@article{jin_xu_2024, title={Forecasting wholesale prices of yellow corn through the Gaussian process regression}, ISSN={["1433-3058"]}, DOI={10.1007/s00521-024-09531-2}, journal={NEURAL COMPUTING & APPLICATIONS}, author={Jin, Bingzi and Xu, Xiaojie}, year={2024}, month={Mar} }
 @article{xu_zhang_2024, title={Platinum and palladium price forecasting through neural networks}, ISSN={["1532-4141"]}, DOI={10.1080/03610918.2024.2330700}, abstractNote={To many commodity market participants, forecasts of price series represent a critical task. In this work, nonlinear autoregressive neural network models' potential is explored for forecasting daily prices series of platinum and palladium over about a fifty-year period. For this purpose, one hundred and twenty model settings are examined, including different training algorithms, numbers of hidden neurons and delays, and ratios used to segment the data. With the analysis, two models leading to stable and accurate forecast results are constructed for the prices of the two commodities. In particular, the models' performance in terms of the relative root mean square error is 1.86% and 3.61% for platinum and palladium, respectively, for the overall sample. Results in this work could help technical forecasts and policy analysis. The forecast framework might be extended to other different commodities.}, journal={COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION}, author={Xu, Xiaojie and Zhang, Yun}, year={2024}, month={Mar} }
 @article{xu_zhang_2022, title={Coking coal futures price index forecasting with the neural network}, ISSN={["2191-2211"]}, DOI={10.1007/s13563-022-00311-9}, journal={MINERAL ECONOMICS}, author={Xu, Xiaojie and Zhang, Yun}, year={2022}, month={Apr} }
 @article{xu_zhang_2022, title={Contemporaneous causality among one hundred Chinese cities}, ISSN={["1435-8921"]}, DOI={10.1007/s00181-021-02190-5}, journal={EMPIRICAL ECONOMICS}, author={Xu, Xiaojie and Zhang, Yun}, year={2022}, month={Jan} }
 @article{zhang_xu_2022, title={Disordered MgB2 superconductor critical temperature modeling through regression trees}, volume={597}, ISSN={["1873-2143"]}, DOI={10.1016/j.physc.2022.1354062}, abstractNote={Magnesium boride superconductors are promising candidates in high energy physics applications. These superconductors have several advantages as compared to other high temperature superconductors, such as the absence of weaklinks in grain boundaries, abundant availability of raw materials, simple wire fabrication process, and increased isotropy in microstructure and material performance. Critical temperature, Tc, is the most critical parameter in superconductor characterizations. Various factors have impacts on Tc, including the chemical doping, irradiation, and synthesis conditions. It has been shown that disorders in the crystal structure lead to changes in normal state resistivities and Tc, which are correlated with each other. Here, the regression tree model is developed to predict Tc of disordered magnesium boride superconductors through room temperature resistivities. This modeling approach manifests a high degree of accuracy and stability, contributing to efficient low-cost estimations of critical temperature and understandings of disorder and superconductivity in MgB2 superconductors.}, journal={PHYSICA C-SUPERCONDUCTIVITY AND ITS APPLICATIONS}, author={Zhang, Yun and Xu, Xiaojie}, year={2022}, month={Jun} }
 @article{zhang_xu_2021, title={Machine learning modeling of metal surface energy}, volume={267}, ISSN={["1879-3312"]}, DOI={10.1016/j.matchemphys.2021.124622}, abstractNote={We develop the Gaussian process regression model to shed light on relationships between metal surface energy and pertinent physical parameters. A total of 43 metals with surface energy ranging from 0.10 to 3.68 Jm−2 are explored for this purpose. The dataset contains alkali, alkaline earth, and transition metals, Lanthanides, and metals in other groups with the face-centered cubic, body-centered cubic, or hexagonal-closed-packed structure. The model is accurate and stable that contributes to fast estimations of surface energy of various metals at low cost.}, journal={MATERIALS CHEMISTRY AND PHYSICS}, author={Zhang, Yun and Xu, Xiaojie}, year={2021}, month={Jul} }
 @article{alade_zhang_xu_2021, title={Modeling and prediction of lattice parameters of binary spinel compounds (AM(2)X(4)) using support vector regression with Bayesian optimization}, ISSN={["1369-9261"]}, DOI={10.1039/d1nj01523k}, abstractNote={The lattice constants of spinel compounds AM2X4 are correlated with the constituent elemental properties using support vector regression (SVR) optimized with Bayesian optimization.}, journal={NEW JOURNAL OF CHEMISTRY}, author={Alade, Ibrahim Olanrewaju and Zhang, Yun and Xu, Xiaojie}, year={2021}, month={Aug} }
 @article{zhang_xu_2022, title={Predicting the superconducting transition temperature and relative resistance ratio in YBa2Cu3O7 films}, volume={592}, ISSN={["1873-2143"]}, DOI={10.1016/j.physc.2021.1353998}, abstractNote={The increase in critical temperature, Tc, of high-temperature superconductors fulfills the needs of practical applications with liquid-helium-free refrigeration and a delay in magnet failure. The YBa2Cu3O7 (YBCO) superconductor exhibits Tc of greater than 90 K and an upper critical field of greater than 100 T, which is a promising candidate in high-field magnet design. Due to their large anisotropy in current transportation, YBCO superconductors are usually processed as thin films by pulsed-laser deposition. But the research requires significant manpower for materials synthesis, analysis, and quench detection, as well as costly equipment and facilities. In this work, we develop the multiple linear regression model to shed light on the relationship between pulsed laser deposition parameters and the superconducting transition temperature (Tc) and relative resistance ratio (rR) in the laser deposition of YBa2Cu3O7 films. The model is straightforward and simple and demonstrates a high degree of accuracy and stability, contributing to fast low-cost estimations of Tc and rR.}, journal={PHYSICA C-SUPERCONDUCTIVITY AND ITS APPLICATIONS}, author={Zhang, Yun and Xu, Xiaojie}, year={2022}, month={Jan} }
 @article{xu_liu_huang_2009, title={Two-Phase Interleaved Critical Mode PFC Boost Converter With Closed Loop Interleaving Strategy}, volume={24}, ISSN={["1941-0107"]}, DOI={10.1109/TPEL.2009.2019824}, abstractNote={This paper presents a two-phase interleaved critical mode (CRM) power factor correction (PFC) boost converter with a novel closed loop interleaving technique. This new interleaving technique makes each phase work at ideally CRM. Natural current sharing and precise 180° phase shift are achieved. The scheme can be easily integrated into a PFC control chip. Full-order averaged model of CRM boost is derived to analyze the stability of the converter. The loop response and stability of the closed-phase regulation loop have been analyzed. A 400 W two-phase interleaved CRM PFC boost converter prototype is built. This proposed scheme is verified by simulation and experimental results.}, number={12}, journal={IEEE TRANSACTIONS ON POWER ELECTRONICS}, author={Xu, Xiaojun and Liu, Wei and Huang, Alex Q.}, year={2009}, month={Dec}, pages={3003–3013} }