IIoT information processing model for transfer learning with data quality management

Alexander Grebeshkov
Generally, the use of transfer learning techniques is challenging when the testing data and the training data are not collected into a single enterprise data storage and the data items are not linked explicitly one to another, as happens with the sensor data flows in the sensor network. The objective of this paper is to propose a transfer learning service delivery model based on the collaborative information processing with consolidation data sets and data quality management. In order to achieve objective we suppose model with an ontology-based rules applying to check quality of an enterprise database which is used in Industrial internet of things platform for machine learning service support.