Characteristics of crowdsourcing for outdoor radio fingerprinting positioning

Leca, Cristian L.; Ciotîrnae, Petrică; Rincu, Cristian Iulian; Nicolaescu, Ioan

doi:10.1109/ecai.2017.8166385

Cited by 4 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li [14] approach of handling outliers was to characterize the crowdsourced datasets into spatial, localization algorithm and combined RSS with spatial. These are illustrated in Fig 2. Similar issues on outlier variances were faced by studies to predict outdoor base station positions [2,4,26] and WiFi positions [3,13]. The common methods used to discard outliers are dependent on the algorithm used.…”

Section: Outliersmentioning

confidence: 93%

“…The study concluded that as long as these errors are not corrected the accuracy of prediction is affected hence requiring margins to be introduced. A study on location based services using TOA to calculate the location of a target mobile using nonlinear least squares indicated that prediction accuracy decreases when the number of base station is larger than five [3]. Similar studies using TDoA and AOA to locate a point source in a three dimensional space indicated that a hybrid method increases prediction accuracy.…”

Section: Fig 5: Voronoi Diagram [23]mentioning

confidence: 97%

“…Leca [3] studied characteristics of outdoor radio fingerprinting positioning using WiFi crowdsourcing data. The research found that fading influence caused by the environment results in high variances over 6dB for RSS values below -80dBm while better RSS values have standard deviation below 5dB.…”

Section: Scene Analysis and Fingerprintingmentioning

confidence: 99%

“…There are thousands of these base stations deployed worldwide however these are well kept secret by the MNOs (Mobile Network Operator) as these are used for mobile radio planning to create competitive advantage [1,2]. Official public databases containing positions of these cellular base stations are generally non-existent and their accuracy has been the subject of several studies [2][3][4][5]. Therefore, this study shall focus on improving the inaccuracy of geo-positioning localization of signal source derived from mobile crowdsourcing data.…”

Section: Introductionmentioning

confidence: 99%

“…Other issues such as accuracy of user equipment and errors generated by these volunteers are to be noted. Accordingly, studies done with crowdsourcing does show inaccuracies related to prediction of the intended position whether mobile device or cell site location for both indoor and outdoor environment [2][3][4][5]8]. Nevertheless, crowdsourcing is a good alternative to traditional method such as wardriving and warwalking, which requires lots of time, cost and effort.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Weighted-Range Classification Model for Localizing Cell using Crowdsource Data

2019

IJRTE

View full text Add to dashboard Cite

The vast amount of mobile smartphone users provides an infinite source of data for crowdsourcing. Crowdsourcing provides an economical method of gathering data to cover a large geographical area compared to traditional methods. However, the inaccurate predictions for base station localization derived from mobile crowdsourcing impacts its effectiveness for use in radio planning. Therefore, the purpose of this study is to design a model that can yield a more accurate localization through the introduction of a rule-based weighted classification. The methodology deployed is a permutation series based on fingerprint of the cell site with weightage derived from rule-based classification. DeLaunay triangulation and Voronoi diagrams are used to determine the positions of the existing base stations and the prediction of new site location respectively. The expected results are better accuracy of the classification model in the localization prediction of the base station leading to a more accurate prediction of new site location.

show abstract