An Energy Efficient ECG Ventricular Ectopic Beat Classifier Using Binarized CNN for Edge AI Devices

Adaptive Global Power-of-Two Ternary Quantization Algorithm Based on Unfixed Boundary Thresholds

In the field of edge computing, quantizing convolutional neural networks (CNNs) using extremely low bit widths can significantly alleviate the associated storage and computational burdens in embedded hardware, thereby improving computational efficiency. However, such quantization also presents a challenge related to substantial decreases in detection accuracy. This paper proposes an innovative method, called Adaptive Global Power-of-Two Ternary Quantization Based on Unfixed Boundary Thresholds (APTQ). APTQ achieves adaptive quantization by quantizing each filter into two binary subfilters represented as power-of-two values, thereby addressing the accuracy degradation caused by a lack of expression ability of low-bit-width weight values and the contradiction between fixed quantization boundaries and the uneven actual weight distribution. It effectively reduces the accuracy loss while at the same time presenting strong hardware-friendly characteristics because of the power-of-two quantization. This paper extends the APTQ algorithm to propose the APQ quantization algorithm, which can adapt to arbitrary quantization bit widths. Furthermore, this paper designs dedicated edge deployment convolutional computation modules for the obtained quantized models. Through quantization comparison experiments with multiple commonly used CNN models utilized on the CIFAR10, CIFAR100, and Mini-ImageNet data sets, it is verified that the APTQ and APQ algorithms possess better accuracy performance than most state-of-the-art quantization algorithms and can achieve results with very low accuracy loss in certain CNNs (e.g., the accuracy loss of the APTQ ternary ResNet-56 model on CIFAR10 is 0.13%). The dedicated convolutional computation modules enable the corresponding quantized models to occupy fewer on-chip hardware resources in edge chips, thereby effectively improving computational efficiency. This adaptive CNN quantization method, combined with the power-of-two quantization results, strikes a balance between the quantization accuracy performance and deployment efficiency in embedded hardware. As such, valuable insights for the industrial edge computing domain can be gained.

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.

Wearable Technologies and AI at the Far Edge for Chronic Heart Failure Prevention and Management: A Systematic Review and Prospects

Smart wearable devices enable personalized at-home healthcare by unobtrusively collecting patient health data and facilitating the development of intelligent platforms to support patient care and management. The accurate analysis of data obtained from wearable devices is crucial for interpreting and contextualizing health data and facilitating the reliable diagnosis and management of critical and chronic diseases. The combination of edge computing and artificial intelligence has provided real-time, time-critical, and privacy-preserving data analysis solutions. However, based on the envisioned service, evaluating the additive value of edge intelligence to the overall architecture is essential before implementation. This article aims to comprehensively analyze the current state of the art on smart health infrastructures implementing wearable and AI technologies at the far edge to support patients with chronic heart failure (CHF). In particular, we highlight the contribution of edge intelligence in supporting the integration of wearable devices into IoT-aware technology infrastructures that provide services for patient diagnosis and management. We also offer an in-depth analysis of open challenges and provide potential solutions to facilitate the integration of wearable devices with edge AI solutions to provide innovative technological infrastructures and interactive services for patients and doctors.

Design of an Efficient CNN-based Cough Detection System on Lightweight FPGA

Precisely and automatically detecting the cough sound is of vital clinical importance. Nevertheless, due to privacy protection considerations, transmitting the raw audio data to the cloud is not permitted, and therefore there is a great demand for an efficient, accurate, and low-cost solution at the edge device. To address this challenge, we propose a semi-custom software-hardware co-design methodology to help build the cough detection system. Specifically, we first design a scalable and compact convolutional neural network (CNN) structure that generates many network instances. Second, we develop a dedicated hardware accelerator to perform the inference computation efficiently, and then we find the optimal network instance by applying network design space exploration. Finally, we compile the optimal network and let it run on the hardware accelerator. The experimental results demonstrate that our model achieves 88.8% classification accuracy, 91.2% sensitivity, 86.5% specificity, and 86.5% precision, while the computation complexity is only 1.09M multiply-accumulation (MAC). Additionally, when implemented on a lightweight field programmable gate array (FPGA), the complete cough detection system only occupies 7.9K lookup tables (LUTs), 12.9K flip-flops (FFs), and 41 digital signal processing (DSP) slices, providing 8.3 GOP/s actual inference throughput and total power dissipation of 0.93 W. This framework meets the needs of partial application and can be easily extended or integrated into other healthcare applications.

Low Complexity Binarized 2D-CNN Classifier for Wearable Edge AI Devices

Wearable Artificial Intelligence-of-Things (AIoT) devices exhibit the need to be resource and energy-efficient. In this paper, we introduced a quantized multilayer perceptron (qMLP) for converting ECG signals to binary image, which can be combined with binary convolutional neural network (bCNN) for classification. We deploy our model into a low-power and low-resource field programmable gate array (FPGA) fabric. The model requires 5.8× lesser multiply and accumulate (MAC) operations than known wearable CNN models. Our model also achieves a classification accuracy of 98.5%, sensitivity of 85.4%, specificity of 99.5%, precision of 93.3%, and F1-score of 89.2%, along with dynamic power dissipation of 34.9 μW.

A 746 nW ECG Processor ASIC Based on Ternary Neural Network

This paper presents an ultra-low power electrocardiography (ECG) processor application-specific integrated circuit (ASIC) for the real-time detection of abnormal cardiac rhythms (ACRs). The proposed ECG processor can support wearable or implantable ECG devices for long-term health monitoring. It adopts a derivative-based patient adaptive threshold approach to detect the R peaks in the PQRST complex of ECG signals. Two tiny machine learning classifiers are used for the accurate classification of ACRs. A 3-layer feed-forward ternary neural network (TNN) is designed, which classifies the QRS complex's shape, followed by the adaptive decision logics (DL). The proposed processor requires only 1 KB on-chip memory to store the parameters and ECG data required by the classifiers. The ECG processor has been implemented based on fully-customized near-threshold logic cells using thick-gate transistors in 65-nm CMOS technology. The ASIC core occupies a die area of 1.08 mm². The measured total power consumption is 746 nW, with 0.8 V power supply at 2.5 kHz real-time operating clock. It can detect 13 abnormal cardiac rhythms with a sensitivity and specificity of 99.10% and 99.5%. The number of detectable ACR types far exceeds the other low power designs in the literature.