Respiratory sound analysis : noise suppression techniques

• Main Author: Ge, Yihui
• Other Authors: Ser Wee
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
• Online Access: https://hdl.handle.net/10356/142932
• Institution: Nanyang Technological University

Respiratory sound signal is the signal generated by the respiratory system. It contains information of respiratory system and can be used to monitor the condition of the system. However, the process of recording respiratory signals will introduce noise from all sources. It is essential to filter the noise because it will affect the precision of medical diagnosis. This paper analyzes the composition of the noise and proposes solutions to eliminate noise accordingly. In this paper, a denoising system based on the technique of digital filters and adaptive filter is designed to remove the unwanted noise components from the original signal. The system consists of two parts, processing with digital filters, and adaptive filters. The result of the system is analyzed, and the performance of the system is evaluated in this paper. Due to the experiments, the processing with digital filters removes the most of noise components and improves the quality of signal greatly, and the rest of the noise can be removed with adaptive filters. RLS has better performance and faster speed of convergence compared with LMS in denoising respiratory signals.