Abstract:
Disclosed is a device which includes a data manager, a learner, and a predictor. The data manager generates output data based on time-series data, receives device prediction results corresponding to the output data from the prediction devices, and calculates device errors based on the difference between device prediction results and time-series data. The learner may adjust a parameter group of a prediction model for generating device weights, based on device prediction results and device errors. The predictor generates the ensemble result of first and second device prediction results based on device weights.
Abstract:
Provided is a constrained application protocol (CoAP) communication method and a system for performing the method, wherein the method includes receiving a POST message for a registration request, verifying whether the registration request is valid in response to the POST message, extracting a unit identifier (ID) of at least one resource associated with a node from a message payload of the POST message, and returning a response message.