Indoor smartphone localization via fingerprint crowdsourcing: challenges and approaches

Wang, Bang; Chen, Qiuyun; Yang, Laurence T.; Chao, Han‐Chieh

doi:10.1109/mwc.2016.7498078

Cited by 156 publications

(63 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reasons behind such contradiction include: (1) reporting the accuracy as mean positioning error distance; (2) testing the IPS in specific (probably controlled) environments; and (3) testing the IPS without considering temporal signals changes. The previous challenges have been addressed, e.g., by: (1) providing other metrics such as 75 percentile instead of the mean [8]; (2) providing databases [9,10]; and (3) periodically updating the IPS training data [11][12][13] or making the positioning method adaptable to signal changes [14,15]. Methods able to cope with temporal signal variation, such as those in Gu et al [14], Hayashi et al [15], are tested with measurements that allow the analysis of short-term signal variations occurred at known positions (e.g., seconds or minutes apart, caused by network devices dynamic behavior, network usage, and people movement) and also the analysis of long-term signal variations (e.g., days or months apart, caused by changes in network devices' configuration or environment' structure).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Long-Term WiFi Fingerprinting Dataset for Research on Robust Indoor Positioning

Mendoza-Silva

Richter

Torres-Sospedra

et al. 2018

Data

133

View full text Add to dashboard Cite

Abstract:WiFi fingerprinting, one of the most popular methods employed in indoor positioning, currently faces two major problems: lack of robustness to short and long time signal changes and difficult reproducibility of new methods presented in the relevant literature. This paper presents a WiFi RSS (Received Signal Strength) database created to foster and ease research works that address the above-mentioned two problems. A trained professional took several consecutive fingerprints while standing at specific positions and facing specific directions. The consecutive fingerprints may enable the study of short-term signals variations. The data collection spanned over 15 months, and, for each month, one type of training datasets and five types of test datasets were collected. The measurements of a dataset type (training or test) were taken at the same positions and directions every month, in order to enable the analysis of long-term signal variations. The database is provided with supporting materials and software, which give more information about the collection environment and eases the database utilization, respectively. The WiFi measurements and the supporting materials are available at the Zenodo repository under the open-source MIT license.

show abstract

Section: Introductionmentioning

confidence: 99%

“…However, they have a well-known challenge: labels quality [13]. A professional collection approach can provide reliable measurements to discover insights into short-and long-term signals variability that could otherwise be untrustworthy.…”

Section: Introductionmentioning

confidence: 99%

Long-Term WiFi Fingerprinting Dataset for Research on Robust Indoor Positioning

Mendoza-Silva

Richter

Torres-Sospedra

et al. 2018

Data

133

View full text Add to dashboard Cite

show abstract

“…Among the approaches for deploying location-based services, Relative Signal Strength (RSS) fingerprinting is one of the most promising approaches. However, there are some challenges that need to be considered in the deployment of such approach including fingerprint annotation and device diversity [26]. The use of fingerprint-based approaches to identify an indoor position has been studied well in the past decade.…”

Section: B Review Of Indoor Localizationmentioning

confidence: 99%

Semisupervised Deep Reinforcement Learning in Support of IoT and Smart City Services

Mohammadi

Al-Fuqaha

Guizani

et al. 2018

IEEE Internet Things J.

352

143

View full text Add to dashboard Cite

Smart services are an important element of the smart cities and the Internet of Things (IoT) ecosystems where the intelligence behind the services is obtained and improved through the sensory data. Providing a large amount of training data is not always feasible; therefore, we need to consider alternative ways that incorporate unlabeled data as well. In recent years, Deep reinforcement learning (DRL) has gained great success in several application domains. It is an applicable method for IoT and smart city scenarios where auto-generated data can be partially labeled by users' feedback for training purposes.In this paper, we propose a semi-supervised deep reinforcement learning model that fits smart city applications as it consumes both labeled and unlabeled data to improve the performance and accuracy of the learning agent. The model utilizes Variational Autoencoders (VAE) as the inference engine for generalizing optimal policies. To the best of our knowledge, the proposed model is the first investigation that extends deep reinforcement learning to the semi-supervised paradigm. As a case study of smart city applications, we focus on smart buildings and apply the proposed model to the problem of indoor localization based on BLE signal strength. Indoor localization is the main component of smart city services since people spend significant time in indoor environments. Our model learns the best action policies that lead to a close estimation of the target locations with an improvement of 23% in terms of distance to the target and at least 67% more received rewards compared to the supervised DRL model.

show abstract

“…The SSFM-based localization method is an attractive topic in wireless indoor localization [25,26,27,28,29]. Chang et al [25] integrated Pedestrian Dead Reckoning (PDR) with WiFi fingerprinting to provide an accurate positioning algorithm.…”

Section: Related Workmentioning

confidence: 99%

“…Wang et al proposed some effective fingerprinting-based indoor location methods, such as the surface fitting technique-based indoor localization method [27] and the Curve Fitting (CF) and location search-based indoor localization scheme [28]. For reducing the computation complexity during the localization process, Wang et al [29] proposed a new indoor subarea localization scheme via fingerprint crowdsourcing, clustering and matching, which first constructs subarea fingerprints from crowdsourced RSS measurements and relates them to indoor layouts. Since this localization method does not need any additional hardware, it is a low-cost and easily executed localization technology.…”

Section: Related Workmentioning

confidence: 99%

RSS Fingerprint Based Indoor Localization Using Sparse Representation with Spatio-Temporal Constraint

Piao

Zhang

et al. 2016

Sensors

View full text Add to dashboard Cite

The Received Signal Strength (RSS) fingerprint-based indoor localization is an important research topic in wireless network communications. Most current RSS fingerprint-based indoor localization methods do not explore and utilize the spatial or temporal correlation existing in fingerprint data and measurement data, which is helpful for improving localization accuracy. In this paper, we propose an RSS fingerprint-based indoor localization method by integrating the spatio-temporal constraints into the sparse representation model. The proposed model utilizes the inherent spatial correlation of fingerprint data in the fingerprint matching and uses the temporal continuity of the RSS measurement data in the localization phase. Experiments on the simulated data and the localization tests in the real scenes show that the proposed method improves the localization accuracy and stability effectively compared with state-of-the-art indoor localization methods.

show abstract

Indoor smartphone localization via fingerprint crowdsourcing: challenges and approaches

Cited by 156 publications

References 15 publications

Long-Term WiFi Fingerprinting Dataset for Research on Robust Indoor Positioning

Long-Term WiFi Fingerprinting Dataset for Research on Robust Indoor Positioning

Semisupervised Deep Reinforcement Learning in Support of IoT and Smart City Services

RSS Fingerprint Based Indoor Localization Using Sparse Representation with Spatio-Temporal Constraint

Contact Info

Product

Resources

About