Narrow Results

A general technique for representing quasi-periodic oscillations, typical of biomedical signals, is described. Using energy thresholding and Gaussian kernels, in conjunction with a nonlinear gradient descent optimization, it is shown that significant noise reduction, compression and turning point location is possible. As such, the signal representation model can be considered a form of correlated source separation. Applications to filtering, modelling and robust ECG QT-analysis are described.

In the recent past, blind source separation (BSS) algorithms using multivariate statistical data analysis technique have been successfully used for source identification and separation in the field of biomedical and statistical signal processing. Recently numbers of different BSS techniques have been developed. With BSS methods being the feasible method for source separation and decomposition of biosignals, it is important to compare the different techniques and determine the most suitable method for the applications. This paper presents the performance of five BSS algorithms (SOBI, TDSEP, FastICA, JADE and Infomax) for decomposition of sEMG to identify subtle finger movements. It is observed that BSS algorithms based on second-order statistics (SOBI and TDSEP) gives better performance compared to algorithms based on higher-order statistics (FastICA, JADE and infomax).

The analysis of complex protein samples can be time-consuming and expensive, due to the problems in identifying low abundance proteins in complex biological samples. We show that morphological source separation and multiscale filtering by wavelet transforms yield 2-DE gel images whose partial suppression of noise improves the spot detection phase from reconstructed serum maps.

Classification of surface electromyogram (sEMG) for identification of hand and finger flexions has a number of applications such as sEMG-based controllers for near elbow amputees and human-computer interface devices for the elderly. However, the classification of an sEMG becomes difficult when the level of muscle contraction is low and when there are multiple active muscles. The presence of noise and crosstalk from closely located and simultaneously active muscles is exaggerated when muscles are weakly active such as during sustained wrist and finger flexion and of people with neuropathological disorders or who are amputees. This paper reports analysis of fractal length and fractal dimension of two channels to obtain accurate identification of hand and finger flexion. An alternate technique, which consists of source separation of an sEMG to obtain individual muscle activity to identify the finger and hand flexion actions, is also reported. The results show that both the fractal features and muscle activity obtained using modified independent component analysis of an sEMG from the forearm can accurately identify a set of finger and wrist flexion-based actions even when the muscle activity is very weak.