scholarly journals Classification of Heart Sounds Associated With Murmur For Diagnosis of Cardiac Valve Disorders

2021 ◽  
Author(s):  
Ahmed Ali Dawud ◽  
Bheema Lingaiah ◽  
Towfik Jemal
Keyword(s):  
South Carolina ◽  
Signal To Noise Ratio ◽  
Heart Sounds ◽  
Experimental Result ◽  
Svm Classifier ◽  
Feature Selection Technique ◽  
Electronic Stethoscope ◽  
Correlation Based Feature Selection ◽  
Hybrid Classifiers ◽  
Future Work

Abstract Background: Now a day, cardiovascular diseases have been a major cause of death in the world. The heart sound is still the primary tool used for screening and diagnosing many pathological conditions of the human heart. The abnormality in the heart sounds starts appearing much earlier than the symptoms of the disease. In this study, the Phonocardiography signal has been studied and classified into three classes, namely normal signal, murmur signal and extra sound signal. A total of 15 features from different domains have been extracted and then reduced to 7 features. The features have been selected on the basis of correlation based feature selection technique. The selected features are used to classify the signal into the predefined classes using multi- class SVM classifier. The performance of the proposed denoising algorithm is evaluated using the signal to noise ratio, percentage root means square difference, and root mean square error. For this work a publically available database for researchers, Partnership Among South Carolina Academic Libraries (PASCAL) and MATLAB 2018a was used to develop the proposed algorithm.Results: Our experimental result shows that the 4th level of decomposition for the Db10 wavelets shows the highest SNR values when using the soft and hard thresholding. The overall accuracy, Sensitivity and Specificity of the developed algorithm is 97.96%, 97.92 % and of 98.0% respectively.Conclusion: even if the proposed algorithm is useful for murmur detection mainly valve-related diseases and the efficiency of the proposed study is increased, future work will intend to generalize the algorithm by using hybrid classifiers on a larger dataset. Since all experiments used the PASCAL datasets, additional experiments will be needed using new datasets to be implemented using the latest mobile phones which can work as an electronic stethoscope or phonocardiogram. In addition, the case of continuous murmur and types of murmur has been included for classification in further studies.

scholarly journals Detected Changes in Precipitation Extremes at Their Native Scales Derived from In Situ Measurements

2019 ◽  
Vol 32 (23) ◽  
pp. 8087-8109 ◽  
Author(s):  
Mark D. Risser ◽  
Christopher J. Paciorek ◽  
Travis A. O’Brien ◽  
Michael F. Wehner ◽  
William D. Collins
Keyword(s):  
Extreme Precipitation ◽  
Seasonal Changes ◽  
Signal To Noise Ratio ◽  
Statistical Technique ◽  
In Situ Measurements ◽  
Absolute Sense ◽  
Underlying Causes ◽  
Changes Over Time ◽  
Future Work

Abstract The gridding of daily accumulated precipitation—especially extremes—from ground-based station observations is problematic due to the fractal nature of precipitation, and therefore estimates of long period return values and their changes based on such gridded daily datasets are generally underestimated. In this paper, we characterize high-resolution changes in observed extreme precipitation from 1950 to 2017 for the contiguous United States (CONUS) based on in situ measurements only. Our analysis utilizes spatial statistical methods that allow us to derive gridded estimates that do not smooth extreme daily measurements and are consistent with statistics from the original station data while increasing the resulting signal-to-noise ratio. Furthermore, we use a robust statistical technique to identify significant pointwise changes in the climatology of extreme precipitation while carefully controlling the rate of false positives. We present and discuss seasonal changes in the statistics of extreme precipitation: the largest and most spatially coherent pointwise changes are in fall (SON), with approximately 33% of CONUS exhibiting significant changes (in an absolute sense). Other seasons display very few meaningful pointwise changes (in either a relative or absolute sense), illustrating the difficulty in detecting pointwise changes in extreme precipitation based on in situ measurements. While our main result involves seasonal changes, we also present and discuss annual changes in the statistics of extreme precipitation. In this paper we only seek to detect changes over time and leave attribution of the underlying causes of these changes for future work.

scholarly journals The development of non-coherent passive radar techniques for space situational awareness with the Murchison Widefield Array

2020 ◽  
Vol 37 ◽  
Author(s):  
Steve Prabu ◽  
Paul J. Hancock ◽  
Xiang Zhang ◽  
Steven J. Tingay
Keyword(s):  
Situational Awareness ◽  
Signal To Noise Ratio ◽  
Space Station ◽  
Passive Radar ◽  
Space Situational Awareness ◽  
Direct Path ◽  
Orbital Parameters ◽  
Ratio Spectrum ◽  
Murchison Widefield Array ◽  
Future Work

Abstract The number of active and non active satellites in Earth orbit has dramatically increased in recent decades, requiring the development of novel surveillance techniques to monitor and track them. In this paper, we build upon previous non-coherent passive radar space surveillance demonstrations undertaken using the Murchison Widefield Array (MWA). We develop the concept of the Dynamic Signal to Noise Ratio Spectrum (DSNRS) in order to isolate signals of interest (reflections of FM transmissions of objects in orbit) and efficiently differentiate them from direct path reception events. We detect and track Alouette-2, ALOS, UKube-1, the International Space Station, and Duchifat-1 in this manner. We also identified out-of-band transmissions from Duchifat-1 and UKube-1 using these techniques, demonstrating the MWA’s capability to look for spurious transmissions from satellites. We identify an offset from the locations predicted by the cataloged orbital parameters for some of the satellites, demonstrating the potential of using MWA for satellite catalog maintenance. These results demonstrate the capability of the MWA for Space Situational Awareness and we describe future work in this area.

Combining Correlation-Based Feature and Machine Learning for Sensory Evaluation of Saigon Beer

2020 ◽  
Vol 11 (2) ◽  
pp. 71-85
Author(s):  
Nhat-Vinh Lu ◽  
Trong-Nhan Vuong ◽  
Duy-Tai Dinh
Keyword(s):  
Machine Learning ◽  
Sensory Evaluation ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Learning Methods ◽  
Feature Selection Technique ◽  
Machine Learning Methods ◽  
Learning Techniques ◽  
Correlation Based Feature Selection ◽  
Positive Results

Sensory evaluation plays an important role in the food and consumer goods industry. In recent years, the application of machine learning techniques to support food sensory evaluation has become popular. Many different machine learning methods have been applied and produced positive results in this field. In this article, the authors propose a new method to support sensory evaluation on multiple criteria based on the use of a correlation-based feature selection technique, combined with machine learning methods such as linear regression, multilayer perceptron, support vector machine, and random forest. Experimental results are based on considering the correlation between physicochemical components and sensory factors on the Saigon beer dataset.

scholarly journals HUMAN IDENTIFICATION BASED ON HEART SOUND AUSCULTATION POINT

2017 ◽  
Vol 79 (7) ◽  
Author(s):  
I. Nur Fariza ◽  
Sh-Hussain Salleh ◽  
Fuad Noman ◽  
Hadri Hussain
Keyword(s):  
Heart Sound ◽  
Recognition Rate ◽  
Human Identification ◽  
Personal Identification ◽  
Heart Sounds ◽  
Electronic Stethoscope ◽  
The Past ◽  
Technology Advancement ◽  
Aortic Area ◽  
Mitral Area

The application of human identification and verification has widely been used for over the past few decades.  Drawbacks of such system however, are inevitable as forgery sophisticatedly developed alongside the technology advancement.  Thus, this study proposed a research on the possibility of using heart sound as biometric. The main aim is to find an optimal auscultation point of heart sounds from either aortic, pulmonic, tricuspid or mitral that will most suitable to be used as the sound pattern for personal identification.  In this study, the heart sound was recorded from 92 participants using a Welch Allyn Meditron electronic stethoscope whereas Meditron Analyzer software was used to capture the signal of heart sounds and ECG simultaneously for duration of 1 minute.  The system is developed by a combination Mel Frequency Cepstrum Coefficients (MFCC) and Hidden Markov Model (HMM).  The highest recognition rate is obtained at aortic area with 98.7% when HMM has 1 state and 32 mixtures, the lowest Equal Error Rate (EER) achieved was 0.9% which is also at aortic area.  In contrast, the best average performance of HMM for every location is obtained at mitral area with 99.1% accuracy and 17.7% accuracy of EER at tricuspid area.

scholarly journals A Low-Noise-Level Heart Sound System Based on Novel Thorax-Integration Head Design and Wavelet Denoising Algorithm

Micromachines ◽  
2019 ◽  
Vol 10 (12) ◽  
pp. 885
Author(s):  
Shuo Zhang ◽  
Ruiqing Zhang ◽  
Shijie Chang ◽  
Chengyu Liu ◽  
Xianzheng Sha
Keyword(s):  
Noise Level ◽  
Filter Bank ◽  
Heart Sound ◽  
Low Noise ◽  
Heart Sounds ◽  
Noisy Environments ◽  
Sound System ◽  
Electronic Stethoscope ◽  
Surrounding Environment ◽  
Great Performance

Along with the great performance in diagnosing cardiovascular diseases, current stethoscopes perform unsatisfactorily in controlling undesired noise caused by the surrounding environment and detector operation. In this case, a low-noise-level heart sound system was designed to inhibit noise by a novel thorax-integration head with a flexible electric film. A hardware filter bank and wavelet-based algorithm were employed to enhance the recorded heart sounds from the system. In the experiments, we used the new system and the 3M™ Littmann® Model 3200 Electronic Stethoscope separately to record heart sounds in different noisy environments. The results illustrated that the average estimated noise ratio represented 21.26% and the lowest represented only 12.47% compared to the 3M stethoscope, demonstrating the better performance in denoising ability of this system than state-of-the-art equipment. Furthermore, based on the heart sounds recorded with this system, some diagnosis results were achieved from an expert and compared to echocardiography reports. The diagnoses were correct except for two uncertain items, which greatly confirmed the fact that this system could reserve complete pathological information in the end.

scholarly journals A Comparative Study of Indian Food Image Classification Using K-Nearest-Neighbour and Support-Vector-Machines

2018 ◽  
Vol 7 (3.12) ◽  
pp. 521 ◽  
Author(s):  
Pathanjali C ◽  
Vimuktha E Salis ◽  
Jalaja G ◽  
Latha A
Keyword(s):  
Comparative Study ◽  
Detection System ◽  
Experimental Result ◽  
Support Vector ◽  
Svm Classifier ◽  
Nearest Neighbour ◽  
Classification Models ◽  
Food Detection ◽  
Knn Classifier ◽  
Indian Food

Food being the vital part of everyone’s lives, food detection and recognition becomes an interesting and challenging problem in computer vision and image processing. In this paper we mainly propose an automatic food detection system that detects and recognises varieties of Indian food. This paper uses a combined colour and shape features. The K-Nearest-Neighbour (KNN) and Support-Vector -Machine (SVM) classification models are used to classify the features. A comparative study on the performance of both the classification models is performed. The experimental result shows the higher efficiency of SVM classifier over KNN classifier. 

Hybrid adapted fast correlation FCBF-support vector machine recursive feature elimination for feature selection

2020 ◽  
Vol 14 (3) ◽  
pp. 269-279
Author(s):  
Hayet Djellali ◽  
Nacira Ghoualmi-Zine ◽  
Souad Guessoum
Keyword(s):  
Support Vector Machine ◽  
Feature Selection ◽  
Recursive Feature Elimination ◽  
Support Vector ◽  
Svm Classifier ◽  
Hybrid Architecture ◽  
Features Selection ◽  
K Nearest Neighbors ◽  
Correlation Based Feature Selection ◽  
Embedded Method

This paper investigates feature selection methods based on hybrid architecture using feature selection algorithm called Adapted Fast Correlation Based Feature selection and Support Vector Machine Recursive Feature Elimination (AFCBF-SVMRFE). The AFCBF-SVMRFE has three stages and composed of SVMRFE embedded method with Correlation based Features Selection. The first stage is the relevance analysis, the second one is a redundancy analysis, and the third stage is a performance evaluation and features restoration stage. Experiments show that the proposed method tested on different classifiers: Support Vector Machine SVM and K nearest neighbors KNN provide a best accuracy on various dataset. The SVM classifier outperforms KNN classifier on these data. The AFCBF-SVMRFE outperforms FCBF multivariate filter, SVMRFE, Particle swarm optimization PSO and Artificial bees colony ABC.

scholarly journals Classification of Microcalcification Clusters in Digital Mammograms Using a Stack Generalization Based Classifier

2019 ◽  
Vol 5 (9) ◽  
pp. 76 ◽  
Author(s):  
Nashid Alam ◽  
Erika R. E. Denton ◽  
Reyer Zwiggelaar
Keyword(s):  
Screening Mammography ◽  
Morphological Operations ◽  
Feature Selection Technique ◽  
Digital Database ◽  
Distribution Features ◽  
Analysis Society ◽  
Correlation Based Feature Selection ◽  
Mammography Image ◽  
Microcalcification Clusters

This paper presents a machine learning based approach for the discrimination of malignant and benign microcalcification (MC) clusters in digital mammograms. A series of morphological operations was carried out to facilitate the feature extraction from segmented microcalcification. A combination of morphological, texture, and distribution features from individual MC components and MC clusters were extracted and a correlation-based feature selection technique was used. The clinical relevance of the selected features is discussed. The proposed method was evaluated using three different databases: Optimam Mammography Image Database (OMI-DB), Digital Database for Screening Mammography (DDSM), and Mammographic Image Analysis Society (MIAS) database. The best classification accuracy ( 95 . 00 ± 0 . 57 %) was achieved for OPTIMAM using a stack generalization classifier with 10-fold cross validation obtaining an A z value equal to 0 . 97 ± 0 . 01 .

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.

Surface Spot Defects Inspection of Multi-Crystalline Silicon Wafers Based on HALCON

2014 ◽  
Vol 1081 ◽  
pp. 241-245 ◽  
Author(s):  
Xiao Song Wu ◽  
Rui Miao ◽  
Yu Dong Si ◽  
Cheok Man Lou ◽  
Duan Xia Xu ◽  
...  
Keyword(s):  
Surface Defects ◽  
Crystalline Silicon ◽  
Image Sensor ◽  
Experimental Result ◽  
Wafer Surface ◽  
Svm Classifier ◽  
Crystalline Silicon Solar Cells ◽  
Ccd Image Sensor ◽  
Surface Spot ◽  
Ccd Image

As a common kind of surface defects on multi-crystalline silicon solar cells (about 65% of total defects). Based on HALCON image processing library, an automatic silicon wafer surface spot defects detection and classification system has been developed: captured color images via CCD image sensor, located wafers and spots, extracted the spot features, computed and separated the qualified regions from the unqualified ones by SVM classifier. The experimental result showed a high accuracy of 95.7% and fast image analyzing and classifying process (less than 600ms).

Sign in / Sign up

Export Citation Format

Share Document