何志爽,万亚平,赵庆,王明艳.WiFi的室内定位技术的改进研究[J].南华大学学报(自然科学版),2018,32(3):60~64.[HE Zhishuang,WAN Yaping,ZHAO Qing,WANG Mingyan.Research and Improvement of Indoor Positioning Technology Based on WiFi[J].Journal of University of South China(Science and Technology),2018,32(3):60~64.] |
WiFi的室内定位技术的改进研究 |
Research and Improvement of Indoor Positioning Technology Based on WiFi |
投稿时间:2018-02-23 |
DOI: |
中文关键词: 室内定位 指纹匹配 朴素贝叶斯概率算法 BKWNN 比重系数 |
英文关键词:Indoor location fingerprint matching naive bayes probability algorithm BKWNN specific gravity coefficient |
基金项目: |
|
摘要点击次数: 872 |
全文下载次数: 713 |
中文摘要: |
现行传统WiFi(wireless fidelity)接收信号强度指示RSSI(receievd signal strength inication)的位置指纹室内定位技术存在定位误差大、稳定性差的缺陷.因此,我们对原有的K最近邻KNN(K-Nearest neighbor)算法提出了改进的方案.同时,在原有的KNN算法的基础上提出了融合朴素贝叶斯概率算法的新算法-BKWNN(Bayes K-Nearest weighted neighbor)算法.通过仿真实验的结果表明:在相同的实验环境下,BKWNN算法显著地提高了室内定位的精确度,BKWNN算法相比于原来其它常用的指纹匹配算法具有更高的稳定性. |
英文摘要: |
The current traditional WiFi (Wireless Fidelity) signal intensity indication RSSI (Receievd Signal Strength Inication) location fingerprint localization technology has the defects of large positioning error and poor stability.In this regard,it proposes an improved scheme for the original K nearest neighbor KNN (K-Nearest Neighbor) algorithm,and on the basis of the original KNN algorithm,a new algorithm,-BKWNN (Bayes K-Nearest Weighted Neighbor),is proposed,which combines the simple Bias probability algorithm (Bayes K-Nearest Weighted Neighbor).The simulation results show that in the same experimental environment,the BKWNN algorithm significantly improves the accuracy of the indoor location,while the BKWNN algorithm has better stability than the other common fingerprint matching algorithms. |
查看全文 查看/发表评论 下载PDF阅读器 |
关闭 |
|
|
|