Chiba University Researcher Highlights Recent Research in Machine Learning (Impr oved Particle Filter in Machine Learning-Based BLE Fingerprinting Method to Redu ce Indoor Location Estimation Errors)
Chiba University Researcher Highlights Recent Research in Machine Learning (Impr oved Particle Filter in Machine Learning-Based BLE Fingerprinting Method to Redu ce Indoor Location Estimation Errors)
机器人与机器学习每日新闻的一位新闻记者兼新闻编辑发表了关于人工智能的新研究结果。根据NewsRx记者来自日本千叶的新闻，研究表明，“基于室内位置指纹的定位估计方法已经被智能手机的应用广泛使用。”本文从千叶大学的研究中得到一句话:“在这些定位估计方法中,普遍采用信号的接收信号强度指示(Rescensed Signal Strength Indication,RSSI)来表示位置指纹,本文提出了一种粒子滤波器的设计,以减小基于机器学习的室内BLE定位指纹法的估计误差。”在考虑距离的基础上，设计了改进的似然函数，利用RSSI值的均值和方差考虑基于指纹点的坐标，将粒子滤波与K-NN(K-Nest Neighbor)算法相结合，实现了室内定位误差的减少。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New study results on artificial intell igence have been published. According to news originating from Chiba, Japan, by NewsRx correspondents, research stated, “Indoor position fingerprintbased locat ion estimation methods have been widely used by applications on smartphones.” Our news journalists obtained a quote from the research from Chiba University: “ In these localization estimation methods, it is very popular to use the RSSI (Re ceived Signal Strength Indication) of signals to represent the position fingerpr int. This paper proposes the design of a particle filter for reducing the estima tion error of the machine learning-based indoor BLE location fingerprinting meth od. Unlike the general particle filter, taking into account the distance, the pr oposed system designs improved likelihood functions, considering the coordinates based on fingerprint points using mean and variance of RSSI values, combining t he particle filter with the k-NN (k-Nearest Neighbor) algorithm to realize the r eduction in indoor positioning error.”
NETL
NSTL