A Nanowatt Real-Time Cardiac Autonomic Neuropathy Detector

AutoMLP: A Framework for the Acceleration of Multi-Layer Perceptron Models on FPGAs for Real-Time Atrial Fibrillation Disease Detection

Cardiovascular diseases are a leading cause of death globally, and atrial fibrillation (AF) is a common arrhythmia that affects many people. Detecting AF in real-time using hardware acceleration can prompt timely medical intervention. Multi-layer perceptron (MLP) has demonstrated the ability to detect AF accurately. However, implementing MLP on Field-Programmable Gate Array (FPGA) for real-time detection poses challenges due to the complex hardware design requirements. This study presents a novel framework for generating hardware accelerators to detect AF in real-time using MLP on FPGA. The framework automates evaluating MLP model topology, data type, and bit-widths to generate parallel acceleration. The generated solutions are evaluated using two AF datasets, PhysioNet MIT-BIH atrial fibrillation (AFDB) and China Physiological Signal Challenge 2018 (CPSC2018), regarding execution time, resource utilization, and accuracy. The evaluation results demonstrate that the hardware MLP can achieve a speedup higher than 1500× and around 25000× lower energy consumption than an embedded CPU. These satisfactory results prove the framework's suitability and convenience for the online detection of AF in an accelerated and automatic way through FPGA hardware implementation.

Compact conformal tattoo-polymer antenna for on-body wireless power transfer

This paper presents a 35.0 × 35.0 × 2.7 mm3 compact, low-profile, and lightweight wearable antenna for on-body wireless power transfer. The proposed antenna can be easily printed on a piece of flexible tattoo paper and transformed onto a PDMS substrate, making the entire antenna structure conform to the human body for achieving a better user experience. Here, a layer of frequency selective surface (FSS) is inserted in between the antenna and human tissue, which has successfully reduced the loading effects of the tissue, with 13.8 dB improvement on the antenna gain. Also, the operating frequency of the rectenna is not affected much by deformation. To maximize the RF-DC conversion efficiency, a matching loop, a matching stub, and two coupled lines are integrated with the antenna for tuning the rectenna so that a wide bandwidth (~ 24%) can be achieved without the use of any external matching networks. Measurement results show that the proposed rectenna can achieve a maximum conversion efficiency of 59.0% with an input power of 5.75 μW/cm2 and can even exceed 40% for a low input power of 1.0 μW/cm2 with a 20 kΩ resistive load, while many other reported rectennas can only achieve a high PCE at a high power density level, which is not always practical for a wearable antenna.

A High Accuracy & Ultra-Low Power ECG-Derived Respiration Estimation Processor for Wearable Respiration Monitoring Sensor

The respiratory rate is widely used for evaluating a person's health condition. Compared to other invasive and expensive methods, the ECG-derived respiration estimation is a more comfortable and affordable method to obtain the respiration rate. However, the existing ECG-derived respiration estimation methods suffer from low accuracy or high computational complexity. In this work, a high accuracy and ultra-low power ECG-derived respiration estimation processor has been proposed. Several techniques have been proposed to improve the accuracy and reduce the computational complexity (and thus power consumption), including QRS detection using refractory period refreshing and adaptive threshold EDR estimation. Implemented and fabricated using a 55 nm processing technology, the proposed processor achieves a low EDR estimation error of 0.73 on CEBS database and 1.2 on MIT-BIH Polysomnographic Database while demonstrating a record-low power consumption (354 nW) for the respiration monitoring, outperforming the existing designs. The proposed processor can be integrated in a wearable sensor for ultra-low power and high accuracy respiration monitoring.

Complexity Analysis in the PR, QT, RR and ST Segments of ECG for Early Assessment of Severity in Cardiac Autonomic Neuropathy

Early-stage detection of cardiac autonomic neuropathy (CAN) is important for better management of the disease and prevents hospitalization. This study has investigated the complex nature of PR, QT, RR, and ST time segments of ECG signals by computing the fractal dimension (FD) of all segments from 20 min ECG recordings of people with different severity of the disease and healthy individuals. The mean computed for each ECG time segment to distinguish between subjects was insufficient for an early diagnosis. Statistical analysis shows that the change of FD in various time segments of ECG throughout the recording was most suitable to assess the steps for severity in symptoms of CAN between the healthy and the subjects with early symptoms of CAN. The complexity of ECG features was evaluated using various classifier models, namely, support vector machine (SVM), naïve Bayes, random forest, K-nearest neighbor (KNN), AdaBoost, and neural networks. Performance measures were computed on all models, with a maximum neural network classifier having an accuracy of 96.9%. Feature ranking results show that fractal features have more significance than the time segments of ECG in differentiating the subjects. The results of statistical validation show that all the selected features based on ECG physiology proved to have an evident complexity change between normal and severity stages of CAN. Thus, this work reports the complexity analysis in all the selected time segments of ECG that can be an effective tool for early diagnostics for CAN.

A 1.2nW Analog Electrocardiogram Processor Achieving a 99.63% QRS Complex Detection Sensitivity

An energy-efficient electrocardiogram (ECG) processor for real-time QRS detection is presented. The proposed algorithm is based on the Pan-Tompkins algorithm and it is implemented in the analog domain leveraging ultra-low power analog electronics biased in subthreshold. Operational transconductance amplifiers with ∼100 mV linear range are used in almost all of the processing blocks, while squaring is performed on current signals. Additionally, instead of adaptive thresholding, a fixed-level thresholding is performed, thereby eliminating the need for additional blocks such as memory and threshold update. The processor is designed in 65 nm TSMC CMOS technology and has a footprint of 0.078 mm². When supplied by a 1 V supply, the processor consumes 1.2 nW. Using the recordings in the MIT-BIH database, the processor achieves an average QRS detection sensitivity of 99.63% and positive predictivity of 99.47%.

All 3D Printed Stretchable Piezoelectric Nanogenerator for Self-Powered Sensor Application

With the rapid development of wearable electronic systems, the need for stretchable nanogenerators becomes increasingly important for autonomous applications such as the Internet-of-Things. Piezoelectric nanogenerators are of interest for their ability to harvest mechanical energy from the environment with its inherent polarization arising from crystal structures or molecular arrangements of the piezoelectric materials. In this work, 3D printing is used to fabricate a stretchable piezoelectric nanogenerator which can serve as a self-powered sensor based on synthesized oxide–polymer composites.

Physiological fractals: visual and statistical evidence across timescales and experimental states

A marker of engaging in compassion meditation and related processes is an increase in heart-rate variability (HRV), typically interpreted as a marker of parasympathetic nervous system response. While insightful, open questions remain. For example, which timescale is best to examine the effects of meditation and related practices on HRV? Furthermore, how might advanced time-series analyses--such as stationarity--be able to examine dynamic changes in the mean and variance of the HRV signal across time? Here we apply such methods to previously published data, which measured HRV pre- and post- a two-week compassionate mind training (CMT) intervention. Inspection of these data reveals that a visualization of HRV correlations across resting and compassion meditation states, pre- and post-two-week training, is retained across numerous recording timescales. Here, the fractal-like nature of our data indicates that the accuracy of representing HRV data can exist across timescales, albeit with greater or lesser granularity. Interestingly, inspection of the HRV signal at Time 2 compassion meditation versus Time 1 revealed a more highly correlated (i.e. potentially more stable) signal. We followed up these results with tests of stationarity, which revealed Time 2 had a less stochastic (variable) signal than Time 1, and a measure of distance in the time series, which showed that Time 2 had less of an average difference between rest and meditation than at Time 1. Our results provide novel assessment of visual and statistical markers of HRV change across distinct experimental states.