An application of the independent component analysis to monitor acoustic emission signals generated by termite activity in wood

In this paper an extended robust independent components analysis (ERICA) algorithm based on cumulants is applied to identify vibrational alarm signals generated by soldier termites in southern Spain (reticulitermes grassei), by drumming their heads against the substratum, and measured by low cost equipment. A seismic accelerometer is employed to strongly characterize these acoustic emissions. To support the proposed technique, vibrational signals from a low cost microphone have been mixed with known signals, and the mixtures processed by ERICA. The experimental results confirm the validity of the proposed method, which has been taken as the basis for the development of a low cost, non-invasive, termite detection system. (C) 2004 Elsevier Ltd. All rights reserved.