A Gaussian Mixture Models Approach to Human Heart Signal Verification Using Different Feature Extraction Algorithms

Wahid, Rasha; Ghali, Neveen I.; Own, Hala S.; Kim, Tai-hoon; Hassanien, Aboul Ella

doi:10.1007/978-3-642-35521-9_3

Cited by 4 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their proposed system worked on 12 PCG signals reaching an error acceptance rate of 1% -8%, verification rate of 95%, and error rejection rate below 3%. Rasha Wahid et al, [35] proposed a verification system based on two main feature extraction methods, the first one reached an accuracy of 100%, and the second one reached 85% final accuracy. The classification was done using GMM for both feature extraction techniques.…”

Section: History Of Pcg Biometricmentioning

confidence: 99%

“…So, a piece-wise function is used to replace the log function. In this case, the signal attenuation in the low-frequency sections will be more appropriate [35].…”

Section:  Heart Sounds Linear Band Frequency Coefficients (Hs-lbfc)mentioning

confidence: 99%

“…The windowing step can be performed using different functions such as hamming, hanning, and rectangular. Some approaches[20,24,25,26,35,43] depend on framing, and implemented short-time discrete Fourier transform (STDFT) with fl of 256 ms or 512samples at a sampling rate of 2 kHz). It is also deduced that the non-over-lapping…”

mentioning

confidence: 99%

See 2 more Smart Citations

PCG signals for biometric authentication systems: An in-depth review

El‐Dahshan

Bassiouni

Sharvia

et al. 2021

Computer Science Review

View full text Add to dashboard Cite

Section: History Of Pcg Biometricmentioning

confidence: 99%

“…So, a piece-wise function is used to replace the log function. In this case, the signal attenuation in the low-frequency sections will be more appropriate [35].…”

Section:  Heart Sounds Linear Band Frequency Coefficients (Hs-lbfc)mentioning

confidence: 99%

See 1 more Smart Citation

PCG signals for biometric authentication systems: An in-depth review

El‐Dahshan

Bassiouni

Sharvia

et al. 2021

Computer Science Review

View full text Add to dashboard Cite

“…GMM has been widely used in voice recognition systems [Reynolds and Rose 1995]. This is why most of its uses related to biometric identification have focused on sounds emitted by the body, specifically the heart [Wahid et al 2012;Zhao and Shen 2011;Fatemian et al 2010]. Experiments achieved accuracy between 0.86 and 1.0 with medium-sized populations of subjects (between 10 and 80 subjects).…”

Section: Gaussian Mixture Model (Gmm)mentioning

confidence: 99%

A Survey of Wearable Biometric Recognition Systems

et al. 2016

View full text Add to dashboard Cite

The growing popularity of wearable devices is leading to new ways to interact with the environment, with other smart devices, and with other people. Wearables equipped with an array of sensors are able to capture the owner's physiological and behavioural traits, and thus are well suited for biometric authentication to control other devices or access digital services. However, wearable biometrics have substantial differences from traditional biometrics for computer systems, such as fingerprints, eye features, or voice. In this paper we discuss these differences and analyse how researchers are approaching the wearable biometrics field. We review and provide a categorization of wearable sensors useful for capturing biometric signals. We analyse the computational cost of the different signal processing techniques, an important practical factor in constrained devices such as wearables. Finally, we review and classify the most recent proposals in the field of wearable biometrics in terms of the structure of the biometric system proposed, their experimental setup, and their results. We also present a critique of experimental issues such as evaluation and feasibility aspects, and offer some final thoughts on research directions that need attention in future work.

show abstract

“…In the proposed framework, i-vector is used as a feature representation technique. The underlying motivation for using i-vector in this context is that human heart sounds can be considered as the physiological traits of a person [12] and only irregular events such as accidents, illnesses, genetic defects, or aging can alter or destroy these traits [12].…”

Section: Introductionmentioning

confidence: 99%

Statistical feature embedding for heart sound classification

Adiban

BabaAli

Shehnepoor

2019

Journal of Electrical Engineering

View full text Add to dashboard Cite

Cardiovascular Disease (CVD) is considered as one of the principal causes of death in the world. Over recent years, this field of study has attracted researchers' attention to investigate heart sounds' patterns for disease diagnostics. In this study, an approach is proposed for normal/abnormal heart sound classification on the Physionet challenge 2016 dataset. For the first time, a fixed length feature vector; called i-vector; is extracted from each heart sound using Mel Frequency Cepstral Coefficient (MFCC) features. Afterwards, Principal Component Analysis (PCA) transform and Variational Autoencoder (VAE) are applied on the ivector to achieve dimension reduction. Eventually, the reduced size vector is fed to Gaussian Mixture Models (GMMs) and Support Vector Machine (SVM) for classification purpose. Experimental results demonstrate the proposed method could achieve a performance improvement of 16% based on Modified Accuracy (MAcc) compared with the baseline system on the Physionet2016 dataset.

show abstract

A Gaussian Mixture Models Approach to Human Heart Signal Verification Using Different Feature Extraction Algorithms

Cited by 4 publications

References 5 publications

PCG signals for biometric authentication systems: An in-depth review

PCG signals for biometric authentication systems: An in-depth review

A Survey of Wearable Biometric Recognition Systems

Statistical feature embedding for heart sound classification

Contact Info

Product

Resources

About