Analytics on Anonymity for Privacy Retention in Smart Health Data

Advancements in smart technology, wearable and mobile devices, Internet of Things, have made health an integral part modern living to better individual healthcare well-being. By enhancing self-monitoring, data collection sharing among users service providers, can increase healthy lifestyles, timely treatments, save lives. However, as become larger more accessible multiple parties, they vulnerable privacy attacks. One way safeguard is users’ anonymity increases indistinguishability making it harder for re-identification. Still the challenge not only preserve but also ensure that shared are sufficiently informative be useful. Our research studies analytics focusing on protection. This paper presents a multi-faceted analytical approach (1) identifying attributes susceptible information leakages by using entropy-based measure analyze loss, (2) anonymizing generalization attribute hierarchies, (3) balancing between informativeness our anonymization technique produces anonymized satisfying given requirement while optimizing retention. automated Artificial Intelligent search based two simple heuristics. The describes illustrates detailed including pre post analytics. Experiments published performed technique. Results, compared with other similar techniques, show gives most effective solution, respect computational cost