XZXin Zhang

Xin Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xin Zhang has a total of 38 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A function-space variational inference-based method for bearing RUL prediction and uncertainty quantification

    by Wenwei Jiang, Xin Zhang, Marc Zolghadri, 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.

  • Open Access

    A heterogeneous crowd evacuation model integrating multi-dimensional panic emotion characteristics

    by Chaoran Zhou, Haijian Wang, 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.


  • Open Access

    Coconut: covariate-assisted composite null hypothesis testing with applications to replicability analysis of high-throughput experimental data

    by Yan Li, Yanmei Li, Han Ma, Zitong Yue, 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.


  • Open Access

    BIPNN: Learning to Solve Binary Integer Programming via Hypergraph Neural Networks

    by Sen Bai, Chunqi Yang, Xin Bai, Xin Zhang, Zhengang Jiang

    Binary (0-1) integer programming (BIP) is pivotal in scientific domains requiring discrete decision-making. As the advance of AI computing, recent works explore neural network-based solvers for integer linear programming (ILP) problems. Yet, they lack scalability for tackling nonlinear challenges. To handle nonlinearities, state-of-the-art Branch-and-Cut solvers employ linear relaxations, leading to exponential growth in auxiliary variables and severe computation limitations. To overcome these limitations, we propose BIPNN (Binary Integer Programming Neural Network), an unsupervised learning framework to solve nonlinear BIP problems via hypergraph neural networks (HyperGNN). Specifically, BIPNN reformulates BIPs-constrained, discrete, and nonlinear (sin, log, exp) optimization problems-into unconstrained, differentiable, and polynomial loss functions. The reformulation stems from the observation of a precise one-to-one mapping between polynomial BIP objectives and hypergraph structures, enabling the unsupervised training of HyperGNN to optimize BIP problems in an end-to-end manner. On this basis, we propose a GPU-accelerated and continuous-annealing-enhanced training pipeline for BIPNN. The pipeline enables BIPNN to optimize large-scale nonlinear terms in BIPs fully in parallel via straightforward gradient descent, thus significantly reducing the training cost while ensuring the generation of discrete, high-quality solutions. Extensive experiments on synthetic and real-world datasets highlight the superiority of our approach.

  • Open Access

    Deep k-grouping: An Unsupervised Learning Framework for Combinatorial Optimization on Graphs and Hypergraphs

    by Sen Bai, Chunqi Yang, Xin Bai, Xin Zhang, Zhengang Jiang

    Along with AI computing shining in scientific discovery, its potential in the combinatorial optimization (CO) domain has also emerged in recent years. Yet, existing unsupervised neural network solvers struggle to solve $k$-grouping problems (e.g., coloring, partitioning) on large-scale graphs and hypergraphs, due to limited computational frameworks. In this work, we propose Deep $k$-grouping, an unsupervised learning-based CO framework. Specifically, we contribute: Novel one-hot encoded polynomial unconstrained binary optimization (OH-PUBO), a formulation for modeling k-grouping problems on graphs and hypergraphs (e.g., graph/hypergraph coloring and partitioning); GPU-accelerated algorithms for large-scale k-grouping CO problems. Deep $k$-grouping employs the relaxation of large-scale OH-PUBO objectives as differentiable loss functions and trains to optimize them in an unsupervised manner. To ensure scalability, it leverages GPU-accelerated algorithms to unify the training pipeline; A Gini coefficient-based continuous relaxation annealing strategy to enforce discreteness of solutions while preventing convergence to local optima. Experimental results demonstrate that Deep $k$-grouping outperforms existing neural network solvers and classical heuristics such as SCIP and Tabu.

  • Open Access

    A bike-sharing demand prediction model based on Spatio-Temporal Graph Convolutional Networks

    by Chaoran Zhou, Jiahao Hu, Xin Zhang, Zerui Li, 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.


  • Open Access

    A Fuzzy Ontology-Based Decision Tool for Concept Selection to Maintain Consistency Throughout Design Iterations

    by Yan Liu, Xinru Chen, Claudia Eckert, 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.