• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Low Power Electronics >Power-Accuracy Trade-Offs for Heartbeat Classification on Neural Networks Hardware
【24h】

Power-Accuracy Trade-Offs for Heartbeat Classification on Neural Networks Hardware

机译：神经网络硬件心跳分类的功率准确性权衡

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Heartbeat classification using electrocardiogram (ECG) data is an essential feature of modern day wearable devices. State-of-the-art machine learning-based heartbeat classifiers are designed using convolutional neural networks (CNN). Despite their high classification accuracy, CNNsrequire significant computational resources and power. This makes the mapping of CNNs on resource- and power-constrained wearable devices challenging. In this paper, we propose heartbeat classification using spiking neural networks (SNN), an alternative approach based on a biologically inspired,event-driven neural networks. SNNs compute and transfer information using discrete spikes that require fewer operations and less complex hardware resources, making them energy-efficient compared to CNNs. However, due to complex error-backpropagation involving spikes, supervised learning ofdeep SNNs remains challenging. We propose an alternative approach to SNN-based heartbeat classification. We start with an optimized CNN implementation of the heartbeat classification task and then convert the CNN operations, such as multiply-accumulate, pooling and softmax, into spiking equivalentwith a minimal loss of accuracy. We evaluate the SNN-based heartbeat classification using publicly available ECG database of the Massachusetts Institute of Technology and Beth Israel Hospital (MIT/BIH), and demonstrate a minimal loss in accuracy when compared to 85.92% accuracy of a CNN-basedhearbeat classification. We demonstrate that, for every operation, the activation of SNN neurons in each layer is sparse when compared to CNN neurons, in the same layer. We also show that this sparsity increases with an increase in the number of layers of the neural network. In addition, wedetail the power-accuracy trade-off of the SNN and show a 87.76% and 96.82% reduction in SNN neuron and synapse activity, respectively, for accuracy loss ranging between 0.6% and 1.00%, when compared to a CNN-only implementation.
机译：使用心电图（ECG）数据的心跳分类是现代佩戴设备的重要特征。基于最先进的机器学习的心跳分类器使用卷积神经网络（CNN）设计。尽管他们的分类精度高，CNNSREQUIRE显着的计算资源和电力。这使CNN映射到资源和功率受限的可佩戴设备具有挑战性。在本文中，我们用尖刺神经网络（SNN）提出了心跳分类，这是一种基于生物启发的事件驱动的神经网络的替代方法。 SNNS使用需要更少的运营和更复杂的硬件资源的离散尖峰计算和传输信息，与CNN相比，使其能够节能。然而，由于涉及尖峰的复杂错误逆产，监督学习患者仍然具有挑战性。我们提出了一种替代方法，以替代的基于SNN的心跳分类。我们首先从节食分类任务的优化CNN实现，然后将CNN操作转换为乘法累积，汇集和软邮件，进入尖刺等同于最小的精度损失。我们使用Massachusetts技术研究所和Beth以色列医院（MIT / BIH）的公开可用的ECG数据库评估了基于SNN的心跳分类，并且在与CNN的良好分类的高精度相比时，准确度的最小损失。我们证明，对于每种操作，与CNN神经元在同一层中，每层的SNN神经元的激活是稀疏的。我们还表明，这种稀疏性随着神经网络层数的增加而增加。此外，呈现SNN的功率准确性权衡，分别显示SNN神经元和突触活动的87.76％和96.82％，以便精度损耗范围为0.6％和1.00％，与仅限CNN--相比执行。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号