Due to the exponential growth of hardware technology particularly in the field of electronic data storage media and processing such data, has raised serious issues related in order to protect the individual privacy like ethical, philosophical and legal. Data mining techniques are employed to ensure the privacy. Privacy Preserving Data Mining (PPDM) techniques aim at protecting the sensitive data and mining results. In this study, the different Clustering techniques via classification with and without anonym zed data using mining tool WEKA is presented. The aim of this study is to investigate the performance of different clustering methods for the diabetic data set and to compare the efficiency of privacy preserving mining. The accuracy of classification via clustering is evaluated using K-means, Expectation-Maximization (EM) and Density based clustering methods.

With the proliferation of information available in the internet and databases, the privacy-preserving data mining is extensively used to maintain the privacy of the underlying data. Various methods of the state art are available in the literature for privacy-preserving. Evolutionary Algorithms (EAs) provide effective solutions for various real-world optimization problems. Evolutionary Algorithms are efficiently employed in business practice. In privacy-preserving domain, the existing EA solutions are restricted to specific problems such as cost function evaluation. In this work, it is proposed to implement a Hybrid Evolutionary Algorithm using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Both GA and PSO in the proposed system work with the same population. In the proposed framework, k-anonymity is accomplished by generalization of the original dataset. The hybrid optimization is used to search for optimal generalized feature set.

Feature contribution means that what features actually participates more in grouping data patterns that maximizes the system’s ability to classify object instances. In this paper, modified K-means fast learning artificial neural network (K-FLANN) was used to cluster multidimensional data. The operation of neural network depends on two parameters namely tolerance (δ) and vigilance (ρ). By setting the vigilance parameter, it is possible to extract significant attributes from an array of input attributes and thus determine the principal features that contribute to the particular output. Exhaustive search and Heuristic search techniques are applied to determine the features that contribute to cluster data. Experiments are conducted to predict the network's ability to extract important factors in the presented test data and comparisons are made between two search methods.