English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Time-Frequency Distributions (TFDs) support the heart sound characterisationand classification in early cardiac screening. However, despite the frequentuse of TFDs in signal analysis, no study comprehensively compared theirperformances on deep learning for automatic diagnosis. Furthermore, thecombination of signal processing methods as inputs for Convolutional NeuralNetworks (CNNs) has been proved as a practical approach to increasing signalclassification performance. Therefore, this study aimed to investigate theoptimal use of TFD/ combined TFDs as input for CNNs. The presented resultsrevealed that: 1) The transformation of the heart sound signal into the TFdomain achieves higher classification performance than using of raw signals.Among the TFDs, the difference in the performance was slight for all the CNNmodels (within $1.3\%$ in average accuracy). However, Continuous wavelettransform (CWT) and Chirplet transform (CT) outperformed the rest. 2) Theappropriate increase of the CNN capacity and architecture optimisation canimprove the performance, while the network architecture should not be overlycomplicated. Based on the ResNet or SEResNet family results, the increase inthe number of parameters and the depth of the structure do not improve theperformance apparently. 3) Combining TFDs as CNN inputs did not significantlyimprove the classification results. The findings of this study provided theknowledge for selecting TFDs as CNN input and designing CNN architecture forheart sound classification.

Time-Frequency Distributions of Heart Sound Signals: A Comparative Study using Convolutional Neural Networks