Classification of Bio-Optical Signals using Soft Computing Tools

The identification of the state of human skin tissues is discussed here. The bio-optical signals recorded in vitro have been analyzed by extracting various statistical features. Using LAB VIEW 7.1 programs/tools, different statistical features are extracted from both normal and pathology spectra. Each spectrum is filttered and normalized. Then different features like skewness, summation, median residuals, power spectral density, etc. were extracted. The values of the feature vector reveal information regarding tissue state. The values of the feature vector reveal information regarding tissue state. These parameters have been analyzed for discrimination between normal and pathology conditions. For analysis, a specific data set has been considered. Further discrimination between normal and pathology spectra is also be achieved by using MATLAB @6.1 tool based classical multilayer feed forward neural network with back propagation algorithm.