The purpose of this paper is to detect the existence of unknown wireless devices which could result negative means to the privacy. The perceptual layer of internet of things (IoTs) suffers the most significant privacy disclosing because of limited hardware resources, huge quantity and wide varieties of sensing equipment. Determining whether there are unknown wireless devices in the communicating environment is an effective method to implement the privacy protection for the perceptual layer of IoTs.
The authors use horizontal hierarchy slicing (HHS) algorithm to extract the morphology feature of signals. Meanwhile, partitioning around medoids algorithm is used to cluster the HHS curves and agglomerative hierarchical clustering algorithm is utilized to distinguish final results. Link quality indicator (LQI) data are chosen as the network parameters in this research.
Nowadays data encryption and anonymization are the most common methods to protect private information for the perceptual layer of IoTs. However, these efforts are ineffective to avoid privacy disclosure if the communication environment exists unknown wireless nodes which could be malicious devices. How to detect these unknown wireless devices in the communication environment is a valuable topic in the further research.
The authors derive an innovative and passive unknown wireless devices detection method based on the mathematical morphology and machine learning algorithms to detect the existence of unknown wireless devices which could result negative means to the privacy. The simulation results show their effectiveness in privacy protection.
This work was supported by JSPS Grant-in-Aid for Scientific Research (C) 15K00495. This paper is the further work based on our paper in MoMM2016 series.
Li, X., Yoshie, O. and Huang, D. (2017), "A passive method for privacy protection in the perceptual layer of IoTs", International Journal of Pervasive Computing and Communications, Vol. 13 No. 2, pp. 194-210. https://doi.org/10.1108/IJPCC-03-2017-0025Download as .RIS
Emerald Publishing Limited
Copyright © 2017, Emerald Publishing Limited