HEART SOUND CLASSIFICATION AND RECOGNITION BASED ON EEMD AND CORRELATION DIMENSION

2014 ◽  
Vol 14 (04) ◽  
pp. 1450046 ◽  
Author(s):  
WENYING ZHANG ◽  
XINGMING GUO ◽  
ZHIHUI YUAN ◽  
XINGHUA ZHU
Keyword(s):  
Feature Extraction ◽  
Heart Sound ◽  
Linear Time ◽  
Heart Diseases ◽  
Recognition Rate ◽  
Heart Sounds ◽  
Support Vector ◽  
Svm Classifier ◽  
Intrinsic Mode Functions ◽  
Sound Classification

Analysis of heart sound is of great importance to the diagnosis of heart diseases. Most of the feature extraction methods about heart sound have focused on linear time-variant or time-invariant models. While heart sound is a kind of highly nonstationary and nonlinear vibration signal, traditional methods cannot fully reveal its essential properties. In this paper, a novel feature extraction approach is proposed for heart sound classification and recognition. The ensemble empirical mode decomposition (EEMD) method is used to decompose the heart sound into a finite number of intrinsic mode functions (IMFs), and the correlation dimensions of the main IMF components (IMF1~IMF4) are calculated as feature set. Then the classical Binary Tree Support Vector Machine (BT-SVM) classifier is employed to classify the heart sounds which include the normal heart sounds (NHSs) and three kinds of abnormal signals namely mitral stenosis (MT), ventricular septal defect (VSD) and aortic stenosis (AS). Finally, the performance of the new feature set is compared with the correlation dimensions of original signals and the main IMF components obtained by the EMD method. The results showed that, for NHSs, the feature set proposed in this paper performed the best with recognition rate of 98.67%. For the abnormal signals, the best recognition rate of 91.67% was obtained. Therefore, the proposed feature set is more superior to two comparative feature sets, which has potential application in the diagnosis of cardiovascular diseases.

scholarly journals Persian Handwritten Digit Recognition Using Combination of Convolutional Neural Network and Support Vector Machine Methods

2020 ◽  
Vol 17 (4) ◽  
pp. 572-578
Author(s):  
Mohammad Parseh ◽  
Mohammad Rahmanimanesh ◽  
Parviz Keshavarzi
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Feature Extraction ◽  
Convolutional Neural Network ◽  
Recognition Rate ◽  
Support Vector ◽  
Svm Classifier ◽  
Handwritten Digit Recognition ◽  
Digit Recognition ◽  
Handwritten Digit

Persian handwritten digit recognition is one of the important topics of image processing which significantly considered by researchers due to its many applications. The most important challenges in Persian handwritten digit recognition is the existence of various patterns in Persian digit writing that makes the feature extraction step to be more complicated.Since the handcraft feature extraction methods are complicated processes and their performance level are not stable, most of the recent studies have concentrated on proposing a suitable method for automatic feature extraction. In this paper, an automatic method based on machine learning is proposed for high-level feature extraction from Persian digit images by using Convolutional Neural Network (CNN). After that, a non-linear multi-class Support Vector Machine (SVM) classifier is used for data classification instead of fully connected layer in final layer of CNN. The proposed method has been applied to HODA dataset and obtained 99.56% of recognition rate. Experimental results are comparable with previous state-of-the-art methods

scholarly journals Biometric Identification Method for Heart Sound Based on Multimodal Multiscale Dispersion Entropy

Entropy ◽  
2020 ◽  
Vol 22 (2) ◽  
pp. 238 ◽  
Author(s):  
Xiefeng Cheng ◽  
Pengfei Wang ◽  
Chenjun She
Keyword(s):  
Markov Models ◽  
Heart Sound ◽  
Recognition Rate ◽  
Ensemble Empirical Mode Decomposition ◽  
Heart Sounds ◽  
Feature Representation ◽  
Intrinsic Mode Functions ◽  
Single Cycle ◽  
Starting Position ◽  
Mode Decomposition

In this paper, a new method of biometric characterization of heart sounds based on multimodal multiscale dispersion entropy is proposed. Firstly, the heart sound is periodically segmented, and then each single-cycle heart sound is decomposed into a group of intrinsic mode functions (IMFs) by improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN). These IMFs are then segmented to a series of frames, which is used to calculate the refine composite multiscale dispersion entropy (RCMDE) as the characteristic representation of heart sound. In the simulation experiments I, carried out on the open heart sounds database Michigan, Washington and Littman, the feature representation method was combined with the heart sound segmentation method based on logistic regression (LR) and hidden semi-Markov models (HSMM), and feature selection was performed through the Fisher ratio (FR). Finally, the Euclidean distance (ED) and the close principle are used for matching and identification, and the recognition accuracy rate was 96.08%. To improve the practical application value of this method, the proposed method was applied to 80 heart sounds database constructed by 40 volunteer heart sounds to discuss the effect of single-cycle heart sounds with different starting positions on performance in experiment II. The experimental results show that the single-cycle heart sound with the starting position of the start of the first heart sound (S1) has the highest recognition rate of 97.5%. In summary, the proposed method is effective for heart sound biometric recognition.

scholarly journals Multi-Stage Feature Extraction and Classification for Ship-Radiated Noise

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 112
Author(s):  
Hamada Esmaiel ◽  
Dongri Xie ◽  
Zeyad A. H. Qasem ◽  
Haixin Sun ◽  
Jie Qi ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Recognition Rate ◽  
Extraction Methods ◽  
Permutation Entropy ◽  
Support Vector ◽  
Intrinsic Mode Functions ◽  
Radiated Noise ◽  
Passive Sonar ◽  
Multi Stage ◽  
Mode Decomposition

Due to the complexity and unique features of the hydroacoustic channel, ship-radiated noise (SRN) detected using a passive sonar tends mostly to distort. SRN feature extraction has been proposed to improve the detected passive sonar signal. Unfortunately, the current methods used in SRN feature extraction have many shortcomings. Considering this, in this paper we propose a new multi-stage feature extraction approach to enhance the current SRN feature extractions based on enhanced variational mode decomposition (EVMD), weighted permutation entropy (WPE), local tangent space alignment (LTSA), and particle swarm optimization-based support vector machine (PSO-SVM). In the proposed method, first, we enhance the decomposition operation of the conventional VMD by decomposing the SRN signal into a finite group of intrinsic mode functions (IMFs) and then calculate the WPE of each IMF. Then, the high-dimensional features obtained are reduced to two-dimensional ones by using the LTSA method. Finally, the feature vectors are fed into the PSO-SVM multi-class classifier to realize the classification of different types of SRN sample. The simulation and experimental results demonstrate that the recognition rate of the proposed method overcomes the conventional SRN feature extraction methods, and it has a recognition rate of up to 96.6667%.

scholarly journals A Feature Extraction Method of Ship-Radiated Noise Based on Fluctuation-Based Dispersion Entropy and Intrinsic Time-Scale Decomposition

Entropy ◽  
2019 ◽  
Vol 21 (7) ◽  
pp. 693 ◽  
Author(s):  
Zhaoxi Li ◽  
Yaan Li ◽  
Kai Zhang
Keyword(s):  
Feature Extraction ◽  
Time Scale ◽  
Recognition Rate ◽  
Support Vector ◽  
Svm Classifier ◽  
Feature Extraction Method ◽  
Radiated Noise ◽  
Intrinsic Time ◽  
Different Types ◽  
Time Scale Decomposition

To improve the feature extraction of ship-radiated noise in a complex ocean environment, fluctuation-based dispersion entropy is used to extract the features of ten types of ship-radiated noise. Since fluctuation-based dispersion entropy only analyzes the ship-radiated noise signal in single scale and it cannot distinguish different types of ship-radiated noise effectively, a new method of ship-radiated noise feature extraction is proposed based on fluctuation-based dispersion entropy (FDispEn) and intrinsic time-scale decomposition (ITD). Firstly, ten types of ship-radiated noise signals are decomposed into a series of proper rotation components (PRCs) by ITD, and the FDispEn of each PRC is calculated. Then, the correlation between each PRC and the original signal are calculated, and the FDispEn of each PRC is analyzed to select the Max-relative PRC fluctuation-based dispersion entropy as the feature parameter. Finally, by comparing the Max-relative PRC fluctuation-based dispersion entropy of a certain number of the above ten types of ship-radiated noise signals with FDispEn, it is discovered that the Max-relative PRC fluctuation-based dispersion entropy is at the same level for similar ship-radiated noise, but is distinct for different types of ship-radiated noise. The Max-relative PRC fluctuation-based dispersion entropy as the feature vector is sent into the support vector machine (SVM) classifier to classify and recognize ten types of ship-radiated noise. The experimental results demonstrate that the recognition rate of the proposed method reaches 95.8763%. Consequently, the proposed method can effectively achieve the classification of ship-radiated noise.

scholarly journals Optimized Variational Mode Decomposition and Permutation Entropy with Their Application in Feature Extraction of Ship-Radiated Noise

Entropy ◽  
2021 ◽  
Vol 23 (5) ◽  
pp. 503
Author(s):  
Dongri Xie ◽  
Shaohua Hong ◽  
Chaojun Yao
Keyword(s):  
Feature Extraction ◽  
Recognition Rate ◽  
Permutation Entropy ◽  
Support Vector ◽  
Variational Mode Decomposition ◽  
Intrinsic Mode Functions ◽  
Marine Animals ◽  
Practical Applications ◽  
Radiated Noise ◽  
Mode Decomposition

The complex and changeable marine environment surrounded by a variety of noise, including sounds of marine animals, industrial noise, traffic noise and the noise formed by molecular movement, not only interferes with the normal life of residents near the port, but also exerts a significant influence on feature extraction of ship-radiated noise (S-RN). In this paper, a novel feature extraction technique for S-RN signals based on optimized variational mode decomposition (OVMD), permutation entropy (PE), and normalized Spearman correlation coefficient (NSCC) is proposed. Firstly, with the mode number determined by reverse weighted permutation entropy (RWPE), OVMD decomposes the target signal into a set of intrinsic mode functions (IMFs). The PE of all the IMFs and SCC between each IMF with the raw signal are then calculated, respectively. Subsequently, feature parameters are extracted through the sum of PE weighted by NSCC for the IMFs. Lastly, the obtained feature vectors are input into the support vector machine multi-class classifier (SVM) to discriminate various types of ships. Experimental results indicate that five kinds of S-RN samples can be accurately identified with a recognition rate of 94% by the proposed scheme, which is higher than other previously published methods. Hence, the proposed method is more advantageous in practical applications.

scholarly journals A Peak Detection Algorithm for Localization and Classification of Heart Sounds in PCG Signals using K-means Clustering

2021 ◽  
Author(s):  
Muhammad Zubair
Keyword(s):  
Detection Algorithm ◽  
Heart Sounds ◽  
Stochastic Gradient Descent ◽  
Support Vector ◽  
Svm Classifier ◽  
Mel Frequency Cepstral Coefficients ◽  
Sound Classification ◽  
Clustering Model ◽  
Peak Detection Algorithm

Traditionally, the heart sound classification process is performed by first finding the elementary heart sounds of the phonocardiogram (PCG) signal. After detecting sounds S1 and S2, the features like envelograms, Mel frequency cepstral coefficients (MFCC), kurtosis, etc., of these sounds are extracted. These features are used for the classification of normal and abnormal heart sounds, which leads to an increase in computational complexity. In this paper, we have proposed a fully automated algorithm to localize heart sounds using K-means clustering. The K-means clustering model can differentiate between the primitive heart sounds like S1, S2, S3, S4 and the rest of the insignificant sounds like murmurs without requiring the excessive pre-processing of data. The peaks detected from the noisy data are validated by implementing five classification models with 30 fold cross-validation. These models have been implemented on a publicly available PhysioNet/Cinc challenge 2016 database. Lastly, to classify between normal and abnormal heart sounds, the localized labelled peaks from all the datasets were fed as an input to the various classifiers such as support vector machine (SVM), K-nearest neighbours (KNN), logistic regression, stochastic gradient descent (SGD) and multi-layer perceptron (MLP). To validate the superiority of the proposed work, we have compared our reported metrics with the latest state-of-the-art works. Simulation results show that the highest classification accuracy of 94.75% is achieved by the SVM classifier among all other classifiers.

scholarly journals Performance Evaluation of Face Recognition system by Concatenation of Spatial and Transformation Domain Features

2021 ◽  
Vol 13 (1) ◽  
pp. 47-60
Author(s):  
Raveendra K ◽  
◽  
Ravi J
Keyword(s):  
Feature Extraction ◽  
Performance Evaluation ◽  
Face Recognition ◽  
Frequency Domain ◽  
Recognition Rate ◽  
Curvelet Transform ◽  
Recognition System ◽  
Support Vector ◽  
Svm Classifier ◽  
Fast Discrete Curvelet Transform

Face biometric system is one of the successful applications of image processing. Person recognition using face is the challenging task since it involves identifying the 3D object from 2D object. The feature extraction plays a very important role in face recognition. Extraction of features both in spatial as well as frequency domain has more advantages than the features obtained from single domain alone. The proposed work achieves spatial domain feature extraction using Asymmetric Region Local Binary Pattern (ARLBP) and frequency domain feature extraction using Fast Discrete Curvelet Transform (FDCT). The obtained features are fused by concatenation and compared with trained set of features using different distance metrics and Support Vector Machine (SVM) classifier. The experiment is conducted for different face databases. It is shown that the proposed work yields 95.48% accuracy for FERET, 92.18% for L-space k, 76.55% for JAFFE and 81.44% for NIR database using SVM classifier. The results show that the proposed system provides better recognition rate for SVM classifier when compare to the other distance matrices. Further, the work is also compared with existing work for performance evaluation.

scholarly journals A Peak Detection Algorithm for Localization and Classification of Heart Sounds in PCG Signals using K-means Clustering

2021 ◽  
Author(s):  
Muhammad Zubair
Keyword(s):  
Detection Algorithm ◽  
Heart Sounds ◽  
Stochastic Gradient Descent ◽  
Support Vector ◽  
Svm Classifier ◽  
Mel Frequency Cepstral Coefficients ◽  
Sound Classification ◽  
Clustering Model ◽  
Peak Detection Algorithm

Traditionally, the heart sound classification process is performed by first finding the elementary heart sounds of the phonocardiogram (PCG) signal. After detecting sounds S1 and S2, the features like envelograms, Mel frequency cepstral coefficients (MFCC), kurtosis, etc., of these sounds are extracted. These features are used for the classification of normal and abnormal heart sounds, which leads to an increase in computational complexity. In this paper, we have proposed a fully automated algorithm to localize heart sounds using K-means clustering. The K-means clustering model can differentiate between the primitive heart sounds like S1, S2, S3, S4 and the rest of the insignificant sounds like murmurs without requiring the excessive pre-processing of data. The peaks detected from the noisy data are validated by implementing five classification models with 30 fold cross-validation. These models have been implemented on a publicly available PhysioNet/Cinc challenge 2016 database. Lastly, to classify between normal and abnormal heart sounds, the localized labelled peaks from all the datasets were fed as an input to the various classifiers such as support vector machine (SVM), K-nearest neighbours (KNN), logistic regression, stochastic gradient descent (SGD) and multi-layer perceptron (MLP). To validate the superiority of the proposed work, we have compared our reported metrics with the latest state-of-the-art works. Simulation results show that the highest classification accuracy of 94.75% is achieved by the SVM classifier among all other classifiers.

scholarly journals LPI Radar Waveform Recognition Based on Deep Convolutional Neural Network Transfer Learning

Symmetry ◽  
2019 ◽  
Vol 11 (4) ◽  
pp. 540 ◽  
Author(s):  
Qiang Guo ◽  
Xin Yu ◽  
Guoqing Ruan
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Recognition Rate ◽  
Training Model ◽  
Recognition System ◽  
Support Vector ◽  
Svm Classifier ◽  
Time Frequency ◽  
Deep Convolution Network ◽  
Original Time

Low Probability of Intercept (LPI) radar waveform recognition is not only an important branch of the electronic reconnaissance field, but also an important means to obtain non-cooperative radar information. To solve the problems of LPI radar waveform recognition rate, difficult feature extraction and large number of samples needed, an automatic classification and recognition system based on Choi-Williams distribution (CWD) and depth convolution neural network migration learning is proposed in this paper. First, the system performs CWD time-frequency transform on the LPI radar waveform to obtain a 2-D time-frequency image. Then the system preprocesses the original time-frequency image. In addition, then the system sends the pre-processed image to the pre-training model (Inception-v3 or ResNet-152) of the deep convolution network for feature extraction. Finally, the extracted features are sent to a Support Vector Machine (SVM) classifier to realize offline training and online recognition of radar waveforms. The simulation results show that the overall recognition rate of the eight LPI radar signals (LFM, BPSK, Costas, Frank, and T1–T4) of the ResNet-152-SVM system reaches 97.8%, and the overall recognition rate of the Inception-v3-SVM system reaches 96.2% when the SNR is −2 dB.

scholarly journals EEG Signals Feature Extraction Based on DWT and EMD Combined with Approximate Entropy

2019 ◽  
Vol 9 (8) ◽  
pp. 201 ◽  
Author(s):  
Ji ◽  
Ma ◽  
Dong ◽  
Zhang
Keyword(s):  
Feature Extraction ◽  
Signal Reconstruction ◽  
Recognition Rate ◽  
Approximate Entropy ◽  
Stationary Time Series ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Eeg Signal ◽  
Intrinsic Mode Functions ◽  
Reconstructed Signal

The classification recognition rate of motor imagery is a key factor to improve the performance of brain–computer interface (BCI). Thus, we propose a feature extraction method based on discrete wavelet transform (DWT), empirical mode decomposition (EMD), and approximate entropy. Firstly, the electroencephalogram (EEG) signal is decomposed into a series of narrow band signals with DWT, then the sub-band signal is decomposed with EMD to get a set of stationary time series, which are called intrinsic mode functions (IMFs). Secondly, the appropriate IMFs for signal reconstruction are selected. Thus, the approximate entropy of the reconstructed signal can be obtained as the corresponding feature vector. Finally, support vector machine (SVM) is used to perform the classification. The proposed method solves the problem of wide frequency band coverage during EMD and further improves the classification accuracy of EEG signal motion imaging,

Sign in / Sign up

Export Citation Format

Share Document