Title:
PREDICTION MODEL GENERATION SYSTEM, METHOD AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2019/087381
Kind Code:
A1
Abstract:
According to the present invention, a prediction model generation unit 72 generates a prediction model for predicting an amount of traffic in one node. Here, the prediction model generation unit 72 specifies a node related to the one node on the basis of topology information which indicates a relation between nodes, and generates the prediction model by means of teacher data that includes information on the one node and information on nodes related to the one node. In addition, the information on the node includes at least an amount of traffic passing the node.
Inventors:
AKIMOTO ICHIROU (JP)
MOTOHASHI YOUSUKE (JP)
SAWADA NAOKI (JP)
MOTOHASHI YOUSUKE (JP)
SAWADA NAOKI (JP)
Application Number:
PCT/JP2017/039894
Publication Date:
May 09, 2019
Filing Date:
November 06, 2017
Export Citation:
Assignee:
NEC CORP (JP)
International Classes:
H04L12/70
Foreign References:
| US20170309171A1 | 2017-10-26 | |||
| US20160129787A1 | 2016-05-12 |
Other References:
CORTEZ, P ET AL.: "Topology aware internet traffic forecasting using neural networks", ARTIFICIAL NEURAL NETWORKS - ICANN, vol. 2007, 2007, pages 445 - 454, XP019069483
MIN, X ET AL.: "Short-term traffic flow forecasting of urban network based on dynamic STARIMA model", IN INTELLIGENT TRANSPORTATION SYSTEMS, 2009. ITSC' 09. 12TH INTERNATIONAL IEEE CONFERENCE ON, 2009, pages 1 - 6, XP031560085
MIN, X ET AL.: "Short-term traffic flow forecasting of urban network based on dynamic STARIMA model", IN INTELLIGENT TRANSPORTATION SYSTEMS, 2009. ITSC' 09. 12TH INTERNATIONAL IEEE CONFERENCE ON, 2009, pages 1 - 6, XP031560085
Attorney, Agent or Firm:
IWAKABE Fuyuki et al. (JP)
Download PDF: