شماره ركورد كنفرانس :
3926
عنوان مقاله :
A Harmonic Emotional Neural Network for Non-linear System Identification
پديدآورندگان :
Mirhajianmoghadam Hengameh hengameh.mirhajian@stu.um.ac.ir hengameh_mirhajian@yahoo.com Center of Excellence on Soft Computing and Intelligent Information Processing Departments of Electrical Engineering Ferdowsi University Mashhad, Iran , Akbarzadeh-T Mohammad-R akbarzadeh@ieee.org Center of Excellence on Soft Computing and Intelligent Information Processing Departments of Electrical and Computer Engineering Ferdowsi University Mashhad, Iran , Lotfi Ehsan esilotf@gmail.com elotfi@bitools.ir Department of Computer Engineering Torbat-e-Jam Branch, Islamic Azad Torbat-e-Jam, Iran
كليدواژه :
Emotional neural network , nonlinear system identification , computation cost reduction , modeling , BEL
عنوان كنفرانس :
بيست و چهارمين كنفرانس مهندسي برق ايران
چكيده فارسي :
Emotional neural networks (ENNs) are a learnable structure that have been inspired from the physiological features of human s emotional brain. In this paper, a single layered ENN is modified in a way to be differentiable for nonlinear system identification problems. In the proposed ENN, thalamusamygdala expansion link is modeled by a sine and cosine basis function. That is why is named the harmonic emotional neural network (HENN). Due to this proposed expansion, presented method is well-suited for the model based identification methodologies. Simulation results indicate the validity of this claim besides that the supremacy of HENN in terms of accuracy, easy learning and simplicity of model in system identification is shown.
