Abstract | ||
---|---|---|
In this paper, a data-driven extension of the variational algorithm is proposed. Based on a few selected sensors, target tracking is performed distributively without any information about the observation model. Tracking under such conditions is possible if one exploits the information collected from extra inter-sensor RSSI measurements. The target tracking problem is formulated as a kernel matrix completion problem. A probabilistic kernel regression is then proposed that yields a Gaussian likelihood function. The likelihood is used to derive an efficient and accelerated version of the variational filter without resorting to Monte Carlo integration. The proposed data-driven algorithm is, by construction, robust to observation model deviations and adapted to non-stationary environments. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICASSP.2009.4960108 | Taipei |
Keywords | Field | DocType |
Gaussian processes,filtering theory,matrix algebra,probability,regression analysis,target tracking,wireless sensor networks,Gaussian likelihood function,RSSI measurement,data-driven online variational filtering algorithm,kernel matrix completion problem,probabilistic kernel regression,target tracking,wireless sensor network,Bayesian filtering,machine learning,sensor networks | Kernel (linear algebra),Mathematical optimization,Likelihood function,Pattern recognition,Computer science,Filter (signal processing),Gaussian,Artificial intelligence,Monte Carlo integration,Gaussian process,Probabilistic logic,Kernel regression | Conference |
ISSN | ISBN | Citations |
1520-6149 E-ISBN : 978-1-4244-2354-5 | 978-1-4244-2354-5 | 0 |
PageRank | References | Authors |
0.34 | 4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hichem Snoussi | 1 | 0 | 0.34 |
Jean-Yves Tourneret | 2 | 835 | 64.32 |
Djurić, P.M. | 3 | 10 | 1.93 |
Cédric Richard | 4 | 940 | 71.61 |