This work describes a bio-potential acquisition system for portable ubiquitous healthcare applications using flexible polydimethylsiloxane dry electrodes (FPDEs) and a low-power recording circuit. This novel FPDE used Au as the skin contact layer, which was made using a CO₂ laser and replica method technology. The FPDE was revised from a commercial bio-potential electrode with a conductive snap using dry electrodes rather than wet electrodes that proposed reliable and robust attachment for the purpose of measurement, and attaching velcro made it wearable on the forearm for bio-potential applications. Furthermore, this study proposes a recording device to store bio-potential signal data and provides portability and low-power consumption for the proposed acquisition system. To acquire differential bio-potentials, such as electrocardiogram (ECG) signals, the proposed recording device includes a low-power front-end acquisition chip fabricated using a complementary metal-oxide-semiconductor (CMOS) process, a commercial microcontroller (MSP430F149), and a secure digital (SD) card for portable healthcare applications. The proposed system can obtain ECG signals efficiently and are comfortable to the skin. The power consumption of the system is about 85 mW for continuous working over a 3 day period with two AA batteries. It can also be used as a compact Holter ECG system.

This paper presents a portable low-power battery-driven bioelectrochemical signal acquisition system for urea detection. The proposed design has several advantages, including high performance, low cost, low-power consumption, and high portability. A LT1789-1 low-supply-voltage instrumentation amplifier (IA) was used to measure and amplify the open-circuit potential (OCP) between the working and reference electrodes. An MSP430 micro-controller was programmed to process and transduce the signals to the custom-developed software by ZigBee RF module in wireless mode and UART in able mode. The immobilized urease sensor was prepared by embedding urease into the polymer (aniline-co-o-phenylenediamine) polymeric matrix and then coating/depositing it onto a MEMS-fabricated Au working electrode. The linear correlation established between the urea concentration and the potentiometric change is in the urea concentrations range of 3.16 × 10⁻⁴ to 3.16 × 10⁻² M with a sensitivity of 31.12 mV/log [M] and a precision of 0.995 (R² = 0.995). This portable device not only detects urea concentrations, but can also operate continuously with a 3.7 V rechargeab-le lithium-ion battery (500 mA·h) for at least four days. Accordingly, its use is feasible and even promising for home-care applications.

In this paper, a system is designed using flexible poly-dimethylsiloxane (PDMS) dry electrodes instead of wet electrodes to acquire electrocardiogram (ECG) signals. This flexible PDMS dry electrode (FPDE) is revised from the hard commercial biopotential conductive snap to a flexible electrode using a replica method that provides a reliable attachment for the ECG measurement method. The measurement result shows the proposed FPDE, which has the ability to acquire ECG signals, is comparable with the traditional wet electrodes applied in medicine. In addition, an acquisition circuit design integrated with commercial ICs and an field-programmable gate array (FPGA) platform is built for the development of longterm ECG monitoring. A variable-transform-length DCT-IVbased ECG compression algorithm with a higher quality score (QS) and a better compressing ratio (CR) is further proposed to significantly reduce the large amount of recording data in both storage and transmission. The QS parameter, which denotes a ratio of a CR value to a percent rms difference (PRD) value, is another key index applied to fairly evaluate the performance of various compression algorithms. DCT-IV is used as a unified transform kernel for ECG signal encoding and decoding, because the forward DCT-IV formula is the same as its inverse. It can be easily converted into a compact hardware accelerator with fewer hardware resources. To fairly evaluate the proposed compression algorithm, ECG signals sourced from MIT-BIT arrhythmia database with a sampling rate of 360 Hz are employed as the test patterns. The simulation results show the averages of CR, PRD, and QS to be 6.86, 0.18, 2.60, 1.68, 32.19, and 39.86, respectively, for all 48 lead-II patterns of the MIT-BIH database. Compared with Lee et al.'s DCT-II based algorithm, the QS value of the proposed method exhibits a 76% improvement. The experimental results clearly show that the proposed system would be a better choice for achieving ECG signal acquisition in the future.

This paper presents a channel-wise average pooling and one dimension pixel-shuffle architecture for a denoising autoencoder (CPDAE) design that can be applied to efficiently remove electrode motion (EM) artifacts in an electrocardiogram (ECG) signal. The three advantages of the proposed design are as follows: (1) In the skip connection layer, less memory is needed to transfer the features extracted by the neural network; (2) Pixel shuffle and pixel unshuffle techniques with point-wise convolution are used to effectively reserve the key features generated from each layer in both the encoder and decoder; (3) Overall, fewer parameters are required to reconstruct the ECG signal. This paper describes three deep neural network models, namely CPDAE_Lite, CPDAE_Regular, and CPDAE_Full, which support various computational capacity and hardware arrangements. The three proposed structures involve an encoder and decoder with six, seven, and eight layers, respectively. Furthermore, the CPDAE_Lite, CPDAE_Regular, and CPDAE_Full structures require fewer multiply-accumulate operations—355.01, 56.96, and 14.69 million, respectively—and less parameter usage—2.69 million, 149.7 thousand, and 55.5 thousand, respectively. To evaluate the denoising performance, the MIT–BIH noise stress test database containing six signal-to-noise ratios (SNRs) of noisy ECGs was employed. The results demonstrated that the proposed models had a higher improvement of SNR and lower percentage root-mean-square difference than other state-of-the-art methods under various conditions of SNR.

The modeling of human body kye-points is the most significant aspect of pose estimation appropriately. Computer vision algorithm identifies human pose, body-movement, and action in many ways. Most of the previous works taken advantage for finding accuracy or efficiency in terms of speed. However, many techniques suffer for intensive computational demands with low-latency or higher proceeding speed. We have designed a unique approach for single-person pose estimation and action recognition which is well suited for fitness application and mobility activities. The proposed framework has been developed with a base network that provides an initial pose to further refinement through Intensive Feature Consistency (IFC) network. The IFC network enforces high-level constraints on the global body intensity correction and local body part adjustments. The proposed module reduces the impact of body joint movement diversity by interpreting long-term consistent view. We have illustrated the effectiveness of proposed framework through pose estimation accuracy improvement with two benchmark datasets. Which is specified state-of the- art performance of IFC network under the required real-time processing speed on the CPU platform. The IFC network has improved 99.1% of PCK body and 94.7% of PCK torso accuracy under 31 FPS, which is comparatively higher than the existing work.

This study proposes two denoising autoencoder models with discrete cosine transform and discrete wavelet transform, to remove electrode motion artifacts in noisy electrocardiography. Initially, the discrete cosine transform and discrete wavelet transform efficiently removed the high-frequency noise. The six encoder layers then retain important electrocardiography features, whereas the six decoder layers reconstruct the clean electrocardiography. To improve the denoising performance, two network layers, the residual block and pixel adjustment, are added to the encoder and decoder layers to solve the vanishing gradient and improve subtle feature extraction. The proposed methods were applied to 66,000 real-recorded noisy electrocardiography fragments. The experimental result indicates that discrete wavelet transform based denoising autoencoder and discrete cosine transform based denoising autoencoder can improve the signal-to-noise ratio by 25.29 and 25.13 dB on average when the input signal-to-noise ratio is −6 dB.