A performance guaranteed indoor positioning system using conformal prediction and the WiFi signal strength

Abstract

Indoor navigation provides the positioning service to the indoor users, where the GPS coverage is not available. The challenges for most signal-based indoor positioning systems are the unpredictable signal propagation caused by the complex building interiors, and the dynamic of the environment caused by the peoples' movements. However, most existing systems made no assumption about the quality of their predictions, which is crucial in such noisy indoor environment. To address this challenge, this article proposes a confidence measure to reflect the uncertainty of the positioning prediction. More importantly, the users may control the size of the prediction set by setting the confidence level tailoring to their personal requirement. The proposed approach in this article has been validated in three real office buildings with challenging indoor environments, which indicated that it performed up to 20% more accurate than traditional Naïve Bayes and Weighted K-nearest neighbours (W-KNN) algorithms. ARTICLE HISTORY

A review of smartphones‐based indoor positioning: Challenges and applications

“…The more unpredictable the signal attenuation is, the more unique the training data will be, which aids the positioning estimation process. However, the major drawback of fingerprinting is the sheer amount of building space to be meticulously surveyed, the time it takes to F I G U R E 8 Fingerprinting method F I G U R E 9 The machine learning approaches for fingerprinting perform such process, and the lack of physical reference for the training positions [28]. As fingerprinting relies on a training database, below are some open research questions.…”

“…The machine learning approaches for fingerprinting perform such process, and the lack of physical reference for the training positions [28]…”

A review of smartphones based indoor positioning: challenges and applications

“…The more unpredictable the signal attenuation is, the more unique the training data will be, which aids the positioning estimation process. However, the major drawback of fingerprinting is the sheer amount of building space to be meticulously surveyed, the time it takes to perform such process, and the lack of physical reference for the training positions [23]. As fingerprinting relies on a training database, below are some open research questions.…”

On-Device Learning of Indoor Location for WiFi Fingerprint Approach

“…In [ 17 ], the authors presented an enhanced machine-learning localization scheme incorporating AP selection and signal strength reconstruction based on RSSI measurements. In [ 18 ], a confidence measure, which is capable of reflecting the uncertainty of the positioning predictions and adjusting the size of the prediction set accordingly, was proposed. In [ 19 ], the problem of IPS was explained from the perspective of GPS signals.…”