Hierarchical Embedded System Based on FPGA for Classification of Respiratory Diseases

Objectives: This research aims to design and develop a hierarchical embedded system that utilizes respiratory sound features for diagnosing COPD and other respiratory disorders. The system is engineered to achieve high accuracy and efficiency while minimizing energy consumption, making it suitable for deployment in mobile devices or embedded systems. Methods: Lung sounds are segmented into individual breathing cycles. Thirty-nine main respiratory features in the time and frequency domains are extracted and organized into four layers. The Random Forest algorithm and Artificial Neural Network are fine-tuned with the dataset and applied to disease classification. The first layer contains recorded information, while the second and third layers contain features extracted from fixed-length sound segments classified via Random Forest. The fourth layer utilizes Wavelet Transform to convert breathing patterns into Spectrogram images, which the Artificial Neural Network processes for disease diagnosis. The system is implemented on the Xilinx PYNQ-Ultra96-V2 FPGA development board. Results: The system achieves the highest accuracy of 98.81% for five disease classes: COPD, Healthy, URTI, Bronchitis, and Pneumonia, and saves 52.5% of energy consumption compared to CPU-GPU-based traditional methods. Conclusion: This study demonstrates the effectiveness of the proposed method in diagnosing COPD and other respiratory disorders. The hierarchical embedded system is designed with high accuracy and energy efficiency, with potential real-world applications to support clinical diagnosis.