Extreme learning machine for indoor location fingerprinting

Abstract

With the rapid growing market of wireless devices, positioning systems that make use of the signal strength of wireless devices are gaining more interest nowadays. Being able to track the location of a Wi-Fi or Radio Frequency Identification device could improve the quality of services in various sectors, including security, warehouse, logistic management, and healthcare. As compared with outdoor environment, positioning systems face a greater challenge in indoor environment because wireless signal is significantly influenced by building layout and surrounding objects, for which a location fingerprinting approach is needed. Moreover, the signal strength of a wireless device may also change over time, which is known as temporal variation, and therefore a reliable location estimation system must have the ability to learn and adapt with temporal changes. However, if the learning process is highly complex and requires long processing time, deploying the system into a larger scale would not be feasible. In recent years, Extreme Learning Machine (ELM) has surfaced as a viable alternative that challenged the norm of iterative and progressive learning. ELM has also been considered as a solution for indoor location fingerprinting. However, there has not been a comprehensive review on how the ELM-based approaches are linked with existing location fingerprinting techniques. Here we discuss some major location fingerprinting techniques, B Felis Dwiyasa 123 Multidim Syst Sign Process which are nearest-neighbor, LANDMARC, and LEMT, and formulate a new framework for systematically translating the techniques into ELM-based methods.

Positioning by floors based on WiFi fingerprint

“…KNN was first applied to the indoor positioning system RADAR [12], which finds K RPs with the smallest distance by calculating the Euclidean distance between TP and RP fingerprints, and uses its average value as the estimated coordinates of TP. The extreme learning machine (ELM) has also been applied to indoor location fingerprinting due to its simplicity and speed [29]. Wang et al [30] used the kernel ELM (KELM) for indoor positioning of robots and showed that KELM not only has high positioning accuracy but also strong real-time performance.…”

RF-KELM indoor positioning algorithm based on WiFi RSS fingerprint

“…Roos et al [24] uses Gaussian kernel function (GK) in the form of kernel density estimator for indoor positioning by finding K RPs with the maximum likelihood probability and averaging their coordinates as the estimated positioning. Extreme learning machine (ELM), a simple and fast neural network algorithm, has attracted the attention of scholars in the field of indoor positioning due to its good performance and has been widely used in the field of fingerprintbased positioning [25]. Zou et al [26] use the online sequential extreme learning machine (OSELM) algorithm for indoor positioning, which reduces the positioning error by learning the environment dynamics.…”

A Tool to Calculate the Level of Occupancy in Indoor and Outdoor Spaces Using BLE and Open Data to Be Published in Real-Time

“…Moreover, the signal strength of a wireless device may also change over time, or an indoor environment may change. Recent studies are focusing on improving location accuracy of Wi-Fi fingerprinting localization from different approaches, with self-calibration time-reversal (TR) [ 6 ], using probabilistic [ 7 ] or Extreme Learning Machine (ELM) [ 8 ]. All of these technologies have certain drawbacks that can be solved, as explained below, with Bluetooth Low Energy (BLE).…”