YGYue Geng

Yue Geng

*This is an algorithmically generated author record based on publicly available information.

Yue Geng has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    An NTK-Aware Multi-Round Iterative Moving Collocation Point Framework for Physics-Informed Neural Networks

    by Hanchen Luo, Yue Geng, Shaopu Wang, Yike Gao, Chunlei Wang

    Physics-Informed Neural Networks (PINNs) have emerged as a mesh-free alternative for solving Partial Differential Equations (PDEs), bypassing the computationally expensive mesh generation required by traditional numerical methods. However, this flexibility comes at a cost: by replacing a fixed mesh with a set of collocation points, PINNs shift the core challenge of spatial discretization to the strategic distribution of these points. Consequently, the arrangement of these collocation points directly impacts the efficacy and convergence speed of PINNs. Conventional sampling strategies, such as uniform distribution or residual-based sampling methods, essentially treat the PDE residual field as a static target and typically rely solely on residual magnitudes, overlooking the intrinsic training dynamics of the neural network. Unlike methods that rely solely on residual magnitudes, our approach leverages NTK-aware information to explicitly account for the network’s training behavior. To address these challenges, this paper proposes a Neural Tangent Kernel (NTK)-aware iterative moving collocation point framework. Specifically, we design an NTK-aware point selection strategy that uses training-dynamics-related signals to guide the redistribution of collocation points, prioritizing candidate points that better facilitate the learning of critical solution components. This selection strategy is embedded within a multi-round iterative framework, allowing collocation points to dynamically relocate and track evolving stiff regions. Experimental results on test cases featuring localized stiff regions demonstrate that the proposed framework exhibits superior convergence performance and achieves higher accuracy compared to both standard PINNs and residual-based adaptive methods.

  • Cost-sensitive convolutional neural networks for imbalanced time series classification

    by Yue Geng, Xinyu Luo

    Time series classification and class imbalance problem are two common issues in a multitude of real-life scenarios. This paper simultaneously explores both issues with deep convolution neural networks (CNNs). Because standard networks treat the major


  • Open Access

    Seismic Events Prediction Using Deep Temporal Convolution Networks

    by Yue Geng, Lingling Su, Yunhong Jia, Ce Han

    Seismic events prediction is a crucial task for preventing coal mine rock burst hazards. Currently, this task attracts increasing research enthusiasms from many mining experts. Considering the temporal characteristics of monitoring data, seismic events prediction can be abstracted as a time series prediction task. This paper contributes to address the problem of long-term historical dependence on seismic time series prediction with deep temporal convolution neural networks (CNN). We propose a dilated causal temporal convolution network (DCTCNN) and a CNN long short-term memory hybrid model (CNN-LSTM) to forecast seismic events. In particular, DCTCNN is designed with dilated CNN kernels, causal strategy, and residual connections; CNN-LSTM is established in a hybrid modeling way by utilizing advantage of CNN and LSTM. Based on these manners, both of DCTCNN and CNN-LSTM can extract long-term historical features from the monitoring seismic data. The proposed models are experimentally tested on two real-life coal mine seismic datasets. Furthermore, they are also compared with one traditional time series prediction method, two classic machine learning algorithms, and two standard deep learning networks. Results show that DCTCNN and CNN-LSTM are superior than the other five algorithms, and they successfully complete the seismic prediction task.


  • Open Access

    Cost-Sensitive Convolution based Neural Networks for Imbalanced Time-Series Classification

    by Yue Geng, Xinyu Luo

    Some deep convolutional neural networks were proposed for time-series classification and class imbalanced problems. However, those models performed degraded and even failed to recognize the minority class of an imbalanced temporal sequences dataset. Minority samples would bring troubles for temporal deep learning classifiers due to the equal treatments of majority and minority class. Until recently, there were few works applying deep learning on imbalanced time-series classification (ITSC) tasks. Here, this paper aimed at tackling ITSC problems with deep learning. An adaptive cost-sensitive learning strategy was proposed to modify temporal deep learning models. Through the proposed strategy, classifiers could automatically assign misclassification penalties to each class. In the experimental section, the proposed method was utilized to modify five neural networks. They were evaluated on a large volume, real-life and imbalanced time-series dataset with six metrics. Each single network was also tested alone and combined with several mainstream data samplers. Experimental results illustrated that the proposed cost-sensitive modified networks worked well on ITSC tasks. Compared to other methods, the cost-sensitive convolution neural network and residual network won out in the terms of all metrics. Consequently, the proposed cost-sensitive learning strategy can be used to modify deep learning classifiers from cost-insensitive to cost-sensitive. Those cost-sensitive convolutional networks can be effectively applied to address ITSC issues.