期刊
COMPUTERS ENVIRONMENT AND URBAN SYSTEMS
卷 33, 期 6, 页码 409-418出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.compenvurbsys.2009.08.004
关键词
Spatial associations; DRNN; Space-time analysis; Spatial weight matrix
类别
资金
- EPSRC [EP/G023212/1] Funding Source: UKRI
- Engineering and Physical Sciences Research Council [EP/G023212/1] Funding Source: researchfish
Dynamic recurrent neural networks (DRNN) are neural networks with feedback connections. They are superior to static feedforward neural networks (SFNN) in nonlinear time-series analysis because they can also accommodate temporal associations. However, like SFNN, DRNN presents a black box approach to space-time analysis. This paper seeks to incorporate spatial associations into a DRNN, through its structure and initial weights. It suggests a novel approach to defining the topological structure and initial weights of DRNN based on the spatial associations of spatial units. This is seen as vital for improving the accuracy and efficiency of prediction and forecasting using space-time models. The proposed method is illustrated using three instances of space-time analysis, which are each characterized by different spatial data types (discrete and continuous). Computational accuracy and efficiency are much improved by incorporating spatial associations in DRNN. This reveals that DRNN can be a powerful tool for modeling space-time series with complex spatial and temporal characteristics. (C) 2009 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据