基于CFSFDP与ELM相结合的半监督室内定位算法

A Semi-Supervised Indoor Location Algorithm Based on CFSFDP and ELM

针对室内环境复杂,难以获取足够多的有效标记数据进行定位,提出了一种将密度峰值快速搜索聚类(CFSFDP)和极限学习机(ELM)相结合的半监督室内定位算法(SLACE).SLACE利用CFSFDP聚类数据集,并标记聚类中心缺失的位置信息,扩充初始标记数据;利用ELM训练初始标记数据,根据输出阈值向量和"换位"思想扩充标记数据,提高定位准确率.实验表明:在标记数据个数相同时,该算法运行时间短,较ELM算法、BP算法而言,定位准确率明显提高.

Aiming the difficulty of gaining sufficient labeled samples in complex indoor environment,this paper proposes a semi-supervised location algorithm（SLACE）based on clustering by fast search and find of density peaks（CFSFDP）and extreme learning machine（ELM）.SLACE uses CFSFDP to cluster initial samples and label the unlabeled clustering centers,which helps to expand the initial labeled samples.Then SLACE uses ELM to train the labeled samples and extend the labeled samples through the output threshold vector and strategy of transposition,which improves location accuracy effectively.Comparative experiments show that with same number of labeled samples,this algorithm has low running time and outperforms original ELM and Back Propagation network,which significantly improves location accuracy.