RSS based indoor localization with limited deployment load

摘要: One major bottleneck in the practical implementation of received signal strength (RSS) based indoor localization systems is extensive deployment load required to construct radio maps through fingerprinting. Several works aimed employ propagation models as alternative fingerprinting but different sources inaccuracies generation these result high errors. In this paper, we propose an scheme that can be directly deployed and employed without building a full map environment. The proposed employs information from simulator limited number calibration measurements perform direct using manifold alignment. For moving users, exploit correlation their reported observations improve accuracy. online performance evaluation shows our algorithm achieves errors order 2.5 3 m with low 15% – 30 % complete load.