广东工业大学学报 ›› 2017, Vol. 34 ›› Issue (05): 15-21.doi: 10.12052/gdutxb.170080

• 综合研究 • 上一篇    下一篇

一种基于深度自编码器的指纹匹配定位方法

刘震宇, 李嘉俊, 王昆   

  1. 广东工业大学 信息工程学院, 广东 广州 510006
  • 收稿日期:2017-04-06 出版日期:2017-09-09 发布日期:2017-07-10
  • 通信作者: 李嘉俊(1992-),男,硕士研究生,主要研究方向为室内定位技术.E-mail:jia_jun_li@foxmail.com E-mail:jia_jun_li@foxmail.com
  • 作者简介:刘震宇(1976-),男,副研究员,博士,主要研究方向为物联网技术、室内定位技术、数字信号处理和通信网安全.E-mail:zhenyuliu@gdut.edu.cn
  • 基金资助:
    国家自然科学基金青年科学基金资助项目（61401106）；广东省产学研专项（2016B090918126）；广州市科技计划项目科学研究专项（2014J4100206）

A Fingerprint Matching Localization Method Based on Deep Auto Encoder

Liu Zhen-yu, Li Jia-jun, Wang Kun   

  1. School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China
  • Received:2017-04-06 Online:2017-09-09 Published:2017-07-10

HTML

PDF (PC)

3299

摘要： 对于浅层结构的室内定位方法难以构造复杂的室内信号模型，从而导致定位精度不高的问题，本文提出利用深度学习方法建立深层非线性学习模型，提高室内定位精度的RFB-SDAE算法.该算法通过约简及预处理去除指纹采集中的冗余信息，经过堆叠式去噪自编码器多层网络的预训练及参数调整，获得较为精确的非线性室内无线信号的模型表示，并利用该模型实现室内的区域定位.实验结果表明，RFB-SDAE相比于堆叠式去噪编码器和单层神经网络提高了定位准确率，且比堆叠式去噪编码器使用更少的运行时间.

关键词: 室内定位, 深度学习, 自编码器, 指纹匹配, 约简

Abstract: Indoor localization methods of simple structure are hard to construct a complex indoor signal model, which leads to a poor position result. To solve this problem, a RFB-SDAE algorithm is proposed. The algorithm uses a deep learning structure to establish a deep nonlinear learning model to improve the indoor position accuracy. It removes the redundant information from fingerprint acquisition by the method of simplification and preprocessing. Via the pertaining and parameter adjustment of the networks of stacked denoising auto encoder, it acquires a more exact indoor wireless signal model which is used for indoor localization. The experimental result shows that, compared with stacked denoising auto encoder (SDAE) and single neural network, the RFB-SDAE has improved its accuracy and shortened its execution time.

Key words: indoor localization, deep learning, auto encoder, fingerprint matching, reduction

中图分类号: 

  • TN911.23
[1] LIU H, DARABI H, BANERJEE P, et al. Survey of wireless indoor positioning techniques and systems[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 2007, 37(6):1067-1080. [2] 黄婷婷, 刘广聪, 陈海南. 无线传感器网络自定位算法的研究[J]. 广东工业大学学报, 2015, 32(4):127-131.HUANG T T, LIU G C, CHEN H N. Self-localization algorithm of wireless sensors networks[J]. Journal of Guangdong University of Technology, 2015, 32(4):127-131. [3] FARID Z, NORDIN R, ISMAIL M. Recent advances in wireless indoor localization techniques and system[J]. Journal of Computer Networks & Communications, 2013, 2013(42):15-15. [4] KIM R, LIM H, HWANG S N, et al. Robust indoor localization based on hybrid Bayesian graphical models[C]//IEEE GLOBECOM. Austin:IEEE. 2014:423-429. [5] YU F, JIANG M H, LIANG J, et al. An indoor localization of wifi based on support vector machines[J]. Advanced Materials Research, 2014, 926-930(5):2438-2441. [6] WANG X, GAO L, MAO S, et al. DeepFi:Deep learning for indoor fingerprinting using channel state information[C]//Wireless Communications and Networking Conference. New Orleans:IEEE, 2015:1666-1671. [7] LUO J, GAO H. Deep belief networks for fingerprinting indoor localization using ultrawide band technology[J]. International Journal of Distributed Sensor Networks, 2016, 2016:1-8. [8] GU Y, CHEN Y, LIU J, et al. Semi-supervised deep extreme learning machine for Wi-Fi based localization[J]. Neurocomputing, 2015, 166(C):282-293. [9] ZHANG W, LIU K, ZHANG W, et al. Deep neural networks for wireless localization in indoor and outdoor environments[J]. Neurocomputing, 2016, 194(C):279-287. [10] SPOLAÔR N, CHERMAN E A, MONARD M C, et al. ReliefF for multi-label feature selection[C]//Intelligent Systems (BRACIS), 2013 Brazilian Conference on Fortaleza. Brazil:IEEE, 2013:6-11. [11] TORRES-SOSPEDRA J, MONTOLIU R, MARTINEZ-USO A, et al. UJⅡndoorLoc:A new multi-building and multi-floor database for WLAN fingerprint-based indoor localization problems[C]//International Conference on Indoor Positioning and Indoor Navigation. Busan:IEEE, 2014:261-270. [12] 陈丽娜. WLAN位置指纹室内定位关键技术研究[D]. 上海:华东师范大学信息科学技术学院. [13] O'CONNOR P, NEIL D, LIU S C, et al. Real-time classification and sensor fusion with a spiking deep belief network[J]. Frontiers in Neuroscience, 2013, 7:178 [14] VINCENT P, LAROCHELLE H, LAJOIE I, et al. Stacked denoising autoencoders:learning useful representations in a deep network with a local denoising criterion[J]. Journal of Machine Learning Research, 2010, 11(12):3371-3408. [15] SCHMIDHUBER J. Deep learning in neural networks:An overview[J]. Neural Networks, 2014, 61:85 [16] DOUGHERTY E R. Small sample issues for microarray-based classification[J]. Comparative & Functional Genomics, 2001, 2(2):28-34. [17] FÉLIX G, SILLER M, ÁLVAREZ E N. A fingerprinting indoor localization algorithm based deep learning[C]//Ubiquitous and Future Networks (ICUFN), 2016 Eighth International Conference on. Vienna:IEEE, 2016:1006-1011.
[1] 吴俊贤, 何元烈. 基于通道注意力的自监督深度估计方法[J]. 广东工业大学学报, 2023, 40(02): 22-29.
[2] 刘冬宁, 王子奇, 曾艳姣, 文福燕, 王洋. 基于复合编码特征LSTM的基因甲基化位点预测方法[J]. 广东工业大学学报, 2023, 40(01): 1-9.
[3] 徐伟锋, 蔡述庭, 熊晓明. 基于深度特征的单目视觉惯导里程计[J]. 广东工业大学学报, 2023, 40(01): 56-60,76.
[4] 刘洪伟, 林伟振, 温展明, 陈燕君, 易闽琦. 基于MABM的消费者情感倾向识别模型——以电影评论为例[J]. 广东工业大学学报, 2022, 39(06): 1-9.
[5] 章云, 王晓东. 基于受限样本的深度学习综述与思考[J]. 广东工业大学学报, 2022, 39(05): 1-8.
[6] 郑佳碧, 杨振国, 刘文印. 基于细粒度混杂平衡的营销效果评估方法[J]. 广东工业大学学报, 2022, 39(02): 55-61.
[7] Gary Yen, 栗波, 谢胜利. 地球流体动力学模型恢复的长短期记忆网络渐进优化方法[J]. 广东工业大学学报, 2021, 38(06): 1-8.
[8] 赖峻, 刘震宇, 刘圣海. 基于全局数据混洗的小样本数据预测方法[J]. 广东工业大学学报, 2021, 38(03): 17-21.
[9] 揭云飞, 王峰, 钟有东, 智凯旋, 熊超伟. 基于地面特征的单目视觉机器人室内定位方法[J]. 广东工业大学学报, 2020, 37(05): 31-37.
[10] 岑仕杰, 何元烈, 陈小聪. 结合注意力与无监督深度学习的单目深度估计[J]. 广东工业大学学报, 2020, 37(04): 35-41.
[11] 曾碧, 任万灵, 陈云华. 基于CycleGAN的非配对人脸图片光照归一化方法[J]. 广东工业大学学报, 2018, 35(05): 11-19.
[12] 陈旭, 张军, 陈文伟, 李硕豪. 卷积网络深度学习算法与实例[J]. 广东工业大学学报, 2017, 34(06): 20-26.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2017 《广东工业大学学报》编辑部
地址：广州市东风东路729号广东工业大学 邮编：510090
电话：020-37626653,020-37626139,020-37626396
邮箱：xbzrb@gdut.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发