We propose a novel method that uses convolutional neural networks (CNNs) for feature extraction. Not just limited to conventional spatial domain representation, we use multilevel 2D discrete Haar wavelet transform, where image representations are scaled to a variety of different sizes. These are then used to train different CNNs to select features. To be precise, we use 10 different CNNs that s...

Dryer system is a controlled plant which is normally used in chemical industry. The proper modeling of this system facilitates its maintenance and keeping. Normally this is not an easy task, unless having a complete model of the process, due to sudden and nonlinear events. In this paper the linear identification of dryer plant in Arak petroleum, is introduced according to the Autoregressive wit...

This paper gives the definition of Transparent Neural Network “TNN” for the simulation of the globallocal vision and its application to the segmentation of administrative document image. We have developed and have adapted a recognition method which models the contextual effects reported from studies in experimental psychology. Then, we evaluated and tested the TNN and the multi-layer perceptron...

In this paper, the application of neural networks to study the maximum and minimum relative humidity for Chandigarh city is explored. One important architecture of neural networks named Multi-Layer Perceptron (MLP) to model forecasting system is used and Back Propagation algorithm is used to train the network. The proposed network is trained with actual data of the past 10 years (2000-2010) and...

This work addresses a fuzzy set based evolving modeling (FBeM) approach and the task of trading strategies performance. FBeM is a granular computing technique that uses fuzzy information granules to model nonstationary functions providing functional and linguistic approximations. As an application, we consider the BRL/USD exchange rate for the period from January 2000 to October 2012. Caparison...

| Estimating the Skew Angle in text document images can be a crucial problem in Optical Character Recognition. Based on a new sensor array processing technique, an original solution to Skew Angle Estimation (SAE) is proposed. Thanks to the reformulation of the SAE problem in the framework of Angle of Arrival theory, a fast and accurate method is presented, that is based on the cooperation of tw...

We use a multi-layer perceptron (MLP) to transform cepstral features into features better suited for speaker recognition. Two types of MLP output targets are considered: phones (Tandem/HATS-MLP) and speakers (Speaker-MLP). In the former case, output activations are used as features in a GMM speaker recognition system, while for the latter, hidden activations are used as features in an SVM syste...

Loss rate is one of the most important Quality of Service (QoS) requirements in a packet communication network carrying multimedia traac. This paper presents a method for estimating loss rates as a function of a feature vector, x, based on a maximum likelihood principle. Two backpropagation networks, a multi-layer perceptron (MLP) network and a radial basis function (RBF) network, are applied t...

A supervised method is proposed for automated segmentation of vessels in fundus images of retina. This method is used to detect the retinal diseases by extracting the retinal vasculature utilizing 9-D feature vector based on orientation analysis of gradient vector field, morphological transformation, line strength measures, and Gabor filter responses. The feature vector encodes information to h...

The development of a structure/reactivity relationship for aqueous phase reactions of organic compounds with OH is presented. An empirical model is used to relate the functional groups of the molecule and the rate constant of the molecule reacting with OH. An artificial neural network, the multi layer perceptron (MLP), is found to be capable of predicting the rate constants, for which the slope...