Classification of heart sound signal using curve fitting and fractal dimension

Hamidi, Maryam; Ghassemian, Hassan; Imani, Maryam

doi:10.1016/j.bspc.2017.08.002

Cited by 104 publications

(41 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, it can also be concluded that the use of fractal dimensions plus other techniques such as artificial neural networks, frequency analysis, principals components analysis, among others, offer greater applications of identification and classification on ECG and EEG signals allowing the early detection of Alzheimer's, identifying cardiovascular diseases, predicting sudden deaths due to heart problems, classifying heart signals [3], [7], [11], [12], etc.…”

Section: Discussionmentioning

confidence: 99%

“…In the same way, the work of [11] investiged three fractal dimension methods, among them, Higuchi and Katz, plus artificial neural networks, as a methodology to predict sudden cardiac death. And, in [12], the use of two methods for the extraction of characteristics in ECG signals is proposed, where the second method is a fusion of fractal characteristics by stacking.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Fractal Algorithms to Identify Cardiovascular Diseases in ECG Signals

Dávalos¹,

Navarrete²

2019

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

The aim of this article was the identification of cardiovascular diseases, after applying Katz and Higuchi fractal algorithms on 4 databases of ECG signals downloaded from the Physionet website: heart failure (HF), hypertension (H), ischemic heart disease (IHD) and normal sinus rhythm (NSR). For this purpose, initially the ECG signals passed through a filtering stage using a Butterworth high pass filter of order 6 and 0.5Hz of cutoff frequency, in order to cancel variations of the baseline. The fractal algorithms were applied independently for each database. For such application, all signals were standardized with a total of 100,000 data, and for the calculation of each fractal dimension (FD) a frame equal to 10,000 with an overlap of 1,000 was used in a first stage; in a second stage, a frame equal to 1,000 with an overlap of 100 was used. Thus, the results showed that the Higuchi algorithm, in general, has a better performance compared with the Katz algorithm. These results refer to the observation of the variance of the FD averages, which are shown in Table 4. For example, in the cardiovascular disease Arterial Hypertension, the Higuchi algorithm presented 0.0093 of variance compared with the algorithm of Katz that only reached 0.0352. Complementarily, we used the Principal Component Analysis (PCA) to show graphically the differences between algorithms, so the components related to the Higuchi algorithm were presented in a less dispersed and grouped form, making possible their differentiation, mainly when the second analysis stage was carried out.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Application of Fractal Algorithms to Identify Cardiovascular Diseases in ECG Signals

Dávalos¹,

Navarrete²

2019

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

show abstract

“…Higuchi's algorithm can get the more accurate result than the other two algorithms. 6,13,14,19,24 In this paper, our proposed protein comparison algorithm will adopt Higuchi's algorithm as the calculation of fractal dimension.…”

Section: Higuchi's Algorithmmentioning

confidence: 99%

A Fractal Dimension and Empirical Mode Decomposition-Based Method for Protein Sequence Analysis

Yang

Zhong

et al. 2019

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

In bioinformatics, the biological functions of proteins and their interactions can often be analyzed by the similarity of their sequences. In this paper, the authors combine the fractal dimension, empirical mode decomposition (EMD), and sliding window for protein sequence comparison. First, the protein sequence is characterized and digitized into a signal, and then the signal characteristics are obtained by using EMD and fractal dimension. Each protein sequence can be decomposed into Intrinsic Mode Functions (IMFs). The¯xed window's fractal dimension is applied to each IMF and the original signal to extract the protein sequence characteristics. Experiments have shown that the feature extracted by this hybrid method is superior to the EMD method alone.

show abstract

“…Classification of a heart using unsegmented PCG signals was performed in limited papers [22][23][24][25]. Hamidi et al [23] extracted the features from unsegmented PCG based on curve fitting and fractal dimension, which were then further classified using the K-nearest neighbors (KNN) classifier. Philip et al [24] showed that unsegmented-based PCG classification was 11 times faster compared with segmented-based PCG classification.…”

Section: Introductionmentioning

confidence: 99%

Short unsegmented PCG classification based on ensemble classifier

Singh¹,

Majumder²

2020

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Diseases associated with the heart are one of the main reasons of death worldwide. Hence, early examination of the heart is important. For analysis of cardiac disorders, a study of heart sounds is a crucial and beneficial approach.Still, automated classification of heart sounds is a challenging task that mainly depends on segmentation of heart sounds and derivation of features using segmented samples. In the literature available for PCG classification provided by PhysioNet/CinC Challenge 2016, most of the research has focused on enhancing the accuracy of the classification model based on complicated segmentation processes and has failed to improve the sensitivity. In this paper, we present an automated heart sound classification by eliminating the segmentation steps using multidomain features, which results in enhanced sensitivity. The study is based on homomorphic envelogram, mel frequency cepstral coefficient (MFCC), power spectral density (PSD), and multidomain feature extraction. The extracted features are trained using the 5-fold cross-validation method based on an ensemble boosting algorithm over 100 independent iterations. Our proposed design is evaluated using public datasets published in PhysioNet/Computers in Cardiology Challenge 2016. Accuracy of 92.47% with improved sensitivity of 94.08% and specificity of 91.95% is achieved using our model. The output performance proves that our proposed model offers superior performance results.

show abstract

Classification of heart sound signal using curve fitting and fractal dimension

Cited by 104 publications

References 11 publications

Application of Fractal Algorithms to Identify Cardiovascular Diseases in ECG Signals

Application of Fractal Algorithms to Identify Cardiovascular Diseases in ECG Signals

A Fractal Dimension and Empirical Mode Decomposition-Based Method for Protein Sequence Analysis

Short unsegmented PCG classification based on ensemble classifier

Contact Info

Product

Resources

About