摘要
随着室内定位市场的不断扩大,人们对室内定位技术的要求越来越高。现有的WiFi位置指纹定位技术容易受到外部环境变化的影响,导致在中空楼宇进行平面定位时,存在将待定位点定位到中空区域的问题,不利于后续的导航规划。为了弥补这一不足,提出了一种基于机器学习辅助的WiFi位置指纹算法,通过机器学习将定位区域分割为不同的子区域,有效地避免了中空区域的误定位问题。实验结果表明,所提出的定位算法可以解决中空区域的误定位问题,具有较高的定位精度。
With the continuous expansion of the indoor positioning market, people’s requirements for indoor positioning technology are getting higher and higher. The existing WiFi location fingerprinting positioning technology is easily affected by changes in the external environment, resulting in the problem of locating the to-be-located point to the hollow area when performing plane positioning in a hollow building, which is not conducive to subsequent navigation planning. In order to make up for this deficiency, a WiFi location fingerprinting algorithm assisted by machine learning is proposed, which divides the positioning area into different sub-regions through machine learning is proposed, thus effectively avoiding the problem of false positioning in hollow areas. The experimental results show that the proposed localization algorithm can effectively solve the problem of false localization in hollow areas and achieve high localization accuracy.
作者
杨家强
别昊泽
张更新
唐华鹏
秦丹阳
YANG Jiaqiang;BIE Haoze;ZHANG Gengxin;TANG Huapeng;QIN Danyang(College of Electronie Engineering,Heilongjiang University,Harbin 150080,China)
出处
《黑龙江大学自然科学学报》
CAS
2023年第1期92-97,共6页
Journal of Natural Science of Heilongjiang University
基金
国家自然科学基金(61771186)
黑龙江省自然科学基金优秀青年项目(YQ2020F012)。
