电讯技术2024，Vol.64Issue(4)：504-511,8.DOI:10.20079/j.issn.1001-893x.230702001
利用无监督预训练的轨迹深度关联
Deep Trajectory Matching Using Unsupervised Pre-training
李平 1李雨航1
作者信息
- 1. 中国西南电子技术研究所,成都 610036
- 折叠
摘要
Abstract
Due to the limitations of spatiotemporal similarity algorithm for trajectory matching,a deep learning method is adopted and a matching neural network training method based on unsupervised pre-training is proposed.Geohash vector embedding is used to perform feature engineering processing on trajectory signals,a self-attention mechanism neural network structure is built,and unlabeled trajectory data is used to conduct model pre-training based on mask prediction task.Then a siamese matching network structure is constructed and the pre-training model parameters are loaded.Finally,labeled trajectory pair data is used to fine-tune the parameters of the pre-training model based on the mean square error loss function to obtain the trajectory matching model.The Geolife GPS trajectory data is used as the evaluation dataset for model training and testing.The experimental results show that the proposed method improves the matching accuracy by 5 percentage points(reaching 96.3%)compared with the existing optimal algorithm,thus fully demonstrating the effectiveness of the method.At present,there is limited research in the field of trajectory matching based on deep learning pre-training models,and the proposed method has important reference significance.关键词
轨迹关联/深度学习/无监督预训练/向量嵌入/自注意力机制/孪生网络结构Key words
trajectory matching/deep learning method/unsupervised pre-training/vector embedding/self-attention mechanism/siamese network structure分类
信息技术与安全科学引用本文复制引用
李平,李雨航..利用无监督预训练的轨迹深度关联[J].电讯技术,2024,64(4):504-511,8.
