Adaptive State Estimation of Stochastic Delayed Neural Networks with Fractional Brownian Motion

This paper considers the adaptive state estimation problem for stochastic neural networks with fractional Brownian motion (FBM). The problem for the stochastic neural networks with FBM is handled according to the theory of Hilbert–Schmidt and the principle of analytic semigroup. Using the stochastic analytic technique and adaptive control method, the asymptotic stability and the exponential stability criteria are established. Finally, a simulation example is given to prove the efficiency of developed criteria.

[1]  Jian-an Fang,et al.  Global stability of stochastic high-order neural networks with discrete and distributed delays , 2008 .

[2]  Jinde Cao,et al.  Existence and Uniform Stability Analysis of Fractional-Order Complex-Valued Neural Networks With Time Delays , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[3]  A. Fauth,et al.  Multifractal Random Walks With Fractional Brownian Motion via Malliavin Calculus , 2012, IEEE Transactions on Information Theory.

[4]  Peng Shi,et al.  State estimation for discrete-time neural networks with time-varying delay , 2012, Int. J. Syst. Sci..

[5]  A physically-based fractional diffusion model for semi-dilute suspensions of rods in a Newtonian fluid , 2017 .

[6]  Yuhua Xu,et al.  Adaptive Finite-Time Synchronization of Neutral Type Dynamical Network with Double Derivative Coupling , 2017, Neural Processing Letters.

[7]  Yehoshua Y. Zeevi,et al.  Single-Image Superresolution of Natural Stochastic Textures Based on Fractional Brownian Motion , 2014, IEEE Transactions on Image Processing.

[8]  B. Manley,et al.  How does real option value compare with Faustmann value when log prices follow fractional Brownian motion , 2017 .

[9]  B. Øksendal,et al.  Stochastic Calculus for Fractional Brownian Motion and Applications , 2008 .

[10]  Ju H. Park,et al.  Network-based H∞ state estimation for neural networks using imperfect measurement , 2018, Appl. Math. Comput..

[11]  G. Jumarie.  Modeling fractional stochastic systems as non-random fractional dynamics driven by Brownian motions , 2008 .

[12]  Hao Shen,et al.  Extended Dissipative State Estimation for Markov Jump Neural Networks With Unreliable Links , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[13]  Xiang Li,et al.  Exponential synchronization and phase locking of a multilayer Kuramoto-oscillator system with a pacemaker , 2018, Neurocomputing.

[14]  Jiming Chen,et al.  Energy-Efficient Data Forwarding for State Estimation in Multi-Hop Wireless Sensor Networks , 2016, IEEE Transactions on Automatic Control.

[15]  Qi-min Zhang,et al.  Numerical analysis for stochastic age-dependent population equations with fractional Brownian motion , 2012 .

[16]  Wai Keung Wong,et al.  Stochastic Stability of Delayed Neural Networks With Local Impulsive Effects , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[17]  Peng Shi,et al.  Exponential Synchronization for Markovian Stochastic Coupled Neural Networks of Neutral-Type via Adaptive Feedback Control , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[18]  Lei Liu,et al.  Exponential Stability of Uncertain Stochastic Neural Networks with Markovian Switching , 2010, Neural Processing Letters.

[19]  Zhaohua Gong,et al.  Robust parameter estimation for nonlinear multistage time-delay systems with noisy measurement data , 2018 .

[20]  Ju H. Park,et al.  State estimation of neural networks with time-varying delays and Markovian jumping parameter based on passivity theory , 2012 .

[21]  Jun Yang,et al.  pth Moment synchronization of Markov switched neural networks driven by fractional Brownian noise , 2016, Neural Computing and Applications.

[22]  Yuhua Xu,et al.  Multi-Delay-Dependent Exponential Synchronization for Neutral-Type Stochastic Complex Networks with Markovian Jump Parameters via Adaptive Control , 2018, Neural Processing Letters.

[23]  Antonio Gómez Expósito,et al.  State estimation in two time scales for smart distribution systems , 2015, 2015 IEEE Power & Energy Society General Meeting.

[24]  Yi Zhao,et al.  Geometrical invariability of transformation between a time series and a complex network. , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

[25]  Jun Yang,et al.  Exponential synchronization for stochastic neural networks with multi-delayed and Markovian switching via adaptive feedback control , 2015, Commun. Nonlinear Sci. Numer. Simul..

[26]  Zu-Guo Yu,et al.  Topological properties and fractal analysis of a recurrence network constructed from fractional Brownian motions. , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

[27]  Baoye Song,et al.  Finite-time state estimation for jumping recurrent neural networks with deficient transition probabilities and linear fractional uncertainties , 2017, Neurocomputing.

[28]  T. Caraballo,et al.  The existence and exponential behavior of solutions to stochastic delay evolution equations with a fractional brownian motion , 2011 .

[29]  J. H. Cushman,et al.  Fractional Brownian motion run with a multi-scaling clock mimics diffusion of spherical colloids in microstructural fluids. , 2014, Langmuir : the ACS journal of surfaces and colloids.

[30]  Yan Gao,et al.  Mode and Delay-Dependent Adaptive Exponential Synchronization in $p$th Moment for Stochastic Delayed Neural Networks With Markovian Switching , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[31]  Jun Zhou,et al.  Stability Analysis and Application for Delayed Neural Networks Driven by Fractional Brownian Noise , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[32]  Jinde Cao,et al.  Robust Stability of Markovian Jump Stochastic Neural Networks with Time Delays in the Leakage Terms , 2013, Neural Processing Letters.

[33]  I︠U︡lii︠a︡ S. Mishura.  Stochastic Calculus for Fractional Brownian Motion and Related Processes , 2008 .

[34]  Johanna L. Mathieu,et al.  State Estimation and Control of Electric Loads to Manage Real-Time Energy Imbalance , 2013 .

[35]  Peng Shi,et al.  Adaptive Synchronization for Neutral-Type Neural Networks with Stochastic Perturbation and Markovian Switching Parameters , 2014, IEEE Transactions on Cybernetics.

[36]  Zhong Liu,et al.  An approach to variable-order prediction via multiple distal dendrites of neurons , 2018, Neural Computing and Applications.

[37]  Gürkan Solmaz,et al.  A Mobility Model of Theme Park Visitors , 2015, IEEE Transactions on Mobile Computing.