Breast cancer is known as one of the most common cancers to afflict the female population. Computer assisted diagnosis can be helpful for doctors in detection and diagnosing of potential abnormalities. Several techniques can be useful for accomplishing this task. This paper outlines an approach for recognizing breast cancer diagnosis using neuro-fuzzy inference technique namely ANFIS (Adaptative Neuro-Fuzzy Inference System). Wisconsin breast cancer diagnosis (WBCD)database developed at University of California, Irvine (UCI) is used to evaluate this method. Results show that the best performances are obtained by our model compared to others cited in literatur (an accuracy of 98, 25 % ).

Abstract. The standard Homogeneity-Based (SHB) optimization algorithm is a metaheuristic which is proposed based on a simultaneously balance between fitting and generalization of a given classification system. However, the SHB algorithm does not penalize the structure of a classification model. This is due to the way SHB's objective function is defined. Also, SHB algorithm uses only genetic algorithm to tune its parameters. This may reduce SHB's freedom degree. In this paper we have proposed an Improved Homogeneity-Based Algorithm (IHBA) which adopts computational complexity of the used data mining approach. Additionally, we employs several metaheuristics to optimally find SHB's parameters values. In order to prove the feasibility of the proposed approach, we conducted a computational study on some benchmarks datasets obtained from UCI repository. Experimental results confirm the theoretical analysis and show the effectiveness of the proposed IHBA method.

No abstract

No abstract

As simple and effective optimisation approach, homogeneity-based algorithm (HBA) is one of the recent metaheuristics, proposed to minimise the total misclassification cost of data mining approaches. However, one problem is that HBA does not adopt computational complexity of the used data mining technique. This is due to the way objective function is defined. So, in this paper, we have proposed an improved HBA (IHBA), which is utilising a modified objective function that compute the computational complexity of the used classification method. We also test several clustering techniques as HBA parameters tuning, in order to enhance classifiers' performance. We have tested IHBA on different benchmarks and the obtained results show the effectiveness of the proposed method.