摘要
在用户行为无法预知的实际计步应用中,如何保持计步算法的准确性和稳定性是一个极具挑战的问题。传统的计步算法利用阈值设定和峰值检测,并不能解决计步算法的普适性和稳定性。针对上述问题,提出了基于加速度差分作为特征的有限状态机(acceleration differential based on finite state machine,AD-FSM)计步算法。该算法将原始加速度取平方和,并通过卡尔曼滤波去除噪声干扰,最后使用加速度差分有限状态机实现计步检测。实验结果表明,该算法在正常和干扰情况下能够提供精确的计步结果,误差分别为1.12%、4.00%,验证了该计步算法在降低状态机复杂度的同时具有较强的稳定性和鲁棒性,更能适应复杂的应用场景。
In the application of step counting, how to keep the stability and accuracy of step counting algorithm is achallenging problem. The traditional approach using fixed thresholds and peak detection can not solve the problem ofstability and adaptability. In response to these problems, this paper proposes a step counting algorithm based on finitestate machine using acceleration differential as a feature (AD-FSM). Firstly, AD-FSM uses the sum of squared accelerationto orientation-independent and applies Kalman filtering to eliminate noise. Then, AD-FSM counts steps by finitestate machine. The experimental results show that the proposed algorithm can provide accurate counting results in thenormal and interference situations, the errors are only 1.12% and 4.00%. This highlights the ability of the proposedalgorithm to provide stability, robustness, and efficient counting in complex scenarios with fewer complications.
作者
王革超
梁久祯
陈璟
朱向军
WANG Gechao ;LIANG Jiuzhen;CHEN Jing;ZHU Xiangjun(School of Internet of Things Engineering, Jiangnan University,Wuxi, Jiangsu 214122, China)
出处
《计算机科学与探索》
CSCD
北大核心
2016年第8期1133-1142,共10页
Journal of Frontiers of Computer Science and Technology
基金
国家自然科学基金Nos.61170121
71503103~~
关键词
室内定位
计步
抗干扰
有限状态机
加速度差分
indoor location
step counting
anti-interference
finite state machine
acceleration differential
