摘要
传统基于接收信号强度指示(received signal strength indication,RSSI)的室内定位方法易受环境影响且精确度低、稳定性差。为解决这一问题,提出基于受限玻尔兹曼机(restricted Boltzmann machine,RBM)的CSI (channel state information)指纹室内定位方法。在离线阶段时,设计使用RBM来训练校准相应的CSI数据,建立特征指纹库;在线阶段时,利用朴素贝叶斯分类器对数据进行处理并与指纹库匹配,得到定位结果。实验结果表明,基于RBM的CSI指纹室内定位方法优于传统指纹室内定位方法。
The traditional indoor positioning method based on received signal strength (RSSI) is easy to be influenced by the environment with low accuracy and weak stability,a fingerprint based indoor positioning method of channel state information grounded on restricted Boltzmann machine (RBM) was proposed.In the off-line phase,RBM was designed and used to train and adjust the corresponding CSI data,and a feature fingerprint library was built.In the on-line phase,the Naive Bayes Classifier was utilized to process data and match the fingerprint library,and positioning result was obtained.Experimental results show that the me- thod presented is superior to traditional fingerprint based indoor positioning methods.
作者
党小超
唐续豪
郝占军
DANG Xiao-chao;TANG Xu-hao;HAO Zhan-jun(College of Computer Science and Engineering,Northwest Normal University,Lanzhou 730070,China;Gansu Province Internet of Things Engineering Research Center,Lanzhou 730070,China)
出处
《计算机工程与设计》
北大核心
2019年第5期1264-1270,共7页
Computer Engineering and Design
基金
国家自然科学基金项目(61662070
61363059)
甘肃省科技重点研发基金项目(1604FKCA097
17YF1GA015)
甘肃省科技创新基金项目(17CX2JA037
17CX2JA039)