Xu Zheng Yang N ic hola s D Lane Zuwei Yin School of Software Tsinghua University University College London and Bell Labs 913 in Maui ID: 813402
Download The PPT/PDF document "Chenshu Wu*, Jingao" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Chenshu Wu*, Jingao Xu*, Zheng Yang*, Nicholas D. Lane^, Zuwei Yin**School of Software, Tsinghua University^University College London and Bell Labs9.13 in Maui, Hawaii
Gain Without Pain: Accurate WiFi-based Localization using Fingerprint Spatial Gradient
Slide2MotivationVarious location-based ubiquitous applications.And locating with Wi-Fi is superior in Ubiquitous: Almost everywhere installed infrastructure.Low-cost: Off-the-shelf Wi-Fi devices.Non-invasive: not required to wear/carry any special devices.2Indoor LocationNavigationMobile Tracking
Slide3Major Problems3RSS bias over timeThe RSS bias is large, usually >10dbNo matter whether the AP is strong or notSpatial ambiguity and Temporal instability
Slide4Major Problems4Fingerprint spatial ambiguityFingerprint temporal instabilityOne fingerprint might be similar to those from two or more quite distant locationsRe-collected fingerprints from same location can’t match with initially fingerprintMismatch &
Degrade the performance of original fingerprint database!
Slide5Existing Arts5Argus, Ubicomp ’15Acoustic, Mobicom ’12Followme, Mobicom ’15While achieved better accuracy, these solutions degraded the delightful ubiquity and induce additional costs
Slide6Existing Arts6Walkie-Markie, NSDI’13GIFT, TIE ’16Need a path and continuous fingerprints, can’t work when user is static!
Slide7Problem StatementAccurate localization using RSS fingerprint.Overcomes spatial ambiguity & temporal instability using only Wi-Fi signals.Without any additional system costs7
Slide8Problem Statement8Gain With PainGain Without PainHigh precisionMitigate spatial ambiguity Ease temporal instabilityInduce system costBring many restrictionsSpecial hardware
Additional information
A
new
form
Slide9Key InsightThe spatial relationships of multiple RSS fingerprints from neighbouring locations would be more robust than individual RSS fingerprints from one single location.Leverage Fingerprint Spatial Gradient9
Slide10FSG Specification10The FSG profile for defined as : : RSSI fingerprint of location : similarity of
defined as common p-norm distance
: physical distance between locations
FSG Specification11The FSG profile for defined as :
Slide12FSG AdvantagesLeverage Fingerprint Spatial GradientTemporally stable & Spatially distinctiveCertain spatial neighbouring relationships would be more stable12
Slide13System Overview13Inputs are no more than traditional fingerprintsComputed within constant time
Slide14ChallengesHow to select the nearby points set from the single location to generate the most useful FSG?How to compare the similarity between two FSG?How to locate according to a query fingerprint?14
Slide15ChallengesHow to select the nearby points set from the single location to generate the most useful FSG?How to compare the similarity between two FSG?How to locate according to a query fingerprint?15
Slide16Profiling a Reference Location16Obtaining the most stable and distinctive FSGMinimizing Local Gradient (MLG)Maximizing Global Gradient (MGG)Optimizing Spatial Stability (OptSS)
Slide17ChallengesHow to select the nearby points set from the single location to generate the most useful FSG?How to compare the similarity between two FSG?How to locate according to a query fingerprint?17
Slide18Comparing FSG18Cosine SimilarityTurning Function Distance
Discrete
Frechet
Distance(Walking
Dog
distance..)
ChallengesHow to select the nearby points set from the single location to generate the most useful FSG?How to compare the similarity between two FSG?How to locate according to a query fingerprint?19
Slide20Profiling a Query FingerprintUnknown location Q, its fingerprint and candidate location C:
Where
is location
C
’s neighboring points set
20
Slide21Profiling a Query FingerprintUnknown location Q, its fingerprint and candidate location C:
Where
is location
C
’s neighboring points set
21
Slide22Profiling a Query FingerprintUnknown location Q, its fingerprint and candidate location C:
Where
is location
C
’s neighboring points set
22
Same
location
1-m
away
2
-m
away
Slide2323Evaluations & ResultsHow much gains we can get without pains?
Slide24Experiment4 DevicesGoogle Nexus 5Google Nexus 6p*2Google Nexus 7 padHUAWEI Mate 83 Experiment areasAcademic: 23.4k samplesOffice: 27.2k samplesClassroom: 87.0k samplesExperiment measurementsEach location 60 measurements244 BaselinesHorus (Winet’08)TW-KNN (Pervasive Computing’14)KLDivGIFT (TIE’16)
Slide25Experiment25OfficeAcademicClassroom
Slide26Explore best metric26OptSS+CS achieves the highest accuracy with mean accuracy of 3.6m and 95th percentile error of 6.7m.Three profiling methodsThree FSG similarity
Slide27Performance in different areas27Average accuracy in three areas: 3.3m,4.3m,3.8mSmaller areas yields better accuracyDifferent areas
Slide28Performance comparison28Average accuracy outperforms :Horus by 18.2%GIFT by 21.7%TW-KNN by 25.0% KLDiv by 30.8%Our system can combine TW-KNN and HorusDifferent methods
Slide29Performance comparison29System latency(Average time delays for 1000 queries):ViVi: 0.33s per queryHorus: 0.28s per queryTW-KNN: 0.77s per queryGIFT: 0.84s per queryParameter StudyDifferent AP numberDifferent nearby points’ range
Slide30ConclusionA new form based on RSS fingerprintAn underlying spatial properties of nearby fingerprints More stable and distinctive than the original RSS fingerprints. Present a system ViVi to incorporate FSGGain without the pains of resorting to additional information or restrictions or vulnerable RSS model assumptions. Median accuracy outperforms 4 state-of-the-art approaches by more than 20%30
Slide3131Thanks!Q&AJingao XuTsinghua Universityxujingao13@gmail.com