W
Wanli Min
Researcher at Alibaba Group
Publications - 45
Citations - 1339
Wanli Min is an academic researcher from Alibaba Group. The author has contributed to research in topics: Intersection & Signal. The author has an hindex of 15, co-authored 45 publications receiving 1234 citations. Previous affiliations of Wanli Min include University of Chicago & IBM.
Papers
More filters
Journal ArticleDOI
Real-time road traffic prediction with spatio-temporal correlations
Wanli Min,Laura Wynter +1 more
TL;DR: The method presented provides predictions of speed and volume over 5-min intervals for up to 1 h in advance for real-time road traffic prediction to be both fast and scalable to full urban networks.
Journal ArticleDOI
On linear processes with dependent innovations
Wei Biao Wu,Wanli Min +1 more
TL;DR: In this article, the authors consider asymptotic behavior of partial sums and sample covariances for linear processes whose innovations are dependent, and establish central limit theorems and invariance principles under fairly mild conditions.
Journal ArticleDOI
Locality pursuit embedding
Wanli Min,Ke Lu,Xiaofei He +2 more
TL;DR: Locality pursuit embedding as discussed by the authors is a linear algorithm that arises by solving a variational problem and produces a linear embedding that respects the local geometrical structure described by the Euclidean distances.
Patent
Knowledge-based models for data centers
TL;DR: In this paper, a method for modeling thermal distributions in a data center is provided, where the vertical temperature distribution data for each of the locations is plotted as an s curve, and each of these s curves is represented with a set of parameters that characterize the shape of the s curve.
Journal ArticleDOI
Uncovering energy-efficiency opportunities in data centers
Hendrik F. Hamann,T. van Kessel,M. Iyengar,J.-Y. Chung,Walter Hirt,Michael Alan Schappert,A. Claassen,J. M. Cook,Wanli Min,Yasuo Amemiya,V. López,James A. Lacey,Martin P. O'Boyle +12 more
TL;DR: A mobile measurement technology for optimizing the space and energy efficiency of DCs is presented and the combination of these two data types, in conjunction with innovative modeling techniques, provides the basis for extending the MMT concept toward an interactive energy management solution.