Blind EGG separation using ICA neural networks

Blind electrogastrogram (EGG) signal separation technology by using neural network-based independent component analysis (ICA) is presented in this paper. The experimental results show that using this technology, the true EGG components can be separated from the multi-channel EGG data contaminated by measurement artefacts, such as respiratory, motion, electrocardiogram (ECG) and so on, even though no prior information on such contaminating can be obtained, which is closer to practical situations in clinical applications