• Annual Conference of KIPS
• /
• 2024.10a
• /
• pp.461-462
• /
• 2024

In pediatric healthcare, early detection of cardiovascular diseases in newborns is crucial. Analyzing heart sounds using stethoscopes can be subjective and reliant on physician expertise, potentially leading to delayed diagnosis. There is a need for a simple method that can help even inexperienced doctors detect heart abnormalities without an electrocardiogram or ultrasound. Automated heart sound diagnosis systems can aid clinicians by providing accurate and early detection of abnormal heartbeats. To address this, we developed an intelligent deep-learning model incorporating CNN and LSTM to detect heart abnormalities based on artificial intelligence using heart sound data from stethoscope recordings. Our research achieved a high accuracy rate of 97.8%. Using audio data to introduce advanced models for cardiac abnormalities in children is essential for enhancing early detection and intervention in pediatric cardiovascular healthcare.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.252-255
• /
• 2016

The objective of this paper is to find an easier and non-invasive a way of diagnosing heart diseases based on the heart sound, rigidly heart murmurs, recordings from subjects. Although most of the heart sounds can be easily heard, analysis of the findings by auscultation strongly depends on skills and experience of the physician. Therefore, the heart murmur is require quantitative analysis for automatic diagnosis equipment. For a good sound analysis, the noisy component ware filtered. This can be done using Wiener filter. Once the signal is filtered, it can be segmented into its basic components by signal energy using FFT. After segment the heart sound signal, the relative positions of the different heart sound components will be identified and will be used for quantification purposes. We are using murmur energy ratio. The experimental results are fairly good in relation to automatic diagnosis.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.2051-2052
• /
• 2011

The structural defects of a heart often reflects the sounds that the heart produces. This paper describes heart sound analysis method using Wavelet transform and average Shannon energy. This can extract the features of heart sounds in various disease identify the heart sounds. Experimental results show that the presented method has potential application in detecting various heart diseases.

• Journal of Korea Multimedia Society
• /
• v.24 no.11
• /
• pp.1500-1507
• /
• 2021

Identification and analysis of the first and second heart sounds(S1, S2) is the easiest way for cardiovascular disease prevention and early diagnosis. However, accurate identification is difficult because the heart sound includes organ movement, blood vortex, user experience, and noise influenced by subjective judgment. Therefore, an algorithm to automatically identify the S1 and S2 heart sounds based on blood vessel transit time(VTT) is presented in this paper. According to the experimental results of comparing the algorithm developed for S1 and S2 heart sound analysis with the conventional Shannon energy algorithm in 10 volunteers, it has been proven that the proposed algorithm can automatically identify S1 and S2 heart sounds with higher accuracy than existing algorithms.

• Journal of Korea Multimedia Society
• /
• v.19 no.3
• /
• pp.557-566
• /
• 2016

Heart sounds generated by the beating heart and blood flow reflect the turbulence created when the heart valves snap shut. Cardiac diagnosis is typically started by an auscultation using a stethoscope, from which a medical doctor, depending on his hearing capabilities and training, listens and interprets the acoustic signal. This method of diagnostic is uncertain, mostly due to the fact that human ear loses the acoustic frequency sensitivity through the years. Even though an auscultation has some weaknesses like uncertainty, it is considered as a primary tool due to its simplicity. In this paper, heart murmur detection algorithm is proposed using time and frequency characteristics of heart sound. The propose heart murmur detection method adapted conventional primary heart sound detection method in time domain and modified spectral flatness method in frequency domain for detecting heart murmurs. From experimental results, it is confirmed that the proposed algorithm detect the heart murmurs efficiently.

• ETRI Journal
• /
• v.37 no.4
• /
• pp.824-832
• /
• 2015

Heart sounds are the main obstacle in lung sound analysis. To tackle this obstacle, we propose a diagnosis algorithm that uses singular spectrum analysis (SSA) and frequency features of heart and lung sounds. In particular, we introduce a frequency coefficient that shows the frequency difference between heart and lung sounds. The proposed algorithm is applied to a synthetic mixture of heart and lung sounds. The results show that heart sounds can be extracted successfully and localizations for the first and second heart sounds are remarkably performed. An error analysis of the localization results shows that the proposed algorithm has fewer errors compared to the SSA method, which is one of the most powerful methods in the localization of heart sounds. The presented algorithm is also applied in the cases of recorded respiratory sounds from the chest walls of five healthy subjects. The efficiency of the algorithm in extracting heart sounds from the recorded breathing sounds is verified with power spectral density evaluations and listening. Most studies have used only normal respiratory sounds, whereas we additionally use abnormal breathing sounds to validate the strength of our achievements.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.1
• /
• pp.32-43
• /
• 2009

In this paper, we improve the performance of cardiac disorder classification by continuous heart sound signals using automatic segmentation and extreme learning machine (ELM). The accuracy of the conventional cardiac disorder classification systems degrades because murmurs and click sounds contained in the abnormal heart sound signals cause incorrect or missing starting points of the first (S1) and the second heart pulses (S2) in the automatic segmentation stage, In order to reduce the performance degradation due to segmentation errors, we find the positions of the S1 and S2 pulses, modify them using the time difference of S1 or S2, and extract a single period of heart sound signals. We then obtain a feature vector consisting of the mel-scaled filter bank energy coefficients and the envelope of uniform-sized sub-segments from the single-period heart sound signals. To classify the heart disorders, we use ELM with a single hidden layer. In cardiac disorder classification experiments with 9 cardiac disorder categories, the proposed method shows the classification accuracy of 81.6% and achieves the highest classification accuracy among ELM, multi-layer perceptron (MLP), support vector machine (SVM), and hidden Markov model (HMM).

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.4
• /
• pp.167-174
• /
• 2002

This study describes a fetal heart rate(FHR) estimation algorithm using phonogram. Using a phonogram amplifier, various fetal heart sounds are collected in a university hospital. The FHR estimation algorithms consists of a lowpass filter, decimation, envelop detection, pitch detection, and post-processing. The post-processing is the FHR decision procedure using all informations of fetal heart rates. Using the algorithm and other parameters of fetal heart sound, a fetal monitoring software was developed. This can display the original signals, the FFT spectra, FHR and its trajectory. Even though the fetal phonogram amplifier detects the fetal heart sounds well, the sound quality is not so good as the ultrasonography. In case of very week fetal heart sound, autocorrelation of it showed clear periodicity. But two main peaks in one period is an obstacle in pitch detection and peaks are not so vivid. The proposed FHR estimation algorithm showed very accurate and stable results. Since the developed software displays multiple parameters in real time and has convenient functions, it will be useful for the phonogram-style fetal monitoring device.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.3
• /
• pp.144-150
• /
• 2006

Clinicians usually use stethoscopic auscultation for the diagnosis of heart diseases. However, the heart sound signal has varying characteristics due to the noise and/or the conditions of the patients. Also, it is not easy for junior clinicians to find the acoustical differences between different kinds or heart sound signals. which may result in errors in the diagnosis. Thus it will be quite useful for the clinicians to make use of an automatic classification system using signal processing techniques. In this paper, we propose to use hidden Markov models in stead of artificial neural networks which have been conventionally used for the automatic classification of heart sounds. In the experiments classifying heart sound signals. we could see that the proposed methods were quite successful in the classification accuracy.

• Journal of Korea Multimedia Society
• /
• v.25 no.9
• /
• pp.1251-1256
• /
• 2022

Auscultation of heart sounds using a stethoscope is the basic method to diagnose the cardiovascular disease and observation of abnormalities. However, the heart sound transmitted to the ear through the stethoscope is greatly affected by internal sounds such as organ movement or breathing. In addition, the user's experience significantly influences the accuracy of the auscultation result. Therefore, in this paper, we developed a wearable device that simultaneously measures heart sound and PPG signals for cardiac condition monitoring. The structure of the proposed device is designed to simultaneously measure heart sound and PPG signals when worn on a finger and placed on the chest. A prototype was implemented according to the design structure, and it was confirmed that the performance of measurements and collection for physiological signals was excellent through experiments.