Self-recurrent Neural Network Research Articles

Self Recurrent Neural Network Based Target Tracking in Wireless Sensor Network using State Observer

Background & Objective:Mobile target tracking based on data from wireless sensor networks (WSN) is a hot topic that has been investigated both from a theoretical and practical point of view in the literature. Tracking the position and velocity of a target moving in WSN (especially in the context of uncertain noisy measurement channel) is a very challenging task. To deal with the uncertainty in system dynamics as well as uncertainty in target states, an Observer Based Self Recurrent Neural Network (OBSRNN) is proposed in this paper.Methods:The proposed algorithm employs a state observer based tracking control strategy and thereby allows for accurate estimation of mobile target moving along a predefined route in WSN. The Self Recurrent Neural Network (SRNN) framework is used to approximate the uncertainty in the system dynamics, while a full-order state observer is used to estimate the unknown state vector.Conclusion:The simulation analysis is performed to evaluate the efficacy of the proposed work.

Control of structural seismic response by self‐recurrent neural network (SRNN)

A new paradigm called self-recurrent neural network (SRNN) is proposed. Two SRNNs are utilized in a control system, one as an emulator and the other as a controller. To guarantee convergence and for faster learning, an approach using adaptive learning rate is developed by Lyapunov function. Finally, the neural network control algorithm is developed for on-line control of structural seismic response in real time. Simulation-results have shown that it can effectively control structural seismic response and make it consist with the desired response. © 1998 John Wiley & Sons, Ltd.

Control of structural seismic response by self-recurrent neural network (SRNN)

A new paradigm called self-recurrent neural network (SRNN) is proposed. Two SRNNs are utilized in a control system, one as an emulator and the other as a controller. To guarantee convergence and for faster learning, an approach using adaptive learning rate is developed by Lyapunov function. Finally, the neural network control algorithm is developed for on-line control of structural seismic response in real time. Simulation-results have shown that it can effectively control structural seismic response and make it consist with the desired response. © 1998 John Wiley & Sons, Ltd.

Neural network modeling in optimisation of continuous fermentation processes

The capability of self-recurrent neural networks in dynamic modeling of continuous fermentation is investigated in this simulation study. In the past, feedforward neural networks have been successfully used as one-step-ahead predictors. However, in steady-state optimisation of continuous fermentations the neural network model has to be iterated to predict many time steps ahead into the future in order to get steady-state values of the variables involved in objective cost function, and this iteration may result in increasing errors. Therefore, as an alternative to classical feedforward neural network trained by using backpropagation method, self-recurrent multilayer neural net trained by backpropagation through time method was chosen in order to improve accuracy of long-term predictions. Prediction capabilities of the resulting neural network model is tested by implementing this into the Integrated System Optimisation and Parameter Estimation (ISOPE) optimisation algorithm. Maximisation of cellular productivity of the baker's yeast continuous fermentation was used as the goal of the proposed optimising control problem. The training and prediction results of proposed neural network and performances of resulting optimisation structure are demonstrated.