Wanwan Xia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wanwan Xia has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Yujie Gao
School of Physical and Mathematical Sciences, Nanjing Tech University, Nanjing 210037, China
2 shared publications - Zhenkai Zhang
School of Physical and Mathematical Sciences, Nanjing Tech University, Nanjing 210037, China
2 shared publications - Danqin Huang
School of Mathematical and Physical Sciences, Nanjing Tech University, 30 South Puzhu Road, Nanjing 211816, China
1 shared publication - Fan Yang
School of Physical and Mathematical Sciences, Nanjing Tech University, Nanjing 211816, China
1 shared publication - Jingwen Zhang
College of Energy Science and Engineering, Nanjing Tech University, Nanjing 210037, China
1 shared publication - Ningjia Xu
School of Foreign Languages and Literature, Nanjing Tech University, Nanjing 211816, China
1 shared publication
Latest Publications
- Open Access
- 29 May 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (11) , 1886
Exploring Large Language Models for University-Level Mathematics: A Comparative Study
Large language models (LLMs) have shown great potential in solving complex mathematical problems, but their performance in university-level mathematics is still underexplored. This study provides a systematic evaluation of eleven state-of-the-art LLMs on five core undergraduate mathematics courses. An end-to-end automated pipeline is proposed for solution inference and answer evaluation, including a reliable ensemble evaluation scheme using seven reasoning-enabled LLMs as expert evaluators. The experimental results show that reasoning models outperform non-reasoning ones significantly, with DeepSeek-V3.2 and Kimi-K2.5 achieving average scores of 88.24 and 88.99, respectively. Under the conditions of the conducted experiment in this study, DeepSeek-V3.2 achieves the most reasonable accuracy–cost trade-off. This work reveals the strengths and limitations of modern LLMs in advanced mathematical reasoning and provides insights into their application in AI mathematical education.
- 29 May 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (11) , 1886
Open AccessExploring Large Language Models for University-Level Mathematics: A Comparative Study
Large language models (LLMs) have shown great potential in solving complex mathematical problems, but their performance in university-level mathematics is still underexplored. This study provides a systematic evaluation of eleven state-of-the-art LLMs on five core undergraduate mathematics courses. An end-to-end automated pipeline is proposed for solution inference and answer evaluation, including a reliable ensemble evaluation scheme using seven reasoning-enabled LLMs as expert evaluators. The experimental results show that reasoning models outperform non-reasoning ones significantly, with DeepSeek-V3.2 and Kimi-K2.5 achieving average scores of 88.24 and 88.99, respectively. Under the conditions of the conducted experiment in this study, DeepSeek-V3.2 achieves the most reasonable accuracy–cost trade-off. This work reveals the strengths and limitations of modern LLMs in advanced mathematical reasoning and provides insights into their application in AI mathematical education.
- Open Access
- 24 July 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (15) , 6753
Behavior Prediction of Connections in Eco-Designed Thin-Walled Steel–Ply–Bamboo Structures Based on Machine Learning for Mechanical Properties
This study employed multiple machine learning and hyperparameter optimization techniques to analyze and predict the mechanical properties of self-drilling screw connections in thin-walled steel–ply–bamboo shear walls, leveraging the renewable and eco-friendly nature of bamboo to enhance structural sustainability and reduce environmental impact. The dataset, which included 249 sets of measurement data, was derived from 51 disparate connection specimens fabricated with engineered bamboo—a renewable and low-carbon construction material. Utilizing factor analysis, a ranking table recording the comprehensive score of each connection specimen was established to select the optimal connection type. Eight machine learning models were employed to analyze and predict the mechanical performance of these connection specimens. Through comparison, the most efficient model was selected, and five hyperparameter optimization algorithms were implemented to further enhance its prediction accuracy. The analysis results revealed that the Random Forest (RF) model demonstrated superior classification performance, prediction accuracy, and generalization ability, achieving approximately 61% accuracy on the test set (the highest among all models). In hyperparameter optimization, the RF model processed through Bayesian Optimization (BO) further improved its predictive accuracy to about 67%, outperforming both its non-optimized version and models optimized using the other algorithms. Considering the mechanical performance of connections within TWS composite structures, applying the BO algorithm to the RF model significantly improved the predictive accuracy. This approach enables the identification of the most suitable specimen type based on newly provided mechanical performance parameter sets, providing a data-driven pathway for sustainable bamboo–steel composite structure design.
- 24 July 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (15) , 6753
Open AccessBehavior Prediction of Connections in Eco-Designed Thin-Walled Steel–Ply–Bamboo Structures Based on Machine Learning for Mechanical Properties
This study employed multiple machine learning and hyperparameter optimization techniques to analyze and predict the mechanical properties of self-drilling screw connections in thin-walled steel–ply–bamboo shear walls, leveraging the renewable and eco-friendly nature of bamboo to enhance structural sustainability and reduce environmental impact. The dataset, which included 249 sets of measurement data, was derived from 51 disparate connection specimens fabricated with engineered bamboo—a renewable and low-carbon construction material. Utilizing factor analysis, a ranking table recording the comprehensive score of each connection specimen was established to select the optimal connection type. Eight machine learning models were employed to analyze and predict the mechanical performance of these connection specimens. Through comparison, the most efficient model was selected, and five hyperparameter optimization algorithms were implemented to further enhance its prediction accuracy. The analysis results revealed that the Random Forest (RF) model demonstrated superior classification performance, prediction accuracy, and generalization ability, achieving approximately 61% accuracy on the test set (the highest among all models). In hyperparameter optimization, the RF model processed through Bayesian Optimization (BO) further improved its predictive accuracy to about 67%, outperforming both its non-optimized version and models optimized using the other algorithms. Considering the mechanical performance of connections within TWS composite structures, applying the BO algorithm to the RF model significantly improved the predictive accuracy. This approach enables the identification of the most suitable specimen type based on newly provided mechanical performance parameter sets, providing a data-driven pathway for sustainable bamboo–steel composite structure design.
- Open Access
- 11 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (14) , 7793
Predicting Olympic Medal Performance for 2028: Machine Learning Models and the Impact of Host and Coaching Effects
This study develops two machine learning models to predict the medal performance of countries at the 2028 Olympic Games while systematically analyzing and quantifying the impacts of the host effect and exceptional coaching on medal gains. The dataset encompasses records of total medals by country, event categories, and athletes’ participation from the Olympic Games held between 1896 and 2024. We use K-means clustering to analyze medal trends, categorizing 234 nations into four groups (, , , ). Among these, , , represent medal-winning countries, while consists of non-medal-winning nations. For the 1, 2, and 3 groups, 2–3 representative countries from each are selected for trend analysis, with the United States serving as a case study. This study extracts ten factors that may influence medal wins from the dataset, including participant data, the number of events, and medal growth rates. Factor analysis is used to reduce them into three principal components: Factor analysis condenses ten influencing factors into three principal components: the event scale factor (F1), the medal trend factor (F2), and the gender and athletic ability factor (F3). An ARIMA model predicts the factor coefficients for 2028 as 0.9539, 0.7999, and 0.2937, respectively. Four models (random forest, BP Neural Network, XGBoost, and SVM) are employed to predict medal outcomes, using historical data split into training and testing sets to compare their predictive performance. The research results show that XGBoost is the optimal medal predicted model, with the United States projected to win 57 gold medals and a total of 135 medals in 2028. For non-medal-winning countries (), a three-layer fully connected neural network (FCNN) is constructed, achieving an accuracy of 85.5% during testing. Additionally, a formula to calculate the host effect and a Bayesian linear regression model to assess the impact of exceptional coaching on athletes’ medal performance are proposed. The overall trend of countries in the 1 group is stable, but they are significantly affected by the host effect; the trend in the 2 group shows an upward trend; the trend in the 3 group depend on the athletes’ conditions and whether the events they excel in are included in that year’s Olympics. In the 4 group, the probabilities of the United Arab Republic (UAR) and Mali (MLI) winning medals in the 2028 Olympic Games are 77.47% and 58.47%, respectively, and there are another four countries with probabilities exceeding 30%. For the eight most recent Olympic Games, the gain rate of the host effect is 74%. Great coaches can bring an average increase of 0.2 to 0.5 medals for each athlete. The proposed models, through an innovative integration of clustering, dimensionality reduction, and predictive algorithms, provide reliable forecasts and data-driven insights for optimizing national sports strategies. These contributions not only address the gap in predicting first-time medal wins for non-medal-winning nations but also offer guidance for policymakers and sports organizations, though they are constrained by assumptions of stable historical trends, minimal external disruptions, and the exclusion of unknown athletes.- 11 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (14) , 7793
Open AccessPredicting Olympic Medal Performance for 2028: Machine Learning Models and the Impact of Host and Coaching Effects
This study develops two machine learning models to predict the medal performance of countries at the 2028 Olympic Games while systematically analyzing and quantifying the impacts of the host effect and exceptional coaching on medal gains. The dataset encompasses records of total medals by country, event categories, and athletes’ participation from the Olympic Games held between 1896 and 2024. We use K-means clustering to analyze medal trends, categorizing 234 nations into four groups (, , , ). Among these, , , represent medal-winning countries, while consists of non-medal-winning nations. For the 1, 2, and 3 groups, 2–3 representative countries from each are selected for trend analysis, with the United States serving as a case study. This study extracts ten factors that may influence medal wins from the dataset, including participant data, the number of events, and medal growth rates. Factor analysis is used to reduce them into three principal components: Factor analysis condenses ten influencing factors into three principal components: the event scale factor (F1), the medal trend factor (F2), and the gender and athletic ability factor (F3). An ARIMA model predicts the factor coefficients for 2028 as 0.9539, 0.7999, and 0.2937, respectively. Four models (random forest, BP Neural Network, XGBoost, and SVM) are employed to predict medal outcomes, using historical data split into training and testing sets to compare their predictive performance. The research results show that XGBoost is the optimal medal predicted model, with the United States projected to win 57 gold medals and a total of 135 medals in 2028. For non-medal-winning countries (), a three-layer fully connected neural network (FCNN) is constructed, achieving an accuracy of 85.5% during testing. Additionally, a formula to calculate the host effect and a Bayesian linear regression model to assess the impact of exceptional coaching on athletes’ medal performance are proposed. The overall trend of countries in the 1 group is stable, but they are significantly affected by the host effect; the trend in the 2 group shows an upward trend; the trend in the 3 group depend on the athletes’ conditions and whether the events they excel in are included in that year’s Olympics. In the 4 group, the probabilities of the United Arab Republic (UAR) and Mali (MLI) winning medals in the 2028 Olympic Games are 77.47% and 58.47%, respectively, and there are another four countries with probabilities exceeding 30%. For the eight most recent Olympic Games, the gain rate of the host effect is 74%. Great coaches can bring an average increase of 0.2 to 0.5 medals for each athlete. The proposed models, through an innovative integration of clustering, dimensionality reduction, and predictive algorithms, provide reliable forecasts and data-driven insights for optimizing national sports strategies. These contributions not only address the gap in predicting first-time medal wins for non-medal-winning nations but also offer guidance for policymakers and sports organizations, though they are constrained by assumptions of stable historical trends, minimal external disruptions, and the exclusion of unknown athletes. - Open Access
- 19 June 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (12) , 2030
Modeling Supply Chain Finance Resilience with a Complex Adaptive SEIJR Framework
This study develops a novel framework for supply chain financial resilience (SCFR) by integrating complex adaptive systems theory with supply chain finance and resilience concepts. To explore how disruption risks propagate through the supply chain, we propose an SEIJR epidemic model that categorizes node enterprises into five distinct states: susceptible (S), exposed (E), infected (I), quarantined (J), and recovered (R). Transitions between these states are captured using differential equations. Through numerical simulations linking this epidemiological approach to financial resilience metrics, we demonstrate several key findings: first, disruption risks temporarily reduce resilience; second, properly managed risk propagation through timely isolation and effective mitigation can transform disruptions into opportunities for systemic improvement; third, isolation measures need to work alongside recovery mechanisms to significantly improve the overall resilience of supply chain finance. Our results show that optimal isolation strategies enable the system to reach a risk-free equilibrium while simultaneously elevating the supply chain’s long-term financial resilience above initial levels. These findings offer theoretical and practical guidance for dynamic, adaptive risk management strategies in supply chain finance. Empirical validation and other research topics will be explored in subsequent studies.
- 19 June 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (12) , 2030
Open AccessModeling Supply Chain Finance Resilience with a Complex Adaptive SEIJR Framework
This study develops a novel framework for supply chain financial resilience (SCFR) by integrating complex adaptive systems theory with supply chain finance and resilience concepts. To explore how disruption risks propagate through the supply chain, we propose an SEIJR epidemic model that categorizes node enterprises into five distinct states: susceptible (S), exposed (E), infected (I), quarantined (J), and recovered (R). Transitions between these states are captured using differential equations. Through numerical simulations linking this epidemiological approach to financial resilience metrics, we demonstrate several key findings: first, disruption risks temporarily reduce resilience; second, properly managed risk propagation through timely isolation and effective mitigation can transform disruptions into opportunities for systemic improvement; third, isolation measures need to work alongside recovery mechanisms to significantly improve the overall resilience of supply chain finance. Our results show that optimal isolation strategies enable the system to reach a risk-free equilibrium while simultaneously elevating the supply chain’s long-term financial resilience above initial levels. These findings offer theoretical and practical guidance for dynamic, adaptive risk management strategies in supply chain finance. Empirical validation and other research topics will be explored in subsequent studies.
- Open Access
- 29 January 2024
- Published by Cambridge University Press (CUP) in Probability in the Engineering and Informational Sciences
- Vol. 38 (3) , 579-593
Log-concavity and relative log-concave ordering of compound distributions
In this paper, we compare the entropy of the original distribution and its corresponding compound distribution. Several results are established based on convex order and relative log-concave order. The necessary and sufficient condition for a compound distribution to be log-concave is also discussed, including compound geometric distribution, compound negative binomial distribution and compound binomial distribution.
- 29 January 2024
- Published by Cambridge University Press (CUP) in Probability in the Engineering and Informational Sciences
- Vol. 38 (3) , 579-593
Open AccessLog-concavity and relative log-concave ordering of compound distributions
In this paper, we compare the entropy of the original distribution and its corresponding compound distribution. Several results are established based on convex order and relative log-concave order. The necessary and sufficient condition for a compound distribution to be log-concave is also discussed, including compound geometric distribution, compound negative binomial distribution and compound binomial distribution.