The advent of dedicated Deep Learning (DL) accelerators and neuromorphic processors has brought on new opportunities for applying both Deep and Spiking Neural Network (SNN) algorithms to healthcare and biomedical applications at the edge. This can facilitate the advancement of medical Internet of Things (IoT) systems and Point of Care (PoC) devices. In this paper, we provide a tutorial describing how various technologies including emerging memristive devices, Field Programmable Gate Arrays (FPGAs), and Complementary Metal Oxide Semiconductor (CMOS) can be used to develop efficient DL accelerators to solve a wide variety of diagnostic, pattern recognition, and signal processing problems in healthcare. Furthermore, we explore how spiking neuromorphic processors can complement their DL counterparts for processing biomedical signals. The tutorial is augmented with case studies of the vast literature on neural network and neuromorphic hardware as applied to the healthcare domain. We benchmark various hardware platforms by performing a sensor fusion signal processing task combining electromyography (EMG) signals with computer vision. Comparisons are made between dedicated neuromorphic processors and embedded AI accelerators in terms of inference latency and energy. Finally, we provide our analysis of the field and share a perspective on the advantages, disadvantages, challenges, and opportunities that various accelerators and neuromorphic processors introduce to healthcare and biomedical domains.

Hardware Implementation of Deep Network Accelerators Towards Healthcare and Biomedical Applications

With the advent of dedicated Deep Learning (DL) accelerators and neuromorphic processors, new opportunities are emerging for applying deep and Spiking Neural Network (SNN) algorithms to healthcare and biomedical applications at the edge. This can facilitate the advancement of the medical Internet of Things (IoT) systems and Point of Care (PoC) devices. In this paper, we provide a tutorial describing how various technologies ranging from emerging memristive devices, to established Field Programmable Gate Arrays (FPGAs), and mature Complementary Metal Oxide Semiconductor (CMOS) technology can be used to develop efficient DL accelerators to solve a wide variety of diagnostic, pattern recognition, and signal processing problems in healthcare. Furthermore, we explore how spiking neuromorphic processors can complement their DL counterparts for processing biomedical signals. After providing the required background, we unify the sparsely distributed research on neural network and neuromorphic hardware implementations as applied to the healthcare domain. In addition, we benchmark various hardware platforms by performing a biomedical electromyography (EMG) signal processing task and drawing comparisons among them in terms of inference delay and energy. Finally, we provide our analysis of the field and share a perspective on the advantages, disadvantages, challenges, and opportunities that different accelerators and neuromorphic processors introduce to healthcare and biomedical domains. This paper can serve a large audience, ranging from nanoelectronics researchers, to biomedical and healthcare practitioners in grasping the fundamental interplay between hardware, algorithms, and clinical adoption of these tools, as we shed light on the future of deep networks and spiking neuromorphic processing systems as proponents for driving biomedical circuits and systems forward.

Non-invasive photoplethysmography (PPG) technology was developed to track heart rate during motion. Automated analysis of PPG has made it useful in both clinical and non-clinical applications. However, PPG-based heart rate tracking is a challenging problem due to motion artifacts (MAs) which are main contributors towards signal degradation as they mask the location of heart rate peak in the spectra. A practical analysis system must have good performance in MA removal as well as in tracking. In this article, we have presented state-of-art techniques in both areas of the automated analysis, i.e., MA removal and heart rate tracking, and have concluded that adaptive filtering and multi-resolution decomposition techniques are better for MA removal and machine learning-based approaches are future perspective of heart rate tracking. Hence, future systems will be composed of machine learning-based trackers fed with either empirically decomposed signal or from output of adaptive filter.

/pdf/heart-rate-tracking-in-photoplethysmography-signals-affected-534u7ij9sr.pdf

Heart rate tracking in photoplethysmography signals affected by motion artifacts: a review

Nowadays, Vending Machines are well known among Japan, Malaysia and Singapore. The quantity of machines in these countries is on the top worldwide. This is due to the modern lifestyles which require fast food processing with high quality. This paper describes the designing of multi select machine using Finite State Machine Model with Auto-Billing Features. Finite State Machine (FSM) modelling is the most crucial part in developing proposed model as this reduces the hardware. In this paper the process of four state (user Selection, Waiting for money insertion, product delivery and servicing) has been modelled using MEALY Machine Model. The proposed model is tested using Spartan 3 development board and its performance is compared with CMOS based machine.

/pdf/finite-state-machine-based-vending-machine-controller-with-3dcch3xfsh.pdf

Finite State Machine based Vending Machine Controller with Auto-Billing Features

Photoplethysmography (PPG) sensor-enabled wearable health monitoring devices can monitor realtime health status. PPG technology is a low-cost, noninvasive optical method used to measure a volumetric change in blood during a cardiac cycle. Continues analysis of change in light signal due to change in the blood helps medical professionals to extract valuable information regarding the cardiovascular system. Traditionally, an electrocardiogram (ECG) has been used as a dominant monitoring technique to detect irregularities in the cardiovascular system. However, in ECG for monitoring cardiac status, several electrodes have to be placed at different body locations, limiting its uses under medical assistantship and in a stationary position. Therefore, to fulfill the market demand for wearable and portable health monitoring devices, researchers are now showing interest in the PPG sensor enable wearable devices. However, the robustness of PPG sensor-enabled wearable devices is highly deviating due to motion artifacts. Therefore before extracting vital sign information like heart rate with PPG sensor, efficient removal of motion artifact is very important. This review orients the research survey on the principles and methods proposed for denoising and heart rate peak detection with PPG. The efficacy of each method related to heart rate peak detection with PPG technologies was compared in terms of mean absolute error, error percentage, and correlation coefficient. A comparative analysis is formulated to estimate heart rate based on the literature survey from the last ten years on PPG technology. This review article aims to explore different methods and challenges mentioned in state-of-the-art research related to motion artifacts removal and heart rate estimation from PPG-enabled wearable devices.

A Review on Computation Methods Used in Photoplethysmography Signal Analysis for Heart Rate Estimation

MoDTRAP: Improved heart rate tracking and preprocessing of motion-corrupted photoplethysmographic data for personalized healthcare

In this paper we propose an implementation technique for sequential circuit using single electron tunneling technology (SET-s) with the example of designing of a “coffee vending machine” with the goal of getting low power and faster operation. We implement the proposed design based on single electron encoded logic (SEEL).The circuit is tested and compared with the existing CMOS technology.

Design of a Coffee Vending Machine Using Single Electron Devices: (An Example of Sequential Circuit Design)

Photoplethysmographic (PPG) measurements from ambulatory subjects may suffer from unreliability due to body movements and missing data segments due to loosening of sensor. This paper describes an on-device reliability assessment from PPG measurements using a stack denoising autoencoder (SDAE) and multilayer perceptron neural network (MLPNN). The missing segments were predicted by a personalized convolutional neural network (CNN) and long-short term memory (LSTM) model using a short history of the same channel data. Forty sets of volunteers’ data, consisting of equal share of healthy and cardiovascular subjects were used for validation and testing. The PPG reliability assessment model (PRAM) achieved over 95% accuracy for correctly identifying acceptable PPG beats out of total 5000 using expert annotated data. Disagreement with experts’ annotation was nearly 3.5%. The missing segment prediction model (MSPM) achieved a root mean square error (RMSE) of 0.22, and mean absolute error (MAE) of 0.11 for 40 missing beats prediction using only four beat history from the same channel PPG. The two models were integrated in a standalone device based on quad-core ARM Cortex-A53, 1.2 GHz, with 1 GB RAM, with 130 MB memory requirement and latency ∼0.35 s per beat prediction with a 30 s frame. The present method also provides improved performance with published works on PPG quality assessment and missing data prediction using two public datasets, CinC and MIMIC-II under PhysioNet.

On-Device Reliability Assessment and Prediction of Missing Photoplethysmographic Data Using Deep Neural Networks

Noninvasive monitoring of respiratory activity is an emerging research area in biomedical health monitoring. This article describes a neural network-based model, intelligent Photoplethysmography derived Respiration signal Extraction, and Tracking ( ${i}$ -PRExT). Here, an ensemble empirical mode decomposition (EEMD) is used to select the appropriate intrinsic mode functions (IMFs) through filtering in the respiration band and reconstruct by a linear weighted sum to obtain the photoplethysmography derived respiration (PDR) signal. The weight factors are derived by a multilayer perceptron neural network (MLPNN) fed with respiratory induced amplitude variation (RIAV) features extracted by a deep autoencoder (DAE). The tracking of respiration rate (RR) is done by an adaptive filter-based predictor. ${i}$ -PRExT was tested and validated with BIDMC data set under PhysioNet and 30 volunteers’ data collected under resting condition. The PDRs achieved over 90% correlation and low error (NRMSE~0.2) with reference respiration signal, while RRs have almost 100% correlation even under motion artifact (MA) corrupted photoplethysmography (PPG). The PDR shows improved performance, while RR tracking outperforms the published research on respiration signal extraction based on PPG.

i -PRExT: Photoplethysmography Derived Respiration Signal Extraction and Respiratory Rate Tracking Using Neural Networks

In this paper, we propose a new technique for implementing a low power high speed multiplier using full adder consisting of minimum no. of transistors (8-T). Multiplier circuits are used comprehensively in Application Specific Integrated Circuits (ASICs). Thus it is desirable to have high speed operation for the sub components. The explored method of implementation achieves a high speed low power design for the multiplier. Simulated results indicate the superior performance of the proposed technique over conventional CMOS multiplier. Detailed comparison of simulated results for the conventional and present method of implementation is presented.

Biplab Roy

Papers

MoDTRAP: Improved heart rate tracking and preprocessing of motion-corrupted photoplethysmographic data for personalized healthcare

Design of a Coffee Vending Machine Using Single Electron Devices: (An Example of Sequential Circuit Design)

On-Device Reliability Assessment and Prediction of Missing Photoplethysmographic Data Using Deep Neural Networks

i -PRExT: Photoplethysmography Derived Respiration Signal Extraction and Respiratory Rate Tracking Using Neural Networks

Design of a low power 4×4 multiplier based on five transistor (5-T) half adder, eight transistor (8-T) full adder & two transistor (2-T) AND gate