Arrow Research search

Author name cluster

Fei Xu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

13 papers
1 author row

Possible papers

13

EAAI Journal 2025 Journal Article

An optimisation approach guided by crack variation mechanism in the informer prediction model

  • Xujia Liu
  • Youliang Ding
  • Fei Xu
  • Yichao Xu
  • Kang Yang

Structural health monitoring (SHM) faces a fundamental challenge in reconciling predictive performance with physical interpretability for infrastructure diagnostics. Conventional deep learning (DL) approaches neglect essential mechanisms governing crack width variation—including thermal gradients, hysteretic responses, and phase-shifted correlations—limiting their reliability in real-world applications. To bridge this gap, we propose a mechanism-guided optimization (MGO) framework that integrates domain knowledge into the Informer architecture through physics-informed enhancements: auto-correlation modeling for capturing temperature-crack hysteresis, static gated fusion for multi-feature integration, and adaptive elastic net regularization for feature selection. Validated on cable-stayed bridge monitoring data, our framework achieves significant mean absolute error reductions (MAE) (5 %–60 %) and root mean square error reductions (RMSE) (10 %–55 %) versus baseline Informer across all cracks and prediction horizons, with diebold-mariano (DM) tests confirming statistical superiority in most cases. Crucially, it demonstrates superior precision relative to six state-of-the-art benchmarks across all evaluation scenarios. The ordinary least squares (OLS)-enhanced variant further delivers volatility reduction, while sensor failure tests establish quantifiable robustness benchmarks through MAE progression from 0. 013 mm to 0. 391 mm. This work establishes an interpretable, physics-grounded paradigm that explicitly links environmental drivers to structural degradation.

Details DOI

AAAI Conference 2025 Conference Paper

Guided and Variance-Corrected Fusion with One-shot Style Alignment for Large-Content Image Generation

  • Shoukun Sun
  • Min Xian
  • Tiankai Yao
  • Fei Xu
  • Luca Capriotti

Producing large images using small diffusion models is gaining increasing popularity, as the cost of training large models could be prohibitive. A common approach involves jointly generating a series of overlapped image patches and obtaining large images by merging adjacent patches. However, results from existing methods often exhibit obvious artifacts, e.g., seams and inconsistent objects and styles. To address the issues, we proposed Guided Fusion (GF), which mitigates the negative impact from distant image regions by applying a weighted average to the overlapping regions. Moreover, we proposed Variance-Corrected Fusion (VCF), which corrects data variance at post-averaging, generating more accurate fusion for the Denoising Diffusion Probabilistic Model. Furthermore, we proposed a one-shot Style Alignment (SA), which generates a coherent style for large images by adjusting the initial input noise without adding extra computational burden. Extensive experiments demonstrated that the proposed fusion methods improved the quality of the generated image significantly. As a plug-and-play module, the proposed method can be widely applied to enhance other fusion-based methods for large image generation.

PDF Details DOI

AAAI Conference 2024 Conference Paper

CFR-ICL: Cascade-Forward Refinement with Iterative Click Loss for Interactive Image Segmentation

  • Shoukun Sun
  • Min Xian
  • Fei Xu
  • Luca Capriotti
  • Tiankai Yao

The click-based interactive segmentation aims to extract the object of interest from an image with the guidance of user clicks. Recent work has achieved great overall performance by employing feedback from the output. However, in most state-of-the-art approaches, 1) the inference stage involves inflexible heuristic rules and requires a separate refinement model, and 2) the number of user clicks and model performance cannot be balanced. To address the challenges, we propose a click-based and mask-guided interactive image segmentation framework containing three novel components: Cascade-Forward Refinement (CFR), Iterative Click Loss (ICL), and SUEM image augmentation. The CFR offers a unified inference framework to generate segmentation results in a coarse-to-fine manner. The proposed ICL allows model training to improve segmentation and reduce user interactions simultaneously. The proposed SUEM augmentation is a comprehensive way to create large and diverse training sets for interactive image segmentation. Extensive experiments demonstrate the state-of-the-art performance of the proposed approach on five public datasets. Remarkably, our model reduces by 33.2%, and 15.5% the number of clicks required to surpass an IoU of 0.95 in the previous state-of-the-art approach on the Berkeley and DAVIS sets, respectively.

PDF Details DOI

TCS Journal 2024 Journal Article

Languages generated by numerical P systems with thresholds

  • Luping Zhang
  • Fei Xu

Numerical P systems with thresholds (NPT systems) are a type of distributive and parallel computing model in the framework of membrane computing, inspired by the mechanism of information processing in cells. In membrane computing, the study of language generating/accepting power of a computing model is essential for understanding its capabilities and limitations, while the language generating/accepting power of NPT systems remains open. In this work, a language hierarchy for NPT systems is established by considering polynomials of degree one as production functions. Specifically, if each production function is a variable with a positive integer coefficient, the NPT systems characterize regular languages. If each production function is a variable with an integer coefficient, the languages generated by the NPT systems are no more than context-sensitive. Further, the NPT systems generate all recursively enumerable languages if each production function is a linear combination of no more than two variables and each term of a production function is a variable with an integer coefficient. The results show that the language generating power of NPT systems is closely related to the number of variables and the range of coefficients in production functions.

Details DOI

TCS Journal 2022 Journal Article

Asynchronous homogenous spiking neural P systems with local rule synchronization

  • Luping Zhang
  • Fei Xu

Homogenous spiking neural P systems (HSNP systems) are a class of neuron-inspired computing models, where each neuron contains an identical set of rules. It remains open how to design universal asynchronous HSNP systems. In this work, we introduce local rule synchronization into asynchronous HSNP systems, and such systems are abbreviated as AHSNPR systems. Specifically, a family of the rule sets is specified; a rule in a specified rule set is applied synchronously with all the other rules in the same set, and a rule not in any specified rule set is applied asynchronously. We investigate the number generating power of AHSNPR systems. It is proved that general and unbounded AHSNPR systems are universal, and bounded AHSNPR systems are only able to characterize the semilinear sets of numbers achieving the corresponding properties of decidability and closure. The results show that the local rule synchronization is useful in constructing universal asynchronous HSNP systems.

Details DOI

TCS Journal 2021 Journal Article

Control languages accepted by labeled spiking neural P systems with rules on synapses

  • Luping Zhang
  • Fei Xu
  • Ajeesh Ramanujan
  • K.G. Subramanian

Spiking neural P systems with rules on synapses (RSSNP systems) are a class of computation models which are inspired by the information processing and communication manner of neurons. In this work, we consider labeled RSSNP systems (lRSSNP systems), where each rule is assigned either with a label chosen from an alphabet Σ or with the empty label λ. A string over an alphabet is accepted by an lRSSNP system if the string is processed from left to right by the system in the sense that in a step only rules labeled with the processed symbol or with λ are used (not both), and the system reaches a final configuration in the moment when the whole string is processed. The set of all accepted strings is categorized as the restricted (computations are done with the application of the rules labeled with symbols from the given alphabet) control language and the unrestricted (rules labeled with λ are allowed in the computations) control language of the system. We study the language accepting power of lRSSNP systems using only standard spiking rules by comparing the family of control languages of lRSSNP systems with the families of languages in the Chomsky hierarchy. It is proved that restricted lRSSNP systems can accept no more than context-sensitive languages, and unrestricted lRSSNP systems can accept recursively enumerable languages.

Details DOI

AIIM Journal 2021 Journal Article

Tumor saliency estimation for breast ultrasound images via breast anatomy modeling

  • Fei Xu
  • Yingtao Zhang
  • H.D. Cheng
  • Boyu Zhang
  • Jianrui Ding
  • Chunping Ning
  • Ying Wang

Tumor saliency estimation aims to localize tumors by modeling the visual stimuli in medical images. However, it is a challenging task for breast ultrasound (BUS) image due to the complicated anatomic structure of the breast and poor image quality; and existing saliency estimation approaches only model the generic visual stimuli, e. g. , local and global contrast, location, and feature correlation, and achieve poor performance for tumor saliency estimation. In this paper, we propose a novel optimization model to estimate tumor saliency by utilizing breast anatomy. First, we model breast anatomy and decompose breast ultrasound image into layers using Neutro-Connectedness; then utilize the layers to generate the foreground and background maps; and finally propose a novel objective function to estimate the tumor saliency by integrating the foreground map, background map, adaptive center bias, and region-based correlation cues. The extensive experiments demonstrate that the proposed approach obtains more accurate foreground and background maps with breast anatomy; especially, for the images having large or small tumors. Meanwhile, the new objective function can handle the images without tumors. The newly proposed method achieves state-of-the-art performance comparing to eight tumor saliency estimation approaches using two BUS datasets.

Details DOI

AAAI Conference 2017 Short Paper

Attention Based LSTM for Target Dependent Sentiment Classification

  • Min Yang
  • Wenting Tu
  • Jingxuan Wang
  • Fei Xu
  • Xiaojun Chen

We present an attention-based bidirectional LSTM approach to improve the target-dependent sentiment classification. Our method learns the alignment between the target entities and the most distinguishing features. We conduct extensive experiments on a real-life dataset. The experimental results show that our model achieves state-of-the-art results.

PDF Details

AAAI Conference 2017 Short Paper

Detecting Review Spammer Groups

  • Min Yang
  • Ziyu Lu
  • Xiaojun Chen
  • Fei Xu

With an increasing number of paid writers posting fake reviews to promote or demote some target entities through Internet, review spammer detection has become a crucial and challenging task. In this paper, we propose a three-phase method to address the problem of identifying review spammer groups and individual spammers, who get paid for posting fake comments. We evaluate the effectiveness and performance of the approach on a real-life online shopping review dataset from amazon. com. The experimental result shows that our model achieved comparable or better performance than previous work on spammer detection.

PDF Details

JBHI Journal 2016 Journal Article

Analysis of the Chaotic Characteristics of Human Colonic Activities and Comparison of Healthy Participants to Costive Subjects

  • Li Lu
  • Guozheng Yan
  • Kai Zhao
  • Fei Xu

Constipation is a common yet distressing disease that has high rates of morbidity and impacts patients' quality of life. However, there is no perfect method to distinguish costive patients from healthy subjects. Is there chaos in human colonic activities? Are there any differences for the chaos indicators of colonic activities between healthy and costive subjects? Can these indicators distinguish patients with constipation from healthy subjects? To answer these questions, colonic pressure data from 16 healthy subjects and 48 patients with constipation were analyzed using the chaos theory. Three chaotic indicators [i. e. , the largest Lyapunov exponent (LyE), correlation dimension (CorDim), and Kolmogorov entropy (KoEn)] were calculated and compared between groups with the Wilcoxon rank sum test. As a result, the LyE was greater than zero and the CorDim was fractioned, which showed that human colonic activities have clear chaotic characteristics. Statistically significant differences were observed between groups for CorDim (p <; 0. 05), whereas LyE did not show statistically significant differences between groups. The chaotic indicator of CorDim was able to differentiate between patients with constipation and healthy subjects. The chaos theory provides a new method for learning the nonlinear dynamics of human gastrointestinal activities.

Details DOI

NeurIPS Conference 2009 Conference Paper

Individuation, Identification and Object Discovery

  • Charles Kemp
  • Alan Jern
  • Fei Xu

Humans are typically able to infer how many objects their environment contains and to recognize when the same object is encountered twice. We present a simple statistical model that helps to explain these abilities and evaluate it in three behavioral experiments. Our first experiment suggests that humans rely on prior knowledge when deciding whether an object token has been previously encountered. Our second and third experiments suggest that humans can infer how many objects they have seen and can learn about categories and their properties even when they are uncertain about which tokens are instances of the same object.

PDF Details

NeurIPS Conference 2008 Conference Paper

A rational model of preference learning and choice prediction by children

  • Christopher Lucas
  • Thomas Griffiths
  • Fei Xu
  • Christine Fawcett

Young children demonstrate the ability to make inferences about the preferences of other agents based on their choices. However, there exists no overarching account of what children are doing when they learn about preferences or how they use that knowledge. We use a rational model of preference learning, drawing on ideas from economics and computer science, to explain the behavior of children in several recent experiments. Specifically, we show how a simple econometric model can be extended to capture two- to four-year-olds’ use of statistical information in inferring preferences, and their generalization of these preferences.

PDF Details

NeurIPS Conference 2008 Conference Paper

An ideal observer model of infant object perception

  • Charles Kemp
  • Fei Xu

Before the age of 4 months, infants make inductive inferences about the motions of physical objects. Developmental psychologists have provided verbal accounts of the knowledge that supports these inferences, but often these accounts focus on categorical rather than probabilistic principles. We propose that infant object perception is guided in part by probabilistic principles like persistence: things tend to remain the same, and when they change they do so gradually. To illustrate this idea, we develop an ideal observer model that includes probabilistic formulations of rigidity and inertia. Like previous researchers, we suggest that rigid motions are expected from an early age, but we challenge the previous claim that expectations consistent with inertia are relatively slow to develop (Spelke et al. , 1992). We support these arguments by modeling four experiments from the developmental literature.

PDF Details
v2026.09.13