• Thota Lakshmi Priyanka
• K.Tulasi Krishna Kumar

: Publishing datasets is crucial for open data study and advancing governmental transparency Such data publication, though, might make users' confidential information public Spatial-temporal trajectory databases are among the most delicate data sources Unfortunately,individual privacy cannot be protected by simply removing distinctive identifiers For the goal of user identification, adversaries might be aware of some of the trajectories or be able to connect the published dataset to other sources So it is essential to use privacy-preserving methods before spatiotemporal trajectory datasets are published In this article, we suggest a robust framework for machine learning-based anonymization of spatiotemporal trajectory datasets (MLA) We are able to employ machine learning algorithms for clustering the trajectories by introducing a novel formulation of the problem,and we suggest using the k-means algorithm for this purpose It is also suggested to modify the k-means algorithm to protect anonymity in overly sensitive datasets Furthermore,by including multiple sequence alignment as part of the MLA,we enhance the alignment procedure On the TDrive location dataset ,the framework and all of the suggested methods are used The experimental findings show that anonymizing datasets using the MLA framework greatly increases their usefulness

:K-anonymity,Machinelearning,Clustering,Alignment,Generalization,Spatiotemporal trajectories, Longitudinal dataset, Privacy preservation, k- means with dynamic SA algorithm.

"MACHINE LEARNING THAT PROTECTS PRIVACY PUBLISHES LOCATION DATA", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 3, page no.d604-d613, March-2023, Available :http://www.jetir.org/papers/JETIR2303376.pdf

"MACHINE LEARNING THAT PROTECTS PRIVACY PUBLISHES LOCATION DATA", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 3, page no. ppd604-d613, March-2023, Available at : http://www.jetir.org/papers/JETIR2303376.pdf