Wearable system design with wheeze signal detection

This paper introduces a wearable microphone array system designed for health condition monitoring. In particular, the paper presents a novel wheeze signal detection method for wearable systems. The detection method is designed to operate at a sampling rate of 1000 Hz which is way below the typical sampling rate of 44 kHz for audio signals. The detection method is simple and involves only the estimation of the power ratios of selected sub-bands of the signals acquired. The wheeze signal detector has been implemented on a DSP based system. Experimental results show that the proposed detector is able to achieve good accuracy even in the presence of a speech interfering source.

[1]  Martin Kompis,et al.  Adaptive heart-noise reduction of lung sounds recorded by a single microphone , 1992, 1992 14th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[2]  Michio Miyakawa,et al.  Acoustic measurement of the respiratory system— An acoustic pneumograph , 1976, Medical and biological engineering.

[3]  Arnon D. Cohen,et al.  Analysis and Automatic Classification of Breath Sounds , 1984, IEEE Transactions on Biomedical Engineering.

[4]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[5]  Henry Cox,et al.  Practical supergain , 1986, IEEE Trans. Acoust. Speech Signal Process..

[6]  H. Pasterkamp,et al.  Respiratory sounds. Advances beyond the stethoscope. , 1997, American journal of respiratory and critical care medicine.

[7]  Y. Nishida,et al.  Non-invasive and unrestrained monitoring of human respiratory system by sensorized environment , 2002, Proceedings of IEEE Sensors.

[8]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.