Due to the great potential of online education platforms, knowledge tracing (KT) has become popular in personalized learning. KT aims at tracing the dynamic change of knowledge state over time based on student’s historical learning trajectory and predicting student’s future performance. However, the existing methods still face some challenges, including the ignoring of forgetting behavior, the loss of higher-order information, and the limit of pair-wise representation in student’s learning trajectory. To address these issues, we propose the multiple graph knowledge tracing (MGKT). Based on forgetting mechanism, MGKT introduces forgetting feature into a graph convolutional network. Considering the topological ordering and relations of exercise-response and skill-response, a dual-channel directed multigraph communication module is developed for MGKT to characterize student’s hidden knowledge states. In addition, we design a hypergraph convolution module with LSTM and attention mechanism for MGKT to learn higher-order semantic information and group-wise relationship in hypergraphs. Comprehensive experiments are performed on three public datasets and the experimental results demonstrate the superiority of MGKT over some state-of-the-art KT models.

Based on student's cognitive structure, the cognitive diagnostic models (CDMs) can reveal the potential relationships among the student's knowledge level, test item features and the corresponding item scores, and then predict each student's future performance. However, due to the simplistic prior information and deficient cognitive mechanism, most of the existing CDMs have limited prediction performance. To address the issues, we propose the multivariate cognitive response framework (MvCRF). We first collect student's learning activity logs to calculate the corresponding effort trait. Considering both student's ability trait and effort trait, MvCRF then introduces the compensation mechanism to calculate student's knowledge level. In addition, we introduce not only the slip and guessing parameters in prediction but also the skill weakness parameter related with the student's knowledge level and the importance of each skill on solving specific item. Experimental results on both simulation study and real-data application on MOOC demonstrate that MvCRF achieves better prediction performance, robustness and interpretability than the baseline CDMs.

Monitoring and forecasting of sintering temperature (ST) is vital for safe, stable, and efficient operation of rotary kiln production process. Due to the complex coupling and time-varying characteristics of process data collected by the distributed control system, its long-range prediction remains a challenge. In this article, we propose a multivariate time series forecasting model based on dynamic spatio-temporal graph attention network (GAT) to model time-varying spatio-temporal correlation between the process data and perform long-range forecasting of ST. Aiming at the problem that there is no preset graph structure for multivariate data, we first propose an adaptive adjacency matrix generation algorithm to construct an elementary graph structure for the process data. Then, we design a spatio-temporal graph attention module, which consists of a multihead GAT for extracting time-varying spatial features and a gated dilated convolutional network for temporal features. Finally, considering the different time delay and rhythm of each process variable, we use dynamic system analysis to estimate the delay time and rhythm of each variable to guide the selection of dilation rates in dilated convolutional layers. The application results based on actual data show that the method has high prediction accuracy, and has broad application prospects in industrial processes.

Keeping combustion stable and detecting unstable states in time is crucial for coal-fired furnaces such as rotary kilns, boilers, and oxygen furnaces. Because of the interference and complex conditions in the industrial field, recognition of combustion conditions by vision analysis is difficult. In this article, we propose a robust nonlinear dynamic system analysis-based approach for combustion condition recognition by extracting chaotic characteristics from a flame video. We first discover chaotic characteristics in the intensity sequence extracted from a flame video of coal-fired kilns, and then we further find that the underlying chaos rules differ between combustion conditions. Based on this finding, we design a set of trajectory evolution features and morphology distribution features of chaotic attractors for combustion condition recognition. After reconstructing the chaotic attractors from the intensity sequence of a flame video by phase space reconstruction, the quantified features are extracted from the recurrence plot and morphology distribution and put into a decision tree to recognize the combustion condition. The experimental results on real-world data show that the proposed method can recognize the combustion condition in coal-fired kilns effectively and promptly. Compared with other methods, the recognition accuracy is improved more than 5%.

Many existing non-local means (NLM) methods either use Euclidean distance to measure the similarity between patches, or compute weight ωijonly once and keep it unchanged during the subsequent denoising iterations, or use only the structure information of the denoised image to update weight ωij. These may lead to the limited denoising performance. To address these issues, this paper proposes the non-local adaptive means (NLAM) for image denoising. NLAM treats weight ωijas an optimization variable and iteratively updates its value. We then introduce three unbiased distances, namely, pixel-pixel, patch- patch, and coupled unbiased distances. These unbiased distances are more robust to measure the image pixel/patch similarity than Euclidean distance. Using the coupled unbiased distance, we propose the unbiased distance non-local adaptive means (UD-NLAM). Because UD-NLAM uses only a single patch size to compute weight ωij, we introduce multipatch UD-NLAM (MUD-NLAM) to adapt different noise levels. To further improve denoising performance, we then propose a new denoising method called MUD-NLAM with wavelet shrinkage (MUD-NLAM-WS). Experimental results show that the proposed NLAM, UD-NLAM, and MUD-NLAM outperform existing NLM methods, and MUDNLAM-WS achieves a better performance than the state-of-theart denoising methods.

This paper first introduces several unbiased distances to measure the similarity between image pixels and between image patches. Based on these unbiased distances, we propose a new non-local means denoising method, named Unbiased Distance based Non-local Fuzzy Means (UDNLFM). UDNLFM considers the weight as a fuzzy variable and updates its value in each denoising iteration. Experiments and comparisons demonstrate that UDNLFM outperforms state-of-the-art non-local means methods for image denoising.