Soft sensing technique has been extensively used to predict key quality variables in industrial systems. However, due to the difficulty of quality variable acquisition, only limited labeled data samples are available, and a large number of unlabeled ones are discarded. This raises a big challenge to build a high-quality soft sensor model. In order to furthest exploit information contained in both the labeled and unlabeled data, this paper proposes a principal component-based semi-supervised extreme learning machine (referred to as PCSELM) model. Through this model, extracting latent features and learning nonlinear input-output relationship can be simultaneously performed. In this way, unlabeled samples are utilized efficiently for feature representation and model accuracy improvement. Moreover, mixed regularizations are employed to work in conjunction with the PCSELM to obtain high generality and flexibility. We also derive an efficient parameter learning algorithm with theoretically guaranteed convergence. Comprehensive experiments are conducted via an industrial process. Comparison results illustrate that the proposed PCSELM outperforms other representative semi-supervised algorithms.Note to Practitioners—Industrial processes in general incorporate unlabeled samples which are ubiquitous in real world applications. The focus of this paper is to develop a semi-supervised soft sensor model (PCSELM) that is capable to learn the nonlinear features and regression relationship efficiently with both the labeled and unlabeled samples. The proposed model can automatically implement the feature representation and the input-output relationship description. In addition, we introduce mixed norms for the model objective function to improve the final prediction performance and generalization. A feasible model optimization technique with proved convergence is also derived. Experimental results based on a real industrial dataset manifest that PCSELM achieves better prediction accuracy than its peers.

Social networks are an essential component of the Internet of People (IoP) and play an important role in stimulating interactive communication among people. Graph convolutional networks provide methods for social network analysis with its impressive performance in semi-supervised node classification. However, the existing methods are based on the assumption of balanced data distribution and ignore the imbalanced problem of social networks. In order to extract the valuable information from imbalanced data for decision making, a novel method named minority-weighted graph neural network (mGNN) is presented in this article. It extends imbalanced classification ideas in the traditional machine learning field to graph-structured data to improve the classification performance of graph neural networks. In a node feature aggregation stage, the node membership values among nodes are calculated for minority nodes’ feature aggregation enhancement. In an oversampling stage, the cost-sensitive learning is used to improve edge prediction results of synthetic minority nodes, and further raise their importance. In addition, a Gumbel distribution is adopted as an activation function. The proposed mGNN is evaluated on six social network data sets. Experimental results show that it yields promising results for imbalanced node classification.

The generation and updating of solutions, e.g., crossover and mutation, of many existing evolutionary algorithms directly operate on decision variables. The operators are very time consuming for large-scale and many-objective optimization problems. Different from them, this work proposes an objective space-based population generation method to obtain new individuals in the objective space and then map them to decision variable space and synthesize new solutions. It introduces three new objective vector generation methods and uses a linear mapping method to tightly connect objective space and decision one to jointly determine new-generation solutions. A loop can be formed directly between two spaces, which can generate new solutions faster and use more feedback information in the objective space. In order to demonstrate the performance of the proposed algorithm, this work performs a series of empirical experiments involving both large-scale decision variables and many objectives. Compared with the state-of-the-art traditional and large-scale algorithms, the proposed method exceeds or at least reaches its peers’ best level in overall performance while achieving great saving in execution time.

Abstract Question generation (QG) refers to the automatic generation of questions based on the given passages and answers, and has a wide range of application scenarios in human–computer interaction, education, medical and other fields. However, for Chinese QG, due to the lack of word separation in the writing rules of Chinese text, many methods are not suitable for it, and the generated results have incorrect word order and invalid expressions. In addition, traditional models only use labeled data, but it is difficult and expensive to obtain data labels. In order to solve this problem, this article proposes a semi‐supervised QG model termed virtual stroke‐aware copy network (VSAC Net). It is based on virtual adversarial training and can be used for Chinese QG tasks with few labeled samples. The VSAC Net model combines word embedding virtual counter disturbance and attention virtual counter disturbance, the fitting of the input layer and the attention layer is taken into account, and reduces the overfitting of the model. According to Dureader dataset, a small sample QG dataset is constructed, and the VSAC Net is used for solving. The results show that the proposed model can achieve a better generation effect on small sample datasets.

Extreme learning machine (ELM) is suitable for nonlinear soft sensor development. Yet it faces an overfitting problem. To overcome it, this work integrates bound optimization theory with variational Bayesian (VB) inference to derive novel L1 norm-based ELMs. An L1 term is attached to the squared sum cost of prediction errors to formulate an objective function. Considering the nonconvexity and nonsmoothness of the objective function, this article uses bound optimization theory, and constructs a proper surrogate function to equivalently convert a challenging L1 norm-based optimization problem into easy one. Then, VB inference is adopted for optimizing the converted problem. Thus, an L1 norm-based ELM can be efficiently optimized by an alternating optimization algorithm with a proved convergence. Finally, a soft sensor is developed based on the proposed algorithm. An industrial case study is carried out to demonstrate that the proposed soft sensor is competitive against recent ones.

Abstract The problem of imbalanced data classification has become a research hotspot in the field of machine learning. Fuzzy support vector machine (FSVM) is an imbalanced classification processing method based on cost‐sensitive theory. The existing methods have cost‐sensitive, causing the prior distribution estimation of data inaccurate. This article proposes a novel FSVM algorithm based on the kernel local outlier factor (KLOF‐FSVM) for this problem. KLOF calculates the local outlier factor of the sample in the kernel space and assigns an appropriate membership value to the sample. This process enables the algorithm to obtain the distribution information of the data better. Compared with the algorithm based on distance only, KLOF has better robustness. It can expand the value range of majority class samples' membership degree to better balance the important relation between the minority class and the majority class. We selected some datasets in the Keel data repository and used cross‐validation to obtain the algorithm's effect under different evaluation indexes such asG‐Mean,F1 measure, and area under curve. By comparing with other algorithms, preliminary results show that this method has better classification quality.

Abstract With the continuous development of convolutional neural networks (CNNs), image classification technology has entered a new stage in solving visual cognition tasks. Recent advances have shown that if containing short connections, convolutional networks can be more accurate and efficient to train. However, these short connections almost only exist between convolutional layers, which potentially make the feature information flow insufficiently. In addition, the multi‐scale representation ability of CNNs using short connections can be further explored. Thus, the dense short connection network (DSCNet) for efficient image classification is designed in this paper. In DSCNet, we propose a simple yet effective architectural unit, namely dense short connection (DSC) module, which allows hierarchical dense short connections for multi‐scale context information across different feature channels within a single convolutional layer. DSCNets have several noteworthy advantages: they improve the multi‐scale representation ability, enhance feature propagation, and reduce the number of parameters. To validate our DSC, we conduct comprehensive experiments on CIFAR‐100 and Tiny ImageNet datasets. Experimental results show that DSCNets achieve very competitive results with previous baseline models, whilst requiring less computation to achieve higher recognition accuracy. Further ablation studies show that our proposed method can achieve consistent performance gains in image classification tasks.

Summary Question generation is a promising and important area in natural language processing. According to the information of the given text, the question generation model can automatically generate a variety of questions, which are conducive to processing various subsequent tasks. Chinese question generation is a specific sub‐area of question generation. Due to the characteristics of Chinese question generation tasks, many methods are not suitable for it, and the generated results are either incorrect in word order or invalid expression. In order to address such challenging problem, we propose the conditional pre‐trained attention model termed A Lite BERT Conditional Question Generation (ALBERT‐CQG) for Chinese question generation. Through introducing general background knowledge of the pre‐trained model and conditional information of the given answers, this model has capacity of generating more valid expression. To our knowledge, we are the first to apply the conditional pre‐trained attention model to Chinese question generation tasks. The experimental results on two known benchmark datasets of Chinese question answering show that the ALBERT‐CQG outperforms its recent peers.

As the supply potential has declined gradually and the pressure for better environment intensifies, the demand for clean energy arises continuously. The consumptive demand for Plug-in Hybrid Electric Vehicle (PHEV) thus increases. However, load peak caused by their disordered charging can be detrimental to an entire power grid. Several methods have been proposed to establish ordered PHEV charging. While focusing on single-objective optimal load scheduling, they fail to meet the real requirements for efficient multiple objective optimization. This work proposes a novel weight-aggregation based multi-objective particle swarm optimization method to solve the load scheduling problem. Its effectiveness and efficiency to generate a Pareto front of this problem are verified and compared with those of the state-of-the-art approaches.

Distributed generation becomes more and more important in modern power systems. However, the increasing use of distributed generators causes the concerns on the increasing system risk due to their likely failure or uncontrollable power outputs based on such renewable energy sources as wind and the sun. This work for the first time formulates an optimal power flow problem by considering controllable and uncontrollable distributed generators in power networks. The problem for the cases of single and multiple generator failures is addressed as an example. The methods are presented to find its power output solution of controllable online generators via particle swarm optimization and group search optimizer for coping with the difficult scenarios in a power network. The proposed methods are tested on an IEEE 14-bus system, and several population initialization strategies are investigated and compared for the algorithms. The simulation results confirm their effectiveness for optimal power management and effective control of a power network.

This paper presents an efficient and reliable approach based on swarm intelligence to solve the optimal power flow problem. The optimal setting of distributed generations (DGs) is addressed if one or more generators broken down in a power distribution system, to achieve minimization of fuel cost and voltage profile stability. The proposed approach employs particle swarm optimization (PSO) and group search optimizer (GSO) for optimal setting of DGs. These algorithms are executed and compared on IEEE 14-bus test system, respectively. The results confirm the effectiveness and potential application of the proposed swarm-based optimization method in power distribution systems.

Turbo Codes present a new direction for the channel encoding, especially since they were adopted for multiple norms of telecommunications, such as deeper communication, etc. To obtain an excellent performance, it is necessary to design robust turbo code interleaver and decoding algorithms. In this paper, we are investigating particle swarm algorithm as a promising optimization method to find good interleaver for the large frame sizes, as well as design the decoding optimization mode (PSO-Turbo); and apply the proposed PSO-Turbo codes mode to the security radio data transmission; in which, a kind of transport control proposal based on PSO-Turbo optimizer for CBTC wireless channel is designed and simulated to validate our method.