| Human-Computer Interaction and Pervasive Computing |
|
|
|
|
| Fusion feature based semi-supervised manifold localization method |
HUANG Zheng-yu, JIANG Xin-long, LIU Jun-fa, CHEN Yi-qiang, GU Yang |
1. College of Information Engineering, Xiangtan University, Xiangtan 411105, China;
2. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China;
3. Beijing Key Laboratory of Mobile Computing and Pervasive Device, Beijing 100190, China;
4. University of Chinese Academy of Sciences, Beijing 100190, China |
|
|
|
Abstract
Wi-Fi and Bluetooth Low Energy based single mode localization methods cannot get satisfactory performance on localization accuracy, robustness and universality. In the training phase, a large amount of calibrated data is required to train a model. A semi-supervised localization method was proposed based on fusing features of Wi-Fi and Bluetooth low energy signals in order to solve these problems. Wi-Fi and Bluetooth Low Energy based localization methods were effectively used, and semi-supervised manifold was employed to import a vast amount of uncalibrated data for model training. Experimental results show that the proposed fusion feature can increase the indoor localization accuracy by more than 20% as well as improving robustness compared with single feature. The semisupervised manifold localization method can dramatically reduce labeled calibration samples by 90%．
|
|
Published: 25 April 2017
|
|
|
|
Cite this article:
HUANG Zheng-yu, JIANG Xin-long, LIU Jun-fa, CHEN Yi-qiang, GU Yang. Fusion feature based semi-supervised manifold localization method. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(4): 655-662.
|
基于融合特征的半监督流形约束定位方法
针对Wi-Fi和低功耗蓝牙单模定位方法在精度、稳定性和普适性上难以满足需求以及现有定位方法须采集大量标定数据这些问题,设计实现了将Wi-Fi和低功耗蓝牙信号进行融合的半监督定位方法,有效利用了Wi-Fi和低功耗蓝牙信号的定位优势,采用半监督流形约束来引入非标定数据进行模型训练.实验表明,与单一特征相比,提出的融合特征在提升了鲁棒性的同时,定位精度提高了20%以上；采用引入的半监督流形约束定位方法,能够使标定训练数据减少90%．
|
|
| ［1］ HONKAVIRTA V, PERL T, ALILYTTY S, et al. A comparative survey of WLAN location fingerprinting methods ［C］∥ 6th Workshop on Positioning, Navigation and Communication. Hannover: IEEE, 2009:243-251.
［2］ NEWMAN N. Apple ibeacon technology briefing ［J］. Journal of Direct, Data and Digital Marketing Practice, 2014, 15(3): 222-225.
［3］ CHEN Z Y. Mining individual behavior pattern based on significant locations and spatial trajectories［C］∥ 2012 IEEE International Conference on Pervasive Computing and Communications Workshops. Lugano: IEEE, 2012: 540-541.
［4］ CHEN Z Y, WANG S Q, CHEN Y Q, et al. InferLoc: calibration free based location inference for temporal and spatial finegranularity magnitude ［C］∥ 2012 IEEE 15th International Conference on Computational Science and Engineering. Lugano: IEEE, 2012: 453-460.
［5］ CHEN Z Y, CHEN Y Q, WANG S Q, et al. A supervised learning based semantic location extraction method using mobile phone data ［C］∥2012 IEEE International Conference on Computer Science and Automation Engineering. Zhangjiajie: IEEE, 2012: 548-551.
［6］ CHEN Z Y, ZHOU J Y, CHEN Y Q, et al. Combing multiple linear regression and manifold regularization for indoor positioning from unique radio signal ［C］∥ 2009 Joint Conferences on Pervasive Computing. Taibei: IEEE, 2009: 611-614.
［7］ CHEN Z Y, CHEN Y Q, GAO X Y, et al. Unobtrusive sensing incremental social contexts using fuzzy class incremental learning ［C］∥ 2015 IEEE International Conference on Data Mining. Atlantic City: IEEE, 2015: 71-80.
［8］ CHEN Z Y, CHEN Y Q, HU L S, et al. ContextSense: unobtrusive discovery of incremental social context using dynamic bluetooth data ［C］∥Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Seattle: ACM, 2014:23-26.
［9］ CHEN Z Y, CHEN Y Q, WANG S Q, et al. Inferring social contextual behavior from bluetooth traces ［C］∥Proceedings of the 2013 ACM Conference on Pervasive and Ubiquitous Computing Adjunct Publication. Zurich: ACM, 2013: 267-270.
［10］ TORTEEKA P, CHUNDI X I U. Indoor positioning based on Wi-Fi fingerprint technique using fuzzy knearest neighbor ［C］∥ 2014 11th International Bhurban Conference on IEEE Applied Sciences and Technology. Islamabad: IEEE, 2014: 461-465.
［11］ MA R, GUO Q, HU C, et al. An improved WiFi indoor positioning algorithm by weighted fusion ［J］. Sensors, 2015, 15(9): 21824-21843.
［12］ ZHU J Y, LUO H Y, CHEN Z L, et al. RSSI based Bluetooth low energy indoor positioning ［C］∥ 2014 International Conference on IEEE Indoor Positioning and Indoor Navigation. Busan: IEEE, 2014: 526-533.
［13］ FARAGHER R, HARLE R. Location fingerprinting with bluetooth low energy BLEs ［J］. IEEE Journal on Selected Area in Communications, 2015, 33(11):2418-2428.
［14］ GAO X Y, CHEN Z Y, TANG S, et al. Adaptive weighted imbalance learning with application to abnormal activity recognition ［J］. Neurocomputing, 2016, 173: 1927-1935.
［15］ GAO X Y, HOI S C H, ZHANG Y D, et al. SOML: sparse online metric learning with application to image retrieval ［C］∥AAAI. Quebec City: ［s. n.］, 2014: 1206-1212.
［16］ ZHAO Z T, CHEN Z Y, CHEN Y Q, et al. A class incremental extreme learning machine for activity recognition ［J］. Cognitive Computation, 2014, 6(3):423-431.
［17］ CHEN Y, CHEN R, PEI L, et al. Knowledge-based error detection and correction method of a multi-sensor multi-network positioning platform for pedestrian indoor navigation ［C］∥ 2010 IEEE/ION Position Location and Navigation Symposium. Indian Wells: IEEE, 2010: 873-879.
［18］ RADU V, LI J, KRIARA L, et al. Poster: a hybrid approach for indoor mobile phone localization ［C］∥ International Conference on Mobile Systems, Applications, and Services. Low Wood Bay: ACM, 2012:527-528.
［19］ ZHUANG Y, WANG K, WANG W, et al. A hybrid sensing approach to mobile robot localization in complex indoor environments ［J］. International Journal of Robotics and Automation, 2012, 27(2): 198-205.
［20］ COLOMBO A, FONTANELLI D, MACII D, et al. Flexible indoor localization and tracking based on a wearable platform and sensor data fusion ［J］. IEEE Transactions on Instrumentation and Measurement, 2014, 63(4): 864-876.
［21］ AYLLON D, SANCHEZHEVIA H, GIL-PITA R, et al. Indoor blind localization of smartphones by means of sensor data fusion ［C］∥ Sensors Applications Symposium. Zadar: IEEE, 2015.
［22］ 王睿,赵方,彭金华,等.基于WI-FI和蓝牙融合的室内定位算法［J］.计算机研究与发展,2011(增2): 2833.WANG Rui, ZHAO Fang, PENG Jin-hua, et al. Combination of WI-FI and bluetooth for indoor localization ［J］. Journal of Computer Research and Development, 2011 (supple.2): 28-33.
［23］ WANG D L, BROWN G J. Computational auditory scene-analysis: principles, algorithms, and applications ［M］. Piscataway: WileyIEEE, 2006.
［24］ ORFANIDIS S J. Optimum signal processing: an introduction ［M］. London: Macmillan, 1988.
［25］ HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: a new learning scheme of feedforward neural networks ［C］∥ Proceedings of 2004 IEEE International Joint Conference on Neural Networks. Budapest: IEEE, 2004: 985-990.
［26］ RAO C R, MITRA S K. Generalized inverse of matrices and its applications ［M］. New York: Wiley, 1971.
［27］ SERRE D. Matrices: theory and applications ［J］. Mathematics, 2002(32): 218-221.
［28］ LIU J, CHEN Y, LIU M, et al. SELM: semi-supervised ELM with application in sparse calibrated location estimation ［J］. Neurocomputing, 2011, 74(16):2566-2572.
［29］ CHUNG F R K. Spectral graph theory ［M］. Washington: American Mathematical Society, 1997, 9(6): 55.
［30］ BELKIN M, MATVEEVA I, NIYOGI P. Regularization and semi-supervised learning on large graphs［C］∥International Conference on Computational Learning Theory. Berlin: Springer, 2004: 624-638.
［31］ BELKIN M, NIYOGI P, SINDHWANI V. Manifold regularization: a geometric framework for learning from labeled and unlabeled examples ［J］. Journal of Machine Learning Research, 2006, 7(1): 2399-2434. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
