Scholarlink

<p>Big data represents a transformative generation with significant packages across diverse sectors, such as healthcare, public records, and social media. In healthcare, massive information facilitates the evaluation, access, and retrieval of electronic health records (EHR), emphasizing the need for privateness through effective anonymization techniques. Addressing gaps in existing literature, this article proposes a framework using Scalable Subtree L-Anonymization (SS-LA) combined with the Whale Optimization Algorithm (WOA) to ensure privacy in dealing with healthcare big data inside cloud environments. The approach begins with the collection and normalization of healthcare big data, accompanied by feature extraction using Independent Component Analysis (ICA). Key overall performance metrics memory utilization, error value, accuracy, and execution time are assessed. Results suggest that the proposed technique continuously outperforms traditional methods through completing tasks more rapidly even as retaining a excessive degree of protection. Overall, this study highlights the efficacy of the proposed technique in enhancing privacy in healthcare facts management.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Optimizing healthcare big data privacy with scalable subtree-based L-Anonymization in cloud environments

  • 期刊论文

  • 发表日期：

    2025年2月8日

查看全文
  • Aravindhraj Natarajan,
  • N. Shanthi

摘要

Big data represents a transformative generation with significant packages across diverse sectors, such as healthcare, public records, and social media. In healthcare, massive information facilitates the evaluation, access, and retrieval of electronic health records (EHR), emphasizing the need for privateness through effective anonymization techniques. Addressing gaps in existing literature, this article proposes a framework using Scalable Subtree L-Anonymization (SS-LA) combined with the Whale Optimization Algorithm (WOA) to ensure privacy in dealing with healthcare big data inside cloud environments. The approach begins with the collection and normalization of healthcare big data, accompanied by feature extraction using Independent Component Analysis (ICA). Key overall performance metrics memory utilization, error value, accuracy, and execution time are assessed. Results suggest that the proposed technique continuously outperforms traditional methods through completing tasks more rapidly even as retaining a excessive degree of protection. Overall, this study highlights the efficacy of the proposed technique in enhancing privacy in healthcare facts management.