arXiv subjects

Shuyang Zhao

Publications and source records attributed to Shuyang Zhao.

6 recordsLinked to original sources

arXiv2026

Efficient Proton Relay Orchestrated by Covalent Bond Switching of Active Amino Acids in Protein Channels

Through systematic mutational simulations of the key site in a proton channel, we find that 13 of the 20 canonical amino acid residues are active for proton transfer through covalent bond switching, whereas the remaining 7 residues, whose side chains terminate in sp3 hybridized carbon-hydrogen covalent bonds, do not undergo such bond switching and are therefore inactive. All active residues have a negative electrostatic potential extremum at the proton accepting atom and lower energy barriers for proton relay orchestrated by bond switching, whereas the inactive residues have positive electrostatic potential extremum and significantly higher barriers for bond switching. We further find that the active residues tend to be distributed within the pore to mediate proton transfer, while the inactive residues are enriched in the periphery to stabilize the structure. This bond switching activity can also be observed in respiratory complex I. These findings establish a new classification criterion for amino acids based on their covalent bond switching activity, providing insights into how life utilizes the 20 types of amino acids.

physics.bio-ph↗

arXiv2024

A Robust Probability-based Joint Registration Method of Multiple Point Clouds Considering Local Consistency

In robotic inspection, joint registration of multiple point clouds is an essential technique for estimating the transformation relationships between measured parts, such as multiple blades in a propeller. However, the presence of noise and outliers in the data can significantly impair the registration performance by affecting the correctness of correspondences. To address this issue, we incorporate local consistency property into the probability-based joint registration method. Specifically, each measured point set is treated as a sample from an unknown Gaussian Mixture Model (GMM), and the registration problem is framed as estimating the probability model. By incorporating local consistency into the optimization process, we enhance the robustness and accuracy of the posterior distributions, which represent the one-to-all correspondences that directly determine the registration results. Effective closed-form solution for transformation and probability parameters are derived with Expectation-Maximization (EM) algorithm. Extensive experiments demonstrate that our method outperforms the existing methods, achieving high accuracy and robustness with the existence of noise and outliers. The code will be available at https://github.com/sulingjie/JPRLC_registration.

cs.RO↗

arXiv2021

On the inductive blockwise Alperin weight condition for the unipotent blocks of finite groups of Lie type E_6

In this article, we consider the finite exceptional groups of Lie type $E_6$ and $^2E_6$. We prove the inductive blockwise Alperin weight condition holds for unipotent $l$-blocks of $E_6^{\varepsilon}(q)$ if $2,3\nmid q$, $l\geq 5$

math.RT↗

arXiv2020

Active Learning for Sound Event Detection

This paper proposes an active learning system for sound event detection (SED). It aims at maximizing the accuracy of a learned SED model with limited annotation effort. The proposed system analyzes an initially unlabeled audio dataset, from which it selects sound segments for manual annotation. The candidate segments are generated based on a proposed change point detection approach, and the selection is based on the principle of mismatch-first farthest-traversal. During the training of SED models, recordings are used as training inputs, preserving the long-term context for annotated segments. The proposed system clearly outperforms reference methods in the two datasets used for evaluation (TUT Rare Sound 2017 and TAU Spatial Sound 2019). Training with recordings as context outperforms training with only annotated segments. Mismatch-first farthest-traversal outperforms reference sample selection methods based on random sampling and uncertainty sampling. Remarkably, the required annotation effort can be greatly reduced on the dataset where target sound events are rare: by annotating only 2% of the training data, the achieved SED performance is similar to annotating all the training data.

eess.AS↗

arXiv2020

Hessian quotient equations on exterior domains

It is well-known that a celebrated Jörgens-Calabi-Pogorelov theorem for Monge-Ampère equations states that any classical (viscosity) convex solution of $\det(D^2u)=1$ in $\mathbb{R}^n$ must be a quadratic polynomial. Therefore, it is an interesting topic to study the existence and uniqueness theorem of such fully nonlinear partial differential equations' Dirichlet problems on exterior domains with suitable asymptotic conditions at infinity. As a continuation of the works of Caffarelli-Li for Monge-Ampère equation and of Bao-Li-Li for $k$-Hessian equations, this paper is devoted to the solvability of the exterior Dirichlet problem of Hessian quotient equations $σ_k(λ(D^2u))/σ_l(λ(D^2u))=1$ for any $1\leq l<k\leq n$ in all dimensions $n\geq 2$. By introducing the concept of generalized symmetric subsolutions and then using the Perron's method, we establish the existence theorem for viscosity solutions, with prescribed asymptotic behavior which is close to some quadratic polynomial at infinity.

math.AP↗

arXiv2019

Tag Recommendation by Word-Level Tag Sequence Modeling

In this paper, we transform tag recommendation into a word-based text generation problem and introduce a sequence-to-sequence model. The model inherits the advantages of LSTM-based encoder for sequential modeling and attention-based decoder with local positional encodings for learning relations globally. Experimental results on Zhihu datasets illustrate the proposed model outperforms other state-of-the-art text classification based methods.

cs.CL↗