期刊名称：International Journal of Artificial Intelligence & Applications (IJAIA)
印刷版ISSN：0976-2191
电子版ISSN：0975-900X
出版年度：2017
卷号：8
期号：4
页码：11
DOI：10.5121/ijaia.2017.8402
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：A recurrent neural network with a self-organizing structure based on the dynamic analysis of a task ispresented in this paper. The stability of the recurrent neural network is guaranteed by design. A dynamicanalysis method to sequence the subsystems of the recurrent neural network according to the fitnessbetween the subsystems and the target system is developed. The network is trained with the network'sstructure self-organized by dynamically activating subsystems of the network according to tasks. Theexperiments showed the proposed network is capable of activating appropriate subsystems to approximatedifferent nonlinear dynamic systems regardless of the inputs. When the network was applied to the problemof simultaneously soft measuring the chemical oxygen demand (COD) and NH3-N in wastewater treatmentprocess, it showed its ability of avoiding the coupling influence of the two parameters and thus achieved amore desirable outcome.
