Fractal dimension to classify the heart sound recordings with KNN and fuzzy c-mean clustering methods

Juniati, Dwi; Khotimah, Chusnul; Wardani, D E K; Budayasa, İ Ketut

doi:10.1088/1742-6596/953/1/012202

Cited by 16 publications

(17 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…1. This paper utilizes level 5 as the fractal dimension input [20]. Fractal sets represent many geometrically complex natural phenomena, where the fractal dimension defines the fracture character.…”

Section: Proposed Modelmentioning

confidence: 99%

See 1 more Smart Citation

Heart Sound Classification Based on Fractal Dimension and MFCC Features Using Hidden Markov Model

Bahreini

Barati

Kamaly

2022

Preprint

View full text Add to dashboard Cite

Early diagnosis is crucial in the treatment of heart diseases. Researchers have applied a variety of techniques for cardiovascular disease diagnosis, including the detection of heart sounds. It is an efficient and affordable diagnosis technique. Body organs, including the heart, generate several sounds. These sounds are different in different individuals. A number of methodologies have been recently proposed to detect and diagnose normal/abnormal sounds generated by the heart. The present study proposes a technique on the basis of the Mel-frequency cepstral coefficients, fractal dimension, and hidden Markov model. It uses the fractal dimension to identify sounds S1 and S2. Then, the Mel-frequency cepstral coefficients and the first- and second-order difference Mel-frequency cepstral coefficients are employed to extract the features of the signals. The adaptive Hemming window length is a major advantage of the methodology. The S1-S2 interval determines the adaptive length. Heart sounds are divided into normal and abnormal through the improved hidden Markov model and Baum-Welch and Viterbi algorithms. The proposed framework is evaluated using a number of datasets under various scenarios.

show abstract

Section: Proposed Modelmentioning

confidence: 99%

“…This study implemented the fractal dimension on wavelet signals. The iteration begins with a threshold operation given by [20]:…”

Section: Proposed Modelmentioning

confidence: 99%

Heart Sound Classification Based on Fractal Dimension and MFCC Features Using Hidden Markov Model

Bahreini

Barati

Kamaly

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Benoit Mandelbort merupakan matematikawan Prancis Amerika yang memperkenalkan istilah Fraktal pertama kali pada tahun 1975 di buku edisi pertamanya yang berjudul "Les Objets Fractals". Fraktal berasal Bahasa latin " fractus" yang berarti patahan (Juniati et al, 2018). Suatu data deret waktu dapat dicari nilai dimensi farktalnya, dan salah satu algoritma yang dapat digunakan yaitu Algoritma Higuchi (Juniati et al, 2018).…”

Section: Klasifikasi Jenis Delphinidae (Lumba-lumba)unclassified

“…Fraktal berasal Bahasa latin " fractus" yang berarti patahan (Juniati et al, 2018). Suatu data deret waktu dapat dicari nilai dimensi farktalnya, dan salah satu algoritma yang dapat digunakan yaitu Algoritma Higuchi (Juniati et al, 2018). Algoritma ini lebih sederhana dan lebih cepat daripada pengukuran klasik lainnya.…”

Section: Klasifikasi Jenis Delphinidae (Lumba-lumba)unclassified

Case Study of Sound Production and Dolphin Behavior in Waters

Heryani

2022

Jurnal Perikanan dan Kelautan

View full text Add to dashboard Cite

Dolphins belong to the Cetacean Order and are members of the Odontocetes with physical characteristics and the sound signals they emit. This fish lives in the sea and is one of the rare animals. The preparation of this scientific article was carried out in May 2021 using a descriptive analysis based on a literature review using secondary data as a source of information. The sound frequency range with the highest intensity value is 32 dB in the frequency range of 14 - 16 kHz.

show abstract

“…Many research groups have published a wide variety of machine learning models to this end. Survey of the existing literature reveals that many different feature extraction methods (Mel-frequency cepstral coefficients 4,5,6 , discrete wavelet transform 7,8,9 , tensor decomposition 10 , sparse coding 11 ) and classification methods (k-nearest neighbors 7 , support vector machines 4,10,11,12 , hidden Markov models 13,14 , recurrent neural networks 15,16 , convolution neural networks 6,17,18 ), and their different permutations together have been extensively explored.…”

Section: Introductionmentioning

confidence: 99%

On the Analysis of Data Augmentation Methods for Spectral Imaged Based Heart Sound Classification Using Convolutional Neural Networks

Zhou

Chen

Chien

2021

Preprint

View full text Add to dashboard Cite

Background: The application of machine learning to cardiac auscultation has the potential to improve the accuracy and efficiency of both routine and point-of-care screenings. The use of Convolutional Neural Networks (CNN) on heart sound spectrograms in particular has defined state-of-the-art performance. However, the relative paucity of patient data remains a significant barrier to creating models that can adapt to the wide range of between-subject variability. To that end, we examined a CNN model’s performance on automated heart sound classification, before and after various forms of data augmentation, and aimed to identify the most optimal augmentation methods for cardiac spectrogram analysis.Results: We built a standard CNN model to classify cardiac sound recordings as either normal or abnormal. The baseline control model achieved an ROC AUC of 0.945±0.016. Among the data augmentation techniques explored, horizontal flipping of the spectrogram image improved the model performance the most, with an ROC AUC of 0.957±0.009. Principal component analysis color augmentation (PCA) and perturbations of saturation-value (SV) of the hue-saturation-value (HSV) color scale achieved an ROC AUC of 0.949±0.014 and 0.946±0.019, respectively. Time and frequency masking resulted in an ROC AUC of 0.948±0.012. Pitch shifting, time stretching and compressing, noise injection, vertical flipping, and applying random color filters all negatively impacted model performance.Conclusion: Data augmentation can improve classification accuracy by expanding and diversifying the dataset, which protects against overfitting to random variance. However, data augmentation is necessarily domain specific. For example, methods like noise injection have found success in other areas of automated sound classification, but in the context of cardiac sound analysis, noise injection can mimic the presence of murmurs and worsen model performance. Thus, care should be taken to ensure clinically appropriate forms of data augmentation to avoid negatively impacting model performance.

show abstract

Fractal dimension to classify the heart sound recordings with KNN and fuzzy c-mean clustering methods

Cited by 16 publications

References 3 publications

Heart Sound Classification Based on Fractal Dimension and MFCC Features Using Hidden Markov Model

Heart Sound Classification Based on Fractal Dimension and MFCC Features Using Hidden Markov Model

Case Study of Sound Production and Dolphin Behavior in Waters

On the Analysis of Data Augmentation Methods for Spectral Imaged Based Heart Sound Classification Using Convolutional Neural Networks

Contact Info

Product

Resources

About