arXiv subjects

Lin Yang

Publications and source records attributed to Lin Yang.

At least 181 records · Page 10Linked to original sources

arXiv2022

The low-entropy hydration shell at the binding site of spike RBD determines the contagiousness of SARS-CoV-2 variants

The infectivity of SARS-CoV-2 depends on the binding affinity of the receptor-binding domain (RBD) of the spike protein with the angiotensin converting enzyme 2 (ACE2) receptor. The calculated RBD-ACE2 binding energies indicate that the difference in transmission efficiency of SARS-CoV-2 variants cannot be fully explained by electrostatic interactions, hydrogen-bond interactions, van der Waals interactions, internal energy, and nonpolar solvation energies. Here, we demonstrate that low-entropy regions of hydration shells around proteins drive hydrophobic attraction between shape-matched low-entropy regions of the hydration shells, which essentially coordinates protein-protein binding in rotational-configurational space of mutual orientations and determines the binding affinity. An innovative method was used to identify the low-entropy regions of the hydration shells of the RBDs of multiple SARS-CoV-2 variants and the ACE2. We observed integral low-entropy regions of hydration shells covering the binding sites of the RBDs and matching in shape to the low-entropy region of hydration shell at the binding site of the ACE2. The RBD-ACE2 binding is thus found to be guided by hydrophobic collapse between the shape-matched low-entropy regions of the hydration shells. A measure of the low-entropy of the hydration shells can be obtained by counting the number of hydrophilic groups expressing hydrophilicity within the binding sites. The low-entropy level of hydration shells at the binding site of a spike protein is found to be an important indicator of the contagiousness of the coronavirus.

q-bio.BM↗

arXiv2022

Hybrid Curriculum Learning for Emotion Recognition in Conversation

Emotion recognition in conversation (ERC) aims to detect the emotion label for each utterance. Motivated by recent studies which have proven that feeding training examples in a meaningful order rather than considering them randomly can boost the performance of models, we propose an ERC-oriented hybrid curriculum learning framework. Our framework consists of two curricula: (1) conversation-level curriculum (CC); and (2) utterance-level curriculum (UC). In CC, we construct a difficulty measurer based on "emotion shift" frequency within a conversation, then the conversations are scheduled in an "easy to hard" schema according to the difficulty score returned by the difficulty measurer. For UC, it is implemented from an emotion-similarity perspective, which progressively strengthens the model's ability in identifying the confusing emotions. With the proposed model-agnostic hybrid curriculum learning strategy, we observe significant performance boosts over a wide range of existing ERC models and we are able to achieve new state-of-the-art results on four public ERC datasets.

cs.CL↗

arXiv2022

Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesis

Synthesizing a subject-specific pathology-free image from a pathological image is valuable for algorithm development and clinical practice. In recent years, several approaches based on the Generative Adversarial Network (GAN) have achieved promising results in pseudo-healthy synthesis. However, the discriminator (i.e., a classifier) in the GAN cannot accurately identify lesions and further hampers from generating admirable pseudo-healthy images. To address this problem, we present a new type of discriminator, the segmentor, to accurately locate the lesions and improve the visual quality of pseudo-healthy images. Then, we apply the generated images into medical image enhancement and utilize the enhanced results to cope with the low contrast problem existing in medical image segmentation. Furthermore, a reliable metric is proposed by utilizing two attributes of label noise to measure the health of synthetic images. Comprehensive experiments on the T2 modality of BraTS demonstrate that the proposed method substantially outperforms the state-of-the-art methods. The method achieves better performance than the existing methods with only 30\% of the training data. The effectiveness of the proposed method is also demonstrated on the LiTS and the T1 modality of BraTS. The code and the pre-trained model of this study are publicly available at https://github.com/Au3C2/Generator-Versus-Segmentor.

eess.IV↗

arXiv2022

Mechanism, measurement, and quantification of stress in decision process: a model based systematic-review protocol

Every human action begins with decision-making. Stress is a significant source of biases that can influence human decision-making. In order to understand the relationship between stress and decision-making, stress quantification is fundamental. Different methods of measuring and quantifying stress in decision-making have been described in the literature while an up-to-date systematic review of the existing methods is lacking. Moreover, mental stress, mental effort, cognitive workload, and workload are often used interchangeably but should be distinguished to enable in-depth investigations of decision-mechanisms. Our objectives are to clarify stress related concepts and review the measurement, quantification, and application of stress during decision making activities.

cs.HC↗

arXiv2022

Weakly Supervised Learning for cell recognition in immunohistochemical cytoplasm staining images

Cell classification and counting in immunohistochemical cytoplasm staining images play a pivotal role in cancer diagnosis. Weakly supervised learning is a potential method to deal with labor-intensive labeling. However, the inconstant cell morphology and subtle differences between classes also bring challenges. To this end, we present a novel cell recognition framework based on multi-task learning, which utilizes two additional auxiliary tasks to guide robust representation learning of the main task. To deal with misclassification, the tissue prior learning branch is introduced to capture the spatial representation of tumor cells without additional tissue annotation. Moreover, dynamic masks and consistency learning are adopted to learn the invariance of cell scale and shape. We have evaluated our framework on immunohistochemical cytoplasm staining images, and the results demonstrate that our method outperforms recent cell recognition approaches. Besides, we have also done some ablation studies to show significant improvements after adding the auxiliary branches.

eess.IV↗

arXiv2022

Space Layout of Low-entropy Hydration Shells Guides Protein Binding

Protein-protein binding enables orderly and lawful biological self-organization, and is therefore considered a miracle of nature. Protein-protein binding is steered by electrostatic forces, hydrogen bonding, van der Waals force, and hydrophobic interactions. Among these physical forces, only the hydrophobic interactions can be considered as long-range intermolecular attractions between proteins in intracellular and extracellular fluid. Low-entropy regions of hydration shells around proteins drive hydrophobic attraction among them that essentially coordinate protein-protein docking in rotational-conformational space of mutual orientations at the guidance stage of the binding. Here, an innovative method was developed for identifying the low-entropy regions of hydration shells of given proteins, and we discovered that the largest low-entropy regions of hydration shells on proteins typically cover the binding sites. According to an analysis of determined protein complex structures, shape matching between the largest low-entropy hydration shell region of a protein and that of its partner at the binding sites is revealed as a regular pattern. Protein-protein binding is thus found to be mainly guided by hydrophobic collapse between the shape-matched low-entropy hydration shells that is verified by bioinformatics analyses of hundreds of structures of protein complexes. A simple algorithm is developed to precisely predict protein binding sites.

q-bio.BM↗

arXiv2022

Consecutive topological phase transitions and colossal magnetoresistance in a magnetic topological semimetal

The combination of magnetic symmetries and electronic band topology provides a promising route for realizing topologically nontrivial quasiparticles, and the manipulation of magnetic structures may enable the switching between topological phases, with the potential for achieving functional physical properties. Here, we report measurements of the electrical resistivity of EuCd$_2$As$_2$ under pressure, which show an intriguing insulating dome at pressures between $p_{\rm c1}\sim1.0$~GPa and $p_{\rm c2}\sim2.0$~GPa, situated between two regimes with metallic transport. The insulating state can be fully suppressed by a small magnetic field, leading to a colossal negative magnetoresistance on the order of $10^5$\%, accessible via a modest field of $\sim0.2$~T. First-principles calculations reveal that the dramatic evolution of the resistivity under pressure is due to consecutive transitions of EuCd$_2$As$_2$ from a magnetic topological insulator to a trivial insulator, and then to a Weyl semimetal, with the latter resulting from a pressure-induced change in the magnetic ground state. Similarly, the colossal magnetoresistance results from a field-induced polarization of the magnetic moments, transforming EuCd$_2$As$_2$ from a trivial insulator to a Weyl semimetal. These findings underscore weak magnetic exchange couplings and spin anisotropy as ingredients for discovering tunable magnetic topological materials with desirable functionalities.

cond-mat.str-el↗

arXiv2022

Distributed Bandits with Heterogeneous Agents

This paper tackles a multi-agent bandit setting where $M$ agents cooperate together to solve the same instance of a $K$-armed stochastic bandit problem. The agents are \textit{heterogeneous}: each agent has limited access to a local subset of arms and the agents are asynchronous with different gaps between decision-making rounds. The goal for each agent is to find its optimal local arm, and agents can cooperate by sharing their observations with others. While cooperation between agents improves the performance of learning, it comes with an additional complexity of communication between agents. For this heterogeneous multi-agent setting, we propose two learning algorithms, \ucbo and \AAE. We prove that both algorithms achieve order-optimal regret, which is $O\left(\sum_{i:\tildeΔ_i>0} \log T/\tildeΔ_i\right)$, where $\tildeΔ_i$ is the minimum suboptimality gap between the reward mean of arm $i$ and any local optimal arm. In addition, a careful selection of the valuable information for cooperation, \AAE achieves a low communication complexity of $O(\log T)$. Last, numerical experiments verify the efficiency of both algorithms.

cs.LG↗

arXiv2022

Towards Lightweight Applications: Asymmetric Enroll-Verify Structure for Speaker Verification

With the development of deep learning, automatic speaker verification has made considerable progress over the past few years. However, to design a lightweight and robust system with limited computational resources is still a challenging problem. Traditionally, a speaker verification system is symmetrical, indicating that the same embedding extraction model is applied for both enrollment and verification in inference. In this paper, we come up with an innovative asymmetric structure, which takes the large-scale ECAPA-TDNN model for enrollment and the small-scale ECAPA-TDNNLite model for verification. As a symmetrical system, our proposed ECAPA-TDNNLite model achieves an EER of 3.07% on the Voxceleb1 original test set with only 11.6M FLOPS. Moreover, the asymmetric structure further reduces the EER to 2.31%, without increasing any computational costs during verification.

cs.SD↗

arXiv2022

Magnetic interlayer coupling between ferromagnetic SrRuO$_3$ layers through a SrIrO$_3$ spacer

A key element to tailor the properties of magnetic multilayers is the coupling between the individual magnetic layers. In case of skyrmion hosting multilayers, coupling of skyrmions across the magnetic layers is highly desirable. Here the magnetic interlayer coupling was studied in epitaxial all-oxide heterostructures of ferromagnetic perovskite SrRuO$_3$ layers separated by spacers of the strong spin-orbit coupling oxide SrIrO$_3$. This combination of oxide layers is being discussed as a potential candidate system to host Néel skyrmions. First order reversal curve (FORC) measurements were performed in order to distinguish between magnetic switching processes of the individual layers and to disentangle the signal of soft magnetic impurities from the samples$'$ signal. Additionally, FORC investigations enabled to determine whether the coupling between the magnetic layers is ferromagnetic or antiferromagnetic. The observed interlayer coupling strength was weak for all the heterostructures, with SrIrO$_3$ spacers between 2 monolayers and 12 monolayers thick.

cond-mat.mtrl-sci↗

arXiv2021

J-PLUS: Stellar Parameters, C, N, Mg, Ca and [α/Fe] Abundances for Two Million Stars from DR1

Context. The Javalambre Photometric Local Universe Survey (J-PLUS) has obtained precise photometry in twelve specially designed filters for large numbers of Galactic stars. Deriving their precise stellar atmospheric parameters and individual elemental abundances is crucial for studies of Galactic structure, and the assembly history and chemical evolution of our Galaxy. Aims. Our goal is to estimate not only stellar parameters (effective temperature, Teff, surface gravity, log g, and metallicity, [Fe/H]), but also [α/Fe] and four elemental abundances ([C/Fe], [N/Fe], [Mg/Fe], and [Ca/Fe]) using data from J-PLUS DR1. Methods. By combining recalibrated photometric data from J-PLUS DR1, Gaia DR2, and spectroscopic labels from LAMOST, we design and train a set of cost-sensitive neural networks, the CSNet, to learn the non-linear mapping from stellar colors to their labels. Results. We have achieved precisions of δTeff {\sim}55K, δlogg{\sim}0.15dex, and δ[Fe/H]{\sim}0.07dex, respectively, over a wide range of temperature, surface gravity, and metallicity. The uncertainties of the abundance estimates for [α/Fe] and the four individual elements are in the range 0.04-0.08 dex. We compare our parameter and abundance estimates with those from other spectroscopic catalogs such as APOGEE and GALAH, and find an overall good agreement. Conclusions. Our results demonstrate the potential of well-designed, high-quality photometric data for determinations of stellar parameters as well as individual elemental abundances. Applying the method to J-PLUS DR1, we have obtained the aforementioned parameters for about two million stars, providing an outstanding data set for chemo-dynamic analyses of the Milky Way. The catalog of the estimated parameters is publicly accessible.

astro-ph.SR↗

arXiv2021

Stellar Loci V: Photometric Metallicities of 27 Million FGK Stars based on Gaia Early Data Release 3

We combine LAMOST DR7 spectroscopic data and Gaia EDR3 photometric data to construct high-quality giant (0.7 $< (BP-RP) <$ 1.4) and dwarf (0.5 $< (BP-RP) < $ 1.5) samples in the high Galactic latitude region, with precise corrections for magnitude-dependent systematic errors in the Gaia photometry and careful reddening corrections using empirically determined color- and reddening-dependent coefficients. We use the two samples to build metallicity-dependent stellar loci of Gaia colors for giants and dwarfs, respectively. For a given $(BP-RP)$ color, a one dex change in [Fe/H] results in about a 5 mmag change in $(BP-G)$ color for solar-type stars. These relations are used to determine metallicity estimates from EDR3 colors. Despite the weak sensitivity, the exquisite data quality of these colors enables a typical precision of about $δ$\,[Fe/H] = 0.2 dex. Our method is valid for FGK stars with $G \leq 16$, [Fe/H] $\geq -2.5$, and $E(B-V) \leq 0.5$. Stars with fainter $G$ magnitudes, lower metallicities, or larger reddening suffer from higher metallicity uncertainties. With the enormous data volume of Gaia, we have measured metallicity estimates for about 27 million stars with 10 $< G \leq 16$ across almost the entire sky, including over 6 million giants and 20 million dwarfs, which can be used for a number of studies. These include investigations of Galactic formation and evolution, the identification of candidate stars for subsequent high-resolution spectroscopic follow-up, the identification of wide binaries, and to obtain metallicity estimates of stars for asteroseismology and exoplanet research.

astro-ph.SR↗

arXiv2021

High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning

We introduce a method combining variational autoencoders (VAEs) and deep metric learning to perform Bayesian optimisation (BO) over high-dimensional and structured input spaces. By adapting ideas from deep metric learning, we use label guidance from the blackbox function to structure the VAE latent space, facilitating the Gaussian process fit and yielding improved BO performance. Importantly for BO problem settings, our method operates in semi-supervised regimes where only few labelled data points are available. We run experiments on three real-world tasks, achieving state-of-the-art results on the penalised logP molecule generation benchmark using just 3% of the labelled data required by previous approaches. As a theoretical contribution, we present a proof of vanishing regret for VAE BO.

cs.LG↗

arXiv2021

Sparsely Overlapped Speech Training in the Time Domain: Joint Learning of Target Speech Separation and Personal VAD Benefits

Target speech separation is the process of filtering a certain speaker's voice out of speech mixtures according to the additional speaker identity information provided. Recent works have made considerable improvement by processing signals in the time domain directly. The majority of them take fully overlapped speech mixtures for training. However, since most real-life conversations occur randomly and are sparsely overlapped, we argue that training with different overlap ratio data benefits. To do so, an unavoidable problem is that the popularly used SI-SNR loss has no definition for silent sources. This paper proposes the weighted SI-SNR loss, together with the joint learning of target speech separation and personal VAD. The weighted SI-SNR loss imposes a weight factor that is proportional to the target speaker's duration and returns zero when the target speaker is absent. Meanwhile, the personal VAD generates masks and sets non-target speech to silence. Experiments show that our proposed method outperforms the baseline by 1.73 dB in terms of SDR on fully overlapped speech, as well as by 4.17 dB and 0.9 dB on sparsely overlapped speech of clean and noisy conditions. Besides, with slight degradation in performance, our model could reduce the time costs in inference.

cs.SD↗

arXiv2021

The DKU-DukeECE-Lenovo System for the Diarization Task of the 2021 VoxCeleb Speaker Recognition Challenge

This report describes the submission of the DKU-DukeECE-Lenovo team to the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2021 track 4. Our system including a voice activity detection (VAD) model, a speaker embedding model, two clustering-based speaker diarization systems with different similarity measurements, two different overlapped speech detection (OSD) models, and a target-speaker voice activity detection (TS-VAD) model. Our final submission, consisting of 5 independent systems, achieves a DER of 5.07% on the challenge test set.

eess.AS↗

arXiv2021

Image-based Insider Threat Detection via Geometric Transformation

Insider threat detection has been a challenging task over decades, existing approaches generally employ the traditional generative unsupervised learning methods to produce normal user behavior model and detect significant deviations as anomalies. However, such approaches are insufficient in precision and computational complexity. In this paper, we propose a novel insider threat detection method, Image-based Insider Threat Detector via Geometric Transformation (IGT), which converts the unsupervised anomaly detection into supervised image classification task, and therefore the performance can be boosted via computer vision techniques. To illustrate, our IGT uses a novel image-based feature representation of user behavior by transforming audit logs into grayscale images. By applying multiple geometric transformations on these behavior grayscale images, IGT constructs a self-labelled dataset and then train a behavior classifier to detect anomaly in self-supervised manner. The motivation behind our proposed method is that images converted from normal behavior data may contain unique latent features which keep unchanged after geometric transformation, while malicious ones cannot. Experimental results on CERT dataset show IGT outperforms the classical autoencoder-based unsupervised insider threat detection approaches, and improves the instance and user based Area under the Receiver Operating Characteristic Curve (AUROC) by 4% and 2%, respectively.

cs.CR↗

arXiv2021

A Quantitative Framework for Network Resilience Evaluation using Dynamic Bayesian Network

Measuring and evaluating network resilience has become an important aspect since the network is vulnerable to both uncertain disturbances and malicious attacks. Networked systems are often composed of many dynamic components and change over time, which makes it difficult for existing methods to access the changeable situation of network resilience. This paper establishes a novel quantitative framework for evaluating network resilience using the Dynamic Bayesian Network. The proposed framework can be used to evaluate the network's multi-stage resilience processes when suffering various attacks and recoveries. First, we define the dynamic capacities of network components and establish the network's five core resilience capabilities to describe the resilient networking stages including preparation, resistance, adaptation, recovery, and evolution; the five core resilience capabilities consist of rapid response capability, sustained resistance capability, continuous running capability, rapid convergence capability, and dynamic evolution capability. Then, we employ a two-time slices approach based on the Dynamic Bayesian Network to quantify five crucial performances of network resilience based on core capabilities proposed above. The proposed approach can ensure the time continuity of resilience evaluation in time-varying networks. Finally, our proposed evaluation framework is applied to different attacks and recovery conditions in typical simulations and real-world network topology. Results and comparisons with extant studies indicate that the proposed method can achieve a more accurate and comprehensive evaluation and can be applied to network scenarios under various attack and recovery intensities.

cs.NI↗

arXiv2021

Hierarchical Self-Supervised Learning for Medical Image Segmentation Based on Multi-Domain Data Aggregation

A large labeled dataset is a key to the success of supervised deep learning, but for medical image segmentation, it is highly challenging to obtain sufficient annotated images for model training. In many scenarios, unannotated images are abundant and easy to acquire. Self-supervised learning (SSL) has shown great potentials in exploiting raw data information and representation learning. In this paper, we propose Hierarchical Self-Supervised Learning (HSSL), a new self-supervised framework that boosts medical image segmentation by making good use of unannotated data. Unlike the current literature on task-specific self-supervised pretraining followed by supervised fine-tuning, we utilize SSL to learn task-agnostic knowledge from heterogeneous data for various medical image segmentation tasks. Specifically, we first aggregate a dataset from several medical challenges, then pre-train the network in a self-supervised manner, and finally fine-tune on labeled data. We develop a new loss function by combining contrastive loss and classification loss and pretrain an encoder-decoder architecture for segmentation tasks. Our extensive experiments show that multi-domain joint pre-training benefits downstream segmentation tasks and outperforms single-domain pre-training significantly. Compared to learning from scratch, our new method yields better performance on various tasks (e.g., +0.69% to +18.60% in Dice scores with 5% of annotated data). With limited amounts of training data, our method can substantially bridge the performance gap w.r.t. denser annotations (e.g., 10% vs.~100% of annotated data).

cs.CV↗