| 一种基于流形正则化的半监督指纹定位算法 |
| |
| 引用本文： | 朱顺涛,卢先领,于丹石.一种基于流形正则化的半监督指纹定位算法[J].测绘通报,2018,0(2):11-15,20. |
| |
| 作者姓名： | 朱顺涛 卢先领 于丹石 |
| |
| 作者单位： | 1. 江南大学"轻工过程先进控制"教育部重点实验室, 江苏 无锡 214100;
2. 江南大学物联网工程学院, 江苏 无锡 214100 |
| |
| 基金项目： | 江苏省产学研联合创新资金前瞻性联合研究项目，江苏省"六大人才高峰"项目 |
| |
| 摘 要： | 针对传统指纹定位算法采集带标签训练数据成本高的问题，本文提出了一种基于流形正则化的半监督指纹定位算法。首先以流形假设为依据，利用批量输入的带标签数据与无标签数据之间的相似度构建图拉普拉斯算子；然后与极限学习机算法相结合，通过随机特征映射建立隐含层；最后在流形正则化框架下，求解隐含层和输出层之间的权值矩阵，从而建立位置估计模型。仿真结果表明，与INN、SVR、ELM 3种算法相比，该算法的训练和测试时间相对较短，且在带标签训练数据稀疏的前提下仍能保持较高的准确率与稳定性。
|
| 关 键 词： | 指纹定位 半监督学习 流形正则化 极限学习机 图拉普拉斯算子 |
| 收稿时间： | 2017-11-27 |
A Semi-supervised Fingerprint Localization Algorithm Based on Manifold Regularization |
| |
| ZHU Shuntao,LU Xianling,YU Danshi.A Semi-supervised Fingerprint Localization Algorithm Based on Manifold Regularization[J].Bulletin of Surveying and Mapping,2018,0(2):11-15,20. |
| |
| Authors: | ZHU Shuntao LU Xianling YU Danshi |
| |
| Institution: | 1. Key Laboratory of Advanced Process Control for Light Industry(Ministry of Education), Jiangnan University, Wuxi 214100, China;
2. School of Internet of Things Engineering, Jiangnan University, Wuxi 214100, China |
| |
| Abstract: | Due to traditional fingerprint localization algorithms cost too much on collecting training dataset with labels, a new semi-supervised fingerprint localization algorithm based on manifold regularization is proposed.Firstly,the graph laplacian is initialized with the labeled and unlabeled training dataset under the manifold hypothesis.Subsequently,combined with the extreme learning machine,the hidden layer is constructed by using random mapping.Finally,the output weighted matrix between the hidden layer and output layer is solved under the framework of manifold regularization,so that the location estimated model is established. The simulation results show that,compared with INN,SVR and ELM,the proposed algorithm need shorter training time and testing time.In addition,it can maintain the high accuracy and reliability while labeled training dataset is sparse. |
| |
| Keywords: | fingerprint localization semi-supervised learning manifold regularization extreme learning machine graph Laplacian |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《测绘通报》浏览原始摘要信息 |
| 点击此处可从《测绘通报》下载免费的PDF全文 |
|
