Randomly distributed embedding making short-term high-dimensional data predictable

doi:10.1073/pnas.1802987115

	Randomly distributed embedding making short-term high-dimensional data predictable
	Ma, Huanfei 1; Leng, Siyang 2,3,4; Aihara, Kazuyuki 2,5; Lin, Wei 3,4,6,7,8; Chen, Luonan9,10,11,12
	2018-10-23
发表期刊	PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (IF:9.4[JCR-2023],10.8[5-Year])
ISSN	0027-8424
卷号	115 期号:43 页码:E9994-E10002
发表状态	已发表
DOI	10.1073/pnas.1802987115
摘要	Future state prediction for nonlinear dynamical systems is a challenging task, particularly when only a few time series samples for high-dimensional variables are available from real-world systems. In this work, we propose a model-free framework, named randomly distributed embedding (RDE), to achieve accurate future state prediction based on short-term high-dimensional data. Specifically, from the observed data of high-dimensional variables, the RDE framework randomly generates a sufficient number of low-dimensional "nondelay embeddings" and maps each of them to a "delay embedding," which is constructed from the data of a to be predicted target variable. Any of these mappings can perform as a low-dimensional weak predictor for future state prediction, and all of such mappings generate a distribution of predicted future states. This distribution actually patches all pieces of association information from various embeddings unbiasedly or biasedly into the whole dynamics of the target variable, which after operated by appropriate estimation strategies, creates a stronger predictor for achieving prediction in a more reliable and robust form. Through applying the RDE framework to data from both representative models and real-world systems, we reveal that a high-dimension feature is no longer an obstacle but a source of information crucial to accurate prediction for short-term data, even under noise deterioration.
关键词	prediction nonlinear dynamics time series high-dimensional data short-term data
收录类别	SCI ; SCIE
语种	英语
资助项目	Science and Technology Commission of Shanghai Municipality[18DZ1201000]
WOS研究方向	Science & Technology - Other Topics
WOS类目	Multidisciplinary Sciences
WOS记录号	WOS:000448040500001
出版者	NATL ACAD SCIENCES
WOS关键词	TIME-SERIES ; SYSTEMS ; MODELS ; INFORMATION ; FRAMEWORK ; NETWORK ; SPACE
原始文献类型	Article
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/28181
专题	生命科学与技术学院_特聘教授组_陈洛南组
通讯作者	Aihara, Kazuyuki; Lin, Wei; Chen, Luonan
作者单位	1.Soochow Univ, Sch Math Sci, Suzhou 215006, Peoples R China 2.Univ Tokyo, Inst Ind Sci, Tokyo 1538505, Japan 3.Fudan Univ, Sch Math Sci, Shanghai 200433, Peoples R China 4.Fudan Univ, Ctr Computat Syst Biol, Inst Sci & Technol Brain Inspired Intelligence, Shanghai 200433, Peoples R China 5.Univ Tokyo, Inst Adv Study, Int Res Ctr Neurointelligence, Tokyo 1130033, Japan 6.Fudan Univ, Res Inst Intelligent & Complex Syst, Shanghai 200433, Peoples R China 7.Fudan Univ, Minist Educ, Key Lab Math Nonlinear Sci, Shanghai 200433, Peoples R China 8.Fudan Univ, Minist Educ, Key Lab Computat Neurosci & Brain Inspired Intell, Shanghai 200433, Peoples R China 9.Chinese Acad Sci, Ctr Excellence Mol Cell Sci, Shanghai Inst Biochem & Cell Biol, Key Lab Syst Biol, Shanghai 200031, Peoples R China 10.Chinese Acad Sci, Ctr Excellence Anim Evolut & Genet, Kunming, Yunnan, Peoples R China 11.ShanghaiTech Univ, Sch Life Sci & Technol, Shanghai 200031, Peoples R China 12.Shanghai Res Ctr Brain Sci & Brain Inspired Intel, Shanghai 201210, Peoples R China
通讯作者单位	生命科学与技术学院
推荐引用方式 GB/T 7714	Ma, Huanfei,Leng, Siyang,Aihara, Kazuyuki,et al. Randomly distributed embedding making short-term high-dimensional data predictable[J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA,2018,115(43):E9994-E10002.
APA	Ma, Huanfei,Leng, Siyang,Aihara, Kazuyuki,Lin, Wei,&Chen, Luonan.(2018).Randomly distributed embedding making short-term high-dimensional data predictable.PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA,115(43),E9994-E10002.
MLA	Ma, Huanfei,et al."Randomly distributed embedding making short-term high-dimensional data predictable".PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA 115.43(2018):E9994-E10002.