The Identification of Secular Variation in IoT Based on Transfer Learning

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.

[1]  Mohsen Guizani,et al.  An effective key management scheme for heterogeneous sensor networks , 2007, Ad Hoc Networks.

[2]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[3]  Qiang Ji,et al.  Constrained Deep Transfer Feature Learning and Its Applications , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  John Langford,et al.  Cost-sensitive learning by cost-proportionate example weighting , 2003, Third IEEE International Conference on Data Mining.

[5]  Massimiliano Pontil,et al.  An Algorithm for Transfer Learning in a Heterogeneous Environment , 2008, ECML/PKDD.

[6]  Yoram Singer,et al.  Learning to Order Things , 1997, NIPS.

[7]  Nando de Freitas,et al.  An Introduction to Sequential Monte Carlo Methods , 2001, Sequential Monte Carlo Methods in Practice.

[8]  Mohsen Guizani,et al.  Stream-based cipher feedback mode in wireless error channel , 2009, IEEE Transactions on Wireless Communications.

[9]  Qiang Yang,et al.  Heterogeneous Transfer Learning for Image Classification , 2011, AAAI.

[10]  重田 泰.  Fraud detection system at game parlor , 2016 .

[11]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[12]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[13]  Jialin Pan,et al.  Feature-based transfer learning with real-world applications , 2010 .

[14]  Xiaojiang Du,et al.  A Lightweight Multicast Authentication Mechanism for Small Scale IoT Applications , 2013, IEEE Sensors Journal.

[15]  Lior Wolf,et al.  A theoretical framework for deep transfer learning , 2016 .

[16]  Rajasekhar Mungara,et al.  A Routing-Driven Elliptic Curve Cryptography based Key Management Scheme for Heterogeneous Sensor Networks , 2014 .

[17]  Xiaojiang Du,et al.  Security in wireless sensor networks , 2008, IEEE Wireless Communications.

[18]  Michael A. Temple,et al.  A Comparison of PHY-Based Fingerprinting Methods Used to Enhance Network Access Control , 2015, SEC.

[19]  Caidan Zhao,et al.  Compressed Sensing Based Fingerprint Identification for Wireless Transmitters , 2014, TheScientificWorldJournal.

[20]  Mohsen Guizani,et al.  Transactions papers a routing-driven Elliptic Curve Cryptography based key management scheme for Heterogeneous Sensor Networks , 2009, IEEE Transactions on Wireless Communications.