Shengkun Xie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Shengkun Xie has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
Anna T. Lawniczak
Mathematics and Statistics , University of Guelph , Guelph , ON N1G 2W1 , Canada
19 shared publications- Sridhar Krishnan
Department of Electrical, Computer, and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON, Canada
11 shared publications - Anna. T. Lawniczak
Mathematics and Statistics, University of Guelph, Guelph, ON N1G 2W1, Canada
10 shared publications - Chong Gan
Department of Mathematics and Statistics, University of Guelph, Guelph, ON N1G 2W1, Canada
4 shared publications Jiaying Xu
University of Guelph
3 shared publicationsJin Zhang
Department of Global Management Studies, Ted Rogers School of Management, Toronto Metropolitan University, Toronto, ON, Canada
3 shared publications
Latest Publications
- Open Access
- 1 December 2026
- Published by KEAI Publishing in The Journal of Finance and Data Science
- Vol. 12
Explainable ensemble machine learning for financial transaction fraud detection: Insights from XGBoost and deep neural networks
- 1 December 2026
- Published by KEAI Publishing in The Journal of Finance and Data Science
- Vol. 12
Open AccessExplainable ensemble machine learning for financial transaction fraud detection: Insights from XGBoost and deep neural networks
- Open Access
- 16 October 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (20) , 3757
Spatial Dynamics in a Diffusive Leslie–Gower Predator–Prey Model with Allee Effect, Harvesting, and Cooperative Hunting
In this paper, we investigate the spatiotemporal dynamics of a diffusive Leslie–Gower predator–prey model incorporating the Allee effect, prey harvesting, and cooperative hunting among predators. By introducing spatial diffusion into a previously established ordinary differential system, we formulate and analyze the corresponding reaction–diffusion model. The combined effects of nonlinear ecological interactions and diffusion generate rich dynamical behaviors that are absent in the non-spatial framework. First, we establish the global existence, uniqueness, non-negativity, and ultimate boundedness of solutions, and we derive sufficient conditions for population extinction. We then analyze the existence and local stability of constant steady states and show that diffusion can destabilize spatially homogeneous coexistence equilibria through Turing instability under suitable parameter conditions. Furthermore, by studying the associated elliptic system, we prove the existence and nonexistence of nonconstant steady states, thereby characterizing the emergence of stationary spatial patterns. To further reveal the temporal complexity induced by diffusion, we investigate Hopf bifurcation and analyze the direction and stability of the bifurcating periodic solutions. Our results demonstrate that the spatial domain size plays a crucial role in pattern selection and in the formation of spatially homogeneous and spatially nonhomogeneous periodic oscillations. Numerical simulations are presented to validate the theoretical results and to illustrate the evolution of diffusion-driven spatial patterns and oscillatory spatiotemporal structures. The results show that diffusion fundamentally enriches the qualitative dynamics of the predator–prey system: Turing instability induces stationary heterogeneous patterns, whereas Hopf bifurcation generates sustained oscillatory dynamics and periodic spatiotemporal behaviors. These findings provide new insight into the mechanisms of self-organized pattern formation and dynamic transitions in nonlinear ecological reaction–diffusion systems.
- 16 October 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (20) , 3757
Open AccessSpatial Dynamics in a Diffusive Leslie–Gower Predator–Prey Model with Allee Effect, Harvesting, and Cooperative Hunting
In this paper, we investigate the spatiotemporal dynamics of a diffusive Leslie–Gower predator–prey model incorporating the Allee effect, prey harvesting, and cooperative hunting among predators. By introducing spatial diffusion into a previously established ordinary differential system, we formulate and analyze the corresponding reaction–diffusion model. The combined effects of nonlinear ecological interactions and diffusion generate rich dynamical behaviors that are absent in the non-spatial framework. First, we establish the global existence, uniqueness, non-negativity, and ultimate boundedness of solutions, and we derive sufficient conditions for population extinction. We then analyze the existence and local stability of constant steady states and show that diffusion can destabilize spatially homogeneous coexistence equilibria through Turing instability under suitable parameter conditions. Furthermore, by studying the associated elliptic system, we prove the existence and nonexistence of nonconstant steady states, thereby characterizing the emergence of stationary spatial patterns. To further reveal the temporal complexity induced by diffusion, we investigate Hopf bifurcation and analyze the direction and stability of the bifurcating periodic solutions. Our results demonstrate that the spatial domain size plays a crucial role in pattern selection and in the formation of spatially homogeneous and spatially nonhomogeneous periodic oscillations. Numerical simulations are presented to validate the theoretical results and to illustrate the evolution of diffusion-driven spatial patterns and oscillatory spatiotemporal structures. The results show that diffusion fundamentally enriches the qualitative dynamics of the predator–prey system: Turing instability induces stationary heterogeneous patterns, whereas Hopf bifurcation generates sustained oscillatory dynamics and periodic spatiotemporal behaviors. These findings provide new insight into the mechanisms of self-organized pattern formation and dynamic transitions in nonlinear ecological reaction–diffusion systems.
- 7 October 2026
- Published by Taylor & Francis in Journal of Management Analytics
- p. 1-27
Generalized additive modeling and interpretable territory risk clustering for synthetic usage-based insurance data
1. Rate-making is crucial in auto insurance pricing and regulation. Recent research has advanced rate-making approaches by incorporating sophisticated statistical modeling techniques, especially wi...
- 7 October 2026
- Published by Taylor & Francis in Journal of Management Analytics
- p. 1-27
Generalized additive modeling and interpretable territory risk clustering for synthetic usage-based insurance data
1. Rate-making is crucial in auto insurance pricing and regulation. Recent research has advanced rate-making approaches by incorporating sophisticated statistical modeling techniques, especially wi...
- 14 May 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 328
ASTAC: An adaptive spatio-temporal autocorrelation clustering for complex traffic flow pattern discovery
- 14 May 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 328
ASTAC: An adaptive spatio-temporal autocorrelation clustering for complex traffic flow pattern discovery
- Open Access
- 25 February 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (5) , 758
Modeling and Forecasting U.S. Outbound Travel Demand Across Regions Using Time Series Model and Machine Learning: A Comparative Study
Forecasting of travel demand has become increasingly important in the context of evolving mobility patterns and structural disruptions, including economic fluctuations and public health crises. Classical time series models, although well established in travel-demand analysis, are often limited in their ability to capture non-linear dependencies or adapt to abrupt regime shifts. This study develops and evaluates forecasting techniques drawn from both traditional statistical modeling and machine learning approaches. Their predictive performance and adaptability are benchmarked for U.S. outbound air travel demand across eight global destination regions, Europe, the Caribbean, Asia, South America, Central America, Oceania, the Middle East, and Africa, respectively. Using historical outbound passenger data, six forecasting models are constructed and assessed through multiple forecasting accuracy measures, including the Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). Empirical results demonstrate that machine-learning-based models, particularly those incorporating adaptive learning components, consistently outperform conventional approaches in modeling structural changes in travel demand data. The study further contributes a generalizable methodological framework that enhances robustness under uncertainty and offers broad applicability to forecasting problems in transportation, tourism, and related domains.
- 25 February 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (5) , 758
Open AccessModeling and Forecasting U.S. Outbound Travel Demand Across Regions Using Time Series Model and Machine Learning: A Comparative Study
Forecasting of travel demand has become increasingly important in the context of evolving mobility patterns and structural disruptions, including economic fluctuations and public health crises. Classical time series models, although well established in travel-demand analysis, are often limited in their ability to capture non-linear dependencies or adapt to abrupt regime shifts. This study develops and evaluates forecasting techniques drawn from both traditional statistical modeling and machine learning approaches. Their predictive performance and adaptability are benchmarked for U.S. outbound air travel demand across eight global destination regions, Europe, the Caribbean, Asia, South America, Central America, Oceania, the Middle East, and Africa, respectively. Using historical outbound passenger data, six forecasting models are constructed and assessed through multiple forecasting accuracy measures, including the Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). Empirical results demonstrate that machine-learning-based models, particularly those incorporating adaptive learning components, consistently outperform conventional approaches in modeling structural changes in travel demand data. The study further contributes a generalizable methodological framework that enhances robustness under uncertainty and offers broad applicability to forecasting problems in transportation, tourism, and related domains.
- 22 February 2026
- Published by Springer Nature
- p. 255-273
Analysis of Auto Insurance Loss Metrics During Pre-and Post-COVID-19 Pandemic Using Spatial and Spatial-Temporal Modelling Approaches
- 22 February 2026
- Published by Springer Nature
- p. 255-273
Analysis of Auto Insurance Loss Metrics During Pre-and Post-COVID-19 Pandemic Using Spatial and Spatial-Temporal Modelling Approaches
- 2 February 2026
- Published by Springer Nature
- p. 238-245
Classifying Disaster Tweets Using Natural Language Processing and Machine Learning
- 2 February 2026
- Published by Springer Nature
- p. 238-245
Classifying Disaster Tweets Using Natural Language Processing and Machine Learning
- Open Access
Explainable Machine Learning Framework for Predicting Auto Loan Defaults
This study develops a machine learning framework to improve the prediction of automobile loan defaults by integrating explainable feature selection with advanced resampling techniques. Using publicly available data, we compare Logistic Regression, Random Forest, eXtreme Gradient Boosting (XGBoost), and Stacked classifiers. Feature selection methods, including SHapley Additive exPlanations (SHAP) values and Mutual Information (MI), and resampling techniques such as Synthetic Minority Over-sampling TEchnique (SMOTE), SMOTE-Tomek, and SMOTE Edited Nearest Neighbor (SMOTE-ENN), are evaluated. The results show that combining SHAP-based feature selection with SMOTE-Tomek resampling and a Stacked Classifier consistently achieves superior predictive performance. These findings highlight the value of explainable AI in enhancing credit risk assessment for auto lending. This research also offers valuable insights for addressing other financial modeling challenges involving imbalanced datasets, supporting more informed and reliable decision-making.
Open AccessExplainable Machine Learning Framework for Predicting Auto Loan Defaults
This study develops a machine learning framework to improve the prediction of automobile loan defaults by integrating explainable feature selection with advanced resampling techniques. Using publicly available data, we compare Logistic Regression, Random Forest, eXtreme Gradient Boosting (XGBoost), and Stacked classifiers. Feature selection methods, including SHapley Additive exPlanations (SHAP) values and Mutual Information (MI), and resampling techniques such as Synthetic Minority Over-sampling TEchnique (SMOTE), SMOTE-Tomek, and SMOTE Edited Nearest Neighbor (SMOTE-ENN), are evaluated. The results show that combining SHAP-based feature selection with SMOTE-Tomek resampling and a Stacked Classifier consistently achieves superior predictive performance. These findings highlight the value of explainable AI in enhancing credit risk assessment for auto lending. This research also offers valuable insights for addressing other financial modeling challenges involving imbalanced datasets, supporting more informed and reliable decision-making.
- Open Access
- 1 September 2025
- Published by MDPI AG in Computation
- Vol. 13 (9) , 205
Fuzzy Lyapunov-Based Gain-Scheduled Control for Mars Entry Vehicles: A Computational Framework for Robust Non-Linear Trajectory Stabilization
Accurate trajectory control during atmospheric entry is critical for the success of Mars landing missions, where strong non-linearities and uncertain dynamics pose significant challenges to conventional control strategies. This study develops a computational framework that integrates fuzzy parameter-varying models with Lyapunov-based analysis to achieve robust trajectory stabilization of Mars entry vehicles. The non-linear longitudinal dynamics are reformulated via sector-bounded approximation into a Takagi–Sugeno fuzzy parameter-varying model, enabling systematic gain-scheduled controller synthesis. To reduce the conservatism typically associated with quadratic Lyapunov functions, a fuzzy Lyapunov function approach is adopted, in conjunction with the Full-Block S-procedure, to derive less restrictive stability conditions expressed as linear matrix inequalities. Based on this formulation, several controllers are designed to accommodate the variations in atmospheric density and flight conditions. The proposed methodology is validated through numerical simulations, including Monte Carlo dispersion and parametric sensitivity analyses. The results demonstrate improved stability, faster convergence, and enhanced robustness compared to existing fuzzy control schemes. Overall, this work contributes a systematic and less conservative control design methodology for aerospace applications operating under severe non-linearities and uncertainties.
- 1 September 2025
- Published by MDPI AG in Computation
- Vol. 13 (9) , 205
Open AccessFuzzy Lyapunov-Based Gain-Scheduled Control for Mars Entry Vehicles: A Computational Framework for Robust Non-Linear Trajectory Stabilization
Accurate trajectory control during atmospheric entry is critical for the success of Mars landing missions, where strong non-linearities and uncertain dynamics pose significant challenges to conventional control strategies. This study develops a computational framework that integrates fuzzy parameter-varying models with Lyapunov-based analysis to achieve robust trajectory stabilization of Mars entry vehicles. The non-linear longitudinal dynamics are reformulated via sector-bounded approximation into a Takagi–Sugeno fuzzy parameter-varying model, enabling systematic gain-scheduled controller synthesis. To reduce the conservatism typically associated with quadratic Lyapunov functions, a fuzzy Lyapunov function approach is adopted, in conjunction with the Full-Block S-procedure, to derive less restrictive stability conditions expressed as linear matrix inequalities. Based on this formulation, several controllers are designed to accommodate the variations in atmospheric density and flight conditions. The proposed methodology is validated through numerical simulations, including Monte Carlo dispersion and parametric sensitivity analyses. The results demonstrate improved stability, faster convergence, and enhanced robustness compared to existing fuzzy control schemes. Overall, this work contributes a systematic and less conservative control design methodology for aerospace applications operating under severe non-linearities and uncertainties.