Enrique Calot

Tumor Classification on Mammographies Based on BPNN and Sobel Filter

Breast cancer is a very common disease and the cause of death of many people. It has been proven that prevention decreases the death rate, but the costs of diagnosis and image processing are very high when applied to all the population with potential risk. This paper studies an existent computer aided diagnosis method using neural network and improves its detection success rate from 60% to 73%. This improvement is achieved due to the use of image and statistical operators over concentric regions around the tumor boundaries.

Optimizing Relationships Information in Repertory Grids

The Repertory Grid method is widely used in knowledge engineering to infer functional relationships between constructs given by an expert. The method is ignoring information that could be used to infer more precise dependencies. This paper proposes an improvement to take advantage on the information that is being ignored in the current method. Furthermore, this improvement fixes several other limitations attached to the original method, such as election in a discrete set of two values as a similarity pole or a contrast pole, the arbitrary measurement of distances, the unit-scale dependency and the normalization, among others. The idea is to use linear regression to estimate the correlation between constructs and use the fitness error as a distance measure.