A Semisupervised End-to-End Framework for Transportation Mode Detection by Using GPS-Enabled Sensing Devices

doi:10.1109/JIOT.2021.3115239

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	A Semisupervised End-to-End Framework for Transportation Mode Detection by Using GPS-Enabled Sensing Devices
	Li, Zhishuai1,2 ; Xiong, Gang3,4 ; Wei, Zebing 1,2; Lv, Yisheng1,2 ; Anwar, Noreen 1,2; Wang, Fei-Yue1,2
发表期刊	IEEE INTERNET OF THINGS JOURNAL
ISSN	2327-4662
	2022-05-15
卷号	9 期号:10 页码:7842-7852
通讯作者	Lv, Yisheng(yisheng.lv@ia.ac.cn)
摘要	As an essential component of Internet of Things, GPS-enabled devices record tremendous digital traces, which provide a great convenience for understanding human mobility. How to discover transportation modes efficiently from such valuable sources has come into the spotlight. In this article, the transportation mode detection is treated as a dense classification task, and a similarity entropy-based encoder-decoder (SEED) model is proposed. We first design an encoder-decoder backbone for end-to-end mode detection. Then, a semi-supervised learning module based on similarity entropy is proposed to exploit numerous unlabeled data. Specifically, we stack several convolutional layers as an encoder to capture hierarchical features from fixed-length trajectories, and then adopt transposed convolutional layers as a decoder. For a semi-supervised module, inspired by entropy regularization, we use the K-Means algorithm to cluster prototype vectors from the encoder's predictions. We then fine-tune the encoder by sharpening the similarity distribution between unlabeled predictions and prototypes, aiming to make the former close to one prototype only while staying away from others. A majority-voting post-processing method is used to alleviate jitter impact when inferring. The Experimental results show that SEED significantly outperforms segmentation-then-inference methods. Furthermore, the similarity entropy-based module can improve the generalization performance of the model, and the metrics such as intersection over union can be increased by 5% over baselines. All of these verify the superiority of our method.
关键词	GPS trajectory human mobility semi-supervised learning transportation mode detection (TMD)
DOI	10.1109/JIOT.2021.3115239
关键词[WOS]	TRAVEL
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2020YFB2104001] ; National Natural Science Foundation of China[U1909204] ; National Natural Science Foundation of China[61773381] ; National Natural Science Foundation of China[U1811463] ; National Natural Science Foundation of China[61872365] ; National Natural Science Foundation of China[61773382] ; Chinese Guangdong's ST Project[2019B1515120030] ; Chinese Guangdong's ST Project[2020B0909050001]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Chinese Guangdong's ST Project
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:000803121100059
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：9[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/49576
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
通讯作者	Lv, Yisheng
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Beijing Engn Res Ctr Intelligent Syst & Technol, Inst Automat, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Guangdong Engn Res Ctr 3D Printing & Intelligent, Cloud Comp Ctr, Dongguan 523808, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Li, Zhishuai,Xiong, Gang,Wei, Zebing,et al. A Semisupervised End-to-End Framework for Transportation Mode Detection by Using GPS-Enabled Sensing Devices[J]. IEEE INTERNET OF THINGS JOURNAL,2022,9(10):7842-7852.
APA	Li, Zhishuai,Xiong, Gang,Wei, Zebing,Lv, Yisheng,Anwar, Noreen,&Wang, Fei-Yue.(2022).A Semisupervised End-to-End Framework for Transportation Mode Detection by Using GPS-Enabled Sensing Devices.IEEE INTERNET OF THINGS JOURNAL,9(10),7842-7852.
MLA	Li, Zhishuai,et al."A Semisupervised End-to-End Framework for Transportation Mode Detection by Using GPS-Enabled Sensing Devices".IEEE INTERNET OF THINGS JOURNAL 9.10(2022):7842-7852.