PM02:  LEARNING DIAGNOSTIC CLASSIFIER(LDC) BASED ON MODULAR CLUSTERING,

        MAMDANI  FUZZY  MODEL AND CO-EVOLUTIONARY ALGORITHM

Functions & goal

LDC-generic block diagram is shown in Figure 1 is implemented in two modes. In the first (OFF-line mode), the model can be  trained/learned  by  microarray data sets available in  NCBI, GEOSOFT, GEMS, UCI and other databases, or with the available data from clinic. In the second mode (ON-line mode) the subsystem will receive real data whose sources are microarray data obtained from samples of the treated patient.

Methods

The application of sophisticated (fusion) methods will optimize the microarray input data set using Co-evolutionary Fuzzy Logic (CFL) – Figure 2.

 Figure 1. Learning diagnostic classifier-generic block diagram

The output (responses) from this model will provide predictive cancer diagnosis and predictive biomarkers that may improve the accuracy of the classical diagnostic techniques. The LDC is the first level of support in estimating patient survival scenario.

Figure 2.  Diagnosis and biomarkers block of LDC