Xin Zhang

Dr. Xin Zhang


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
15 October 2024 in PeerJ Computer Science
Verified
Journal Article
Open access
PDF file
CZChaoran Zhou
Chaoran Zhou
JHJiahao Hu
Jiahao Hu
XZXin Zhang
Xin Zhang
ZLZerui Li
Zerui Li
KYKaicheng Yang
Kaicheng Yang
Shared bikes, as an eco-friendly transport mode, facilitate short commutes for urban dwellers and help alleviate traffic. However, the prevalent station-based strategy for bike placements often overlooks urban zones, cycling patterns, and more, resulting in underutilized bikes. To address this, we introduce the Spatio-Temporal Bike-sharing Demand Prediction (ST-BDP) model, leveraging multi-source data and Spatio-Temporal Graph Convolutional Networks (STGCN). This model predicts spatial user demand for bikes between stations by constructing a spatial demand graph, accounting for geographical influences. For precision, ST-BDP integrates an attention-based graph convolutional network for station demand graph’s temporal-spatial features, and a sequential convolutional network for multi-source data (e.g., weather, time). In real dataset, experimental results show that ST-BDP has excellent performance with mean absolute error (MAE) = 1.62, mean absolute percentage error (MAPE) = 15.82%, symmetric mean absolute percentage error (SMAPE) = 16.14%, and root mean square error (RMSE) = 2.36, outperforming the baseline techniques. This highlights its predictive accuracy and potential to guide future bike-sharing policies.

6 June 2018 in IEEE Access
Verified
Journal Article
Open access
YZYing Zhang
Ying Zhang
MGMinghe Gao
Minghe Gao
XZXin Zhang
Xin Zhang
PYPuhai Yang
Puhai Yang
QMQunfei Ma
Qunfei Ma
XHXiang Hu
Xiang Hu
Geographic information, especially represented by points of interest (POIs), is critical for identifying locations and provides the basis for various location-based services. Currently, geospatial data of POI are available through some open map services (e.g., Google Maps, OpenStreetMap, etc.). However, the data supporting these services are either collected through the expensive commercial purchasing and company investment or gathered by the volunteered contribution of high uncertainty. With the rapid geospatial data growing on the Web, we propose an automatic approach of extracting geographic information for building up POI resources-based on the results obtained by the Web search engines to mitigate the negative effect from the traditional means. According to the approach, we first put the types of POIs extracted from Google Maps and the street names obtained from OpenStreetMap into the Google search engine, and then retrieve the potential addresses of POIs through parsing the search results. Second, the Google search engine is employed again with the retrieved addresses of POIs to extract the potential place names. Finally, the Google search engine is employed for a third time with learning both the place names and the corresponding addresses to verify whether the place names are correct. The contributed output of the work is a place-name data set. We respectively select 20 blocks in Chicago and Houston in USA to execute our approach for verifying the research contribution. In the experiments, we choose Google Map that is of high data quality as the reference and compare the results with those from OpenStreetMap and Wikimapia. The final results indicate that the proposed approach could effectively produce the place-name data sets on a par with Google Maps and outperform OpenStreetMap and Wikimapia.

1 July 2025 in BMC Bioinformatics
Verified
Journal Article
Open access
PDF file
YLYan Li
Yan Li
YLYanmei Li
Yanmei Li
HMHan Ma
Han Ma
ZYZitong Yue
Zitong Yue
XZXin Zhang
Xin Zhang
Multiple testing of composite null hypotheses is critical for identifying simultaneous signals across studies. While it is common to incorporate external information in simple null hypotheses, exploiting such auxiliary covariates to provide prior structural relationships among composite null hypotheses and boost the statistical power remains challenging. We propose a robust and powerful covariate-assisted composite null hypothesis testing (CoCoNuT) procedure based on a Bayesian framework to identify replicable signals in two studies while asymptotically controlling the false discovery rate. CoCoNuT innovatively adopts a three-dimensional mixture model to consider two primary studies and an integrative auxiliary covariate jointly. While accounting for heterogeneity across studies, the local false discovery rate optimally captures cross-study and cross-feature information, providing improved rankings of feature importance. Theoretical and empirical evaluations confirm the validity and efficiency of CoCoNuT. Extensive simulations demonstrate that CoCoNuT outperforms conventional methods that do not exploit auxiliary covariates while controlling the FDR. We apply CoCoNuT to schizophrenia genome-wide association studies, illustrating its higher power in identifying replicable genetic variants with the assistance of relevant auxiliary studies.

22 April 2024 in Journal of Mechanical Design
Verified
Journal Article
Open access
PDF file
YLYan Liu
Yan Liu
XCXinru Chen
Xinru Chen
CEClaudia M. Eckert
Claudia M. Eckert
XZXin Zhang
Xin Zhang
Concept selection is one of the most important activities in new product development processes in that it greatly influences the direction of subsequent design activities. As a complex multiple-criteria decision-making problem, it often requires iterations before reaching the final decision where each selection is based on previous selection results. Reusing key decision elements ensures decision consistency between iterations and improves decision efficiency. To support this reuse, this article proposes a fuzzy ontology-based decision tool for concept selection. It models the key decision elements and their relations in an ontological way and scores the concepts using weighted fuzzy TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution). By applying the tool to an example, this article demonstrates how the concepts, criteria, weights, and results generated for one decision can be reused in the next iteration.

31 December 2025 in Journal of Physics: Complexity
Verified
Journal Article
Open access
CZChaoran Zhou
Chaoran Zhou
HWHaijian Wang
Haijian Wang
XZXin Zhang
Xin Zhang
In emergency evacuation scenes, environmental uncertainties and information deficits often trigger panic among individuals, which in turn impairs their ability to make sound judgments and decisions. To address this problem, this study proposes a heterogeneous crowd evacuation model (HCEMMP), aiming to accurately simulate the behavior of crowds influenced by panic factors and reveal the correlation between behavior and different factors. HCEMMP integrates a multi-dimensional panic analysis framework with an enhanced social force model. The framework conceptualizes panic as the joint outcome of environmental stress, individual characteristics, and social group influence, allowing quantitative representation of emotional dynamics under complex conditions. The improved social force model adaptively modulates individual movement intentions through emotional feedback, yielding coordinated and realistic evacuation behaviors. Simulation results across diverse scenes reveal nonlinear, hierarchically regulated patterns in crowd behavior driven by coupled panic factors. Individual traits, environmental stress, and social group influence jointly shape emotional dynamics, forming complex feedback that governs evacuation performance. The findings confirm that HCEMMP outperforms baseline models in evacuation efficiency, behavioral realism, and crowd stability, providing a robust foundation for real-world evacuation strategy optimization.

16 February 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
WJWenwei Jiang
Wenwei Jiang
XZXin Zhang
Xin Zhang
MZMarc Zolghadri
Marc Zolghadri
YFYuwen Feng
Yuwen Feng
Rolling bearings are critical industrial components, and accurate Remaining Useful Life (RUL) prediction remains challenging under unknown fault mechanisms. While data-driven methods are applicable, their reliance on point estimation limits uncertainty quantification, motivating Bayesian methods such as Parameter-Space Variational Inference (PSVI). Nevertheless, the high dimensionality and nonlinearity of neural network parameters hinder PSVI-based methods from effectively integrating informative priors from historical data. To address these limitations, this study proposes a data-driven RUL prediction method based on Function-Space Variational Inference (FSVI), which enables reliable uncertainty quantification and effective prior integration under unknown fault mechanisms. The FSVI approximates the predictive function distribution via local linearization and Monte Carlo sampling to optimize the evidence lower bound in function space. Prior information learned from historical data is incorporated via a constructed context dataset. Finally, the effectiveness of the proposed method is validated on two bearing vibration datasets via comprehensive comparisons with existing methods and ablation.