کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
506527 864919 2009 10 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Accommodating spatial associations in DRNN for space–time analysis
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر نرم افزارهای علوم کامپیوتر
پیش نمایش صفحه اول مقاله
Accommodating spatial associations in DRNN for space–time analysis
چکیده انگلیسی

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.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Computers, Environment and Urban Systems - Volume 33, Issue 6, November 2009, Pages 409–418
نویسندگان
, ,