期刊
IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS
卷 16, 期 5, 页码 822-831出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TBCAS.2022.3196165
关键词
Electrocardiography; Hardware; Feature extraction; Field programmable gate arrays; Computational modeling; Training; Image synthesis; Artificial intelligence-of-things; co-design; convolutional neural network; ECG; field programmable gate array; inference; low-power design; multi-layer perceptron; multi-tasking; reuse; state machine; wearable
In this paper, a quantized multilayer perceptron (qMLP) is introduced to convert ECG signals to binary images, which can be classified using a binary convolutional neural network (bCNN). The model is deployed on a low-power and low-resource FPGA fabric, requiring fewer multiply and accumulate operations compared to known wearable CNN models. The model achieves high classification accuracy and other performance metrics, along with low power dissipation.
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 5.8x 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 mu W.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据