Toward Low-Overhead Fingerprint-Based Indoor Localization via Transfer Learning: Design, Implementation, and Evaluation

Li, Kai; Zhang, Hao; Ng, Joseph Kee‐Yin; Xia, Yusheng; Feng, Liang; Lee, Victor C. S.; Son, Sang H.

doi:10.1109/tii.2017.2750240

Cited by 81 publications

(31 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A feasible strategy is to readjust the radio map, but this requires huge human and financial resources. Another way to cope with the change in signal distribution in the time domain is transfer learning [ 17 , 18 ], which adapts the localization model trained in one time period (the source domain) to a new time period (the target domain). Transfer learning can overcome the influence of the dynamic environment on signal change.…”

Section: Introductionmentioning

confidence: 99%

Localization with Transfer Learning Based on Fine-Grained Subcarrier Information for Dynamic Indoor Environments

Yin

Yang

et al. 2021

Sensors

View full text Add to dashboard Cite

Indoor localization provides robust solutions in many applications, and Wi-Fi-based methods are considered some of the most promising means for optimizing indoor fingerprinting localization accuracy. However, Wi-Fi signals are vulnerable to environmental variations, resulting in data across different times being subjected to different distributions. To solve this problem, this paper proposes an across-time indoor localization solution based on channel state information (CSI) fingerprinting via multi-domain representations and transfer component analysis (TCA). We represent the format of CSI readings in multiple domains, extending the characterization of fine-grained information. TCA, a domain adaptation method in transfer learning, is applied to shorten the distribution distances among several CSI readings, which overcomes various CSI distribution problems at different time periods. Finally, we present a modified Bayesian model averaging approach to integrate the multi-domain outcomes and give the estimated positions. We conducted test-bed experiments in three scenarios on both personal computer (PC) and smartphone platforms in which the source and target fingerprinting data were collected across different days. The experimental results showed that our method outperforms state-of-the-art methods in localization accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Localization with Transfer Learning Based on Fine-Grained Subcarrier Information for Dynamic Indoor Environments

Yin

Yang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Transfer learning can be applied in indoor positioning in the scenario when the amount of data in the source domain is sufficient, whereas the amount of data in the target domain is small. For instance, transfer learning mechanism can be applied into fingerprint-based localization to enhance system scalability without excessive site surveys and without sacrificing accuracy when there is lack of labeled data [29]. In addition to transfer learning, DL techniques have shown great potentials in enhancing localization, in complex environment scenarios.…”

Section: A Motivation Of Using ML In Indoor Localizationmentioning

confidence: 99%

“…The advantage of the transfer learning is that this model can be applied to similar problems and get good results by making minor adjustments to a trained model. Transfer learning can be applied into fingerprint-based localization to enhance system scalability without excessive site survey [29].…”

Section: Transfer Learningmentioning

confidence: 99%

“…However, unsupervised ML fusion technique is superior since it calculates the weights in real-time without offline training [28]. Furthermore, transfer learning has been applied in fingerprint-based localization to enhance system scalability without excessive site surveys and without sacrificing accuracy when there is a lack of labeled data [29].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Machine Learning for Indoor Positioning

et al. 2020

View full text Add to dashboard Cite

Widespread proliferation of wireless coverage has enabled culmination of number of advanced location-based services (LBS). Continuous tracking of accurate physical location is the foundation of these services, which is a challenging task especially indoors. Multitude of techniques and algorithms have been proposed for indoor positioning systems (IPS's). However, accuracy, reliability, scalability and, adaptability to the environment still remain as challenges for widespread deployment. Especially, unpredictable radio propagation characteristics in vastly varying indoor environments plus access technology limitations contribute to these challenges. Machine learning (ML) approaches have been widely attempted recently to overcome these challenges with reasonable success. In this paper, we aim to provide a comprehensive survey of ML enabled localization techniques using most common wireless technologies. First, we provide a brief background on indoor localization techniques. Afterwards, we discuss various ML techniques (supervised and unsupervised) that could alleviate different challenges in indoor localization including Non-line-ofsight (NLOS) issue, device heterogeneity and environmental variations with reasonable complexity. The trade-offs among multitude of issues are discussed using numerous published results. We also discuss how the ML algorithms can be effectively used for fusing different technologies and algorithms to achieve a comprehensive IPS. In essence, this survey will serve as a reference material to acquire a detailed knowledge on recent development of machine learning for accurate indoor positioning. INDEX TERMS Indoor positioning system (IPS), location-based services (LBS), machine learning (ML), non-line-of-sight (NLOS), wireless positioning, indoor tracking.

show abstract

“…Range-based approaches use the distance estimation between reference points and a target object. However, due to signal reflections, non-line-of-sight propagation and object movement, these approaches usually suffer from either low positioning accuracy or high hardware and computational costs [ 10 ]. Fingerprinting-based solutions rely in opportunistic readings from signals that are pervasively available in the majority of environments, which lowers their implementation costs.…”

Section: Introductionmentioning

confidence: 99%

Fingerprints and Floor Plans Construction for Indoor Localisation Based on Crowdsourcing

Santos

Barandas

Leonardo

et al. 2019

Sensors

View full text Add to dashboard Cite

The demand for easily deployable indoor localisation solutions has been growing. Although several systems have been proposed, their limitations regarding the high implementation costs hinder most of them to be widely used. Fingerprinting-based IPS (Indoor Positioning Systems) depend on characteristics pervasively available in buildings. However, such systems require indoor floor plans, which might not be available, as well as environmental fingerprints, that need to be collected through human resources intensive processes. To overcome these limitations, this paper proposes an algorithm for the automatic construction of indoor maps and fingerprints, solely depending on non-annotated crowdsourced data from smartphones. Our system relies on multiple gait-model based filtering techniques for accurate movement quantification in combination with opportunistic sensing observations. After the reconstruction of users’ movement with PDR (Pedestrian Dead Reckoning) techniques, Wi-Fi measurements are clustered to partition the trajectories into segments. Similar segments, which belong to the same cluster, are identified using an adaptive approach based on a geomagnetic field distance. Finally, the floor plans are obtained through a data fusion process. Merging the acquired environmental data using the obtained floor plan, fingerprints are aligned to physical locations. Experimental results show that the proposed solution achieved comparable floor plans and fingerprints to those acquired manually, allowing the conclusion that is possible to automate the setup process of infrastructure-free IPS.

show abstract

Toward Low-Overhead Fingerprint-Based Indoor Localization via Transfer Learning: Design, Implementation, and Evaluation

Cited by 81 publications

References 27 publications

Localization with Transfer Learning Based on Fine-Grained Subcarrier Information for Dynamic Indoor Environments

Localization with Transfer Learning Based on Fine-Grained Subcarrier Information for Dynamic Indoor Environments

A Survey of Machine Learning for Indoor Positioning

Fingerprints and Floor Plans Construction for Indoor Localisation Based on Crowdsourcing

Contact Info

Product

Resources

About