@inproceedings{8a91be50d038492fbe6babbf5f245f51,
title = "An improved data anonymization algorithm for incomplete medical dataset publishing",
abstract = "To protect sensitive information of patients and prevent privacy leakage, it is necessary to deal with data anonymously in medical dataset publishing. Most of the existing anonymity protection technologies discard the records with missing data, and it will cause large differences in characteristics in data anonymization, resulting in severe information loss. To solve this problem, we propose a novel data anonymization algorithm for incomplete medical dataset based on L-diversity algorithm (DAIMDL) in this work. In the premise of preserving records with missing data, DAIMDL clusters data on the basis of the improved k-member algorithm, and uses the information entropy generated by data generalization to calculate the distance in clustering stage. Then, the data groups obtained by clustering are generalized. The experimental results show that it can protect the sensitive attributes of patients better, reduce the information loss during the anonymization process of missing data, and improve the availability of the dataset.",
keywords = "Data anonymization, Incomplete medical dataset, L-diversity, Missing data",
author = "Wei Liu and Mengli Pei and Congcong Cheng and Wei She and Wu, {Chase Q.}",
note = "Publisher Copyright: {\textcopyright} Springer Nature Singapore Pte Ltd 2019.; 2nd International Conference on Healthcare Science and Engineering, Healthcare 2018 ; Conference date: 01-06-2018 Through 03-06-2018",
year = "2019",
doi = "10.1007/978-981-13-6837-0_9",
language = "English (US)",
isbn = "9789811368363",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Verlag",
pages = "115--128",
editor = "Xianxian Li and Wu, {Chase Q.} and Ming-Chien Chyu and Jaime Lloret",
booktitle = "Proceedings of the 2nd International Conference on Healthcare Science and Engineering",
address = "Germany",
}