Independent component analysis for noisy data: MEG data analysis
Neural Networks
Independent component analysis for artefact separation in astrophysical images
Neural Networks - 2003 Special issue: Neural network analysis of complex scientific data: Astronomy and geosciences
Hi-index | 0.00 |
Electrical signals of a plant leaf measured using surface recording are mixed signals which involve the electrical activities of the epidermis cells, guard cells, and mesophyll cells. Blind source separation (BSS) is a general signal processing approach, which estimates the source signals independently if the unknown signal sources are made by mixing linearly. The independent component analysis (ICA) method is one technique used to solve the blind source separation (BSS) problem. In contrast with conventional measuring methods used to investigate the electrical signals of plant cells with a complex treatment procedure, the ICA method was provided to achieve separation of the mixed electrical signals to recover the individual signals of each type of cells non-invasively. The proposed method has been tested using simulated signals and real plant electrical signal recordings. The results showed that ICA algorithms provided an efficient tool for the identification of the independent signal components from surface electrode recordings.