The Identification of Secular Variation in IoT Based on Transfer Learning
Caidan Zhao, Zhibiao Cai, Minmin Huang, Mingxian Shi, Xiaojiang Du, Mohsen Guizani · 2018 International Conference on Computing, Networking and Communications (ICNC) · 2018
In the Internet of Things(IoT) equipment, the characteristic space of the physical layer has changed slightly due to prolongation of the use time and the change of the environment, which may result to the terrible identification of the new target. To solve the problem, this paper uses transfer learning to update the instance weights and combines the weight with rejection sampling to construct the training set. This method provides a black box for transfer learning and a possibility for building multi-classification transfer learning. Some experimental results show that the rate can increase 10% when the number of target samples is too small to train a new learning model.