A Novel Blockchain-Based Privacy-Preserved Data Sharing Using Deep Maxout Network in Federated Learning

The quick emergence in the quantity of data produced through the linked devices of Internet of Things (IoT) models opened the novel potential to improve service qualities for budding tools considering data sharing. However, privacy problems are main issues of data providers for sharing data. The outflow of confidential data causes severe problems beyond the loss in finance of providers. A blockchain-based secured data-sharing model is devised for dealing with various kinds of parties. Thus, data-sharing issue is modeled as a machine learning issue by adapting federated learning (FL). Here, data privacy is controlled by sharing data in spite of exposing genuine data. At last, the FL is combined in consensus task of permissioned blockchain for accomplishing federated training. Here, the data model learning is executed using a deep maxout network (DMN), which is trained using jellyfish search African vultures optimization (JSAVO). Moreover, the data-sharing records are generated to share data amid data providers and requestors. The proposed JSAVO-based DMN outperformed with better accuracy of 93.3%, FPR of 0.054, loss function of 0.067, mean square error (MSE) of 0.346, mean average precision of 94.6, RMSE of 0.589, computational time of 17.47[Formula: see text]s, and memory usage of 48.62[Formula: see text]MB.