AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
We proposed an approach to encode the extracted knowledge to propagate label information from one area to another area, which is formalized as a new optimization problem

Transferring localization models across space

national conference on artificial intelligence, pp.1383-1388, (2009)

Cited: 62|Views62
EI
Full Text
Bibtex
Weibo

Abstract

Machine learning approaches to indoor WiFi localization involve an offline phase and an online phase. In the offline phase, data are collected from an environment to build a localization model, which will be applied to new data collected in the online phase for location estimation. However, collecting the labeled data across an entire bui...More

Code:

Data:

0
Introduction
  • Many location based applications rely on the ability to accurately locate a mobile device in an indoor environment.
  • In order to collect the RSS training data, the authors have to carry a mobile device and walk around in a building to record values of signal strength at various locations.
  • This process is very expensive, especially when the indoor building is large.
Highlights
  • Many location based applications rely on our ability to accurately locate a mobile device in an indoor environment
  • Note that our goal is to derive knowledge of the Access Points’ locations from the labeled data collected in area A, the notations used in the optimization problem in (1) are consistent with those related to Sa given in the Problem Statement section
  • The laptop is equipped with an Intel c Pro/3945ABG internal wireless card and installed with a software to record values of WiFi signal strength every 0.5 seconds
  • We have presented a novel solution to transferring the learned model from one spatial area to another for indoor WiFi localization
  • We developed a manifold learning based approach to discover the hidden structure and knowledge in terms of Access Points’ location information
  • With the help of the transferred knowledge, we can significantly reduce the amount of labeled data which are required for building the localization model
  • We proposed an approach to encode the extracted knowledge to propagate label information from one area to another area, which is formalized as a new optimization problem
Results
  • The authors verify the proposed solution in a real indoor 802.11 WiFi environment.
  • The experimental results demonstrate that the proposed solution is quite effective in exploiting the data collected in an area so as to reduce the calibration efforts for training a localization mapping function for the whole indoor environment.
  • The authors collected the first data set with a total of 665 examples in area A.
  • Star are always fully labeled while a lot of labels of Stbr are hidden.
Conclusion
  • The authors have presented a novel solution to transferring the learned model from one spatial area to another for indoor WiFi localization.
  • The authors developed a manifold learning based approach to discover the hidden structure and knowledge in terms of APs’ location information.
  • The authors proposed an approach to encode the extracted knowledge to propagate label information from one area to another area, which is formalized as a new optimization problem.
  • The authors wish to develop an online solution for the problem
Tables
  • Table1: Comparing the Average Error Distance (unit:m) of different solutions in Area A and Area B. A value outside a parenthesis represents average error distance and a value inside a parenthesis represents standard deviation of three round results (the number of labeled data in the area B is 5)
Download tables as Excel
Funding
  • We thank the support of a research grant from NEC-China under project #: NECLC05/06.EG01
Reference
  • Bahl, P.; Balachandran, A.; and Padmanabhan, V. 2000. Enhancements to the RADAR user location and tracking system. Technical report, Microsoft Research.
    Google ScholarFindings
  • Belkin, M.; Niyogi, P.; and Sindhwani, V. 2006. Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. Journal of Machine Learning Research 7:2399–2434.
    Google ScholarLocate open access versionFindings
  • Boyd, S., and Vandenberghe, L. 2004. Convex Optimization. Cambridge University Press.
    Google ScholarFindings
  • Caruana, R. 1997. Multitask learning. Machine Learning 28(1):41–75.
    Google ScholarLocate open access versionFindings
  • Ferris, B.; Fox, D.; and Lawrence, N. 2007. WiFi-SLAM using gaussian process latent variable models. In Proceedings of the 20th International Joint Conference on Artificial Intelligence, 2480–2485.
    Google ScholarLocate open access versionFindings
  • Ferris, B.; Hahnel, D.; and Fox, D. 200Gaussian processes for signal strength-based location estimation. In Robotics: Science and Systems II.
    Google ScholarLocate open access versionFindings
  • Ham, J.; Lee, D.; and Saul, L. 2005. Semisupervised alignment of manifolds. In Proceedings of the International Workshop on Artificial Intelligence and Statistics.
    Google ScholarLocate open access versionFindings
  • Hendrichson, B. 2006. Latent semantic analysis and fiedler embeddings. In Proceedings of the Fourth Workshop on Text Mining of the Sixth SIAM International Conference on Data Mining.
    Google ScholarLocate open access versionFindings
  • Lanckriet, G. R. G.; Cristianini, N.; Bartlett, P. L.; Ghaoui, L. E.; and Jordan, M. I. 2004. Learning the kernel matrix with semidefinite programming. Journal of Machine Learning Research 5:27–72.
    Google ScholarLocate open access versionFindings
  • Letchner, J.; Fox, D.; and LaMarca, A. 2005. Large-scale localization from wireless signal strength. In Proceedings of the 20th National Conference on Artificial Intelligence, 15–20.
    Google ScholarLocate open access versionFindings
  • Nguyen, X.; Jordan, M. I.; and Sinopoli, B. 2005. A kernelbased learning approach to ad hoc sensor network localization. ACM Transactions on Sensor Networks 1(1):134–152.
    Google ScholarLocate open access versionFindings
  • Pan, J. J., and Yang, Q. 2007. Co-localization from labeled and unlabeled data using graph laplacian. In Proceedings of the 20th International Joint Conference on Artificial Intelligence, 2166–2171.
    Google ScholarLocate open access versionFindings
  • Sturm, J. F. 1999. Using SeDuMi 1.02, a MATLAB toolbox for optimization over symmetric cones. Optimization Methods Software 11/12(1-4):625–653.
    Google ScholarLocate open access versionFindings
  • Zhu, X.; Ghahramani, Z.; and Lafferty, J. D. 2003. Semisupervised learning using gaussian fields and harmonic functions. In Proceeding of The 22th International Conference on Machine Learning, 912–919.
    Google ScholarLocate open access versionFindings
0
Your rating :

No Ratings

Tags
Comments
avatar
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn