An Improved Convolutional Neural Network Based Indoor Localization by Using Jenks Natural Breaks Alg

来源 :中国通信(英文版) | 被引量 : 0次 | 上传用户:ulysseschen
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
With the rapid growth of the demand for indoor location-based services(LBS),Wi-Fi re-ceived signal strength(RSS)fingerprints database has attracted significant attention because it is easy to ob-tain.The fingerprints algorithm based on convolution neural network(CNN)is often used to improve in-door localization accuracy.However,the number of reference points used for position estimation has sig-nificant effects on the positioning accuracy.Mean-while,it is always selected arbitraily without any guid-ing standards.As a result,a novel location estima-tion method based on Jenks natural breaks algorithm(JNBA),which can adaptively choose more reasonable reference points,is proposed in this paper.The output of CNN is processed by JNBA,which can select the number of reference points according to different envi-ronments.Then,the location is estimated by weighted K-nearest neighbors(WKNN).Experimental results show that the proposed method has higher positioning accuracy without sacrificing more time cost than the existing indoor localization methods based on CNN.
其他文献
Non-orthogonal multiple access(NOMA)has been integrated in millimeter-wave(mmWave)Massive MIMO systems to further enhance the spec-trum efficiency,but NOMA has not been fully consid-ered in lens mmWave systems.The fusion of these two technologies requires
In the future smart transportation sys-tem,reliable vehicle-to-infrastructure(V2I)commu-nication is very important to ensure vehicle driving safety and to improve vehicle driving efficiency.In this paper,V2I channel measurements at 5.92 GHz are conducted
In this paper,a low-profile wideband di-electric resonator antenna(DRA)with a very compact planar size is investigated.The antenna consists of a high permittivity dielectric sheet on the top,a low per-mittivity substrate in the middle,and a probe feeding
This paper proposes a novel joint channel estimation and beamforming scheme for the massive multiple-input-multiple-output(MIMO)frequency-division duplexing(FDD)wireless legiti-mate surveillance system.With the proposed scheme,the monitor with the full du
With the rapid increasing of maritime activities,maritime wireless networks(MWNs)with high reliability,high energy efficiency,and low de-lay are required.However,the centralized network-ing with fixed resource scheduling is not suitable for MWNs due to th
Intelligent reflecting surface(IRS)is re-garded as a promising technology because it can achieve higher passive beamforming gain.In partic-ular,the IRS assisted simultaneous wireless informa-tion and power transfer(SWIPT)system can make the information de
With the research of the upcoming sixth generation(6G)systems,new technologies will re-quire wider bandwidth,larger scale antenna arrays and more diverse wireless communication scenarios on the future channel modeling.Considering chan-nel model is prerequ
With energy harvesting capability,the Internet of things(IoT)devices transmit data de-pending on their available energy,which leads to a more complicated coupling and brings new techni-cal challenges to delay optimization.In this paper,we study the delay-
In space-based Automatic Identification Systems(AIS),due to high satellite orbits,several Ad Hoc cells within the observation range of the satellite are vulnerable to interference by an external signal.To increase efficiency in target detection and improv
Low earth orbit(LEO)satellite network is an important development trend for future mobile communication systems,which can truly realize the“ubiquitous connection”of the whole world.In this paper,we present a cooperative computation offload-ing in the LEO