A Novel Weighted Fusion Based Efficient Clustering for Improved Wi-Fi Fingerprint Indoor Positioning
Pampa Sadhukhan, Keshav Dahal, Pradip Kumar Das
Abstract
The <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">received signal strength</i> (RSS) based <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Wi-Fi</i> 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 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$'$ </tex-math></inline-formula> attention to address its several limitations like degraded <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">positioning accuracy</i> due to continuous changes in surrounding environment, high <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">positioning overhead</i> , <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">storage overhead</i> etc. To address these issues, we propose a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">novel weighted fusion based efficient clustering strategy</i> ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">WF-ECS</i> ) for fingerprint positioning system in this paper. Our proposed technique <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">WF-ECS</i> computes a weighted average of the group of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">reference points</i> (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 <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">WF-ECS</i> 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 <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">benchmark dataset</i> . The experimental results depict that our newly proposed technique <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">WF-ECS</i> can outperform the contemporary techniques in terms of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">positioning accuracy</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">positioning overhead</i> while reducing the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">storage overhead</i> in real indoor settings.