fuzzi cluster algorithm help when exist dataset subgroup point have indistinct boundari overlap between cluster tradit method have been extens studi use realworld data requir user have some knowledg outcom priori order determin how mani cluster look addition iter algorithm choos optim number cluster base one sever perform measur studi author compar perform three algorithm fuzzi cmean gustafsonkessel iter version gustafsonkessel when cluster tradit data set well realworld geophys data were collect from archaeolog site wyom area interest were identifi use crisp cutoff valu well fuzzi cut determin which provid better elimin nois nonrelev point result indic cut method elimin more nois than crisp cutoff valu iter version fuzzi cluster algorithm abl select optimum number subclust within point set both tradit realworld data lead proper indic region interest further expert analysi

David J. Miller

Carl A. Nelson

Molly Boeka Cannon

Kenneth P. Cannon

Comparison of Fuzzy Clustering Methods and Their Applications to Geophysics Data

this paper present automat system neural network nns has abil simul predict mani appli problem the system architectur automat reorgan experiment process start again requir perform reach this process continu until perform obtain this system first appli test two spiral problem show excel general perform obtain classifi all point twospir correct after appli test shear stress pressur drop problem across short orific die function shear rate differ mean pressur linear lowdens polyethylen copolym lldpe the system show better agreement experiment data two case shear stress pressur drop the propos system has been also design simul other distribut present train set predict match them effect

G. M. Behery

A. A. El-Harby

Mostafa Y. El-Bakry

Reorganizing Neural Network System for Two Spirals and Linear Low-Density Polyethylene Copolymer Problems

focus time lag recurr neural network ftlr gamma memori filter design learn subtl complex dynam typic cstr process continu stir tank reactor exhibit complex nonlinear oper where reaction exotherm notic from literatur review process control cstr use neurofuzzi system attempt mani optim neural network model identif cstr process yet avail cstr process includ tempor relationship inputoutput map time lag recurr neural network particular use identif purpos the standard back propag algorithm momentum term has been propos model the various paramet like number process element number hidden layer train test percentag learn rule transfer function hidden output layer investig basi perform measur like mse nmse correl coeffici test data set final effect differ norm test along variat gamma memori filter demonstr dynam model has remark system identif capabl problem consid paper thus ftlr gamma memori filter can use learn under high nonlinear dynam system which major contribut paper

S. N. Naikwad

S. V. Dudul

Identification of a Typical CSTR Using Optimal Focused Time Lagged Recurrent Neural Network Model with Gamma Memory Filter

neurofuzzi control design implement use labview over mobil robot platform the control base fuzzi cluster neural network search techniqu also wireless communic bluetooth protocol use communic robot control run labview allow simpl collabor task consist pick place object through know posit robot measur distanc object the neurofuzzi control split two part posit control evas control against collis

Hiram E. Ponce

Dejanira Araiza

Pedro Ponce

A Neuro-Fuzzy Controller for Collaborative Applications in Robotics Using LabVIEW

this studi propos neural networkfamili competit genet algorithm nnfcga solv electromagnet optim other generalpurpos optim problem the nnfcga hybrid evolutionarybas algorithm combin good approxim perform neural network robust effect optimum search abil famili competit genet algorithm fcga acceler optim process studi nnfcga use extract set optim design paramet two repres design exampl multipl section lowpass filter polygon electromagnet absorb our result demonstr optim electromagnet properti given nnfcga compar those fcga reduc larg amount comput time welltrain model can serv nonlinear approxim develop dure optim process nnfcga

P.-Y. Chen

C.-H. Chen

H. Wang

A Neural Network: Family Competition Genetic Algorithm and Its Applications in Electromagnetic Optimization

multistep ahead predict chaotic time seri difficult task has attract increas interest recent year the interest work develop nonlinear neural network model purpos build multistep chaotic time seri predict literatur wide rang differ approach success depend predict perform individu method also most popular neural model base statist tradit feed forward neural network but seen kind neural model may present some disadvantag when longterm predict requir paper focus timelag recurr neural network ftlrnn model gamma memori develop differ predict horizon observ predictor perform remark well shortterm predict well mediumterm predict for coupl partial differenti equat generat chaotic time seri mackey glass duf ftlrnnbase predictor perform consist well differ depth predict rang from short term long term onli slight deterior after increas beyond 50 for realworld high complex nonstationari time seri like sunspot laser though propos predictor doe perform reason short term mediumterm predict it predict abil drop long term ahead predict howev still best possibl predict result consid fact nonstationari time seri matter fact other configur can match perform ftlrnn model the author experi perform ftlrnn model predict dynam behavior typic chaotic mackeyglass time seri duf time seri two realtim chaotic time seri month sunspot laser static multi layer perceptron mlp model also attempt compar against propos model perform measur like mean squar error mse normal mean squar error nmse correl coeffici the standard backpropag algorithm momentum term has been use both model

Sanjay L. Badjate

Sanjay V. Dudul

Novel FTLRNN with Gamma Memory for Short-Term and Long-Term Predictions of Chaotic Time Series

electromyographi emg signal can use clinic biomed applic modern human comput interact emg signal acquir nois while travel through tissu inher nois electron equip ambient nois forth ann approach studi reduct nois emg signal paper shown focus timelag recurr neural network ftlrnn can eleg solv reduc nois from emg signal after rigor comput simul author develop optim ftlrnn model which remov nois from emg signal result show propos optim ftlrnn model has mse mean squar error low 0000067 0000048 correl coeffici high 099950 099939 nois signal emg signal respect when valid test dataset also notic output estim ftlrnn model close follow real one this network inde robust emg signal toler nois varianc from 01 04 uniform nois 030 gaussian nois clear train network independ specif partit dataset seen perform propos ftlrnn model clear outperform best multilay perceptron mlp radial basi function rbf model the simpl model ftlrnn singlehidden layer can employ remov nois from emg signal

S. N. Kale

Intelligent Noise Removal from EMG Signal Using Focused Time-Lagged Recurrent Neural Network

About this journal

Applied Computational Intelligence and Soft Computing provides a forum for research that connects the disciplines of computer science, engineering, and mathematics using the technologies of computational intelligence and soft computing.

Journal profile

Meet the editorial board

Applied Computational Intelligence and Soft Computing maintains an Editorial Board of practicing researchers from around the world, to ensure manuscripts are handled by editors who are experts in the field of study.

Editor spotlight

Submit your proposal

Do you think there is an emerging area of research that really needs to be highlighted? Or an existing research area that has been overlooked or would benefit from deeper investigation? Raise the profile of a research area by leading a Special Issue.

Special Issues

Author guidelines

Editorial board

Databases and indexing

Applied Computational Intelligence and Soft Computing - Table of contents 2009

Applied Computational Intelligence and Soft Computing | Hindawi

title

Applied Computational Intelligence and Soft Computing provides a forum for research that connects the disciplines of computer science, engineering, and mathematics using the technologies of computational intelligence and soft computing.

description

Applied Computational Intelligence and Soft Computing

https://images.hindawi.com/journals/acisc/acisc.banner.jpg

Applied Computational Intelligence and Soft Computing