scholarly journals Feature Extraction Method for Hidden Information in Audio Streams Based on HM-EMD

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Jiu Lou ◽  
Zhongliang Xu ◽  
Decheng Zuo ◽  
Hongwei Liu
Keyword(s):  
Feature Extraction ◽  
Extraction Method ◽  
Intrinsic Mode Functions ◽  
Hidden Information ◽  
Feature Extraction Method ◽  
Mode Decomposition ◽  
Basic Features ◽  
New Research ◽  
Audio Streams ◽  
The Internet Of Things

Using fake audio to spoof the audio devices in the Internet of Things has become an important problem in modern network security. Aiming at the problem of lack of robust features in fake audio detection, an audio streams’ hidden feature extraction method based on a heuristic mask for empirical mode decomposition (HM-EMD) is proposed in this paper. First, using HM-EMD, each signal is decomposed into several monotonic intrinsic mode functions (IMFs). Then, on the basis of IMFs, basic features and hidden information features HCFs of audio streams are constructed, respectively. Finally, a machine learning method is used to classify audio streams based on these features. The experimental results show that hidden information features of audio streams based on HM-EMD can effectively supplement the nonlinear and nonstationary information that traditional features such as mel cepstrum features cannot express and can better realize the representation of hidden acoustic events, which provide a new research idea for fake audio detection.

An Effective EMD-Based Feature Extraction Method for Boring Chatter Recognition

2010 ◽  
Vol 34-35 ◽  
pp. 1058-1063 ◽  
Author(s):  
Xin Li ◽  
Zhe He Yao ◽  
Zi Chen Chen
Keyword(s):  
Feature Extraction ◽  
Extraction Method ◽  
Vibration Signal ◽  
Intrinsic Mode Functions ◽  
Feature Extraction Method ◽  
Chatter Suppression ◽  
Mode Decomposition ◽  
Finished Surface ◽  
Precision Hole

Chatter often occurs during precision hole boring, it results in low quality of finished surface and even damages the cutting tool. In order to identify chatter rapidly and gain the precious time for chatter suppression, a chatter monitoring system was established and an effective feature extraction method for boring chatter recognition was presented. According to the characteristic of chatter signal, empirical mode decomposition (EMD) was introduced into chatter feature extraction, and its basic theories were investigated. The vibration signal was decomposed by EMD, then the intrinsic mode functions (IMF) was got. Finally, the feature of chatter symptom was extracted by analyzing the energy spectrum of each IMF. The results show that feature extracted from vibration of boring bar by EMD can indicate chatter outbreak symptom, and it can be used as feature vectors for rapidly recognizing chatter.

scholarly journals A Novel Feature Extraction Method for the Condition Monitoring of Bearings

Energies ◽  
2021 ◽  
Vol 14 (8) ◽  
pp. 2322
Author(s):  
Abdenour Soualhi ◽  
Bilal El Yousfi ◽  
Hubert Razik ◽  
Tianzhen Wang
Keyword(s):  
Feature Extraction ◽  
Extraction Method ◽  
Health Indicator ◽  
Intrinsic Mode Functions ◽  
Vibration Signals ◽  
Feature Extraction Method ◽  
Mode Decomposition ◽  
Marginal Spectrum ◽  
Spectrum Density ◽  
The Hilbert Transform

This paper presents an innovative approach to the extraction of an indicator for the monitoring of bearing degradation. This approach is based on the principles of the empirical mode decomposition (EMD) and the Hilbert transform (HT). The proposed approach extracts the temporal components of oscillating vibration signals called intrinsic mode functions (IMFs). These components are classified locally from the highest frequencies to the lowest frequencies. By selecting the appropriate components, it is possible to construct a bank of self-adaptive and automatic filters. Combined with the HT, the EMD allows an estimate of the instantaneous frequency of each IMF. A health indicator called the Hilbert marginal spectrum density is then extracted in order to detect and diagnose the degradation of bearings. This approach was validated on two test benches with variable speeds and loads. The obtained results demonstrated the effectiveness of this approach for the monitoring of ball and roller bearings.

scholarly journals A Novel Feature Extraction Method for Power Transformer Vibration Signal Based on CEEMDAN and Multi-Scale Dispersion Entropy

Entropy ◽  
2021 ◽  
Vol 23 (10) ◽  
pp. 1319
Author(s):  
Haikun Shang ◽  
Junyan Xu ◽  
Yucai Li ◽  
Wei Lin ◽  
Jinjuan Wang
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
Extraction Method ◽  
Vibration Signal ◽  
Practical Significance ◽  
Stable Operation ◽  
Intrinsic Mode Functions ◽  
Vibration Signals ◽  
Feature Extraction Method ◽  
Multi Scale

Effective diagnosis of vibration fault is of practical significance to ensure the safe and stable operation of power transformers. Aiming at the traditional problems of transformer vibration fault diagnosis, a novel feature extraction method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and multi-scale dispersion entropy (MDE) was proposed. In this paper, CEEMDAN method is used to decompose the original transformer vibration signal. Additionally, then MDE is used to capture multi-scale fault features in the decomposed intrinsic mode functions (IMFs). Next, the principal component analysis (PCA) method is employed to reduce the feature dimension and extract the effective information in vibration signals. Finally, the simplified features are sent into density peak clustering (DPC) to get the fault diagnosis results. The experimental data analysis shows that CEEMDAN-MDE can effectively extract the information of the original vibration signals and DPC can accurately diagnose the types of transformer faults. By comparing different algorithms, the practicability and superiority of this proposed method are verified.

scholarly journals Audio Information Camouflage Detection for Social Networks

2021 ◽  
Vol 9 ◽  
Author(s):  
Jiu Lou ◽  
Zhongliang Xu ◽  
Decheng Zuo ◽  
Zhan Zhang ◽  
Lin Ye
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Hidden Information ◽  
Mode Decomposition ◽  
New Research ◽  
Audio Information ◽  
Audio Streams ◽  
Mixing Problem ◽  
Emd Method ◽  
Better Than

Sending camouflaged audio information for fraud in social networks has become a new means of social networks attack. The hidden acoustic events in the audio scene play an important role in the detection of camouflaged audio information. Therefore, the application of machine learning methods to represent hidden information in audio streams has become a hot issue in the field of network security detection. This study proposes a heuristic mask for empirical mode decomposition (HM-EMD) method for extracting hidden features from audio streams. The method consists of two parts: First, it constructs heuristic mask signals related to the signal’s structure to solve the modal mixing problem in intrinsic mode function (IMF) and obtains a pure IMF related to the signal’s structure. Second, a series of hidden features in environment-oriented audio streams is constructed on the basis of the IMF. A machine learning method and hidden information features are subsequently used for audio stream scene classification. Experimental results show that the hidden information features of audio streams based on HM-EMD are better than the classical mel cepstrum coefficients (MFCC) under different classifiers. Moreover, the classification accuracy achieved with HM-EMD increases by 17.4 percentage points under the three-layer perceptron and by 1.3% under the depth model of TridentResNet. The hidden information features extracted by HM-EMD from audio streams revealed that the proposed method could effectively detect camouflaged audio information in social networks, which provides a new research idea for improving the security of social networks.

Characteristic Study on the Dynamic Response of Block Based on the EMD Technique of Feature Extraction

2011 ◽  
Vol 88-89 ◽  
pp. 93-98
Author(s):  
Xian Feng Du ◽  
Zhi Jun Li ◽  
Fong Rong Bi ◽  
Jun Hong Zhang ◽  
Xia Wang ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Original Data ◽  
Response Characteristic ◽  
Vibration Response ◽  
Engine Block ◽  
Intrinsic Mode Functions ◽  
Feature Extraction Method ◽  
Mode Decomposition ◽  
Block Based ◽  
The Fourier Transform

A feature extraction method for engine block using the empirical mode decomposition (EMD) technique has been proposed in this paper. The EMD technique is developed to break the limitations of conventional signal processing techniques in some extent and to perform further decomposition of signals. In order to extract feature information of engine block, the vibration response will first be processed by the EMD to generate the intrinsic mode functions (IMFs), and then identified by the Fourier transform. Then the same procedure will be adopted to extract the vibration response characteristic from FEM model of block, which is compared between the original and improved engine block. To verify the feasibility of such an approach, the vibration response generated by the finite element simulation will be analyzed, with results compared with the experimental ones. The results demonstrated that the EMD technique made the vibration characteristic more visible by the sifting process, and using the IMFs computed from vibration response, rather than based on the original data, the vibration sources of engine can be successfully identified. And we can also further confirm the structural weak regions of engine block and the main vibration sources, which are benefited to the engine block optimization.

Sign in / Sign up

Export Citation Format

Share Document