ELM Algorithm Research Articles

A modified ELM algorithm for the prediction of silicon content in hot metal

Silicon content in hot metal in the iron-making process has been used as a major indicator of the internal thermal state in blast furnace for many years. Due to the harsh environment in the blast furnace, how to measure the silicon content in hot metal is quite difficult. Many efforts have been made on the estimation of the silicon content in hot metal. In this paper, a soft-sensing modeling method based on a modified extreme learning machine is proposed to tackle the problem. In this approach, a modified pruning algorithm is utilized to optimize the weights which are generated randomly in the original ELM algorithm. The real data collected from a blast furnace in the factory are applied and tested by the proposed algorithm, and the results show that the proposed prediction model has less error than the other algorithm such as BP algorithm and support vector method.

Identification of nonlinear system using extreme learning machine based Hammerstein model

In this paper, a new method for nonlinear system identification via extreme learning machine neural network based Hammerstein model (ELM-Hammerstein) is proposed. The ELM-Hammerstein model consists of static ELM neural network followed by a linear dynamic subsystem. The identification of nonlinear system is achieved by determining the structure of ELM-Hammerstein model and estimating its parameters. Lipschitz quotient criterion is adopted to determine the structure of ELM-Hammerstein model from input–output data. A generalized ELM algorithm is proposed to estimate the parameters of ELM-Hammerstein model, where the parameters of linear dynamic part and the output weights of ELM neural network are estimated simultaneously. The proposed method can obtain more accurate identification results with less computation complexity. Three simulation examples demonstrate its effectiveness.

A Novel Extreme Learning Machine Based on Hybrid Kernel Function

Extreme learning machine is a new learning algorithm for the single hidden layer feedforward neural networks (SLFNs). ELM has been widely used in various fields and applications to overcome the slow training speed and over-fitting problems of the conventional neural network learning algorithms. ELM algorithm is based on the empirical risk minimization, without considering the structural risk and this may lead to over-fitting problems and at the same time, it is with poor controllability and robustness. For these deficiencies, an optimization method is proposed in this paper, a novel extreme learning machine based on hybrid kernel function (HKELM). The method constructs a hybrid kernel function with better performance by fully combining local kernel function strong learning ability and global kernel function strong generalization ability. Compared with traditional ELM, the results show that this method can effectively improve the ELM classification results, avoid local minimum, with better generalization, robustness, controllability and faster learning rate.

A Comprehensive Evaluation of Weight Growth and Weight Elimination Methods Using the Tangent Plane Algorithm

The tangent plane algorithm is a fast sequential learning method for multilayered feedforward neural networks that accepts almost zero initial conditions for the connection weights with the expectation that only the minimum number of weights will be activated. However, the inclusion of a tendency to move away from the origin in weight space can lead to large weights that are harmful to generalization. This paper evaluates two techniques used to limit the size of the weights, weight growing and weight elimination, in the tangent plane algorithm. Comparative tests were carried out using the Extreme Learning Machine which is a fast global minimiser giving good generalization. Experimental results show that the generalization performance of the tangent plane algorithm with weight elimination is at least as good as the ELM algorithm making it a suitable alternative for problems that involve time varying data such as EEG and ECG signals.

A modified extreme learning machine with sigmoidal activation functions

This paper proposes a modified ELM algorithm that properly selects the input weights and biases before training the output weights of single-hidden layer feedforward neural networks with sigmoidal activation function and proves mathematically the hidden layer output matrix maintains full column rank. The modified ELM avoids the randomness compared with the ELM. The experimental results of both regression and classification problems show good performance of the modified ELM algorithm.

Variational segmentation algorithms with label frequency constraints

We consider image and signal segmentation problems within the Markov random field (MRF) approach and try to take into account label frequency constraints. Incorporating these constraints into MRF leads to an NP-hard optimization problem. For solving this problem we present a two-step approximation scheme that allows one to use hard, interval and soft constraints on label frequencies. On the first step a factorized approximation of the joint distribution is made (only local terms are included) and then, on the second step, the labeling is found by conditional maximization of the factorized joint distribution. The latter task is reduced to an easy-to-solve transportation problem. Basing on the proposed two-step approximation scheme we derive the ELM algorithm for tuning MRF parameters. We show the efficiency of our approach on toy signals and on the task of automated segmentation of Google Maps.

Constructive hidden nodes selection of extreme learning machine for regression

In this paper, we attempt to address the architectural design of ELM regressor by applying a constructive method on the basis of ELM algorithm. After the nonlinearities of ELM network are fixed by randomly generating the parameters, the network will correspond to a linear regression model. The selection of hidden nodes can then be regarded as a subset model selection in linear regression. The proposed constructive hidden nodes selection for ELM (referred to as CS-ELM) selects the optimal number of hidden nodes when the unbiased risk estimation based criterion C P reaches the minimum value. A comparison of the proposed CS-ELM with other model selection algorithms of ELM is evaluated on several real benchmark regression applications. And the empirical study shows that CS-ELM leads to a compact network structure automatically.

Hybrid Modeling of Molten Steel Temperature Prediction in LF

Combining the conventional mechanism method with the newly developed intelligent algorithm, a hybrid model was developed for predicting the molten steel temperature in LF. The mechanism method is used to build the thermal model by analyzing the energy going into and out of the molten steel during the LF refining production process. It is hard to calculate the coefficients in the thermal model by mechanism method, so they are estimated by experience traditionally. In this paper, a new ensemble ELM algorithm using the modified AdaBoost.RT is proposed to calculate these coefficients. The new hybrid model overcomes the difficulty of obtaining the coefficients in thermal model, and solves the problem of limited prediction precision using “black box” model. The experiment demonstrates that the new hybrid model can improve generalization performance and the prediction accuracy.