Zefei Zhu

Illumination correction of dyed fabrics approach using Bagging-based ensemble particle swarm optimization-extreme learning machine

Abstract. Changes in illumination will result in serious color difference evaluation errors during the dyeing process. A Bagging-based ensemble extreme learning machine (ELM) mechanism hybridized with particle swarm optimization (PSO), namely Bagging–PSO–ELM, is proposed to develop an accurate illumination correction model for dyed fabrics. The model adopts PSO algorithm to optimize the input weights and hidden biases for the ELM neural network called PSO–ELM, which enhances the performance of ELM. Meanwhile, to further increase the prediction accuracy, a Bagging ensemble scheme is used to construct an independent PSO–ELM learning machine by taking bootstrap replicates of the training set. Then, the obtained multiple different PSO–ELM learners are aggregated to establish the prediction model. The proposed prediction model is evaluated with real dyed fabric images and discussed in comparison with several related methods. Experimental results show that the ensemble color constancy method is able to generate a more robust illuminant estimation model with better generalization performance.

A novel hybrid model using the rotation forest-based differential evolution online sequential extreme learning machine for illumination correction of dyed fabrics

This study proposes an ensemble differential evolution online sequential extreme learning machine (DE-OSELM) for textile image illumination correction based on the rotation forest framework. The DE-OSELM solves the inaccuracy and long training time problems associated with traditional illumination correction algorithms. First, the Grey–Edge framework is used to extract the low-dimensional and efficient image features as online sequential extreme learning machine (OSELM) input vectors to improve the training and learning speed of the OSELM. Since the input weight and hidden-layer bias of OSELMs are randomly obtained, the OSELM algorithm has poor prediction accuracy and low robustness. To overcome this shortcoming, a differential evolution algorithm that has the advantages of good global search ability and robustness is used to optimize the input weight and hidden-layer bias of the DE-OSELM. To further improve the generalization ability and robustness of the illumination correction model, the rotation forest algorithm is used as the ensemble framework, and the DE-OSELM is used as the base learner to replace the regression tree algorithm in the original rotation forest algorithm. Then, the obtained multiple different DE-OSELM learners are aggregated to establish the prediction model. The experimental results show that compared with the textile color correction algorithm based on the support vector regression and extreme learning machine algorithms, the ensemble illumination correction method achieves high prediction accuracy, strong robustness, and good generalization ability.

Regularization incremental extreme learning machine with random reduced kernel for regression

Abstract For regression tasks, the existing extreme learning machine (ELM) and kernel extreme learning machine (KELM) algorithms exhibit singularity and over-fitting problems when the number of training samples is less than the number of hidden layer neurons. To overcome these shortcomings, this paper introduces random reduction kernel and regularization parameters, and the regularization incremental extreme learning machine with random reduced kernel (RKRIELM) algorithm is proposed. RKRIELM combines the kernel function and incremental extreme learning machine (I-ELM) to avoid randomness, thereby solving the singularity problem when the number of initial training samples of the ELM is less than the number of hidden layer neurons. Moreover, it uses the number of hidden layer neurons as the precondition for the loop ending of the training algorithm. Additionally, the regularization parameter is used to reduce the risk of over-fitting. Regression experiments were conducted for evaluating the proposed method, ELM, KELM, reduced kernel extreme learning machine, rotation forest selective ensemble extreme learning machine, reduced support vector regression, and gray wolf optimization support vector regression with standard data sets. The results indicate that the proposed method has a lower prediction error and better training efficiency than the other algorithms in most cases.

Inverse kinematics solution for robotic manipulator based on extreme learning machine and sequential mutation genetic algorithm

This article presents an intelligent algorithm based on extreme learning machine and sequential mutation genetic algorithm to determine the inverse kinematics solutions of a robotic manipulator with six degrees of freedom. This algorithm is developed to minimize the computational time without compromising the accuracy of the end effector. In the proposed algorithm, the preliminary inverse kinematics solution is first computed by extreme learning machine and the solution is then optimized by an improved genetic algorithm based on sequential mutation. Extreme learning machine randomly initializes the weights of the input layer and biases of the hidden layer, which greatly improves the training speed. Unlike classical genetic algorithms, sequential mutation genetic algorithm changes the order of the genetic codes from high to low, which reduces the randomness of mutation operation and improves the local search capability. Consequently, the convergence speed at the end of evolution is improved. The performance of the extreme learning machine and sequential mutation genetic algorithm is also compared with that of a hybrid intelligent algorithm, and the results showed that there is significant reduction in the training time and computational time while the solution accuracy is retained. Based on the experimental results, the proposed extreme learning machine and sequential mutation genetic algorithm can greatly improve the time efficiency while ensuring high accuracy of the end effector.

RFSEN-ELM: Selective ensemble of extreme learning machines using rotation forest for image classification

Extreme learning machine (ELM), as a new learning mechanism for single hidden layer feedforward neural networks (SLFNs), has shown its good performance, such as fast computation speed and good generalization performance. However, the weak robustness of ELM is an unavoidable defect for image classification tasks. Thus, we propose a novel ensemble method combined rotation forest and selective ensemble model to overcome this problem in this paper. Firstly, ELM and rotation forest are integrated to construct an ensemble classifier (RF-ELM), which combines the advantages of both rotation forest and ELM. The purpose of rotation forest here is to enhance the diversity of each base classifier, thus improving the robustness of classification. Then several ELMs are removed from the ensemble pool by using genetic algorithm (GA) based selective ensemble model to further enhance the generalization performance. Finally, the remaining ELMs are grouped as a selected ensemble classifier (RFSEN-ELM) for image classification. The performance is analysed and compared with several existing methods on benchmark datasets and the experimental results demonstrate that the proposed algorithm substantially improves the accuracy and robustness of classification at an acceptable level of training cost.