SIA OpenIR  > 数字工厂研究室
Moving destination prediction using sparse dataset: A mobility gradient descent approach
Wang L(王亮); Wu ZW(於志文); Guo B(郭斌); Ku T(库涛); Yi, Fei
作者部门数字工厂研究室
关键词Moving Destination Prediction Sparse Dataset Space Division Gradient Descent Markov Transition Model
发表期刊ACM Transactions on Knowledge Discovery from Data
ISSN1556-4681
2017
卷号11期号:3页码:1-33
收录类别SCI ; EI
EI收录号20171703602531
WOS记录号WOS:000399725200012
产权排序3
资助机构National Basic Research Program of China (No. 2015CB352400), the National Natural Science Foundation of China (No. 61402360, 61373119, 61332005, 61402369).
摘要Moving destination prediction offers an important category of location-based applications and provides essential intelligence to business and governments. In existing studies, a common approach to destination prediction is to match the given query trajectory with massive recorded trajectories by similarity calculation. Unfortunately, due to privacy concerns, budget constraints, and many other factors, in most circumstances, we can only obtain a sparse trajectory dataset. In sparse dataset, the available moving trajectories are far from enough to cover all possible query trajectories; thus the predictability of the matching-based approach will decrease remarkably. Toward destination prediction with sparse dataset, instead of searching similar trajectories over the sparse records, we alternatively examine the changes of distances from sampling locations to final destination on query trajectory. The underlying idea is intuitive: It is directly motivated by travel purpose, people always get closer to the final destination during the movement. By borrowing the conception of gradient descent in optimization theory, we propose a novel moving destination prediction approach, namely MGDPre. Building upon the mobility gradient descent, MGDPre only investigates the behavior characteristics of query trajectory itself without matching historical trajectories, and thus is applicable for sparse dataset. We evaluate our approach based on extensive experiments, using GPS trajectories generated by a sample of taxis over a 10-day period in Shenzhen city, China. The results demonstrate that the effectiveness, efficiency, and scalability of our approach outperform state-of-the-art baseline methods.
语种英语
WOS标题词Science & Technology ; Technology
WOS类目Computer Science, Information Systems ; Computer Science, Software Engineering
关键词[WOS]MODEL ; OBJECTS
WOS研究方向Computer Science
引用统计
被引频次:5[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.sia.cn/handle/173321/20426
专题数字工厂研究室
通讯作者Wang L(王亮)
作者单位1.School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, 710072, China
2.Xi'an University of Science and Technology, China
3.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, Liaoning, 110016, China
推荐引用方式
GB/T 7714
Wang L,Wu ZW,Guo B,et al. Moving destination prediction using sparse dataset: A mobility gradient descent approach[J]. ACM Transactions on Knowledge Discovery from Data,2017,11(3):1-33.
APA Wang L,Wu ZW,Guo B,Ku T,&Yi, Fei.(2017).Moving destination prediction using sparse dataset: A mobility gradient descent approach.ACM Transactions on Knowledge Discovery from Data,11(3),1-33.
MLA Wang L,et al."Moving destination prediction using sparse dataset: A mobility gradient descent approach".ACM Transactions on Knowledge Discovery from Data 11.3(2017):1-33.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Moving destination p(1401KB)期刊论文作者接受稿开放获取ODC PDDL浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang L(王亮)]的文章
[Wu ZW(於志文)]的文章
[Guo B(郭斌)]的文章
百度学术
百度学术中相似的文章
[Wang L(王亮)]的文章
[Wu ZW(於志文)]的文章
[Guo B(郭斌)]的文章
必应学术
必应学术中相似的文章
[Wang L(王亮)]的文章
[Wu ZW(於志文)]的文章
[Guo B(郭斌)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Moving destination prediction using sparse dataset.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。