Preliminary segmentation of fetal magnetocardiograms for a wireless diagnosis system

Wireless technology reveals new opportunities for a more efficient medical care system, but requires to reduce the amount of data to be transmitted. Automated diagnosis systems are able to solve this need. In this view, wavelets are well suited for the necessities of non-stationary biological signals, such as provided by magnetocardiograms. Automated diagnosis enhances the chances of a timely prevention of life endangering situations and eases the work of the medical community. The main aim of this paper is to develop an accurate and robust segmentation algorithm based on the Stationary Wavelet Transform. The simulation results prove the performance of the proposed algorithm, enabling thus a further development of a wireless automated diagnosis system.