论文标题
用于预测呼吸异常的深度学习框架的合奏
An Ensemble of Deep Learning Frameworks Applied For Predicting Respiratory Anomalies
论文作者
论文摘要
在本文中，我们评估了各种深度学习框架，用于从输入音频记录中检测呼吸异常。为此，我们首先将收集的从患者收集的音频呼吸周期转变为介绍时间和光谱特征的光谱图，称为前端特征提取。然后，我们将光谱图将其馈送到后端深度学习网络中，以将这些呼吸周期分类为某些类别。最后，融合了高性能深度学习框架的结果以获得最佳分数。我们对洲际际护度基准数据集的实验从基于启动和转移学习的后期融合中获得了最高的洲际志际弹药，基于基于Inception和转移学习的深度学习框架，这表现优于最先进的系统。
In this paper, we evaluate various deep learning frameworks for detecting respiratory anomalies from input audio recordings. To this end, we firstly transform audio respiratory cycles collected from patients into spectrograms where both temporal and spectral features are presented, referred to as the front-end feature extraction. We then feed the spectrograms into back-end deep learning networks for classifying these respiratory cycles into certain categories. Finally, results from high-performed deep learning frameworks are fused to obtain the best score. Our experiments on ICBHI benchmark dataset achieve the highest ICBHI score of 57.3 from a late fusion of inception based and transfer learning based deep learning frameworks, which outperforms the state-of-the-art systems.
