Sahoo, Goloka Behari; Ray, Chittaranjan
January 2008
Journal of Environmental Hydrology;2008, Vol. 16, p1
Academic Journal
The geometry and modeling parameters of an artificial neural network (ANN) have significant effects on its predictive performance efficiency. The optimal geometry of an ANN is problem-dependent. Although some guidance is available in the literature for the choice of geometry and modeling parameters, most ANNs are calibrated using the trial-and-error approach. This paper presents the use of genetic algorithms (GAs) to search for the optimal geometry and values of modeling parameters of a multilayer feedforward back-propagation neural network (BPNN) and a radial basis function network (RBFN). The predictive performance efficiency of the GA-ANN combination is examined using an already published experimental dataset from a crossflow membrane filtration experiment. The data include the permeate flux decline under various operating conditions (e.g., transmembrane pressure and filtration time) with different physicochemical properties of feed water (e.g., different combinations of three particle diameters, three pH values, and four ionic strengths). It is illustrated that the GAoptimized ANN predicts the permeate flux decline more accurately than a network in which the ANN calibration is accomplished using a trial-and-error approach. It is shown that scaling the training dataset to the 0 to 1 range helps the modeler find the solution range of an RBFN using GA.


Related Articles

  • fil·ter.  // American Heritage Student Science Dictionary;2009, p129 

    Definitions of the term "filter" are presented. It refers to a material that has very tiny holes and is used to separate out solid particles contained in a liquid or gas that is passed through it. It also refers to a device that allows certain frequencies of energy waves to pass while blocking...

  • fil·tra·tion.  // American Heritage Student Science Dictionary;2009, p129 

    A definition of the term "filtration" is presented. It refers to the act or process of passing a liquid or gas, such as air, through a filter in order to remove solid particles.

  • Modeling of filtration efficiency of nanoparticles in standard filter media. J. Wang; D.R. Chen; D.Y.H. Pui // Journal of Nanoparticle Research;Jan2007, Vol. 9 Issue 1, p109 

    Abstract??The goal of this study is to model the data from the experiments of nanoparticle filtration performed at the Particle Technology Lab, University of Minnesota and at the 3M Company. Comparison shows that the experimental data for filter efficiency are bounded by the values computed from...

  • Artificial neural network models for indoor temperature prediction: investigations in two buildings. Thomas, Bertil; Soleimani-Mohseni, Mohsen // Neural Computing & Applications;2007, Vol. 16 Issue 1, p81 

    The problem how to identify prediction models of the indoor climate in buildings is discussed. Identification experiments have been carried out in two buildings and different models, such as linear ARX-, ARMAX- and BJ-models as well as non-linear artificial neural network models (ANN-models) of...

  • Synchronization of general chaotic systems using neural controllers with application to secure communication. Sheikhan, Mansour; Shahnazi, Reza; Garoucy, Sahar // Neural Computing & Applications;Feb2013, Vol. 22 Issue 2, p361 

    The main contribution of this paper is to propose a nonlinear robust controller to synchronize general chaotic systems, such that the controller does not need the information of the chaotic system's model. Following this purpose, in this paper, two methods are proposed to synchronize general...

  • Prediction of Climate Change Induced Temperature Rise in Regional Scale Using Neural Network. Kh, Ashrafi; M, Shafiepour; L, Chasemi; B, Najar Araabi // International Journal of Environmental Research;Summer2012, Vol. 6 Issue 3, p677 

    The objective of this paper is to develop an artificial neural network (ANN) model which can be used to predict temperature rise due to climate change in regional scale. In the present work data recorded over years 1985-2008 have been used at training and testing steps for ANN model. The...

  • Architecture Exploration Based on GA-PSO Optimization, ANN Modeling, and Static Scheduling. Elhossini, Ahmed; Areibi, Shawki; Dony, Robert // VLSI Design;2013, p1 

    Embedded systems are widely used today in different digital signal processing (DSP) applications that usually require high computation power and tight constraints. The design space to be explored depends on the application domain and the target platform. A tool that helps explore different...

  • Task Time Optimization of a Robot Manipulator using Artificial Neural Network and Genetic Algorithm. Dubey, Akash Dutt; Mishra, R. B.; Jha, A. K. // International Journal of Computer Applications;8/1/2012, Vol. 51, p26 

    In this paper we have proposed an evolutionary method to optimize the task time of robot manipulators. Tasks can be planned in joint space with respect to robot joints or in Cartesian space with respect to robot end effector under kinodynamic constraints. Genetic algorithm is implemented to...

  • HYBRID NEURAL NETWORK-PARTICLE SWARM ALGORITHM TO DESCRIBE CHAOTIC TIME SERIES. Lazzús, Juan A.; Salfate, Ignacio; Montecinos, Sonia // Neural Network World;2014, Issue 6, p601 

    An artificial neural network (ANN) based on particle swarm optimization (PSO) was developed for the time series prediction. This hybrid ANN+PSO algorithm was applied on Mackey-Glass series in the short-term prediction x(t+6) and the long-term prediction x(t + 84), from the current value x(t) and...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics