Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{175951,
        author = {Suruchi Nannaware and Dr. Hiren Dand},
        title = {DEVO-DNFN A Novel Approach for Secure Medical Data Classification in the Cloud},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {5274-5280},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175951},
        abstract = {In cloud Computing, storing and accessing sensitive information is a major concern. The paper tries to address these issues by providing the novel approach for classifying privacy preserved medical data, named DEVO. It integrates the two optimization algorithm namely, Energy Valley Optimizer (EVO) and Dingo Optimizer (DOX).  Cloud simulation is the first step in the process, which gathers medical data from the dataset as an input. The privacy of data is then maintained in the cloud environment by using DEVO to create a privacy utility coefficient matrix using deep learning principles. The resulting privacy-preserved data is safely kept in the cloud and can only be retrieved by authorized parties with the same key. In addition, DEVO-DNFN uses Deep Neuro Fuzzy Network (DNFN) to classify medical data, which is then refined with DEVO. Assessment metrics like True Positive Rate (TPR), accuracy, and True Negative Rate (TNR) show encouraging results, having observed values of 0.912, 0.907, and 0.915, respectively. This comprehensive method addresses the important issues of privacy and data security in cloud-based medical data classification},
        keywords = {cloud computing, DNFN, optimization, Privacy preservation},
        month = {April},
        }