This thesis presents a practical approach to model based control of nonlinear dynamical systems using multilayered perceptron type neural networks as process models and controllers. A framework for modeling and identification of nonlinear time series models is introduced. Advanced parameter estimation methods are used to identify the weights of the process model and controller networks. A novel...

Controlling the indoor environmental quality in real time is essential for health, well-being and productivity of occupants a building. In recent years, research has focused on improving monitoring devices strategies developing techniques estimating conditions. The use machine learning algorithms this context increased considerably. However, data from large multizone working areas challenging. ...

An attempt is made to implement the soft computing techniques in the prediction of the mishaps behaviors. The main objective of this paper is to implement the Multilayer Perceptron (MLP) neural network topology in mishap analysis and prediction. Efforts are made to summarize past research on the road mishaps causes and their analysis techniques and point out their weaknesses. Indicate new ideas...

In the last decades it often has been shown that Multilayer Perceptrons (MLPs) are powerful function approximators. They were successfully applied to a lot of different classification problems. However, originally they only deal with real valued numbers. Since PolSAR data is a complex valued signal this paper propose the usage of Complex Valued Neural Networks (CVNNs), which are an extension of...

A denoising unit based on wavelet multiresolution analysis is added ahead of the multilayered perceptron with global recurrent connections. The learning algorithm is developed which uses the same cost function for setting all free parameters, those of the denoising unit and those of the neural network. It is illustrated that the proposed model outmatches the models without denoising unit and/or...

Usually in multivariate regression problem it is assumed that residuals of outputs are independent of each other. In many applications a more realistic model would allow dependencies between the outputs. In this paper we show how a Bayesian treatment using Markov Chain Monte Carlo (MCMC) method can allow for a full covariance matrix with Multi Layer Perceptron (MLP) neural networks.

the current study addresses an estimation of investor's optimal portfolio under conditions of uncertainty by using a combination of artificial neural network and markowitz models. for this purpose, such assets as stock prices, house prices, coin and bonds price are used with monthly data over the period 1378-1392. three variables including inflation uncertainty, oil uncertainty and free ma...

Software cost estimation is an important phase in software development. It predicts the amount of effort and development time required to build a software system. It is one of the most critical tasks and an accurate estimate provides a strong base to the development procedure. In this paper, the most widely used software cost estimation model, the Constructive Cost Model (COCOMO) is discussed. ...