Deep CNN for Indoor Localization in IoT-Sensor Systems

Njima, Wafa; Ahriz, Iness; Zayani, Rafik; Terré, Michel; Bouallègue, Ridha

doi:10.3390/s19143127

Cited by 52 publications

(31 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the MAN 2 dataset, the fingerprints from the original dataset have been averaged in 10 blocks of 10 fingerprints for the training and evaluation sets to have one dataset with averaged RSS and fingerprints. We include an artificial dataset, SIM, based on simple the path-loss model with additive Gaussian noise (eq.1) as done in [62,76,77,78].…”

Section: Description Of Data Setsmentioning

confidence: 99%

A Comprehensive and Reproducible Comparison of Clustering and Optimization Rules in Wi-Fi Fingerprinting

Torres-Sospedra

Richter

Moreira

et al. 2022

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

Wi-Fi fingerprinting is a well-known technique used for indoor positioning. It relies on a pattern recognition method that compares the captured operational fingerprint with a set of previously collected reference samples (radio map) using a similarity function. The matching algorithms suffer from a scalability problem in large deployments with a huge density of fingerprints, where the number of reference samples in the radio map is prohibitively large. This paper presents a comprehensive comparative study of existing methods to reduce the complexity and size of the radio map used at the operational stage. Our empirical results show that most of the methods reduce the computational burden at the expense of a degraded accuracy. Among the studied methods, only k-means, affinity propagation, and the rules based on the strongest access point properly balance the positioning accuracy and computational time. In addition to the comparative results, this paper also introduces a new evaluation framework with multiple datasets, aiming at getting more general results and contributing to a better reproducibility of new proposed solutions in the future.

show abstract

Section: Description Of Data Setsmentioning

confidence: 99%

A Comprehensive and Reproducible Comparison of Clustering and Optimization Rules in Wi-Fi Fingerprinting

Torres-Sospedra

Richter

Moreira

et al. 2022

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

show abstract

“…Area classification : Whereas [ 48 ] Liu et al estimated the probability over predefined areas, Laska et al [ 18 ] proposed a framework for adaptive indoor area localization using deep learning to classify the correct segment of a set of predefined segments. Njima et al [ 49 ] constructed 3D input images that consist of the RSS data and the kurtosis values derived from the RSS data. Those are fed to a CNN that predicts the correct area/region of a pre-segmented floor plan.…”

Section: Related Workmentioning

confidence: 99%

DeepLocBox: Reliable Fingerprinting-Based Indoor Area Localization

Laska

Blankenbach

2021

Sensors

View full text Add to dashboard Cite

Location-based services (LBS) have gained increasing importance in our everyday lives and serve as the foundation for many smartphone applications. Whereas Global Navigation Satellite Systems (GNSS) enable reliable position estimation outdoors, there does not exist any comparable gold standard for indoor localization yet. Wireless local area network (WLAN) fingerprinting is still a promising and widely adopted approach to indoor localization, since it does not rely on preinstalled hardware but uses the existing WLAN infrastructure typically present in buildings. The accuracy of the method is, however, limited due to unstable fingerprints, etc. Deep learning has recently gained attention in the field of indoor localization and is also utilized to increase the performance of fingerprinting-based approaches. Current solutions can be grouped into models that either estimate the exact position of the user (regression) or classify the area (pre-segmented floor plan) or a reference location. We propose a model, DeepLocBox (DLB), that offers reliable area localization in multi-building/multi-floor environments without the prerequisite of a pre-segmented floor plan. Instead, the model predicts a bounding box that contains the user’s position while minimizing the required prediction space (size of the box). We compare the performance of DLB with the standard approach of neural network-based position estimation and demonstrate that DLB achieves a gain in success probability by 9.48% on a self-collected dataset at RWTH Aachen University, Germany; by 5.48% for a dataset provided by Tampere University of Technology (TUT), Finland; and by 3.71% for the UJIIndoorLoc dataset collected at Jaume I University (UJI) campus, Spain.

show abstract

“…Currently, most adaptation approaches of FCMs belong to the group of evolutionary computing, for example, [29,47]. However, there are also approaches based on deep learning [48], or on the use of special fuzzy rule sets for each connection individually [49]. There are also other possible alternative approaches to FCMs in the area of navigation as for example, fuzzy state automata described in [50], where such a fuzzy state automaton interconnects several conventional fuzzy controllers.…”

Section: Related Workmentioning

confidence: 99%

Means of IoT and Fuzzy Cognitive Maps in Reactive Navigation of Ubiquitous Robots

et al. 2021

View full text Add to dashboard Cite

Development of accessible and cheap sensors as well as the possibility to transfer and process huge amounts of data offer new possibilities for many areas utilizing till now conventional approaches. Navigation of robots and autonomous vehicles is no exception in this aspect and Internet of Things (IoT), together with the means of computational intelligence, represents a new way for construction and use of robots. In this paper, the possibility to move sensors from robots to their surroundings with the help of IoT is presented and the modification of the IoT concept in the form of intelligent space as well as the concept of ubiquitous robot are shown in the paper. On an example of route tracking, we will clarify the potential of distributed networked sensors and processing their data with the use of fuzzy cognitive maps for robotic navigation. Besides, two modifications of adaptation approaches, namely particle swarm optimization and migration algorithm, are presented here. A series of simulations was performed, which are discussed and future research directions are proposed.

show abstract

Deep CNN for Indoor Localization in IoT-Sensor Systems

Cited by 52 publications

References 51 publications

A Comprehensive and Reproducible Comparison of Clustering and Optimization Rules in Wi-Fi Fingerprinting

A Comprehensive and Reproducible Comparison of Clustering and Optimization Rules in Wi-Fi Fingerprinting

DeepLocBox: Reliable Fingerprinting-Based Indoor Area Localization

Means of IoT and Fuzzy Cognitive Maps in Reactive Navigation of Ubiquitous Robots

Contact Info

Product

Resources

About