Privacy protection based distributed clustering with deep learning algorithm for distributed data mining

Distributed Data Mining (DDM) is vital in various applications for processing large volumes of data. The datasets are saved the local databases and operated by communities, but it provides solution locally globally. However, stored a distributed manner which affects scalability reliability issues. In addition, data influenced security privacy challenges. third party may access DDM, causes authorization Therefore, DDM process fuses sensor from different sources to improve knowledge discovery. During this process, faces several issues such as concerns, restrictions, technical barriers, trust To address these issues, mining should be improved handle homogeneous heterogeneous This work uses protection-based clustering (PPDC) algorithm challenges while analyzing generates semi-trusted parties form cluster, protects unauthorized users. protect analyzed creating random vector-based trusted process. Further, optimized deep learning approach analysis. Then effectiveness introduced PPDC method compared with existing methods, ensures 0.202 error rate, 0.95 % accuracy manages security.