Device-Free Presence Detection and Localization With SVM and CSI Fingerprinting

Abstract

Presence detection and localization are of importance to a variety of applications. Most previous approaches require the objects to carry electronic devices, while on many occasions device-free presence detection and localization are in need. This paper proposes a device-free presence detection and localization algorithm based on WiFi channel state information (CSI) and support vector machines (SVM). In the area of interest covered with WiFi, human movements may cause observable alteration of WiFi signals. By analyzing the CSI fingerprint patterns, the proposed algorithm is able to detect human presence through SVM classification. By establishing the nonlinear relationship between CSI fingerprints and locations through SVM regression, the proposed algorithm is able to estimate the object locations according to the measured CSI fingerprints. To cope with the noisy WiFi channels, the proposed algorithm applies density-based spatial clustering of applications with noise to reduce the noise in CSI fingerprints, and applies principal component analysis to extract the most contributing features and reduce the dimensionality of CSI fingerprints. Evaluations in two typical scenarios achieved the presence detection precision of over 97%, and the localization accuracy of 1.22 and 1.39 m, respectively.