Hilbert time-frequency spectrum feature extraction method

被引：0
|
作者：
Wei J. [1 ]
Gu X. [1 ]
Ning F. [2 ]
机构：
[1] School of Communication Engineering, Xidian University, Xi'an
[2] School of Mechanical Engineering, Northwestern Polytechnical University, Xi'an
来源：
| 1600年 / Huazhong University of Science and Technology卷 / 49期
关键词：
Feature extraction; Hilbert time-frequency spectrum; Hilbert-Huang transform(HHT); Smoothing; Time-frequency analysis;
D O I：
10.13245/j.hust.210109
中图分类号：
学科分类号：
摘要：
In order to optimize the expression effect of Hilbert time-frequency spectrum with high frequency resolution,a method of Hilbert time-frequency spectrum smoothing and adaptive enhancement based on the idea of convolution operation was proposed.First,the Hilbert-Huang transform was used to obtain the time-frequency spectra and marginal spectra with high frequency resolution.By setting the time-domain and frequency-domain smoothing factors and weights,the corresponding kernel matrix was obtained,and the time-frequency spectra was smoothed according to the process of convolution.Then,the marginal spectrum value after smoothing was used as the enhancement factor of the spectral line at the corresponding instantaneous frequency in the time-frequency spectrum,and the time-frequency spectrum was adaptively enhanced.Finally,the UrbanSound8K dataset was used to extract the time-frequency spectrum as a feature,and the deep convolutional neural network was used to perform the verification experiment.The simulation results show that smoothing method can effectively improve the overall expression effect of Hilbert time-frequency spectrum,and can adaptively change the appearance of time-frequency spectrum. © 2021, Editorial Board of Journal of Huazhong University of Science and Technology. All right reserved.
引用
收藏
页码：50 / 54
页数：4
相关论文
共 13 条
  • [1] CHEN Hai, YUAN Xiaocheng, PEI Zhiyuan, Et al., Triple-classification of respiratory sounds using optimized s-transform and deep residual networks[J], IEEE Access, 7, pp. 32845-32852, (2019)
  • [2] XU Yan, ZHENG Yi, HE Chuanlin, Et al., The research on phase spectrum decomposition mechanism based on one-side EMD[C], Proceedings of 2019 Chinese Control And Decision Conference, pp. 1080-1084, (2019)
  • [3] MA Yabin, CHEN Chen, SHU Qiqi, Et al., Fault diagnosis of rolling bearing based on EMD combined with HHT envelope and wavelet spectrum transform[C], Proceedings of 2018 IEEE 7th Data Driven Control and Learning Systems Conference, pp. 481-485, (2018)
  • [4] WANG Jinlin, LIU Yongmei, WANG Li, Et al., Spectrum analysis method of residual current based on Hilbert-Huang transform[C], Proceedings of International Conference on Probabilistic Methods Applied to Power Systems, pp. 1-12, (2016)
  • [5] WANG Jinfang, DU Hailong, GUO Ming, Et al., Feature extraction using HHT-based locally optimized short-time fractional Fourier transform for speaker recognition, Proceedings of IEEE International Conference on Imaging, pp. 24-32, (2017)
  • [6] YUAN Zhuang, ZHANG Laibin, DUAN Lixiang, Et al., Intelligent fault diagnosis of rolling element bearings based on HHT and CNN[C], Proceedings of 2018 Prognostics and System Health Management Conference, pp. 292-296, (2018)
  • [7] LI Ning, HE Fuxing, LI Xinyi, Et al., A novel power quality disturbance recognition method based on improved HHT algorithm[C], Proceedings of 2018 IEEE 4th Information Technology and Mechatronics Engineering Conference, pp. 436-440, (2018)
  • [8] 7
  • [9] ELTIRAIFI O, ELBASHEER E, NAWARI M., A comparative study of MFCC and LPCC features for speech activity detection using deep belief network[C], Proceedings of 2018 International Conference on Computer,Control,Electrical,and Electronics Engineering, pp. 1-5, (2018)
  • [10] LI Jingsong, ZHAO Chi, SU Hang, A mode mixing elimination method of HHT in fault detection, Proceedings of International Conference on Cloud Computing & Internet of Things, pp. 120-123, (2017)
12