In [19], the authors developed neuro-fuzzy inference system by combining features retrieved from discrete wavelet transformation (DWT) decompression and edge images based on gray level co-occurrence.
In this section, based on gray level co-occurrence matrix (GLCM), we first obtain the texture feature information of an image.
The texture features included 5 first-order features based on histogram analysis, 19 second-order features based on gray-level co-occurrence matrix (GLC M, and 16 high-order features based on neighborhood gray-tone difference matrix (NGTDM) and gray-level zone size matrix (GLZSM).
First, we generate the prior probability matrix P of histone mark co-occurrence based on the pairwise co-occurrence frequencies observed in a compendium of MS experiments.
The texture features are extracted based on the gray-level co-occurrence matrix (GLCM) method proposed by Haralick (1979).
Elements are represented as nodes sharing edges based on similarity, as co-occurrence.
The comorbidities for each primary cause were selected based on rates of co-occurrence with the primary diagnosis.
In particular, it must be based on list-specific co-occurrence probabilities.
PFMs are then clustered based on similarity and/or co-occurrence (Fig. 1H).
Based on the co-occurrence probabilities and the window sizes, one can compute P-values for cooperativity.
