scholarly journals A Constrained Neural Network Kalman Filter for Price Estimation in High Frequency Financial Data

1997 ◽  
Vol 08 (04) ◽  
pp. 399-415 ◽  
Author(s):  
Peter J. Bolland ◽  
Jerome T. Connor
Keyword(s):  
Neural Network ◽  
Kalman Filter ◽  
Extended Kalman Filter ◽  
Financial Time Series ◽  
Financial Data ◽  
The Neural Network ◽  
Tick Data ◽  
Price Estimation ◽  
Network Weight ◽  
The Stability

In this paper we present a neural network extended Kalman filter for modeling noisy financial time series. The neural network is employed to estimate the nonlinear dynamics of the extended Kalman filter. Conditions for the neural network weight matrix are provided to guarantee the stability of the filter. The extended Kalman filter presented is designed to filter three types of noise commonly observed in financial data: process noise, measurement noise, and arrival noise. The erratic arrival of data (arrival noise) results in the neural network predictions being iterated into the future. Constraining the neural network to have a fixed point at the origin produces better iterated predictions and more stable results. The performance of constrained and unconstrained neural networks within the extended Kalman filter is demonstrated on "Quote" tick data from the $/DM exchange rate (1993–1995).

scholarly journals Nonlinear Autoregressive Neural Network and Extended Kalman Filters for Prediction of Financial Time Series

2020 ◽  
Vol 2020 ◽  
pp. 1-6 ◽  
Author(s):  
Ghassane Benrhmach ◽  
Khalil Namir ◽  
Abdelwahed Namir ◽  
Jamal Bouyaghroumni
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Kalman Filter ◽  
Extended Kalman Filter ◽  
Financial Time Series ◽  
Broad Class ◽  
Financial Time ◽  
The Neural Network ◽  
Nonlinear Autoregressive ◽  
Autoregressive Neural Network

Time series analysis and prediction are major scientific challenges that find their applications in fields as diverse as finance, biology, economics, meteorology, and so on. Obtaining the method with the least prediction error is one of the difficult problems of financial market and investment analysts. State space modelling is an efficient and flexible method for statistical inference of a broad class of time series and other data. The neural network is an important tool for analyzing time series especially when it is nonlinear and nonstationary. Essential tools for the study of Box-Jenkins methodology, neural networks, and extended Kalman filter were put together. We examine the use of the nonlinear autoregressive neural network method as a prediction technique for financial time series and the application of the extended Kalman filter algorithm to improve the accuracy of the model. As application on a real example, we are analyzing the time series of the daily price of steel over a 790-day period for establishing the superiority of this method over other existing methods. The simulation results using MATLAB and R software show that the model is capable of producing a reasonable accuracy.

scholarly journals Adaptive dynamic programming-based controller with admittance adaptation for robot–environment interaction

2020 ◽  
Vol 17 (3) ◽  
pp. 172988142092461
Author(s):  
Hong Zhan ◽  
Dianye Huang ◽  
Zhaopeng Chen ◽  
Min Wang ◽  
Chenguang Yang
Keyword(s):  
Neural Network ◽  
Dynamic Programming ◽  
Linear Quadratic Regulator ◽  
Adaptive Dynamic Programming ◽  
Environment Interaction ◽  
Linear Quadratic ◽  
Adaptive Dynamic ◽  
The Neural Network ◽  
Network Weight ◽  
The Stability

The problem of optimal tracking control for robot–environment interaction is studied in this article. The environment is regarded as a linear system and an admittance control with iterative linear quadratic regulator method is obtained to guarantee the compliant behaviour. Meanwhile, an adaptive dynamic programming-based controller is proposed. Under adaptive dynamic programming frame, the critic network is performed with radial basis function neural network to approximate the optimal cost, and the neural network weight updating law is incorporated with an additional stabilizing term to eliminate the requirement for the initial admissible control. The stability of the system is proved by Lyapunov theorem. The simulation results demonstrate the effectiveness of the proposed control scheme.

scholarly journals Using an extended Kalman filter learning algorithm for feed-forward neural networks to describe tracer correlations

2004 ◽  
Vol 4 (3) ◽  
pp. 3653-3667 ◽  
Author(s):  
D. J. Lary ◽  
H. Y. Mussa
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Kalman Filter ◽  
Extended Kalman Filter ◽  
Learning Algorithm ◽  
Feed Forward ◽  
The Neural Network ◽  
Fortran Code ◽  
Feed Forward Neural Networks ◽  
Time Of Year

Abstract. In this study a new extended Kalman filter (EKF) learning algorithm for feed-forward neural networks (FFN) is used. With the EKF approach, the training of the FFN can be seen as state estimation for a non-linear stationary process. The EKF method gives excellent convergence performances provided that there is enough computer core memory and that the machine precision is high. Neural networks are ideally suited to describe the spatial and temporal dependence of tracer-tracer correlations. The neural network performs well even in regions where the correlations are less compact and normally a family of correlation curves would be required. For example, the CH4-N2O correlation can be well described using a neural network trained with the latitude, pressure, time of year, and CH4 volume mixing ratio (v.m.r.). The neural network was able to reproduce the CH4-N2O correlation with a correlation coefficient between simulated and training values of 0.9997. The neural network Fortran code used is available for download.

Dynamic Reoptimization of a SNAC Controller for Velocity Tracking in a Nano Array

2005 ◽  
Author(s):  
Nishant Unnikrishnan ◽  
S. N. Balakrishnan
Keyword(s):  
Neural Network ◽  
Universal Function ◽  
Lyapunov Theory ◽  
Feedback Form ◽  
The Neural Network ◽  
Significant Step ◽  
System Equations ◽  
Error Dynamics ◽  
Network Weight ◽  
The Stability

Online trained neural networks have become popular in designing robust and adaptive controllers for dynamic systems with uncertainties in their system equations because of their universal function approximation property. The uniqueness of the method proposed in this work is that the online function approximating network can be used to re-optimize in real time an existing Single Network Adaptive Critic (SNAC) based optimal controller that has already been designed for a nominal system. The controller redesign is carried out in two steps: (i) synthesis of an online neural network that captures the unknown functions in the plant equations on-line (ii) re-optimization of the existing optimal SNAC controller to drive the states of the plant to a desired reference by minimizing a predefined cost function. The neural network weight update rule for the online networks has been derived using Lyapunov theory that guarantees both the stability of the error dynamics as well as boundedness of the weights. This approach has been applied to control the frictional dynamics of a nano-scale array of particles to track a predefined value of average sliding velocity. Here, the system is in an output feedback form where all states are not available for measurement. This is a significant step towards optimal control of systems at nano levels. Numerical results from simulation studies are presented.

Time Series Forecasting via a Higher Order Neural Network trained with the Extended Kalman Filter for Smart Grid Applications

2013 ◽  
pp. 254-274 ◽  
Author(s):  
Luis J. Ricalde ◽  
Glendy A. Catzin ◽  
Alma Y. Alanis ◽  
Edgar N. Sanchez
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Kalman Filter ◽  
Extended Kalman Filter ◽  
Smart Grids ◽  
Real Data ◽  
Higher Order ◽  
Time Series Forecasting ◽  
Wind Energy Generation ◽  
The Neural Network

This chapter presents the design of a neural network that combines higher order terms in its input layer and an Extended Kalman Filter (EKF)-based algorithm for its training. The neural network-based scheme is defined as a Higher Order Neural Network (HONN), and its applicability is illustrated by means of time series forecasting for three important variables present in smart grids: Electric Load Demand (ELD), Wind Speed (WS), and Wind Energy Generation (WEG). The proposed model is trained and tested using real data values taken from a microgrid system in the UADY School of Engineering. The length of the regression vector is determined via the Lipschitz quotients methodology.

Neural Networks L2-Gain Controller Design for Nonlinear System

2011 ◽  
Vol 467-469 ◽  
pp. 1505-1510
Author(s):  
Dan Liu ◽  
Ni Hong Wang ◽  
Gui Ying Li
Keyword(s):  
Neural Network ◽  
Disturbance Rejection ◽  
Differential Inequality ◽  
Controller Design ◽  
Design Method ◽  
General Structure ◽  
The Neural Network ◽  
Network Weight ◽  
Finite Gain ◽  
L2 Gain

This paper proposes a new method that it uses the neural network to construct the solution of the Hamiltion-Jacobi inequality (HJ), and it carries on the optimization of the neural network weight using the genetic algorithm. This method causes the Lyapunov function to satisfy the HJ, avoides solving the HJ parital differential inequality, and overcomes the difficulty which the HJ parital differential inequality analysis. Beside this, it proposes a design method of a nonlinear state feedback L2-gain disturbance rejection controller based on HJ, and introduces general structure of L2-gain disturbance rejection controller in the form of neural network. The simulation demonstrates the design of controller is feasible and the closed-loop system ensures a finite gain between the disturbance and the output.

Sign in / Sign up

Export Citation Format

Share Document