"Support vector machines"

Estimation of the Directions-of-Arrival of correlated signals by means of a SVM-based multi-resolution approach

This paper analyzes a method for the DOA estimation of correlated signals based on the integration of a SVM classifier and an iterative multi-scaling approach (IMSA). The aim of the SVM classifier is the definition of a probability map of the angular …

Three-dimensional real-time localization of subsurface objects - From theory to experimental validation

The detection of buried landmines or unexploded ordnances is a problem of great interest in both civilian and military applications. In such a framework, this paper presents an approach for real-time localization of unknown subsurface objects. Such a …

Real-time indoor localization and tracking of passive targets by means of wireless sensor networks

In this paper, an innovative approach for the localization and tracking of a passive target in an indoor non-infrastructured environment has been presented. The proposed strategy is based on a LBE approach in order to define at each time step a map …

Object tracking through RSSI measurements in wireless sensor networks

The localisation of moving and transceiver-free objects is addressed by processing the received signal strength indicator (RSSI) available at the nodes of a wireless sensor network. Starting from the RSSI measurements, the probability of the presence …