Big Data Analysis in IIoT Systems Using the Federated Machine Learning Method

• Published in: 2022 IEEE 16th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET) pp. 248 - 252
• Main Authors: Klymash, Mykhailo, Hordiichuk-Bublivska, Olena, Kyryk, Marian, Fabri, Liudvih, Kopets, Halyna
• Format: Conference Proceeding
• Language: English
• Published: IEEE 22-02-2022
• Subjects: Big Data; Federated Machine Learning; Industrial Internet of Things; Machine learning; Machine learning algorithms; Prediction algorithms; Recommender Systems; Singular Value Decomposition; Software; Software algorithms; Telecommunications
• DOI: 10.1109/TCSET55632.2022.9766908

The problem of effective Big Data processing in the Industrial Internet of Things was investigated in the work. The method of Federated Machine Learning as a tool for the analysis of large volumes of information in IIoT was described. The algorithm of Singular Value Decomposition was analyzed, which effectively analyzes the user data and the possibility of its modification. The increase of computational reliability using the FedSVD algorithm was investigated. The software modeling which confirms the efficiency of the proposed method has been carried out.