Weak Signal Enhance Based on the Neural Network Assisted Empirical Mode Decomposition

In order to enhance weak signals in strong noise background, a weak signal enhancement method based on EMDNN (neural network-assisted empirical mode decomposition) is proposed. This method combines CEEMD (complementary ensemble empirical mode decomposition), GAN (generative adversarial networks) and LSTM (long short-term memory), it enhances the efficiency of selecting effective natural mode components in empirical mode decomposition, thus the SNR (signal-noise ratio) is improved. It can also reconstruct and enhance weak signals. The experimental results show that the SNR of this method is improved from 4.1 to 6.2, and the weak signal is clearly recovered.

[1]  Kai Xie,et al.  Efficient medical image enhancement based on CNN-FBB model , 2019, IET Image Process..

[2]  Muhammad Mohsin Riaz,et al.  Dual-tree complex wavelet transform and SVD based medical image resolution enhancement , 2014, Signal Process..

[3]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[4]  Peter Wilson,et al.  Linear friction weld process monitoring of fixture cassette deformations using empirical mode decomposition , 2015 .

[5]  S. Edward Jero,et al.  ECG steganography using curvelet transform , 2015, Biomed. Signal Process. Control..

[6]  Jürgen Schmidhuber,et al.  A Clockwork RNN , 2014, ICML.

[7]  Kai Xie,et al.  Face liveness detection: fusing colour texture feature and deep feature , 2019, IET Biom..

[8]  Kai Xie,et al.  Face Recognition Using the SR-CNN Model , 2018, Sensors.

[9]  Ghassan AlRegib,et al.  Curvelet transform with learning-based tiling , 2017, Signal Process. Image Commun..

[10]  Hadi Hadizadeh,et al.  Multi-resolution local Gabor wavelets binary patterns for gray-scale texture description , 2015, Pattern Recognit. Lett..

[11]  María Eugenia Torres,et al.  Improved complete ensemble EMD: A suitable tool for biomedical signal processing , 2014, Biomed. Signal Process. Control..

[12]  Biswajit Basu,et al.  ASDAH: An automated structural change detection algorithm based on the Hilbert–Huang transform , 2014 .

[13]  J. Mohanalin,et al.  Wavelet based seismic signal de-noising using Shannon and Tsallis entropy , 2012, Comput. Math. Appl..

[14]  Juan J. Galiana-Merino,et al.  SeismicWaveTool: Continuous and discrete wavelet analysis and filtering for multichannel seismic data , 2013, Comput. Phys. Commun..

[15]  Bernt Schiele,et al.  Generative Adversarial Text to Image Synthesis , 2016, ICML.

[16]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[17]  Yi Qin,et al.  Adaptive signal decomposition based on wavelet ridge and its application , 2016, Signal Process..

[18]  周亚同 Zhou Yatong,et al.  Three Dimensional Seismic Signal Denoising Based on Four-Dimensional Block Matching Cooperative Filtering Combined with Principle Component Analysis , 2018 .

[19]  Kai Xie,et al.  Fast seismic data compression based on high-efficiency SPIHT , 2014 .

[20]  Yin Huan-ron.  Denoising of nonlinear wavelet transform threshold value method in engineering , 2008 .

[21]  Geoffrey E. Hinton,et al.  Learning distributed representations of concepts. , 1989 .

[22]  Jihong Yan,et al.  Improved Hilbert-Huang transform based weak signal detection methodology and its application on incipient fault diagnosis and ECG signal analysis , 2014, Signal Process..

[23]  Antonio Morales-Esteban,et al.  Identifying P phase arrival of weak events: The Akaike Information Criterion picking application based on the Empirical Mode Decomposition , 2017, Comput. Geosci..

[24]  Norden E. Huang,et al.  Derivative-optimized empirical mode decomposition for the Hilbert-Huang transform , 2014, J. Comput. Appl. Math..

[25]  Yu Hu,et al.  Fast recovery of weak signal based on three-dimensional curvelet transform and generalised cross validation , 2018, IET Signal Process..

[26]  Jing Li,et al.  Robust Face Recognition Using the Deep C2D-CNN Model Based on Decision-Level Fusion , 2018, Sensors.

[27]  Kai Xie,et al.  Voiceprint Identification for Limited Dataset Using the Deep Migration Hybrid Model Based on Transfer Learning , 2018, Sensors.

[28]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[29]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.

[30]  Tianyou Chai,et al.  Multi-frequency signal modeling using empirical mode decomposition and PCA with application to mill load estimation , 2015, Neurocomputing.

[31]  TangBaoping,et al.  Adaptive signal decomposition based on wavelet ridge and its application , 2016 .

[32]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[33]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[34]  Da-Chao Lin,et al.  Elimination of end effects in empirical mode decomposition by mirror image coupled with support vector regression , 2012 .

[35]  YanJihong,et al.  Improved Hilbert-Huang transform based weak signal detection methodology and its application on incipient fault diagnosis and ECG signal analysis , 2014 .

[36]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[37]  Lu Li,et al.  Fast visualisation of massive data based on viewpoint motion model , 2017 .