The Particle Swarm Optimization (PSO) was used to select the three best inputs to explain the input-output relationship of both 'defects' and 'time' models. A ranking-based system was used to select the best features. Using this system, the value of each particle in the swarm represents the importance of each feature. During optimization, the three best-ranked features were used to train the Mu...

In this study, an artificial neural network was used to predict the minimum force required to single point incremental forming (SPIF) of thin sheets of Aluminium AA3003-O and calamine brass Cu67Zn33 alloy. Accordingly, the parameters for processing, i.e., step depth, the feed rate of the tool, spindle speed, wall angle, thickness of metal sheets and type of material were selected as input and t...

Network in network (NiN) is an effective instance and an important extension of deep convolutional neural network consisting of alternating convolutional layers and pooling layers. Instead of using a linear filter for convolution, NiN utilizes shallow multilayer perceptron (MLP), a nonlinear function, to replace the linear filter. Because of the powerfulness of MLP and 1 x 1 convolutions in spa...

In this paper we present an efficient system for independent speaker speech recognition based on neural network approach. The proposed architecture comprises two phases: a preprocessing phase which consists in segmental normalization and features extraction and a classification phase which uses neural networks based on nonparametric density estimation namely the general regression neural networ...

We describe a new approach to multiple class pattern classification problems with noise and high dimensional feature space. The approach uses a random matrix X which has a specified distribution with mean M and covariance matrix ri j(Σs +Σ ) between any two columns of X . When Σ is known, the maximum likelihood estimators of the expectation M, correlation Γ, and covariance Σs can be obtained. T...

A general framework for similarity-based (SB) classification methods is presented. Neural networks, such as the Radial Basis Function (RBF) and the Multilayer Perceptrons (MLPs) models, are special cases of SB methods. Many new versions of minimal distance methods are derived from this framework.

This article compares the performance of some recently developed incremental neural networks with the wellknown multilayer perceptron (MLP) on real-world data. The incremental networks are fuzzy ARTMAP (FAM), growing neural gas (GNG) and growing cell structures (GCS). The realworld datasets consist of four different datasets posing different challenges to the networks in terms of complexity of ...

Two time delay neural network (TDNN) based forecasting systems are proposed to perform dynamic bandwidth reservation for real-time, variable bit rate (VBR) video service in ATM networks. Both multilayered perceptron (MLP) and pi-sigma network (PSN) based systems are found to give highly reliable predictions even in a nonstationary environment. Their performance is quantiied through simulation e...

abstract recent interest in describing the spatial distribution patterns of weeds through using interpolation methods has increased to estimate weed seedling density from spatially refferenced data and evaluation of applicable to site-specific weed management. in this research, a multi layer perceptron neural network (mlpnn) model was developed to predict the spatial distribution of h. glaucum ...