In this paper, a novel Elman-type recurrent neural network (RNN) is presented for the binary classification of arbitrary symbol sequences, and training method, including both evolutionary local search methods, evaluated using sequence databases from wide range scientific areas. An efficient, publicly available, software tool implemented in C++, accelerating significantly (more than 40 times) RN...

Recurrent neural networks, especially for Elman Neural Network, have attracted the attention of researchers in the fields of Dynamic System Identification (DSI) since they took the memory unit through the context delay. In this paper, we propose an Adaptive Local Search (ALS) algorithm to train Elman Neural Network (ENN) for Dynamic Systems Identification (DSI) from a new angle instead of tradi...

The problem of short-term electric load forecasting (STLF) is considered. A modified architecture of Elman-type recurrent neural network is proposed. It utilizes a special fuzzification layer to deal with quantitative as well as ordinal and nominal data. The second hidden layer of the network consists of standard Rosenblatt-type neurons with sigmoidal activation functions. The context layer is ...

In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods...

A modeling based on the improved Elman neural network (IENN) is proposed to analyze the nonlinear circuits with the memory effect. The hidden layer neurons are activated by a group of Chebyshev orthogonal basis functions instead of sigmoid functions in this model. The error curves of the sum of squared error (SSE) varying with the number of hidden neurons and the iteration step are studied to d...

This paper presents a comparative study of state-of-the-art neurocomputing methods applied to several benchmark time series, including the white dwarf light curve. The goal is to determine which of the predictive models work best for data from natural sources. The emphasis is on using a unified methodology for selection of the best architectures among those used for comparison. The specific arc...

Previous research has been dedicated to clustering and predicting time series. Practically, we may hope to extract all re curring temporal patterns out of a temporal signal sequence. This paper proposes a new scheme for unsupervised multi -temporal sequence pattern extraction. The main idea of the scheme is iterative coarse to fine data examination. We decompose a pattern into ambiguous subpatt...