established and the theoretical relationship between the adjustable force and the stress was obtained. A sheep tibia was taken as a representative research object and its ediTable 3D entity was obtained by CT scanning. Then the mechanical model of the fixator and tibia was built using the ABAQUS software. Correction experiments were performed on the sheep tibia to measure the adjustable/support forces and tensions of the tibia. The measured results were imported to the screw and mechanical model, and the theoretical and simulation values were calculated. The theoretical tensions calculated by the screw model had a similar shape and doubled the value compared with that of the measured results. The transfer efficiency between the two results was improved and kept at about 50% after the initial 2~3 periods. The maximum stress occurring at the surface of the broken bone end was near the Kirschner wire pinhole. The simulation results for the tensions from the mechanical model showed a similar change trend, and the value was slightly higher. A biomechanical model of the Ilizarov external fixator was derived and verified through calculations, simulations and experiments. The change law of the adjustable forces and the tensions existing in the broken sheep tibias is presented herein, and offers a helpful contribution to orthopedic treatment. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

18 pages, 7215 KiB

Open AccessArticle

Ergonomic Design and Performance Evaluation of H-Suit for Human Walking

by Leiyu Zhang, Zhenxing Jiao, Yandong He and Peng Su

Micromachines 2022, 13(6), 825; https://doi.org/10.3390/mi13060825 - 25 May 2022

Cited by 4 | Viewed by 2001

Abstract

A soft exoskeleton for the hip flexion, named H-Suit, is developed to improve the walking endurance of lower limbs, delay muscle fatigue and reduce the activation level of hip flexors. Based on the kinematics and biomechanics of the hip joints, the ergonomic design [...] Read more.

A soft exoskeleton for the hip flexion, named H-Suit, is developed to improve the walking endurance of lower limbs, delay muscle fatigue and reduce the activation level of hip flexors. Based on the kinematics and biomechanics of the hip joints, the ergonomic design of the H-Suit system is clearly presented and the prototype was developed. The profile of the auxiliary forces is planned in the auxiliary range where the forces start at the minimum hip angle, reach the maximum (120 N) and end at 90% of each gait cycle. The desired displacements of the traction unit which consist of the natural and elastic displacements of the steel cables are obtained by the experimental method. An assistance strategy is proposed to track the profile of the auxiliary forces by dynamically adjusting the compensation displacement L_c and the hold time Δt. The influences of the variables L_c and Δt on the natural gaits and auxiliary forces have been revealed and analyzed. The real profile of the auxiliary forces can be obtained and is consistent with the theoretical one by the proposed assistance strategy. The H-Suit without the drive unit has little effect on the EMG signal of the lower limbs. In the powered condition, the H-Suit can delay the muscle fatigue of the lower limbs. The average rectified value (ARV) slope decreases and the median frequency (MNF) slope increases significantly. Wearing the H-Suit resulted in a significant reduction of the vastus lateralis effort, averaged over subjects and walking speeds, of 13.3 ± 2.1% (p = 2 × 10⁻⁵). Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

17 pages, 3027 KiB

Open AccessArticle

Accurate and Automatic Extraction of Cell Self-Rotation Speed in an ODEP Field Using an Area Change Algorithm

by Haiyang Wu, Dan Dang, Xieliu Yang, Junhai Wang, Ruolong Qi, Wenguang Yang and Wenfeng Liang

Micromachines 2022, 13(6), 818; https://doi.org/10.3390/mi13060818 - 24 May 2022

Viewed by 2172

Abstract

Cells are complex biological units that can sense physicochemical stimuli from their surroundings and respond positively to them through characterization of the cell behavior. Thus, understanding the motions of cells is important for investigating their intrinsic properties and reflecting their various states. Computer-vision-based [...] Read more.

Cells are complex biological units that can sense physicochemical stimuli from their surroundings and respond positively to them through characterization of the cell behavior. Thus, understanding the motions of cells is important for investigating their intrinsic properties and reflecting their various states. Computer-vision-based methods for elucidating cell behavior offer a novel approach to accurately extract cell motions. Here, we propose an algorithm based on area change to automatically extract the self-rotation of cells in an optically induced dielectrophoresis field. To obtain a clear and complete outline of the cell structure, dark corner removal and contrast stretching techniques are used in the pre-processing stage. The self-rotation speed is calculated by determining the frequency of the cell area changes in all of the captured images. The algorithm is suitable for calculating in-plane and out-of-plane rotations, while addressing the problem of identical images at different rotation angles when dealing with rotations of spherical and flat cells. In addition, the algorithm can be used to determine the motion trajectory of cells. The experimental results show that the algorithm can efficiently and accurately calculate cell rotation speeds of up to ~155 rpm. Potential applications of the proposed algorithm include cell morphology extraction, cell classification, and characterization of the cell mechanical properties. The algorithm can be very helpful for those who are interested in using computer vision and artificial-intelligence-based ideology in single-cell studies, drug treatment, and other bio-related fields. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

Review

Jump to: Research

24 pages, 9333 KiB

Open AccessReview

Single-Line Multi-Channel Flexible Stress Sensor Arrays

by Jiayi Yang, Yuanyuan Chen, Shuoyan Liu, Chang Liu, Tian Ma, Zhenmin Luo and Gang Ge

Micromachines 2023, 14(8), 1554; https://doi.org/10.3390/mi14081554 - 3 Aug 2023

Cited by 3 | Viewed by 2042

Abstract

Flexible stress sensor arrays, comprising multiple flexible stress sensor units, enable accurate quantification and analysis of spatial stress distribution. Nevertheless, the current implementation of flexible stress sensor arrays faces the challenge of excessive signal wires, resulting in reduced deformability, stability, reliability, and increased [...] Read more.

Flexible stress sensor arrays, comprising multiple flexible stress sensor units, enable accurate quantification and analysis of spatial stress distribution. Nevertheless, the current implementation of flexible stress sensor arrays faces the challenge of excessive signal wires, resulting in reduced deformability, stability, reliability, and increased costs. The primary obstacle lies in the electric amplitude modulation nature of the sensor unit’s signal (e.g., resistance and capacitance), allowing only one signal per wire. To overcome this challenge, the single-line multi-channel signal (SLMC) measurement has been developed, enabling simultaneous detection of multiple sensor signals through one or two signal wires, which effectively reduces the number of signal wires, thereby enhancing stability, deformability, and reliability. This review offers a general knowledge of SLMC measurement beginning with flexible stress sensors and their piezoresistive, capacitive, piezoelectric, and triboelectric sensing mechanisms. A further discussion is given on different arraying methods and their corresponding advantages and disadvantages. Finally, this review categorizes existing SLMC measurement methods into RLC series resonant sensing, transmission line sensing, ionic conductor sensing, triboelectric sensing, piezoresistive sensing, and distributed fiber optic sensing based on their mechanisms, describes the mechanisms and characteristics of each method and summarizes the research status of SLMC measurement. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

33 pages, 7351 KiB

Open AccessReview

Recent Advances in Tracking Devices for Biomedical Ultrasound Imaging Applications

by Chang Peng, Qianqian Cai, Mengyue Chen and Xiaoning Jiang

Micromachines 2022, 13(11), 1855; https://doi.org/10.3390/mi13111855 - 29 Oct 2022

Cited by 10 | Viewed by 5484

Abstract

With the rapid advancement of tracking technologies, the applications of tracking systems in ultrasound imaging have expanded across a wide range of fields. In this review article, we discuss the basic tracking principles, system components, performance analyses, as well as the main sources [...] Read more.

With the rapid advancement of tracking technologies, the applications of tracking systems in ultrasound imaging have expanded across a wide range of fields. In this review article, we discuss the basic tracking principles, system components, performance analyses, as well as the main sources of error for popular tracking technologies that are utilized in ultrasound imaging. In light of the growing demand for object tracking, this article explores both the potential and challenges associated with different tracking technologies applied to various ultrasound imaging applications, including freehand 3D ultrasound imaging, ultrasound image fusion, ultrasound-guided intervention and treatment. Recent development in tracking technology has led to increased accuracy and intuitiveness of ultrasound imaging and navigation with less reliance on operator skills, thereby benefiting the medical diagnosis and treatment. Although commercially available tracking systems are capable of achieving sub-millimeter resolution for positional tracking and sub-degree resolution for orientational tracking, such systems are subject to a number of disadvantages, including high costs and time-consuming calibration procedures. While some emerging tracking technologies are still in the research stage, their potentials have been demonstrated in terms of the compactness, light weight, and easy integration with existing standard or portable ultrasound machines. Full article

(This article belongs to the Special Issue Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Bioelectronics & Wearable Devices: Sensing, Signal Processing and Powering

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Related Special Issue

Published Papers (22 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI