A Novel Weighted Fusion Based Efficient Clustering for Improved Wi-Fi Fingerprint Indoor Positioning

The received signal strength (RSS) based Wi-Fi fingerprint technique is not only a cost-effective means for indoor positioning but also provides reliable positioning accuracy in the indoor settings. Thus, such positioning technique has drawn many researchers $'$ attention to address its several limitations like degraded positioning accuracy due to continuous changes in surrounding environment, high positioning overhead, storage overhead etc. To address these issues, we propose a novel weighted fusion based efficient clustering strategy (WF-ECS) for fingerprint positioning system in this paper. Our proposed technique WF-ECS computes a weighted average of the group of reference points (RPs) having similar RSS patterns and thus, creates a more perfect match between fused positional co-ordinates and RSS patterns considered for merging to a single entry. Extensive experimentation have been carried out to evaluate and compare the performances of our proposed system WF-ECS with the contemporary fingerprint positioning systems including our prior work using the simulation test bed, the dataset collected from our departmental building and also the benchmark dataset. The experimental results depict that our newly proposed technique WF-ECS can outperform the contemporary techniques in terms of positioning accuracy and positioning overhead while reducing the storage overhead in real indoor settings.