Wearable Low-Power Wireless Lung Sound Detection Enhanced By Resonant Transducer Array For Pre-Filtered Signal Acquisition

This paper reports the implementation and evaluation of an array-based recognition system for medical wheezing detection. We describe the design and fabrication of a microphone array for pre-filtered acoustic signal acquisition. The use of a sensor-array at the input simplifies several of the required digital processing steps necessary for performing spectral filtering and wheezing recognition. The recognizer is evaluated and compared against a traditional approach, and the experimental results show that recognition processing duration and power consumption can be reduced by 94.5%. The results also indicate a potential for improved recognition accuracy with the array-based approach in environments with large levels of acoustic noise. The data suggests that this technique has potential for enabling very low-power (2.3 mW) self-powered wireless and wearable wheezing detection systems.