Electronics Department, University of Badji Mokhtar Annaba, Annaba, Algeria.
Faculty of Electronics and Computer Engineering, Universiti Teknikal Malaysia Melaka, Melaka, Malaysia.
Biomed Tech (Berl). 2022 Aug 8;67(5):367-390. doi: 10.1515/bmt-2022-0180. Print 2022 Oct 26.
In lung sound classification using deep learning, many studies have considered the use of short-time Fourier transform (STFT) as the most commonly used 2D representation of the input data. Consequently, STFT has been widely used as an analytical tool, but other versions of the representation have also been developed. This study aims to evaluate and compare the performance of the spectrogram, scalogram, melspectrogram and gammatonegram representations, and provide comparative information to users regarding the suitability of these time-frequency (TF) techniques in lung sound classification. Lung sound signals used in this study were obtained from the ICBHI 2017 respiratory sound database. These lung sound recordings were converted into images of spectrogram, scalogram, melspectrogram and gammatonegram TF representations respectively. The four types of images were fed separately into the VGG16, ResNet-50 and AlexNet deep-learning architectures. Network performances were analyzed and compared based on accuracy, precision, recall and F1-score. The results of the analysis on the performance of the four representations using these three commonly used CNN deep-learning networks indicate that the generated gammatonegram and scalogram TF images coupled with ResNet-50 achieved maximum classification accuracies.
在使用深度学习进行肺部声音分类的研究中，许多研究都考虑使用短时傅里叶变换（STFT）作为输入数据最常用的 2D 表示方法。因此，STFT 已被广泛用作分析工具，但也已经开发出了其他版本的表示方法。本研究旨在评估和比较频谱图、线谱图、梅尔频谱图和伽马频图谱表示方法的性能，并为用户提供关于这些时频（TF）技术在肺部声音分类中的适用性的比较信息。本研究中使用的肺部声音信号来自于 ICBHI 2017 呼吸声音数据库。这些肺部声音记录分别转换为频谱图、线谱图、梅尔频谱图和伽马频图谱 TF 表示的图像。将这四种类型的图像分别输入到 VGG16、ResNet-50 和 AlexNet 深度学习架构中。根据准确率、精度、召回率和 F1 分数对网络性能进行分析和比较。对这三种常用的 CNN 深度学习网络对四种表示方法性能的分析结果表明，生成的伽马频图谱和线谱图 TF 图像与 ResNet-50 相结合可以达到最高的分类准确率。
