To improve efficiency and classification accuracy, and overcome the issue of poor generalization performance of traditional fabric defect classification methods, we present a new fabric defect classification algorithm with evolving Inception v3 by improved L_2,1-norm regularized extreme learning machine. Herein, first, the features of fabric images are extracted using Inception v3, which reduces the amount of computation and improves the accuracy of feature extraction. Second, an L2,1-norm regularization extreme learning machine algorithm based on multi-verse optimizer–Henry gas solubility optimization, called MHL21-RELM, is proposed. The proposed algorithm solves the problems of the low classification accuracy of the traditional ELM and prevents the algorithm from easily falling into the local optimal solution. Next, instead of SoftMax, MHL21-RELM is used as the classification network layer of Inception V3, and a new fabric defect classification algorithm named Inv3-MHL21-RELM is proposed to enhance the fabric defect classification performance. Finally, the performance of our algorithm is verified by experiments on different fabric defect datasets. The proposed method achieves 97.29% classification accuracy with the Textile Texture Database; it achieves a 6–30% improvement in classification accuracy compared with other traditional fabric defect classification methods, thus effectively improving the classification accuracy of fabric defects. In addition, this method achieves good classification results with different types of fabric defect datasets, thereby showing strong generalization.

To mitigate the problem of low classification accuracy in solid color printing and dyeing, a color difference classification model based on the differential evolution (DE) improved whale optimization algorithm (WOA) for extreme learning machine (ELM) optimization, named the DE–WOA–ELM, was developed in this study. Considering that the initial population of the WOA has a significant influence on the solution speed and quality, DE was used to generate a more suitable initial population for the WOA by avoiding local optima, thereby improving the performance. The method used an excellent global search ability to improve the WOA for optimization and obtained an optimal parameter combination for the ELM. Thus, the problem of randomly initializing the input weight and the hidden layer bias of the ELM, which leads to a nonuniform training model and unstable algorithm, was solved. Finally, by optimizing the input weight and hidden layer bias, the color difference classification model of the ELM with a strong generalization ability was constructed. The results of the color difference classification experiments on fabric images collected under standard light sources show that the average classification accuracy for the dataset is increased by 2.15%, 11.06%, 12.11%, and 0.47% compared with those of the ELM, support vector machine, back propagation neural network, and kernel ELM, respectively.

The visibility of fishes and invertebrates is highly impacted by the complexity of the environment. Images acquired in underwater environments suffer from blurriness and low contrast. This results in a low classification accuracy. To address this problem, this study uses a pre-trained Resnet50 neural network as the feature extractor, which avoids over-fitting and accuracy saturation while realizing improved feature extraction capabilities. It also proposes an enhancement of the error-minimized random vector functional link (EEMRVFL) neural network, which is used as the classifier in the convolutional neural network (CNN) model instead of the original softmax classifier. EEMRVFL reduces the maximum residual error in each incremental process. The selected hidden nodes are added to the network, which improves the compactness of its structure. The proposed residual CNNs model exhibits improved classification accuracy for underwater image classification compared to existing methods. This is demonstrated experimentally on available datasets such as URPC, LifeCLEF 2015, and Fish4Knowledge with accuracy rates reaching 99.68%, 97.34%, and 99.77%, respectively.

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.

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.

To improve accuracy in clothing image recognition, this paper proposes a clothing classification method based on a parallel convolutional neural network (PCNN) combined with an optimized random vector functional link (RVFL). The method uses the PCNN model to extract features of clothing images. Then, the structure-intensive and dual-channel convolutional neural network (i.e., the PCNN) is used to solve the problems of traditional convolutional neural networks (e.g., limited data and prone to overfitting). Each convolutional layer is followed by a batch normalization layer, and the leaky rectified linear unit activation function and max-pooling layers are used to improve the performance of the feature extraction. Then, dropout layers and fully connected layers are used to reduce the amount of calculation. The last layer uses the RVFL as optimized by the grasshopper optimization algorithm to replace the SoftMax layer and classify the features, further improving the stability and accuracy of classification. In this study, two aspects of the classification (feature extraction and feature classification) are improved, effectively improving the accuracy. The experimental results show that on the Fashion-Mnist dataset, the accuracy of the algorithm in this study reaches 92.93%. This value is 1.36%, 2.05%, 0.65%, and 3.76% higher than that of the local binary pattern (LBP)-support vector machine (SVM), histogram of oriented gradients (HOG)-SVM, LBP-HOG-SVM, and AlexNet-sparse representation-based classifier algorithms, respectively, effectively demonstrating the classification performance of the algorithm.