The source separation of ground borne vibration signals is a challenging problem. The separation of a set of signals from a set of observed signal mixtures, without the information about the source signals or the mixing process is known as Blind Source Separation (BSS). BSS depends on the assumption that the source signals do not correlate with each other. The source separation of artificially mixed and naturally mixed vibration sources are used for our study. The vibration signals from four shakers which are buried in the ground are recorded using four accelerometers to obtain the mixed source in the case of natural mixing. The distance of the buried vibration sources and the mixing system are unknown. So we will use the method of BSS. The separations are performed using efficient statistical algorithms, the FastICA and the SANG.
K. Kumar M., S., G. R., and V., P. K., “Source Separation of ground borne low level vibration signals using statistical methods”, in International Conference on Advances in Computing, Communication and Information Science (ACCIS-2014), 2014.