Implementation of signal classification using frequency spectrum features on the raspberry Pi platform

In this paper, we propose an algorithm for classification of three signals: sink tap, toilet and shower tap, implemented on the Raspberry Pi platform. Signals are analyzed in the frequency domain, and features used for classification are concentration measure and the amount of energy in certain frequency bands. The process consists of 1) sound acquisition from a microphone; 2) data processing and 3) signaling with led diodes. The proposed algorithm presents an efficient way to classify sink tap, toilet and shower tap into proper signal groups, and it can be used in the bathrooms, to classify the water flow signals.