Using K-Means Clustering Algorithm for Handling Data Precision

The sensitive data are patient record details, organization record which are handled only administrative member. Preservation of privacy is a major feature of data mining and individual's privacy without losing of confidential data. The objective of privacy preserving data mining is to mine significant information from large amounts of dataset. To prevent the misuse of sensitive information such as patient record by the system administrator. The database administrator collects patient's data which are maintained in secured manner. The sensitive information has patient's name, Address, Disease, Date of Visit. The privacy preservation mechanism can be carried out through anonymization techniques. In order to preserve the sensitive data, the system administrator modifying the patient details. Privacy preserving techniques used to handle the sensitive information from unsanctioned users. The proposal system is original patient record should be transformed into Anonymized table which is identified only by administrative. To keep anonymized table in cluster form using k-means clustering algorithm. To keep anonymized table in cluster form using k-means clustering algorithm. To partition anonymized table into cluster, and each cluster has similar data object which is based on anonymized data attribute. After that the grouped similar data to be protected using AES encryption algorithm. The aim of this paper is to provide more accuracy and better level of privacy of sensitive attribute.