Outlier-Resistant Remote State Estimation for Recurrent Neural Networks With Mixed Time-Delays

In this brief, a new outlier-resistant state estimation (SE) problem is addressed for a class of recurrent neural networks (RNNs) with mixed time-delays. The mixed time delays comprise both discrete and distributed delays that occur frequently in signal transmissions among artificial neurons. Measurement outputs are sometimes subject to abnormal disturbances (resulting probably from sensor aging/outages/faults/failures and unpredictable environmental changes) leading to measurement outliers that would deteriorate the estimation performance if directly taken into the innovation in the estimator design. We propose to use a certain confidence-dependent saturation function to mitigate the side effects from the measurement outliers on the estimation error dynamics (EEDs). Through using a combination of Lyapunov-Krasovskii functional and inequality manipulations, a delay-dependent criterion is established for the existence of the outlier-resistant state estimator ensuring that the corresponding EED achieves the asymptotic stability with a prescribed H∞ performance index. Then, the explicit characterization of the estimator gain is obtained by solving a convex optimization problem. Finally, numerical simulation is carried out to demonstrate the usefulness of the derived theoretical results.

[1]  Huisheng Shu,et al.  Finite-time resilient H∞ state estimation for discrete-time delayed neural networks under dynamic event-triggered mechanism , 2020, Neural Networks.

[2]  Zidong Wang,et al.  Guaranteed cost control for uncertain nonlinear systems with mixed time-delays: The discrete-time case , 2018, Eur. J. Control.

[3]  Yurong Liu,et al.  Event-Triggered Partial-Nodes-Based State Estimation for Delayed Complex Networks With Bounded Distributed Delays , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[4]  Zhidong Teng,et al.  Finite-time synchronization for memristor-based neural networks with time-varying delays , 2015, Neural Networks.

[5]  Jie Cao,et al.  Detecting Prosumer-Community Groups in Smart Grids From the Multiagent Perspective , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[6]  Goutam Saha,et al.  Lung sound classification using cepstral-based statistical features , 2016, Comput. Biol. Medicine.

[7]  Shumin Fei,et al.  Exponential state estimation for recurrent neural networks with distributed delays , 2007, Neurocomputing.

[8]  Qiankun Song,et al.  Boundedness and Complete Stability of Complex-Valued Neural Networks With Time Delay , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Ian R. Petersen,et al.  Set-valued state estimation via a limited capacity communication channel , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[10]  Jun Hu,et al.  Moving Horizon Estimation With Unknown Inputs Under Dynamic Quantization Effects , 2020, IEEE Transactions on Automatic Control.

[11]  Qiankun Song,et al.  Global stability of complex-valued neural networks with both leakage time delay and discrete time delay on time scales , 2013, Neurocomputing.

[12]  Kunio Doi,et al.  Image-processing technique for suppressing ribs in chest radiographs by means of massive training artificial neural network (MTANN) , 2006, IEEE Transactions on Medical Imaging.

[13]  Yonggang Chen,et al.  Exponential Synchronization for Delayed Dynamical Networks via Intermittent Control: Dealing With Actuator Saturations , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[14]  Fuad E. Alsaadi,et al.  H∞ state estimation for discrete-time neural networks with distributed delays and randomly occurring uncertainties through Fading channels , 2017, Neural Networks.

[15]  Vladimir L. Kharitonov,et al.  Stability of Time-Delay Systems , 2003, Control Engineering.

[16]  Di Zhao,et al.  Proportional–Integral Observer Design for Multidelayed Sensor-Saturated Recurrent Neural Networks: A Dynamic Event-Triggered Protocol , 2020, IEEE Transactions on Cybernetics.

[17]  A. Garulli,et al.  Output-feedback predictive control of constrained linear systems via set-membership state estimation , 2000 .

[18]  Tingwen Huang,et al.  Brief Papers Further Result on Guaranteed H∞ Performance State Estimation of Delayed Static Neural Networks , 2015 .

[19]  Fuwen Yang,et al.  Set-membership filtering for systems with sensor saturation , 2009, Autom..

[20]  Giorgio Battistelli,et al.  Stability of consensus extended Kalman filter for distributed state estimation , 2016, Autom..

[21]  Luca Zaccarian,et al.  Stubborn state observers for linear time-invariant systems , 2018, Autom..

[22]  Huijun Gao,et al.  Fault Detection for Markovian Jump Systems With Sensor Saturations and Randomly Varying Nonlinearities , 2012, IEEE Transactions on Circuits and Systems I: Regular Papers.

[23]  Qing-Long Han,et al.  Security control for a class of discrete-time stochastic nonlinear systems subject to deception attacks , 2016 .

[24]  Yong He,et al.  A New Result on H∞ State Estimation of Delayed Static Neural Networks via Augmented Lyapunov-Krasovskii Functional , 2018, 2018 37th Chinese Control Conference (CCC).

[25]  Yilin Mo,et al.  Attack-Resilient H_2, H_∞, and ℓ_1 State Estimator , 2018, 1803.07053.

[26]  Meiqin Liu,et al.  $H_{\infty }$ State Estimation for Discrete-Time Delayed Systems of the Neural Network Type With Multiple Missing Measurements , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[27]  Hongli Dong,et al.  Partial-Neurons-Based Passivity-Guaranteed State Estimation for Neural Networks With Randomly Occurring Time Delays , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[28]  Qing-Long Han,et al.  An overview of neuronal state estimation of neural networks with time-varying delays , 2019, Inf. Sci..

[29]  Qing-Long Han,et al.  State Estimation for Static Neural Networks With Time-Varying Delays Based on an Improved Reciprocally Convex Inequality , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[30]  Peng Shi,et al.  Robust Estimation for Neural Networks With Randomly Occurring Distributed Delays and Markovian Jump Coupling , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[31]  Shuai Liu,et al.  Probability-guaranteed set-membership filtering for systems with incomplete measurements , 2015, Autom..

[32]  Hui Xiong,et al.  SAIL: Summation-bAsed Incremental Learning for Information-Theoretic Text Clustering , 2013, IEEE Transactions on Cybernetics.

[33]  Fuad E. Alsaadi,et al.  State estimation for a class of artificial neural networks with stochastically corrupted measurements under Round-Robin protocol , 2016, Neural Networks.

[34]  Huijun Gao,et al.  New Delay-Dependent Exponential H ∞ Synchronization for Uncertain Neural Networks With Mixed Time Delays , 2009 .

[35]  Lamine Mili,et al.  Robust Kalman Filter Based on a Generalized Maximum-Likelihood-Type Estimator , 2010, IEEE Transactions on Signal Processing.

[36]  Hongli Dong,et al.  Partial-Nodes-Based Scalable H∞-Consensus Filtering With Censored Measurements Over Sensor Networks , 2021, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[37]  Rathinasamy Sakthivel,et al.  Design of state estimator for bidirectional associative memory neural networks with leakage delays , 2015, Inf. Sci..

[38]  Shuai Liu,et al.  Extended Kalman filtering for stochastic nonlinear systems with randomly occurring cyber attacks , 2016, Neurocomputing.

[39]  Fuwen Yang,et al.  H∞ filtering for nonlinear networked systems with randomly occurring distributed delays, missing measurements and sensor saturation , 2016, Inf. Sci..

[40]  Zidong Wang,et al.  Mixed $H_2/H_\infty$ State Estimation for Discrete-Time Switched Complex Networks With Random Coupling Strengths Through Redundant Channels , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[41]  Francisco Sandoval Hernández,et al.  Hopfield neural networks for optimization: study of the different dynamics , 2002, Neurocomputing.

[42]  Michael V. Basin,et al.  Discrete-time high order neural network identifier trained with cubature Kalman filter , 2018, Neurocomputing.

[43]  Daniel W. C. Ho,et al.  Synchronization of Delayed Memristive Neural Networks: Robust Analysis Approach , 2016, IEEE Transactions on Cybernetics.

[44]  Yang Liu,et al.  UKF-based remote state estimation for discrete artificial neural networks with communication bandwidth constraints , 2018, Neural Networks.

[45]  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.

[46]  Moti L. Tiku,et al.  Robust estimation in multiple linear regression model with non-Gaussian noise , 2008, Autom..

[47]  Massimiliano Di Ventra,et al.  Experimental demonstration of associative memory with memristive neural networks , 2009, Neural Networks.

[48]  Jinde Cao,et al.  Synchronization of Randomly Coupled Neural Networks With Markovian Jumping and Time-Delay , 2013, IEEE Transactions on Circuits and Systems I: Regular Papers.

[49]  Renquan Lu,et al.  Finite-Time State Estimation for Coupled Markovian Neural Networks With Sensor Nonlinearities , 2017, IEEE Transactions on Neural Networks and Learning Systems.