Scalable and Efficient Clustering for Fingerprint-Based Positioning

Abstract

Indoor positioning based on IEEE 802.11 wireless LAN (Wi-Fi) fingerprinting needs a reference data set, also known as a radio map, in order to match the incoming fingerprint in the operational phase with the most similar fingerprint in the data set and then estimate the device position indoors. Scalability problems may arise when the radio map is large, e.g., providing positioning in large geographical areas or involving crowdsourced data collection. Some researchers divide the radio map into smaller independent clusters, such that the search area is reduced to less dense groups than the initial database with similar features. Thus, the computational load in the operational stage is reduced both at the user devices and on servers. Nevertheless, the clustering models are machine-learning algorithms without specific domain knowledge on indoor positioning or signal propagation. This work proposes several clustering variants to optimize the coarse and fine-grained search and evaluates them over different clustering models and data sets. Moreover, we provide guidelines to obtain efficient and accurate positioning depending on the data set features. Finally, we show that the proposed new clustering variants reduce the execution time by half and the positioning error by ≈ 7% with respect to fingerprinting with the traditional clustering models.

Augmentation of Fingerprints for Indoor BLE Localization Using Conditional GANs

“…where p os represents the estimated location, p os i represents the position at the i-th neighbor, and d i signifies the distance between the measured RSS value at BLE of a point of interest and the pre-recorded fingerprint of RSS at location i. (7) calculates the weights (w i ) assigned to each neighbor based on the inverse of their respective distances. Smaller distances are accorded relatively larger weights, ensuring that the nearest neighbors, selected based on the smallest Euclidean distance and highest similarity, correspond to both offline and online RPs.…”

“…As the area and RSS measurement time increase, the dataset size required for calibration increases. Despite the time-consuming and labor-intensive nature of site surveying, fingerprinting-based approaches continue to be popular owing to their applicability to IPSs [6], [7].…”

A Fingerprint Dictionary Processing Approach in Indoor Localization System Based on Wi-Fi

“…A variety of matching algorithms based on minimizing the squared fitting errors (under the assumption that the errors follow Gaussian distribution), including k-nearest neighbor (kNN) based on Euclidean distance 12 , Naive Bayes (NB) 13 , Gaussian process regression (GPR) 14 , k-means (k-Means) clustering algorithm 15 , Artificial Neural Network (ANN) 16 , and Support Vector Machine (SVM) 17 have been proposed in the literature. These algorithms are generally selected based on the initial radio map and frequently prioritize enhancing the localization accuracy in the online phase, resulting in the noise signal in the initial data being brought into the online phase.…”