Yongfang Xie’s research while affiliated with Central South University and other places

The causal structure learning for streaming features (CSLSFs) faces the following challenges: 1) the precision of learned causal structures is limited due to the score-based learning method and 2) they fail to detect the latent confounders. To address the challenges, this article proposes a novel causal structure learning method with linear non-Gaussian acyclic models for streaming features (LiNGAM-SFs), which utilizes the causal identifiability of the data. It is the first time to utilize LiNGAMs for online causal structure learning. First, we utilize the classical SF algorithm to learn the causal skeleton. This article provides the property of this skeleton, proving that two adjacent variables on an edge is one of three possible structures. Second, we give two propositions and identify the causal directions in the presence of latent variables (ICDPLV) subalgorithm to distinguish among the three structures and precisely identify the causal directions. In addition, the subalgorithm can output a candidate set of latent confounders from a local perspective. Finally, the detecting latent confounder (DLC) subalgorithm detects the latent confounders in the candidate set with a global perspective. The precision of the proposed method is increased at least by 11% on average than those of the state-of-the-art method. Furthermore, the experiments verify that the LiNGAM-SF method is able to detect the latent confounders.

In froth flotation, the froth-layer depth is an important indicator for performance monitoring and working-condition recognition. The primary depth-measurement method in a complex industrial process is based on a binocular camera. Much related research has been proposed to obtain accurate object depth. However, since the bubbles in the froth image are convex objects, the top of each bubble has a white spot which makes the texture of each bubble very faint, rendering the existing depth-measurement method inadequate in froth flotation. Therefore, in this article, we propose a method for measuring the froth-layer depth using an intensity correction. First, we use morphological reconstruction to extract the white spots. Next, we calculate the coefficient map for depth adjustment based on the light reflection characteristics of bubbles and white spots. After that, we implement depth optimization with intensity correction using the SGBM method to obtain the froth-layer depth. Finally, based on the froth-layer depth, we design a model for pulp-grade monitoring and conduct comparative experiments in froth flotation. The results show that compared with a monocular froth image, the root mean squared error of the proposed method is reduced by 50% and R ² is increased by 44.38%. Compared with the depth map obtained by the SGBM method, the root mean squared error of the proposed method is reduced by 9.4% and R ² is increased by 13.35%.

Virtual sample generation (VSG) is an important technology for dealing with small sample learning in some industries. Using evolutionary computation algorithms to solve virtual sample generation is a promising way. However, two issues remain unaddressed in the existing VSG approaches: estimating the distribution of original samples and ensuring the authenticity of virtual samples. Thus, this paper proposes a novel Virtual Sample Generation approach based on genetic algorithm (GA) combing with Information Gain and Acceptance-rejection Sampling, abbreviated as VSG3A2. First, this work develops the ARS-VAD subalgorithm, by integrating the acceptance rejection sampling method into the crossover and mutation operations of GA. The algorithm ensures that the distribution of offspring attribute values is close to the distribution of original samples at attribute level. Second, this work presents the IG-VSS subalgorithm, which is combined with the idea of minimizing absolute information gain, to find the optimal offspring sample as a virtual sample in each loop, ensuring the authenticity of virtual samples at the sample level. To the best of our knowledge, this is the first work that introduces the concept of information gain into VSG. Extensive experiments on four public datasets from various fields fully demonstrate that the VSG3A2 is more competitive than six state-of-the-art VSG approaches. The MAE, the RMSE and the MAPE metrics of prediction models, trained on virtual samples generated by the proposed VSG3A2, are reduced at least by 19.78%, 19.56%, 20.16% on average than that of the best compared VSG approach, respectively.

One of the dilemmas faced by forecasting is that the data are collected at different frequencies in some practical applications. This paper treats mixed frequency data as a special kind of multi-source data, that is, data from each source is collected at a different sampling frequency. Based on this cognition, this paper draws on the idea of neural network processing multi-source data to proposes a temporal-attribute attention neural network (TAA-NN for short) model to study the raw mixed frequency data. The new method avoids the problems caused by frequency alignments, such as information loss and artificial assumption of data distribution. First, this paper proposes a new sliding window strategy for mixed frequency data to determine the amount of data input into the model from each source data. Then, a group of convolutional neural network (CNN) with the same number of filters is used to extract or expand temporal features from the hidden state for each source data (a frequency data), so as to realize the information fusion of mixed frequency data at the feature layer. In addition, a temporal-attribute attention mechanism is proposed to mine essential information from the fused feature matrix in temporal and attribute dimensions. Experiments on two simulations and real-world datasets demonstrate that TAA-NN outperforms the compared methods and provides a new solution to the mixed frequency data forecasting.

In real life, some complex problems are multi-objective optimization problems. Most of the existing studies have focused on how to obtain the optimal solutions distributed on the whole Pareto-optimal frontier. However, in some fields such as industrial production, the decision-makers of enterprises usually care about what specific measures can maximize the comprehensive benefits of enterprises. Due to this kind of realistic demands, we prefer to find a small part of the optimal solutions according to the preference information suggested by the decision-makers rather than obtain all of the Pareto-optimal solutions. However, almost all of the existing methods only repeat calculation when they meet the scenario where the user-preferences change over time. To address the multi-objective optimization problem under the scenario with dynamic user-preferences information, we propose a MOEA/D-DPRE (multi-objective optimization algorithm based on dynamic preference information) algorithm in this paper, and its framework is inspired by the MOEA/D-PRE (decomposition user-preference multi-objective evolutionary) algorithm. We analyze the four position relations between the distribution region of the old preference weight vectors (old preference region), and we also present the distribution region of the new preference weight vectors (new preference region) and propose the different strategy to the different case respectively. When the preference information changes, the MOEA/D-DPRE can converge to the region of new interest by responding to the change of preference and the historical information. Experimental results show that the proposed method is better than the compared method in convergence speed and distribution under the scenario with dynamic user-preferences information.

Cause analysis makes great contributions to identifying the priorities of the causes in fault diagnosis system. A fuzzy Petri net (FPN) is a preferable model for knowledge representation and reasoning and has become an effective fault diagnosis tool. However, the existing FPN has some limitations in cause analysis. It is criticized for the inability to fully consider incomplete and unknown knowledge in uncertain situations. In this paper, an enhanced grey reasoning Petri net (EGRPN) based on matrix operations is presented to address the limitations and improves the flexibility of the existing FPN. The proposed EGRPN model uses grey numbers to handle the greyness and inaccuracy of uncertain knowledge. Then, the EGRPN inference algorithm is executed based on the matrix operations, which can express the relevance of uncertain events in the form of grey numbers and improve the reliability of the knowledge reasoning process. Finally, industrial examples of cause diagnosis are used to illustrate the feasibility and reliability of the EGRPN model. The experimental results show that the new EGRPN model is promising for cause analysis.