Experimental Study of Telco Localization Methods

Huang, Yukun; Rao, Weixiong; Zhu, Fangzhou; Liu, Ning; Yuan, Mingxuan; Zeng, Jia; Yang, Hua

doi:10.1109/mdm.2017.48

Cited by 11 publications

(23 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the up-to 7 base stations, one of them is selected as the primary serving base station to provide communication and data transmission services for the mobile device. Previous work on Telco localization [12], [37] might ignore the use of serving base station. Unlike these works, we will carefully exploit serving base stations as the base of TLoc.…”

Section: Background and Related Workmentioning

confidence: 99%

“…Suppose that we are using a RaF regression model to recover the outdoor locations L(s) and L(s ) for the samples s and s , respectively. The outdoor locations are frequently represented by GPS coordinates [12], [19], [23], [37]. Given the two distributed domains D = D , the MR samples s and s within the two domains indicate that the corresponding RNC/CellID and GPS positions are different, indicating s = s and L(s) = L(s ).…”

Section: System Design a General Ideamentioning

confidence: 99%

“…Among the divided domains, due to the uneven distribution of geo-tagged MR samples, some of the domains could be with sufficient samples, and a regression-based position recovery model thus works very well. Yet other domains may contain scarce geo-tagged MR samples, the trained position recovery model usually suffers from poor localization accuracy [12].…”

Section: System Overviewmentioning

confidence: 99%

“…Since Non-Transfer, MTL, and TLoc are all RaFbased approaches, we follow the previous works including a benchmark [12] and Non-transferr [37] to carefully tune the following parameters of RaFs: 1) the number of trees is set to 200 (to achieve a good trade-off between accuracy and time cost), 2) the number of used features when looking for the best split is set to √ n f (e.g., n f = 44 is the number of total features in 2G GSM MR datasets), and 3) nodes are expanded until all leaves are pure. Following the work [12], we adopt the following criteria to empirically determine whether or not a certain domain is treated as a target one. A domain is considered as a target domain, if 1) the median error of this domain is greater than 30 meters for 4G LTE data or 40 meters for 2G GSM data, and 2) the number of training samples within this domain is smaller than a threshold, τ = 50.…”

Section: A Datasets and Counterpartsmentioning

confidence: 99%

“…• To the best of our knowledge, TLoc is the first method to plausibly leverage transfer learning for Telco outdoor localization. Unlike the fingerprinting-based and machine learning-based approaches [12], [16], [37], TLoc mitigates high efforts to collect a large quantity of training samples across an entire area. Moreover, our evaluation empirically verifies that the idea of TLoc can generally benefit other approaches (e.g., fingerprinting-based approaches) to achieve better precision by re-using MR samples from source domains to target ones.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Transfer Learning-Based Outdoor Position Recovery With Cellular Data

Zhang

Ding

Ott

et al. 2021

IEEE Trans. on Mobile Comput.

Self Cite

View full text Add to dashboard Cite

Telecommunication (Telco) outdoor position recovery aims to localize outdoor mobile devices by leveraging measurement report (MR) data. Unfortunately, Telco position recovery requires sufficient amount of MR samples across different areas and suffers from high data collection cost. For an area with scarce MR samples, it is hard to achieve good accuracy. In this paper, by leveraging the recently developed transfer learning techniques, we design a novel Telco position recovery framework, called TLoc, to transfer good models in the carefully selected source domains (those fine-grained small subareas) to a target one which originally suffers from poor localization accuracy. Specifically, TLoc introduces three dedicated components: 1) a new coordinate space to divide an area of interest into smaller domains, 2) a similarity measurement to select best source domains, and 3) an adaptation of an existing transfer learning approach. To the best of our knowledge, TLoc is the first framework that demonstrates the efficacy of applying transfer learning in the Telco outdoor position recovery. To exemplify, on the 2G GSM and 4G LTE MR datasets in Shanghai, TLoc outperforms a nontransfer approach by 27.58% and 26.12% less median errors, and further leads to 47.77% and 49.22% less median errors than a recent fingerprinting approach NBL.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Section: System Design a General Ideamentioning

confidence: 99%

Section: System Overviewmentioning

confidence: 99%

Section: A Datasets and Counterpartsmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Transfer Learning-Based Outdoor Position Recovery With Cellular Data

Zhang

Ding

Ott

et al. 2021

IEEE Trans. on Mobile Comput.

Self Cite

View full text Add to dashboard Cite

show abstract

BSLoc: Base Station ID-Based Telco Outdoor Localization

Zhao

et al. 2019

Algorithms for Sensor Systems

View full text Add to dashboard Cite

DeepFeat: Robust Large-Scale Multi-Features Outdoor Localization in LTE Networks Using Deep Learning

Tharwat²,

Magdy³

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Location-based services in different applications push the research toward outdoor localization for users' equipment in Long Term Evolution (LTE) networks. Telecom operators can introduce valuable services to users based on their location, both in emergency and ordinary situations. This paper introduces DeepFeat: A deep-learning-based framework for outdoor localization using a rich feature set in LTE networks. DeepFeat works on the mobile operator side, and it leverages many mobile network features and other metrics to achieve high localization accuracy. In order to reduce computation and complexity, we introduce a feature selection module to choose the most appropriate features as inputs to the deep learning model. This module reduces the computation and complexity by around 20.6%, with enhancement in system accuracy. The feature selection module uses correlation and Chi-squared algorithms to reduce the feature set to 12 inputs only regardless of the area size, compared to a large number of cell towers in similar systems; such input increases exponentially with increasing the test area. In order to enhance the accuracy of DeepFeat, a One-to-Many augmenter is introduced to extend the dataset and improve the system's overall performance. The results show the impact of the proper features selection adopted by DeepFeat on the system performance. DeepFeat achieved median localization accuracy of 13.179m in an outdoor environment in a mid-scale area of 6.27Km 2 . In a large-scale area of 45Km 2 , the median localization accuracy is 13.7m. DeepFeat was compared to other state-of-the-art deep-learningbased localization systems that leverage a small number of features. We show that using the DeepFeat carefully selected feature set enhances the localization accuracy compared to the state-of-the-art systems by at least 286%.

show abstract

Experimental Study of Telco Localization Methods

Cited by 11 publications

References 17 publications

Transfer Learning-Based Outdoor Position Recovery With Cellular Data

Transfer Learning-Based Outdoor Position Recovery With Cellular Data

BSLoc: Base Station ID-Based Telco Outdoor Localization

DeepFeat: Robust Large-Scale Multi-Features Outdoor Localization in LTE Networks Using Deep Learning

Contact Info

Product

Resources

About