A system for biomedical audio signal processing based on high performance computing techniques

In this paper, a noninvasive portable prototype is presented for biomedical audio signal processing. The proposed suitable monitoring the health of patients. hardware setup consists cost-effective microphone, multipurpose microcontroller and computing node that could be mobile phone or general-purpose computer. Using parallel high-performance techniques, allows one to register wirelessly multicast recorded signals nodes in real time. developed was used as case study estimate heart rate (HR) from captured signal. regard, algorithm estimating HR comprises three stages: preprocessing, separation, estimation. first stage, by microphone adapted Subsequently, separation stage alleviate acoustic interference between lungs heart. performed combining non-negative matrix factorization algorithm, clustering approach, soft-filter strategy. Finally, estimation obtained using novel efficient method based on autocorrelation function. not only HR, but also retrieval other information related recording cardiac respiratory signals. evaluated well-known datasets compared with state-of-the-art algorithms source-separation. results showed it possible obtain an accurate reliable real-time terms source metrics relative error tested scenarios multi-core architectures techniques. validated real-world scenario.