Yuejing Zhai

Mr. Yuejing Zhai

Lanzhou Jiaotong University, Lanzhou, Gansu, China
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 December 2025 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Open access
HLHuijie Li
Huijie Li
KLKunpeng Liu
Kunpeng Liu
YYYide Yu
Yide Yu
YZYuejing Zhai
Yuejing Zhai
AHAn-Min Hu
An-Min Hu
WLWuman Luo
Wuman Luo
Precise and collaborative control of multiple anesthetics in Total Intravenous Anesthesia (TIVA) is essential for ensuring patient safety and maintaining the target depth of anesthesia (DoA). However, existing automated anesthesia control methods often fail to effectively capture the complex synergistic interactions between anesthetics and lack adaptability to patient-specific physiological variability, thereby limiting their clinical applicability. To address these issues, we propose AnesMADRL, a novel Multi-Agent Deep Reinforcement Learning (MADRL)-based framework that leverages the Counterfactual Multi-Agent algorithm for effective credit assignment between agents controlling propofol and remifentanil, and adopts a continuous action space to enable fine-grained dose adjustments. Furthermore, AnesMADRL integrates comprehensive patient-specific physiological indicators and employs a random forest-based simulator to generate dynamic and diverse training environments. Experimental results show that AnesMADRL significantly outperforms baseline methods and human expertise in terms of anesthetic efficiency and total drug consumption. Relative to human expertise, AnesMADRL achieves roughly twofold efficiency while reducing total dose to about one-half, highlighting its potential to enhance patient safety and optimize clinical outcomes.

21 July 2022 in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
Verified
Journal Article
Closed access
PDF file
YZYuejing Zhai
Yuejing Zhai
HLHaizhong Liu
Haizhong Liu
Recent studies have shown that the evolution of infinitely wide neural networks satisfying certain conditions can be described by a kernel function called neural tangent kernel (NTK). We introduce NTK into a one-class support vector machine model and select data from different domains in UCI for a small-sample outlier detection task, demonstrate that NTK-OCSVM generally outperforms a variety of commonly used classification models, with more than 20% improvement in accuracy for similar models. When the kernel function parameters are varied, the experiments show that the model has strong robustness within a certain parameter range. Finally, we experimentally compare the time complexity of different models and the decision boundaries, and demonstrate that NTK-OCSVM improves accuracy at the expense of operational efficiency and has linear decision boundaries.

26 October 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YZYuejing Zhai
Yuejing Zhai
ZLZhouzheng Li
Zhouzheng Li
HLHaiZhong Liu
HaiZhong Liu
Multi-kernel learning methods are essential kernel learning methods. Still, the base kernel functions in most multi-kernel learning methods only with select kernel functions with shallow structures, which are weak for large-scale uneven data. We propose two types of acceleration models from a multidimensional perspective of the data: the neural tangent kernel (NTK)-based multi-kernel learning method is proposed, where the NTK kernel regressor is shown to be equivalent to an infinitely wide neural network predictor, and the NTK with deep structure is used as the base kernel function to enhance the learning ability of multi-kernel models; and a parallel computing kernel model based on data partitioning techniques. An RBF, POLY-based multi-kernel model is also proposed. All models use historical memory-based PSO (HMPSO) for efficient search of parameters within the model. Since NTK has a multi-layer structure and thus has a significant computational complexity, the use of a Monotone Disjunctive Kernel (MDK) to store and train Boolean features in binary achieves a 15–60% training time compression of NTK models in different datasets while obtaining a 1–25% accuracy improvement.

20 November 2025 in iScience
Verified
Journal Article
Open access
YZYuejing Zhai
Yuejing Zhai
YLYiping Li
Yiping Li
LHLihua He
Lihua He
XLXin Li
Xin Li
WLWuman Luo
Wuman Luo
Accurately predicting readmission risk for heart failure patients is a hot topic in the field of survival analysis and healthcare. Current models show room for improvement. This study aims to explore the ability of environmental data to improve prediction accuracy. We conducted a retrospective analysis, integrating environmental factors with clinical data. Experiments show that our combined model achieved a 37% higher C-index than the best baseline. Further tests confirmed that adding any single environmental feature consistently boosted the performance of all baseline models. In addition, environmental data alone have clear limitations. Models using only these variables performed significantly worse than those incorporating clinical features. This indicates that environmental factors are powerful supplements, not replacements, for established clinical predictors. In conclusion, our findings provide strong evidence that environmental information serves as a valuable and complementary tool, significantly improving the accuracy of heart failure readmission-risk prediction when used alongside clinical data.

24 July 2025 in Research Square
Verified
Preprint
Open access
PDF file
WLWuman Luo
Wuman Luo
YZYuejing Zhai
Yuejing Zhai
YLYiping Li
Yiping Li
Accurate time series modeling plays a critical role in health, financial, and industrial applications. However, real-world deployment faces two key issues: (1) scarcity of clean training data, and (2) valuable information is locked in structured tabular formats, and cannot be imported into time series models. These limitations significantly constrain prediction performance in time series tasks. Cross-modal transfer learning (CMTL) provides a possible solution. Existing CMTL approaches succeed with image, text, and audio data by leveraging their inherent local correlations and hierarchical structures. However, tabular data presents unique difficulties. Specifically, the discrete, heterogeneous nature of tabular features, and lack of explicit temporal relationships in columns, prevent direct geometric alignment with time series waveforms. In fact, although it has no temporal nature, tabular data still contains rich domain knowledge that can be used by time series tasks. In this paper, we propose a cross-modal transfer learning (CMTL) model from tabular to time series data, called TSgraph. TSgraph first extracts the domain topology and feature interaction paradigm from tabular data, and constructs it as a graph structure. Then, the time series graph of each time step is dynamically updated in combination with these graphs, and finally get the classification results. We validate the performance of TSgraph on four real-world datasets from different domains and compare the results with state-of-the-art baseline models. Experiments show that our model achieves the best performance on multiple evaluation metrics.

22 August 2026 in Artificial Intelligence Review
Verified
Journal Article
Open access
SQSibo Qi
Sibo Qi
YZYuejing Zhai
Yuejing Zhai
PCPeng Chen
Peng Chen
WLWuman Luo
Wuman Luo
The rapid expansion of multivariate time series (MTS) data has made deep learning a central tool for forecasting across industrial and scientific domains. As these architectures move into settings such as clinical decision support, industrial monitoring, and financial risk management, researchers need to examine not only predictive accuracy but also computational cost and the kinds of explanations that a model can support. This survey re-examines deep learning models for MTS forecasting through the requirements of efficiency and explainability. Our contributions are threefold: (1) We synthesize the literature through a dual-axis scalability view over sequence length L and variate dimension N , together with a three-question explainability taxonomy covering temporal importance, variate importance, and pattern decomposition. (2) We review dominant architectural families, including Transformer variants, frequency-domain methods, linear and channel-independent backbones, state space models, and foundation-style forecasters, to describe how different designs occupy different efficiency–explainability profiles under specific data and deployment assumptions. (3) Building on this synthesis, we identify key open challenges—including the absence of standardized explainability benchmarks for time series, the interpretability gap in state space models, and the need to advance from correlational to causal explanations—and offer reporting considerations to guide more comparable future research.