A Ubiquitous and Accurate Floor Estimation System Using Deep Representational Learning

Abstract

Location-based services have undergone massive improvements over the last decade. Despite intense efforts in industry and academia, a pervasive infrastructure-free localization is still elusive. Towards making this possible, cellular-based systems have recently been proposed due to the widespread availability of the cellular networks and their support by commodity cellphones. However, these systems only consider locating the user in a 2D single floor environment, which reduces their value when used in multi-story buildings. In this paper, we propose CellRise, a deep learning-based system for floor identification in multi-story buildings using ubiquitous cellular signals. Due to the inherent challenges of leveraging the large propagation range and the overlap in the signal space between horizontal and vertical user movements, CellRise provides a novel module to generate floor-discriminative representations. These representations are then fed to a recurrent neural network that learns the sequential changes in signals to estimate the user floor level. Additionally, CellRise incorporates different modules that improve the deep model's generalization against avoiding overtraining and noise. These modules also permit CellRise to generalize to floors completely unseen during training. We have implemented and evaluated CellRise using two different buildings with a side-by-side comparison with the state-of-the-art floor estimation techniques. The results show that CellRise can accurately estimate the exact user's floor 97.7% of the time and within one floor error 100% of the time. This is better than the stateof-the-art systems by at least 17.9% in floor identification accuracy. In addition, we show that CellRise has robust performance in various challenging conditions.

A Survey of Indoor Localization Systems in Multi-Floor Environments

“…It is measured in arbitrary units, and its range is defined by the chip vendor, where its range can be 0 to 60, 0 to 100, or -100 to 0 [28]. RSS is one of the most commonly used signal metrics in indoor localization, such as in [66], [77], [78], [123]- [125].…”

“…Despite these advantages, cellular technology is not commonly used for indoor localization in multi-floor environments. The main reason is that the broad coverage of the cell towers decreases the distinguishability between floors due to the overlap of the effect of horizontal and vertical motion on the signal space [125]. This leads to low accuracy when cellular signals are exploited directly.…”

Drone-Based Water Level Detection in Flood Disasters

“…Based on the Universal Approximation Theorem [ 45 ], Neural Networks could be considered as being capable of approximating any arbitrary function, provided they were suitably complex. Due to performance benefits obtainable from its use, deep networks have been shown to define the state-of-the-art performance in many problem domains (e.g., [ 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 56 ]), in some cases even outperforming humans on the same task.…”

Στρατηγική και management (BPA) για το νέο διεθνοποιημένο και ανταγωνιστικό επιχειρηματικό περιβάλλον, με έμφαση στις επιχειρήσεις τηλεπικοινωνιών και δικτύων

“…Τα πληροφοριακά συστήματα πραγματικού χρόνου δίνουν τη δυνατότητα στα ανώτατα στελέχη να έχουν τον οργανωτικό συντονισμό, να παρακολουθούν και να ελέγχουν τις επιχειρησιακές λειτουργίες και να τις διορθώνουν, αν παρατηρηθεί απόκλιση από τη στρατηγική στόχευση και τους στρατηγικούς δείκτες απόδοσης του τηλεπικοινωνιακού οργανισμού. Τα ανώτατα και ανώτερα τηλεπικοινωνιακά στελέχη με αυτό τον τρόπο είναι διαρκώς ενημερωμένα, προκειμένου να λαμβάνουν τις βέλτιστες αποφάσεις σε πραγματικό χρόνο (Rizk et al, 2020).…”

“…Τα βασικότερα υπάρχοντα μοντέλα στρατηγικής που στηρίζονται στο έργο του Skinner (Skinner, 1969) καθώς και αυτό των Hayes και Wheelwright (Hayes & Wheelwright, 1984), αφιερώνουν λίγη μόνο προσοχή στο ζήτημα της αυτοματοποίησης, ενώ νεότερα μοντέλα, όπως αυτό του Rizk et al (2020), ουσιαστικά δημιουργούν παραλλαγές μοντέλων που μπορούν να επηρεάσουν τη λειτουργία μιας επιχείρησης. Επίσης, τα αρχικά μοντέλα τείνουν να την παρουσιάζουν ως μια απόφαση η οποία σχετίζεται μονάχα με την τεχνολογία πα ρα γωγής.…”