Spectral compression with wavelet neural network

2 Spectral compression with wavelet neural network 

As suggested in reference [25], the traditional sigmoidal function can be replaced with the Morlet wavelet basis function Fqwt in neural network analysis (Fig. 4(b)). When a spectral data, X, is applied to this WNN system, a response or an output value Ydwt s obtained as follows  

In the above equation, W, bj and aj denote the weighting factor, translation coefficient and dilation coefficient, respectively, for each wavelet basis. In Liu s work [25], the wavenumber and transmittance quantities of the IR spectrum were used as the input and target output values, respectively, of the network. Their proposed neural network consisted of a single layer network 

---

A second approach to data compression is to compress infrared spectra with a construct called a wavelet neural network (WNN). The WNN approach stores large amounts of infrared data for fast archiving of spectral data. It is achieved by modifying the machine learning technique of artificial neural networks (ANNs) to capture the shape of infrared spectra using wavelet basis functions. The WNN approach is similar to another approach... 

---