Journal of Frontiers of Computer Science and Technology ›› 2021, Vol. 15 ›› Issue (4): 712-722.DOI: 10.3778/j.issn.1673-9418.2004017

• Artificial Intelligence • Previous Articles     Next Articles

Optimized Layered Convolutional Sub-health Recognition Algorithm of Improved Capsule Network

ZHANG Li, QIU Cunyue, ZHANG Kaixin, ZHANG Dabo, LUO Hao   

  1. College of Information, Liaoning University, Shenyang 110036, China
  • Online:2021-04-01 Published:2021-04-02

改进胶囊网络优化分层卷积的亚健康识别算法

张利邱存月张凯鑫张大波罗浩   

  1. 辽宁大学 信息学院,沈阳 110036

Abstract:

Aiming at the problem that traditional convolutional neural network (CNN) continuously stacks convo-lutional layers and pooling layers in order to obtain high accuracy, resulting in complicated model structure, long training time, and  single data processing method, a optimized layered convolutional sub-health recognition algorithm of improved capsule network is proposed. Firstly, the original vibration data are transformed by wavelet denoising and wavelet packet denoising to better retain the useful information in the original signal for sub-health recognition. Secondly, CNN adopts the idea of layered convolution, parallelizes three convolution kernels of different scales, and carries on multi-angle feature extraction. Finally, the features extracted by the convolution kernels are input into the improved capsule network with pruning strategy for sub-health recognition. The improved capsule network can not only guarantee the accuracy, but also accelerate the sub-health recognition time, thus the problems of too compli-cated CNN structure and poor recognition effect are solved. Experimental results show that the proposed algorithm has high recognition accuracy and less recognition time.

Key words: sub-health recognition, convolutional neural network (CNN), capsule network, wavelet denoising, wavelet packet denoising

摘要:

针对传统卷积神经网络(CNN)为获得高准确率不断堆叠卷积层、池化层致使模型结构复杂、训练时间长且数据处理方式单一的问题,提出改进胶囊网络优化分层卷积的亚健康识别算法。首先,对原始振动数据进行小波降噪和小波包降噪两种数据处理,更好地保留原始信号中对亚健康识别有用的信息;其次,CNN采用分层卷积的思想,并行3个不同尺度的卷积核,多角度地进行特征提取;最后,将卷积核提取的特征输入到剪枝策略的胶囊网络中进行亚健康识别,改进的胶囊网络在保证准确率的同时加快亚健康识别时间,解决CNN结构过于复杂以及识别效果不佳的问题。实验结果表明,提出算法识别准确率高且识别时间较少。

关键词: 亚健康识别, 卷积神经网络(CNN), 胶囊网络, 小波降噪, 小波包降噪