scholarly journals Mental Task Classification Scheme Utilizing Correlation Coefficient Extracted from Interchannel Intrinsic Mode Function

2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Md. Mostafizur Rahman ◽  
Shaikh Anowarul Fattah
Keyword(s):  
Correlation Coefficient ◽  
Classification Performance ◽  
Support Vector ◽  
Svm Classifier ◽  
Eeg Signal ◽  
Statistical Features ◽  
Intrinsic Mode Functions ◽  
Mode Decomposition ◽  
High Level ◽  
Mental Tasks

In view of recent increase of brain computer interface (BCI) based applications, the importance of efficient classification of various mental tasks has increased prodigiously nowadays. In order to obtain effective classification, efficient feature extraction scheme is necessary, for which, in the proposed method, the interchannel relationship among electroencephalogram (EEG) data is utilized. It is expected that the correlation obtained from different combination of channels will be different for different mental tasks, which can be exploited to extract distinctive feature. The empirical mode decomposition (EMD) technique is employed on a test EEG signal obtained from a channel, which provides a number of intrinsic mode functions (IMFs), and correlation coefficient is extracted from interchannel IMF data. Simultaneously, different statistical features are also obtained from each IMF. Finally, the feature matrix is formed utilizing interchannel correlation features and intrachannel statistical features of the selected IMFs of EEG signal. Different kernels of the support vector machine (SVM) classifier are used to carry out the classification task. An EEG dataset containing ten different combinations of five different mental tasks is utilized to demonstrate the classification performance and a very high level of accuracy is achieved by the proposed scheme compared to existing methods.

scholarly journals Gearbox Fault Diagnosis Using Complementary Ensemble Empirical Mode Decomposition and Permutation Entropy

2016 ◽  
Vol 2016 ◽  
pp. 1-8 ◽  
Author(s):  
Liye Zhao ◽  
Wei Yu ◽  
Ruqiang Yan
Keyword(s):  
Fault Diagnosis ◽  
Empirical Mode Decomposition ◽  
Correlation Coefficients ◽  
Ensemble Empirical Mode Decomposition ◽  
Permutation Entropy ◽  
Support Vector ◽  
Svm Classifier ◽  
Intrinsic Mode Functions ◽  
Vibration Signals ◽  
Mode Decomposition

This paper presents an improved gearbox fault diagnosis approach by integrating complementary ensemble empirical mode decomposition (CEEMD) with permutation entropy (PE). The presented approach identifies faults appearing in a gearbox system based on PE values calculated from selected intrinsic mode functions (IMFs) of vibration signals decomposed by CEEMD. Specifically, CEEMD is first used to decompose vibration signals characterizing various defect severities into a series of IMFs. Then, filtered vibration signals are obtained from appropriate selection of IMFs, and correlation coefficients between the filtered signal and each IMF are used as the basis for useful IMFs selection. Subsequently, PE values of those selected IMFs are utilized as input features to a support vector machine (SVM) classifier for characterizing the defect severity of a gearbox. Case study conducted on a gearbox system indicates the effectiveness of the proposed approach for identifying the gearbox faults.

Study on Mechanical Fault Diagnosis Based on IMF Complexity Feature and Support Vector Machine

2012 ◽  
Vol 246-247 ◽  
pp. 37-42
Author(s):  
Wei Dong Liu ◽  
Hu Sheng Wu
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Support Vector ◽  
Svm Classifier ◽  
Intrinsic Mode Functions ◽  
Mutual Correlation ◽  
Vibration Signals ◽  
Comparative Tests ◽  
Mode Decomposition ◽  
Diagnosis Method

According to the non-stationarity characteristics of the vibration signals from reciprocating machinery,a fault diagnosis method based on empirical mode decomposition,Lempel-Ziv complexity and support vector machine(SVM) is proposed.Firstly,the vibration signals were decomposed into a finite number of intrinsic mode functions(IMF), then choosed some IMF components with the criteria of mutual correlation coefficient between IMF components and denoised signal.Thirdly the complexity feature of each IMF component was calculated as faulty eigenvector and served as input of SVM classifier so that the faults of machine are classified.Practical experimental data is used to verify this method,and the diagnosis results and comparative tests fully validate its effectiveness and generalization abilities.

AN IMPROVED ONLINE PARADIGM FOR SCREENING OF DIABETIC PATIENTS USING RR-INTERVAL SIGNALS

2016 ◽  
Vol 16 (01) ◽  
pp. 1640003 ◽  
Author(s):  
RAM BILAS PACHORI ◽  
MOHIT KUMAR ◽  
PAKALA AVINASH ◽  
KORA SHASHANK ◽  
U. RAJENDRA ACHARYA
Keyword(s):  
Kernel Function ◽  
Morlet Wavelet ◽  
Least Square ◽  
Support Vector ◽  
Svm Classifier ◽  
Diabetic Patients ◽  
Intrinsic Mode Functions ◽  
Rr Interval ◽  
Mode Decomposition

Diabetes Mellitus (DM) which is a chronic disease and difficult to cure. If diabetes is not treated in a timely manner, it may cause serious complications. For timely treatment, an early detection of the disease is of great interest. Diabetes can be detected by analyzing the RR-interval signals. This work presents a methodology for classification of diabetic and normal RR-interval signals. Firstly, empirical mode decomposition (EMD) method is applied to decompose the RR-interval signals in to intrinsic mode functions (IMFs). Then five parameters namely, area of analytic signal representation (AASR), mean frequency computed using Fourier-Bessel series expansion (MFFB), area of ellipse evaluated from second-order difference plot (ASODP), bandwidth due to frequency modulation (BFM) and bandwidth due to amplitude modulation (BAM) are extracted from IMFs obtained from RR-interval signals. Statistically significant features are fed to least square-support vector machine (LS-SVM) classifier. The three kernels namely, Radial Basis Function (RBF), Morlet wavelet, and Mexican hat wavelet kernels have been studied to obtain the suitable kernel function for the classification of diabetic and normal RR-interval signals. In this work, we have obtained the highest classification accuracy of 95.63%, using Morlet wavelet kernel function with 10-fold cross-validation. The classification system proposed in this work can help the clinicians to diagnose diabetes using electrocardiogram (ECG) signals.

scholarly journals Performance Evaluation of Empirical Mode Decomposition Algorithms for Mental Task Classification

2016 ◽  
Author(s):  
Akshansh Gupta ◽  
Dhirendra Kumar ◽  
Anirban Chakraborti ◽  
Kiran Sharma
Keyword(s):  
Empirical Mode Decomposition ◽  
Ensemble Empirical Mode Decomposition ◽  
Compact Representation ◽  
Support Vector ◽  
Second Phase ◽  
Eeg Signal ◽  
Mental Task ◽  
Mode Decomposition ◽  
Task Classification ◽  
Mental Tasks

AbstractBrain Computer Interface (BCI), a direct pathway between the human brain and computer, is one of the most pragmatic applications of EEG signal. The electroencephalograph (EEG) signal is one of the monitoring techniques to observe brain functionality. Mental Task Classification (MTC) based on EEG signals is a demanding BCI. Success of BCI system depends on the efficient analysis of these signals. Empirical Mode Decomposition (EMD) is a filter based heuristic technique which is utilized to analyze EEG signal in recent past. There are several variants of EMD algorithms which have their own merits and demerits. In this paper, we have explored three variants of EMD algorithms named Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) on EEG data for MTC-based BCI. Features are extracted from EEG signal in two phases; in the first phase, the signal is decomposed into different oscillatory functions with the help of different EMD algorithms and eight different parameters (features) are calculated for each function for compact representation in the second phase. These features are fed into Support Vector Machine (SVM) classifier to classify the different mental tasks. We have formulated two different types of MTC, the first one is binary and second one is multi-MTC. The proposed work outperforms the existing work for both binary and multi mental tasks classification.

A NOVEL APPLICATION OF HIGHER ORDER STATISTICS OF R-R INTERVAL SIGNAL IN EMD DOMAIN FOR PREDICTING TERMINATION OF ATRIAL FIBRILLATION

2015 ◽  
Vol 23 (01) ◽  
pp. 115-130
Author(s):  
MARYAM MOHEBBI
Keyword(s):  
Atrial Fibrillation ◽  
Higher Order ◽  
Therapeutic Interventions ◽  
Support Vector ◽  
Svm Classifier ◽  
Intrinsic Mode Functions ◽  
Mode Decomposition ◽  
Mean And Variance ◽  
Sensitivity Specificity ◽  
Method R

Predicting termination of atrial fibrillation (AF), based on noninvasive techniques, can be invaluable in order to avoid useless therapeutic interventions and to minimize the risks for the patients. Currently, no reliable method exists to predict the termination of AF. We propose an algorithm for predicting termination of AF using higher order statistical moments of R-R interval signal calculated in both time and empirical mode decomposition (EMD) domains. In the proposed method, R-R interval signal is decomposed into a set of intrinsic mode functions (IMF) and higher order moments including skewness, and kurtosis, as well as mean and variance, are calculated from the first four IMFs. The appropriateness of these features in predicting the termination of AF is studied using atrial fibrillation termination database (AFTDB) which consists of three types of AF episodes: N-type (non-terminated AF episode), S-type (terminated 1'min after the end of the record), and T-type (terminated immediately after the end of the record). By using a support vector machine (SVM) classifier for classification of AF episodes, we obtained sensitivity, specificity, and positive predictivity 92.47%, 95.29%, and 92.80%, respectively. The important advantage of the proposed method compared to the other existing approaches is that our algorithm can simultaneously discriminate the three types of AF episodes with high accuracy. The results demonstrate that the EMD domain is a particularly well-suited domain for analyzing nonstationary and nonlinear R-R interval signal in AF termination prediction application.

Classification of Epileptic Seizure in EEG Signal Using Support Vector Machine and EMD

2020 ◽  
pp. 80-95
Author(s):  
Virender Kumar Mehla ◽  
Ashish Kumar ◽  
Amit Singhal ◽  
Pushpendra Singh ◽  
Manjeet Kumar ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Epileptic Activity ◽  
Support Vector ◽  
Eeg Signal ◽  
Intrinsic Mode Functions ◽  
Mode Decomposition ◽  
Last Stage ◽  
Electrocardiogram Ecg ◽  
Electroencephalogram Eeg

With the rapid innovation in the field of healthcare, various biomedical signals, namely, electrocardiogram (ECG), electroencephalogram (EEG), electromyogram (EMG), play a crucial role for accurate measurement of various diseases such as cardiovascular diseases, brain disorders, etc. In the present work, an efficient method based on empirical mode decomposition (EMD) has been proposed to detect the epileptic activity. The present study is composed of three parts. In the first part, EMD is used to decompose the EEG signal into a set of amplitude modulated and frequency modulated components, referred to as intrinsic mode functions (IMFs). In the second part, features such as standard deviation, kurtosis, and Hjorth parameters have been extracted from various IMFs. In the last stage, the features are employed as inputs to support vector machine classifier for classification between non-seizure and seizure EEG signals. The simulation results show that the proposed scheme has attained better classification accuracy when compared to existing state-of-the-art methods.

Binary Spectrum Feature for Improved Classifier Performance

2020 ◽  
Author(s):  
Nalika Ulapane ◽  
Karthick Thiyagarajan ◽  
sarath kodagoda
Keyword(s):  
Machine Learning ◽  
Classification Performance ◽  
Feature Reduction ◽  
Sensor Data ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Svm Classifier ◽  
Monitoring Task ◽  
Classifier Performance ◽  
Spectrum Feature

<div>Classification has become a vital task in modern machine learning and Artificial Intelligence applications, including smart sensing. Numerous machine learning techniques are available to perform classification. Similarly, numerous practices, such as feature selection (i.e., selection of a subset of descriptor variables that optimally describe the output), are available to improve classifier performance. In this paper, we consider the case of a given supervised learning classification task that has to be performed making use of continuous-valued features. It is assumed that an optimal subset of features has already been selected. Therefore, no further feature reduction, or feature addition, is to be carried out. Then, we attempt to improve the classification performance by passing the given feature set through a transformation that produces a new feature set which we have named the “Binary Spectrum”. Via a case study example done on some Pulsed Eddy Current sensor data captured from an infrastructure monitoring task, we demonstrate how the classification accuracy of a Support Vector Machine (SVM) classifier increases through the use of this Binary Spectrum feature, indicating the feature transformation’s potential for broader usage.</div><div><br></div>

Feature extraction method of pipeline signal based on parameter optimized vocational mode decomposition and exponential entropy

2021 ◽  
pp. 014233122110294
Author(s):  
Yina Zhou ◽  
Yong Zhang ◽  
Jingyi Lu ◽  
Fan Yang ◽  
Hongli Dong ◽  
...  
Keyword(s):  
Correlation Coefficient ◽  
Working Conditions ◽  
Acoustic Signals ◽  
Normal Operation ◽  
Local Characteristic ◽  
Support Vector ◽  
K Value ◽  
Feature Vectors ◽  
Mode Decomposition ◽  
Exponential Entropy

Pipeline leakage is the main reason that affects normal operation of the pipeline. In this paper, a feature recognition method for pipeline acoustic signals based on vocational mode decomposition (VMD) and exponential entropy (EE) is investigated, which could extract the characteristics of pipeline signals and further accurately identify the pipeline acoustic signals under different working conditions. First, the VMD is used to decompose the collected acoustic signals into a number of mode components, during which process the optimal mode number (i.e., K-value) is determined by combining local characteristic scale decomposition (LCD) and correlation analysis methods. Then, the characteristic content of each mode component is analyzed with the help of the determined correlation coefficient (CC) threshold. If the correlation coefficient of a mode component is greater than the threshold, then the mode component is selected as the feature component. Subsequently, the EE values of the selected feature components are calculated to form the feature vectors corresponding to different kinds of pipeline signals. Finally, the feature vectors are input into support vector machine (SVM) to classify and recognize the different pipeline states. The experimental results demonstrate that the proposed method can identify the pipeline signals under different working conditions, and the recognition accuracy is up to [Formula: see text]. By analyzing and comparing with methods of EE-SVM, original data-SVM, VMD-singular spectrum entropy (SSE) and VMD-information entropy (IE), it is further verified that the proposed method is feasible and superior to the methods.

scholarly journals Space Precession Target Classification Based on Radar High-Resolution Range Profiles

2019 ◽  
Vol 2019 ◽  
pp. 1-9
Author(s):  
Yizhe Wang ◽  
Cunqian Feng ◽  
Yongshun Zhang ◽  
Sisan He
Keyword(s):  
Parameter Extraction ◽  
Classification Performance ◽  
Support Vector ◽  
Electromagnetic Data ◽  
Feature Extractor ◽  
Different Types ◽  
Radar Echo ◽  
High Level ◽  
Cone Target

Precession is a common micromotion form of space targets, introducing additional micro-Doppler (m-D) modulation into the radar echo. Effective classification of space targets is of great significance for further micromotion parameter extraction and identification. Feature extraction is a key step during the classification process, largely influencing the final classification performance. This paper presents two methods for classifying different types of space precession targets from the HRRPs. We first establish the precession model of space targets and analyze the scattering characteristics and then compute electromagnetic data of the cone target, cone-cylinder target, and cone-cylinder-flare target. Experimental results demonstrate that the support vector machine (SVM) using histograms of oriented gradient (HOG) features achieves a good result, whereas the deep convolutional neural network (DCNN) obtains a higher classification accuracy. DCNN combines the feature extractor and the classifier itself to automatically mine the high-level signatures of HRRPs through a training process. Besides, the efficiency of the two classification processes are compared using the same dataset.

scholarly journals Classification of sleep apnea using EMD-based features and PSO-trained neural networks

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Sajjad Afrakhteh ◽  
Ahmad Ayatollahi ◽  
Fatemeh Soltani
Keyword(s):  
Neural Networks ◽  
Sleep Apnea ◽  
Back Propagation ◽  
Pso Algorithm ◽  
Bp Algorithm ◽  
Support Vector ◽  
Intrinsic Mode Functions ◽  
Linear Discriminant ◽  
Mode Decomposition ◽  
Obstructive Sleep

Abstract In this study, we propose a method for detecting obstructive sleep apnea (OSA) based on the features extracted from empirical mode decomposition (EMD) and the neural networks trained by particle swarm optimization (PSO) in the classification phase. After extracting the features from the intrinsic mode functions (IMF) of each heart rate variability (HRV) signal of each segment, these features were applied to the input of popular classifiers such as multi-layer perceptron neural networks (MLPNN), Naïve Bayes, linear discriminant analysis (LDA), k-nearest neighborhood (KNN), and support vector machines (SVM) were applied. The results show that the MLPNN learned with back propagation (BP) algorithm has a diagnostic accuracy of less than 90%, and this may be due to being derivative based property of the BP algorithm, which causes trapping in the local minima. For Improving MLPNN’s performance, we used the PSO algorithm instead of the BP method in training part. Therefore, the MLPNN’s accuracy improved from 89.36 to 97.66% after the application of the PSO algorithm. The proposed method has also reached to 97.78 and 97.96% in sensitivity and specificity, respectively. So, it can be concluded that the proposed method achieves better or comparable results when compared with the previous works in this field.

Sign in / Sign up

Export Citation Format

Share Document