针对目前室内指纹定位算法存在实时性差、对动态环境适应性不足的问题,提出一种新的基于半监督极限学习机的定位算法.该算法首先通过半监督极限学习机建立初始化位置估计模型,然后利用新增的半标记数据对原定位模型进行动态调整,最后为新增训练数据分配合适惩罚权重,使模型具有时效机制.仿真结果表明,该定位算法在保证定位实时性的同时提高了对动态环境的适应性.%Due to present indoor fingerprint-based localization algorithms perform poorly in real-time and cannot a-dapt quickly in a dynamic environment,a new localization algorithm based on semi-supervised extreme learning ma-chine is proposed.Firstly,a location estimation model is initialized with the semi-supervised extreme learning ma-chine.Subsequently,the initial model is incrementally adaptively adjusted by incorporating the new semi-labeled training dataset.Finally,an appropriate penalty weight is assigned to the incremental dataset to render the model dy-namic.Simulation results show that the proposed algorithm improves the model's environment adaptability while en-suring its real-time localization capability.
展开▼
