An Ensemble of Deep Learning Frameworks Applied For Predicting Respiratory Anomalies
This work addresses respiratory anomaly detection for medical applications, but it is incremental as it combines existing methods without introducing new paradigms.
The paper tackled the problem of detecting respiratory anomalies from audio recordings by evaluating and fusing deep learning frameworks, achieving a state-of-the-art ICBHI score of 57.3 on the benchmark dataset.
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.