arXiv subjects

Shuzhen Lv

Publications and source records attributed to Shuzhen Lv.

7 recordsLinked to original sources

arXiv2026

Atrial Fibrillation Detection with Arbitrary Leads via a Codebook-Based Reconstruction-Classification Framework

\textbf{Background and Objective}: Reliable atrial fibrillation (AF) detection from electrocardiogram (ECG) signals remains challenging in real-world clinical settings due to variable lead configurations, cross-dataset domain shifts, and pervasive physiological and technical artifacts. So we develop a robust and generalizable deep learning model for accurate AF detection.\\ \textbf{Methods}: We propose the Dual-Codebook Graph Collaborative Network (DCGCNet), a novel end-to-end vector-quantized variational autoencoder that jointly performs AF classification and ECG reconstruction. DCGCNet introduces two key components: (1) a Local-Global Contrastive Module for learning noise-invariant representations, and (2) an Adaptive Codebook Vector Quantizer that dynamically refines codebook prototypes to better align with input data distributions, thereby preventing codebook collapse and enhancing generalization.\\ \textbf{Results}: DCGCNet achieves state-of-the-art performance in standard intra-dataset 12-lead evaluation and demonstrates exceptional cross-dataset generalization across seven diverse settings, consistently attaining AUC > 0.98 in all cases. Furthermore, it maintains high diagnostic accuracy under realistic noisy conditions, including baseline wander, powerline interference, and EMG artifacts.\\ \textbf{Conclusions}: DCGCNet establishes a new benchmark for robust, generalizable, and noise-resilient AF detection, showing strong potential for deployment in real-world clinical environments.

cs.LG↗

arXiv2026

Robust and Generalizable Atrial Fibrillation Detection from ECG Using Time-Frequency Fusion and Supervised Contrastive Learning

Atrial fibrillation (AF) is a common cardiac arrhythmia that significantly increases the risk of stroke and heart failure, necessitating reliable and generalizable detection methods from electrocardiogram (ECG) recordings. Although deep learning has advanced automated AF diagnosis, existing approaches often struggle to exploit complementary time frequency information effectively, limiting both robustness under intra-dataset and generalization across diverse clinical datasets. To address these challenges, we propose a crossmodal deep learning framework comprising two key components: a Bidirectional Gating Module (BGM) and a Cross modal Supervised Contrastive Learning (CSCL) strategy. The BGM facilitates dynamic, reciprocal refinement between time and frequency domain features, enhancing model robustness to signal variations within a dataset. Meanwhile, CSCL explicitly structures the joint embedding space by pulling together label consistent samples and pushing apart different ones, thereby improving interclass separability and enabling strong cross dataset generalization. We evaluate our method using five fold crossvalidation on the AFDB and CPSC2021 datasets. Furthermore, to assess cross dataset generalization, we conduct bidirectional cross dataset experiments across AFDB, CPSC2021, LTAF, and SHDBAF by training on one dataset and testing on another. Results show consistent improvements over state of the art methods across multiple metrics, demonstrating that our approach achieves both high intra dataset robustness and excellent crossdataset generalization. We further demonstrate that our method achieves high computational efficiency and anti interference capability, making it suitable for edge deployment.

q-bio.QM↗

arXiv2025

Stoimenow matchings avoiding multiple Catalan patterns simultaneously

Motivated by Vassiliev's knot invariants, Stoimenow introduced a special class of matchings, now known as Stoimenow matchings. These matchings have since been linked to various combinatorial structures enumerated by the Fishburn numbers. In a recent paper, a problem posed by Bevan et al. was addressed concerning the identification of subsets of Stoimenow matchings counted by the Catalan numbers. Five such subsets were presented, each defined by the avoidance of a single pattern, referred to as a Catalan pattern, within Stoimenow matchings. In the present paper, we extend this line of research by enumerating all cases of simultaneous avoidance of sets of Catalan patterns in Stoimenow matchings. This comprehensive analysis reveals connections to nine integer sequences listed in the OEIS.

math.CO↗

arXiv2025

Catalan structures arising from pattern-avoiding Stoimenow matchings and other Fishburn objects

In connection with Vassiliev's knot invariants, Stoimenow introduced in 1998 a class of matchings, also known as regular linearized chord diagrams. These matchings are linked to various combinatorial structures, all of which are associated with the Fishburn numbers. In this paper, we address a problem posed by Bevan et al.\ in 2025 concerning the identification of subsets of Stoimenow matchings that are counted by the Catalan numbers. We present five solutions in terms of pattern-avoiding matchings. We also consider four infinite families of patterns that generalize four of the five forbidden patterns appearing in the solution to the problem we solved and prove that the matchings avoiding them are equinumerous. Finally, we establish numerous results on distributions and joint equidistribution of statistics over these Catalan-counted subsets of Fishburn structures, namely Stoimenow matchings, $(2+2)$-free posets, ascent sequences, and Fishburn permutations, notably expressing some of them in terms of Narayana numbers and others in terms of ballot numbers.

math.CO↗

arXiv2025

Joint equidistributions of mesh patterns 123 and 132 with minus antipodal shadings

The study of joint equidistributions of mesh patterns 123 and 132 with the same symmetric shadings was recently initiated by Kitaev and Lv, where 75 of 80 potential joint equidistributions were proven. In this paper, we prove 112 out of 126 potential joint equidistributions of mesh patterns 123 and 132 with the same minus antipodal shadings. As a byproduct, we present 562 joint equidistribution results for non-symmetric and non-minus-antipodal shadings. To achieve this, we construct bijections, find recurrence relations, and obtain generating functions. Moreover, we demonstrate that the joint distributions of several pairs of mesh patterns are related to the unsigned Stirling numbers of the first kind.

math.CO↗

arXiv2024

Joint equidistributions of mesh patterns 123 and 321 with symmetric and minus-antipodal shadings

In this paper, we extend recent results by Lv and Kitaev by proving 20 (out of 22 possible) joint equidistributions of mesh patterns 123 and 321 with symmetric shadings, as well as all 36 joint equidistributions of these patterns with minus-antipodal shadings. Our results link several joint equidistributions of mesh patterns to various integer sequences, including unsigned Stirling numbers of the first kind, harmonic numbers, and the numbers of inversion sequences avoiding a certain vincular pattern studied by Lin and Yan.

math.CO↗

arXiv2024

On (joint) equidistributions of mesh patterns 123 and 132 with symmetric shadings

A notable problem within permutation patterns that has attracted considerable attention in literature since 1973 is the search for a bijective proof demonstrating that 123-avoiding and 132-avoiding permutations are equinumerous, both counted by the Catalan numbers. Despite this equivalence, the distributions of occurrences of the patterns 123 and 132 are distinct. When considering 123 and 132 as mesh patterns and selectively shading boxes, similar scenarios arise, even when avoidance is defined by the Bell numbers or other sequences, rather than the Catalan numbers. However, computer experiments suggest that mesh patterns 123 and 132 may indeed be equidistributed. Furthermore, by considering symmetric shadings relative to the anti-diagonal, a maximum of 93 such equidistributed pairs can potentially exist. This paper establishes 75 such equidistributions, leaving the justification of the remaining cases as open problems. As a by-product, we also prove 36 relevant non-symmetric equidistributions. All our proofs are bijective and involve swapping occurrences of the patterns in question, thereby demonstrating their joint equidistribution. Our findings are a continuation of the systematic study of distributions of short-length mesh patterns initiated by Kitaev and Zhang in 2019.

math.CO↗