High-order Neural Networks Research Articles

Exact Takagi-Sugeno descriptor models of recurrent high-order neural networks for control applications

This work presents an exact Takagi-Sugeno descriptor model of a recurrent high-order neural network arising from identification of a nonlinear plant. The proposed rearrangement allows exploiting the nonlinear characteristics of the neural model for $$\mathcal H_\infty $$-optimal controller design whose conditions are expressed as linear matrix inequalities. Simulation and real-time results are presented that illustrate the advantages of the proposal.

LMI-based criterion on stochastic ISS property of delayed high-order neural networks with explicit gain functions and simply event-triggered mechanism

In this paper, by transforming the high-order system into the system with vector-matrix form, the authors employed variational methods in Sobolev spaces, Lyapunov function method, Dynkin’s formula and comparison principle to deduce the stochastic input-to-state stability in mean square on the high-order time-delays reaction-diffusion neural networks under the concise event-triggered mechanism. Remarkably, it is the first paper in which the LMI-based criterion of input-to-state stability of time-delays high-order reaction-diffusion neural networks with event-triggered control is derived, in which the diffusion item plays its role. Not similarly as those of previous literature, the sufficient conditions of the main result in this paper are not involved to Lyapunov function, which implies that the conditions of this paper is easier to be verified than ever. With the help of computer Matlab LMI toolbox, a numerical example illustrates the effectiveness of proposed methods.

Stability analysis of high order neural networks with proportional delays

In this paper, we present a stability criterion for a high-order neural network with one proportional delay. Unlike most existing results about time-delayed high-order neural networks, the proportional delay mentioned here is unbounded and time-varying. The stability criterion obtained in this paper has some improvements and advantages compared with ones in some existing results, which is further explained by numerical examples. The approach proposed in this paper is also available for (high-order) neural networks with multiple proportional delays.

Neural Network Techniques for Time Series Prediction: A Review

It is important to predict a time series because many problems that are related to prediction such as health prediction problem, climate change prediction problem and weather prediction problem include a time component. To solve the time series prediction problem various techniques have been developed over many years to enhance the accuracy of forecasting. This paper presents a review of the prediction of physical time series applications using the neural network models. Neural Networks (NN) have appeared as an effective tool for forecasting of time series. Moreover, to resolve the problems related to time series data, there is a need of network with single layer trainable weights that is Higher Order Neural Network (HONN) which can perform nonlinearity mapping of input-output. So, the developers are focusing on HONN that has been recently considered to develop the input representation spaces broadly. The HONN model has the ability of functional mapping which determined through some time series problems and it shows the more benefits as compared to conventional Artificial Neural Networks (ANN). The goal of this research is to present the reader awareness about HONN for physical time series prediction, to highlight some benefits and challenges using HONN.

A Novel Identification-Based Convex Control Scheme via Recurrent High-Order Neural Networks: An Application to the Internal Combustion Engine

This paper proposes an identification-based nonlinear control scheme which casts the plant model as a recurrent high-order neural network. The model thus obtained consists on polynomials of a fixed number of nonlinearities, a fact that is exploited by transforming it into an exact tensor-product representation whose nested convex sums may increase with the network order while preserving the number of different interpolating functions. Convexity is then used along the direct Lyapunov method to find conditions for controller design in the form of linear matrix inequalities or sum-of-squares; thanks to the fixed number of nonlinearities, they can be made progressively more relaxed while preventing the computational burden usually associated with Polya-like relaxations. The control law thus obtained is a generalization of the well-known parallel distributed compensation; its effectiveness is illustrated in academic examples and an internal combustion engine setup.

Adaptive Neural Event-Triggered Control for Discrete-Time Strict-Feedback Nonlinear Systems.

This paper proposes a novel event-triggered (ET) adaptive neural control scheme for a class of discrete-time nonlinear systems in a strict-feedback form. In the proposed scheme, the ideal control input is derived in a recursive design process, which relies on system states only and is unrelated to virtual control laws. In this case, the high-order neural networks (NNs) are used to approximate the ideal control input (but not the virtual control laws), and then the corresponding adaptive neural controller is developed under the ET mechanism. A modified NN weight updating law, nonperiodically tuned at triggering instants, is designed to guarantee the uniformly ultimate boundedness (UUB) of NN weight estimates for all sampling times. In virtue of the bounded NN weight estimates and a dead-zone operator, the ET condition together with an adaptive ET threshold coefficient is constructed to guarantee the UUB of the closed-loop networked control system through the Lyapunov stability theory, thereby largely easing the network communication load. The proposed ET condition is easy to implement because of the avoidance of: 1) the use of the intermediate ET conditions in the backstepping procedure; 2) the computation of virtual control laws; and 3) the redundant triggering of events when the system states converge to a desired region. The validity of the presented scheme is demonstrated by simulation results.

Almost Periodic Functions on the Quantum Time Scale and Applications

In this paper, we first propose two types of concepts of almost periodic functions on the quantum time scale. Secondly, we study some basic properties of almost periodic functions on the quantum time scale. Thirdly, based on these, we study the existence and uniqueness of almost periodic solutions of dynamic equations on the quantum time scale by Lyapunov method. Then, we give an equivalent definition of almost periodic functions on the quantum time scale. Finally, as an application, we propose a class of high-order Hopfield neural networks on the quantum time scale and establish the existence and global exponential stability of almost periodic solutions of this class of neural networks.

Real-Time Neural Inverse Optimal Control for a Wind Generator

This paper presents a discrete-time inverse optimal control scheme using a neural network for a doubly fed induction generator (DFIG). The DFIG generation scheme has a voltage-source converter connected between the rotor and the electrical grid, which is composed by two insulated-gate bipolar transistors (IGBT) power converters connected in back-to-back configuration. These converters are known as rotor side converter (RSC) and grid side converter (GSC), respectively. The RSC is used to control the electric torque and reactive power of the DFIG, and the GSC is used to control the dc-link voltage in the IGBT connection and the stator terminals reactive power. To take into account possible parameter variations, a recurrent high order neural network (RHONN) is used to approximate the DFIG model in an identification process; after that, based on the neural model obtained, a discrete-time inverse optimal control scheme for the RSC is developed. Using a similar approach, a dc-link neural identifier and a controller are proposed for the GSC. The proposed control scheme applicability is validated by means simulations, which includes a comparison with proportional-integral controllers; then, this control scheme is implemented in real time. The paper novelty consists on the synthesis and real-time implementation of a DFIG inverse optimal control based on a RHONN.

Neural Inverse Optimal Control Implementation for Induction Motors via Rapid Control Prototyping

This paper presents a discrete-time neural inverse optimal control for induction motors, which is implemented on a rapid control prototyping (RCP) system using a C2000 Microcontroller-Simulink platform. Such controller addresses the solution of three issues: system identification, trajectory tracking, and state estimation, which are solved independently. The neural controller is based on a recurrent high order neural network (RHONN), which is trained with an extended Kalman filter. The RHONN is an identifier to obtain an accurate motor model, which is robust to external disturbances and parameter variations. The inverse optimal controller is used to force the system to track a desired trajectory and to reject undesired disturbances. Moreover, the controller is based on a neural model and does not need the a-priori knowledge of motor parameters. A supertwisting observer is implemented to estimate the rotor magnetic fluxes. The hub of the RCP system is a TMS320f28069M MCU, which is an embedded combination of a 32-bit C28x DSP core and a real-time control accelerator. This Microcontroller is fully programmable from the Simulink environment. Simulation and experimental results illustrate the performance of the proposed controller and the RCP system, and a comparison with a control algorithm without the neural identifier is also included.

Trajectory Tracking on Uncertain Complex Networks via NN-Based Inverse Optimal Pinning Control.

A new approach for trajectory tracking on uncertain complex networks is proposed. To achieve this goal, a neural controller is applied to a small fraction of nodes (pinned ones). Such controller is composed of an on-line identifier based on a recurrent high-order neural network, and an inverse optimal controller to track the desired trajectory; a complete stability analysis is also included. In order to verify the applicability and good performance of the proposed control scheme, a representative example is simulated, which consists of a complex network with each node described by a chaotic Lorenz oscillator.

HONN-Based Adaptive ILC for Pure-Feedback Nonaffine Discrete-Time Systems With Unknown Control Directions.

Nearly all adaptive control techniques require that the control directions of dynamical systems are known in advance. In this paper, for a class of pure-feedback nonaffine discrete-time systems with unknown control directions (UCDs), a high-order neural network (HONN)-based adaptive iterative learning control (ILC) approach is presented to address a repetitive tracking control issue. The implicit function theorem is adopted to cope with the difficulty resulting from the nonaffine structure of control input. Employing a discrete Nussbaum-type function in the neural network weight adaptation law to suit the UCD, an HONN is used to iteratively estimate the ideal control signals. In addition, a novel dead-zone method is developed in the HONN-based adaptive ILC algorithm to enhance its robustness against nonrepetitive desired trajectories and random uncertainties in iterative initial errors and external disturbance. Consequently, the system output, except at the initial n time instants, is demonstrated to asymptotically converge to an adjustable range of the desired trajectory along the iteration axis, while all of the system signals remain bounded during the entire ILC process. Two simulation examples show the feasibility of the adaptive ILC approach.

A matrix decomposition based adaptive control scheme for a class of MIMO non-canonical approximation systems

This paper presents a unified study on adaptive control of multi-input multi-output (MIMO) uncertain approximation systems in non-canonical forms. For adaptive control of such systems, this paper develops a new state feedback parametrization-based adaptive control scheme, by specifying relative degrees and establishing a normal form, deriving new system reparametrizations needed for adaptive control designs, and constructing adaptive state feedback parametrized controllers for the controlled plant with different vector relative degrees, where the uncertain control gain matrices are handled using a matrix decomposition technique. The main features of such a new control framework are demonstrated by new results for non-canonical MIMO recurrent high-order neural network systems with closed-loop stability and output tracking performance analyzed. An illustrative example with simulation results is presented to show the control design procedure and desired system performance.

High-Order Neural Networks are Equivalent to Ordinary Neural Networks

Equivalence of computational systems can assist in obtaining abstract systems, and thus enable better understanding of issues related their design and performance. For more than four decades, artificial neural networks have been used in many scientific applications to solve classification problems as well as other problems. Since the time of their introduction, multilayer feedforward neural network referred as Ordinary Neural Network (ONN), that contains only summation activation (Sigma) neurons, and multilayer feedforward High-order Neural Network (HONN), that contains Sigma neurons, and product activation (Pi) neurons, have been treated in the literature as different entities. In this work, we studied whether HONNs are mathematically equivalent to ONNs. We have proved that every HONN could be converted to some equivalent ONN. In most cases, one just needs to modify the neuronal transfer function of the Pi neuron to convert it to a Sigma neuron. The theorems that we have derived clearly show that the original HONN and its corresponding equivalent ONN would give exactly the same output, which means; they can both be used to perform exactly the same functionality. We also derived equivalence theorems for several other non-standard neural networks, for example, recurrent HONNs and HONNs with translated multiplicative neurons. This work rejects the hypothesis that HONNs and ONNs are different entities, a conclusion that might initiate a new research frontier in artificial neural network research.

Real‐time neural sliding mode field oriented control for a DFIG‐based wind turbine under balanced and unbalanced grid conditions

This study proposes a real-time sliding mode field oriented control for a doubly-fed induction generator (DFIG)-based wind turbine prototype connected to the grid. The proposed controller is used to track the desired direct current (DC) voltage reference at the output of the DC link, to maintain constant the grid power factor at the step-up transformer terminals controlled by the grid side converter, and to force independently the stator active and reactive power to track desired values through the rotor currents controlled by the rotor side converter. This control scheme is based on a recurrent high-order neural network (RHONN) identifier trained on-line by an extended Kalman filter. The RHONN is used to approximate the DC link and the DFIG mathematical models. The adequate approximation helps to calculate the exact equivalent control part of the sliding mode controller and to eliminate the effects of disturbances and unknown dynamics appearing in the grid, which improves the robustness of the control scheme. This controller is experimentally validated on a 1/4 HP DFIG prototype and tested for variable wind speed to track a time-varying power reference and to extract the maximum power from the wind, under both balanced and unbalanced grid conditions.

Discrete-time neural synchronization between an Arduino microcontroller and a Compact Development System using multiscroll chaotic signals

In this paper, we present the synchronization of a chaotic system using a discrete-time recurrent high order neural network. This is done by using a Genesio & Tesi oscillator circuit in discrete-time embedded into an Arduino microcontroller that provides the state space variables. A discrete-time recurrent neural network is designed to synchronize the dynamics of the chaotic oscillator. This neural network is trained using a time-varying training algorithm where it is used the Extended Kalman Filter. Two state space variables are captured in real-time in ADC inputs of a compact development system, where these signals are synchronized by the recurrent high order neural network in discrete-time. The proposed work allows synchronization of interactions associated between the neural convergence and the chaotical plant state. The obtained real-time results, and the statistical analyses on the synchronization process validate the possible application in chaos-based communications systems.

Design of a cognitive health app to support caregivers of people with agitation

This chapter addresses fundamental aspects about the identification of uncertain nonlinear systems with unknown time delays using recurrent high-order neural networks trained with an algorithm based on the EKF.

Real-time Neural Input–Output Feedback Linearization control of DFIG based wind turbines in presence of grid disturbances

This paper proposes a Neural Input–Output Feedback Linearization (N-IOFL) controller for a Doubly Fed Induction Generator (DFIG) prototype connected to the grid. Under unbalanced grid voltages, the existing control strategies need to be modified, becoming very complicated. By using an identifier based on Recurrent High Order Neural Network (RHONN), trained on-line with an Extended Kalman Filter (EKF), an adequate model of the DFIG and of the DC-link can be obtained, which helps the control law based on feedback linearization to reject grid disturbances appearing under non-ideal grid conditions without decomposition process. Based on such identification, the proposed controller is used to track a desired Direct Current (DC) voltage reference at the output of DC-link, to maintain constant the electric power factor controlled by the Grid Side Converter (GSC), and to force independently the rotor currents to track a specified reference defined from the required stator powers, controlled by the Rotor Side Converter (RSC), under both balanced and unbalanced grid conditions. Real-time results illustrate the effectiveness of the proposed controller even in presence of non-ideal grid conditions.

RETRACTED ARTICLE: Lung cancer prediction using higher-order recurrent neural network based on glowworm swarm optimization

Therapeutic issues are commonly found in every single person. Tumor is a standout among the most unsafe sicknesses a human can ever had. It is exceptionally hard to distinguish it in its beginning times as its side effects seem just in the progressed stages. Subsequently, the early forecast of lung growth is compulsory for the analysis procedure, and it gives the higher possibilities for fruitful treatment. It is the most difficult approach to upgrade a patient’s possibility for survival. Henceforth, a higher-order neural network system called recurrent neural network with Levenberg–Marquardt model with the help of glowworm swarm optimization algorithm is proposed for managing multimodal disease information. The execution of the proposed strategies is tried with information and the benchmark dataset, and the outcomes demonstrate that the higher-order recurrent neural systems with glowworm swarm optimization give better accuracy of 98% in comparison with customary optimized neural network.

Discrete-time high order neural network identifier trained with cubature Kalman filter

Abstract This paper presents a method to identify a nonlinear system, employing high order neural networks. Given an unknown discrete-time nonlinear plant subject to disturbances, a high order neural network is proposed to approximate its dynamics. To train the neural network weights, considered as new states, the cubature Kalman filter is used. A simulation example and an experimental study are included to show effectiveness of the proposed scheme. The results given by the proposed method are compared to the results produced by the extended Kalman filter training algorithm.

Effects of early adversity on neural mechanisms of distractor suppression are mediated by sympathetic nervous system activity in preschool-aged children.

Multiple theoretical frameworks posit that interactions between the autonomic nervous system and higher-order neural networks are crucial for cognitive regulation. However, few studies have simultaneously examined autonomic physiology and brain activity during cognitive tasks. Such research is promising for understanding how early adversity impacts neurocognitive development in children, given that stress experienced early in life impacts both autonomic function and regulatory behaviors. We recorded event-related potentials (ERPs) as a neural measure of auditory selective attention, and cardiovascular measures of high-frequency heart rate variability (HF-HRV) and preejection period (PEP), in 105 3-5-year-old children with varying degrees of socioeconomic risk. First, we replicated a previous study from our lab: Increased socioeconomic risk was associated with larger ERP amplitudes elicited by distracting sounds. Next, we tested whether PEP and HF-HRV (at rest and during the task) were associated with the distractor ERP response, and found that a physiological profile marked by heightened sympathetic nervous system activity, indexed by shorter PEP, was associated with better ERP suppression of distractor sounds in lower SES children. Finally, we found that PEP mediated the relationship between socioeconomic risk and larger ERP responses to distractor sounds. In line with similar reports, these results suggest that for lower SES children, there is a potential biological cost of achieving better cognitive performance, seen here as increased cardiovascular arousal both at rest and in response to task demands. (PsycINFO Database Record