arXiv subjects

Yan Li

Publications and source records attributed to Yan Li.

At least 325 records · Page 18Linked to original sources

arXiv2024

Exploring Distance Query Processing in Edge Computing Environments

In the context of changing travel behaviors and the expanding user base of Geographic Information System (GIS) services, conventional centralized architectures responsible for handling shortest distance queries are facing increasing challenges, such as heightened load pressure and longer response times. To mitigate these concerns, this study is the first to develop an edge computing framework specially tailored for processing distance queries. In conjunction with this innovative system, we have developed a straightforward, yet effective, labeling technique termed Border Labeling. Furthermore, we have devised and implemented a range of query strategies intended to capitalize on the capabilities of the edge computing infrastructure. Our experiments demonstrate that our solution surpasses other methods in terms of both indexing time and query speed across various road network datasets. The empirical evidence from our experiments supports the claim that our edge computing architecture significantly reduces the latency encountered by end-users, thus markedly decreasing their waiting times.

cs.DB↗

arXiv2024

Study of the pion-mass dependence of $ρ$-meson properties in lattice QCD

We collect spectra extracted in the $I=\ell=1$ $ππ$ sector provided by various lattice QCD collaborations and study the $m_π$ dependence of $ρ$-meson properties using Hamiltonian Effective Field Theory (HEFT). In this unified analysis, the coupling constant and cutoff mass, characterizing the $ρ- ππ$ vertex, are both found to be weakly dependent on $m_π$, while the mass of the bare $ρ$, associated with a simple quark-model state, shows a linear dependence on $m_π^2$. Both the lattice results and experimental data can be described well. Drawing on HEFT's ability to describe the pion mass dependence of resonances in a single formalism, we map the dependence of the phase shift as a function of $m_π$, and expose interesting discrepancies in contemporary lattice QCD results.

hep-lat↗

arXiv2024

DragAnything: Motion Control for Anything using Entity Representation

We introduce DragAnything, which utilizes a entity representation to achieve motion control for any object in controllable video generation. Comparison to existing motion control methods, DragAnything offers several advantages. Firstly, trajectory-based is more userfriendly for interaction, when acquiring other guidance signals (e.g., masks, depth maps) is labor-intensive. Users only need to draw a line (trajectory) during interaction. Secondly, our entity representation serves as an open-domain embedding capable of representing any object, enabling the control of motion for diverse entities, including background. Lastly, our entity representation allows simultaneous and distinct motion control for multiple objects. Extensive experiments demonstrate that our DragAnything achieves state-of-the-art performance for FVD, FID, and User Study, particularly in terms of object motion control, where our method surpasses the previous methods (e.g., DragNUWA) by 26% in human voting.

cs.CV↗

arXiv2024

Knowledge Condensation and Reasoning for Knowledge-based VQA

Knowledge-based visual question answering (KB-VQA) is a challenging task, which requires the model to leverage external knowledge for comprehending and answering questions grounded in visual content. Recent studies retrieve the knowledge passages from external knowledge bases and then use them to answer questions. However, these retrieved knowledge passages often contain irrelevant or noisy information, which limits the performance of the model. To address the challenge, we propose two synergistic models: Knowledge Condensation model and Knowledge Reasoning model. We condense the retrieved knowledge passages from two perspectives. First, we leverage the multimodal perception and reasoning ability of the visual-language models to distill concise knowledge concepts from retrieved lengthy passages, ensuring relevance to both the visual content and the question. Second, we leverage the text comprehension ability of the large language models to summarize and condense the passages into the knowledge essence which helps answer the question. These two types of condensed knowledge are then seamlessly integrated into our Knowledge Reasoning model, which judiciously navigates through the amalgamated information to arrive at the conclusive answer. Extensive experiments validate the superiority of the proposed method. Compared to previous methods, our method achieves state-of-the-art performance on knowledge-based VQA datasets (65.1% on OK-VQA and 60.1% on A-OKVQA) without resorting to the knowledge produced by GPT-3 (175B).

cs.CV↗

arXiv2024

Diamond Micro-Chip for Quantum Microscopy

The nitrogen vacancy (NV) center in diamond is an increasingly popular quantum sensor for microscopy of electrical current, magnetization, and spins. However, efficient NV-sample integration with a robust, high-quality interface remains an outstanding challenge to realize scalable, high-throughput microscopy. In this work, we characterize a diamond micro-chip (DMC) containing a (111)-oriented NV ensemble; and demonstrate its utility for high-resolution quantum microscopy. We perform strain imaging of the DMC and find minimal detrimental strain variation across a field-of-view of tens of micrometer. We find good ensemble NV spin coherence and optical properties in the DMC, suitable for sensitive magnetometry. We then use the DMC to demonstrate wide-field microscopy of electrical current, and show that diffraction-limited quantum microscopy can be achieved. We also demonstrate the deterministic transfer of DMCs with multiple materials of interest for next-generation electronics and spintronics. Lastly, we develop a polymer-based technique for DMC placement. This work establishes the DMC's potential to expand the application of NV quantum microscopy in materials, device, geological, biomedical, and chemical sciences.

physics.app-ph↗

arXiv2024

SELECTOR: Heterogeneous graph network with convolutional masked autoencoder for multimodal robust prediction of cancer survival

Accurately predicting the survival rate of cancer patients is crucial for aiding clinicians in planning appropriate treatment, reducing cancer-related medical expenses, and significantly enhancing patients' quality of life. Multimodal prediction of cancer patient survival offers a more comprehensive and precise approach. However, existing methods still grapple with challenges related to missing multimodal data and information interaction within modalities. This paper introduces SELECTOR, a heterogeneous graph-aware network based on convolutional mask encoders for robust multimodal prediction of cancer patient survival. SELECTOR comprises feature edge reconstruction, convolutional mask encoder, feature cross-fusion, and multimodal survival prediction modules. Initially, we construct a multimodal heterogeneous graph and employ the meta-path method for feature edge reconstruction, ensuring comprehensive incorporation of feature information from graph edges and effective embedding of nodes. To mitigate the impact of missing features within the modality on prediction accuracy, we devised a convolutional masked autoencoder (CMAE) to process the heterogeneous graph post-feature reconstruction. Subsequently, the feature cross-fusion module facilitates communication between modalities, ensuring that output features encompass all features of the modality and relevant information from other modalities. Extensive experiments and analysis on six cancer datasets from TCGA demonstrate that our method significantly outperforms state-of-the-art methods in both modality-missing and intra-modality information-confirmed cases. Our codes are made available at https://github.com/panliangrui/Selector.

cs.CV↗

arXiv2024

Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure

In real-world applications, image degeneration caused by adverse weather is always complex and changes with different weather conditions from days and seasons. Systems in real-world environments constantly encounter adverse weather conditions that are not previously observed. Therefore, it practically requires adverse weather removal models to continually learn from incrementally collected data reflecting various degeneration types. Existing adverse weather removal approaches, for either single or multiple adverse weathers, are mainly designed for a static learning paradigm, which assumes that the data of all types of degenerations to handle can be finely collected at one time before a single-phase learning process. They thus cannot directly handle the incremental learning requirements. To address this issue, we made the earliest effort to investigate the continual all-in-one adverse weather removal task, in a setting closer to real-world applications. Specifically, we develop a novel continual learning framework with effective knowledge replay (KR) on a unified network structure. Equipped with a principal component projection and an effective knowledge distillation mechanism, the proposed KR techniques are tailored for the all-in-one weather removal task. It considers the characteristics of the image restoration task with multiple degenerations in continual learning, and the knowledge for different degenerations can be shared and accumulated in the unified network structure. Extensive experimental results demonstrate the effectiveness of the proposed method to deal with this challenging task, which performs competitively to existing dedicated or joint training image restoration methods. Our code is available at https://github.com/xiaojihh/CL_all-in-one.

cs.CV↗

arXiv2024

Top-k contrast order-preserving pattern mining

Recently, order-preserving pattern (OPP) mining, a new sequential pattern mining method, has been proposed to mine frequent relative orders in a time series. Although frequent relative orders can be used as features to classify a time series, the mined patterns do not reflect the differences between two classes of time series well. To effectively discover the differences between time series, this paper addresses the top-k contrast OPP (COPP) mining and proposes a COPP-Miner algorithm to discover the top-k contrast patterns as features for time series classification, avoiding the problem of improper parameter setting. COPP-Miner is composed of three parts: extreme point extraction to reduce the length of the original time series, forward mining, and reverse mining to discover COPPs. Forward mining contains three steps: group pattern fusion strategy to generate candidate patterns, the support rate calculation method to efficiently calculate the support of a pattern, and two pruning strategies to further prune candidate patterns. Reverse mining uses one pruning strategy to prune candidate patterns and consists of applying the same process as forward mining. Experimental results validate the efficiency of the proposed algorithm and show that top-k COPPs can be used as features to obtain a better classification performance.

cs.DB↗

arXiv2024

Distribution and evolution of Li abundance in red clump stars can be explained by the internal gravity waves

The study of Li phenomena in red clump (RC) stars can give us a deeper understanding of the structure and evolution of stars. \citet{2022ApJ...933...58C} explained the RC Li abundance distributions naturally using only standard post main sequence (MS) Li evolution models when the distribution of progenitor masses and the depletion of Li during the MS observed in MS stars were considered, thus neither extra Li depletion nor Li creation mechanism is required. Nevertheless, it is interesting to consider the effects of mixing caused by some extra mechanisms. By constructing different models, we find that the mixing caused by internal gravity waves can explain the observed Li abundances of RC stars with low mass progenitors. To explain that, we rely on the extra mixing induced by internal gravity waves that are excited at the bottom of the convective envelope at the red giant branch (RGB) stage. During the RGB stage, introducing the internal gravity waves can improve the diffusion coefficient and strengthen the mixing effect. The effective enrichment of Li occurs at the late RGB stage and requires the diffusion coefficient of H-burning shell to reach $\rm \sim 10^{8}\,cm^{2}\,s^{-1}$. Our models predict that the Li abundance decreases from $\rm \sim 1.5\,dex$ to $\rm \sim 0.0\,dex$ at the end of core He-burning stage, thereby revealing the $\sim 99\%$ of the observed Li abundance distribution. The thermohaline mixing regulates the Li abundance of RGB stars, which combines with the internal gravity waves can explain the Li abundances of most giants.

astro-ph.SR↗

arXiv2024

Convective Mixing: The Formation Channel of Li-rich Giants

Increasing observed data indicate that part of giants has abnormally high lithium (Li) inside their surface, and their proportion is around 1%. Instead of pursuing the feasible mechanisms for extra Li enrichment, we focus on how to inhibit Li depletion from the main sequence (MS) phase of giants. With this in mind, we find that convective mixing is capable of achieving this goal and forming Li-rich giants, which is mainly attributed to the convection model with the convective boundary defined by the Ledoux criterion. Another factor in the formation of Li-rich giants in our convection models is related to the Li abundances of their progenitors. If the Li abundances of the progenitors exceed the meteoritic value (3.3 dex), then the majority of giants will be rich in Li. This is the general pattern of stellar Li abundance evolution without factoring in extra Li depletion. We propose that other Li depletion processes should also be adopted in the future, as they may be the key to the 1% puzzle.

astro-ph.SR↗

arXiv2024

Narrowband telecom band polarization-entangled photon source by superposed monolithic cavities

A high-quality narrowband polarization-entangled source in the telecom band is preferred to avoid frequency dispersion for long-distance transmission in optical fibers and to efficiently couple with telecom band quantum memories. Here, we report narrowband, telecom-band, polarization-entangled photon pair generation based on the superposition of single-longitudinal-mode photon pairs from two monolithic nonlinear crystal cavities in a passively stable interferometer based on beam displacers. The photon pairs generated from the cavities exhibit a high coincidence to accidental coincidence ratio of 20000 and a bandwidth below 500 MHz. Two-photon polarization interference, Bell-inequality, and quantum state tomography are performed to indicate the high quality of the entangled source. The current configuration demonstrates greater stability than traditional free space cavity-enhanced polarization-entangled state generation, which is promising for quantum communication applications.

quant-ph↗

arXiv2024

One for Multiple: Physics-informed Synthetic Data Boosts Generalizable Deep Learning for Fast MRI Reconstruction

Magnetic resonance imaging (MRI) is a widely used radiological modality renowned for its radiation-free, comprehensive insights into the human body, facilitating medical diagnoses. However, the drawback of prolonged scan times hinders its accessibility. The k-space undersampling offers a solution, yet the resultant artifacts necessitate meticulous removal during image reconstruction. Although Deep Learning (DL) has proven effective for fast MRI image reconstruction, its broader applicability across various imaging scenarios has been constrained. Challenges include the high cost and privacy restrictions associated with acquiring large-scale, diverse training data, coupled with the inherent difficulty of addressing mismatches between training and target data in existing DL methodologies. Here, we present a novel Physics-Informed Synthetic data learning framework for Fast MRI, called PISF. PISF marks a breakthrough by enabling generalized DL for multi-scenario MRI reconstruction through a single trained model. Our approach separates the reconstruction of a 2D image into many 1D basic problems, commencing with 1D data synthesis to facilitate generalization. We demonstrate that training DL models on synthetic data, coupled with enhanced learning techniques, yields in vivo MRI reconstructions comparable to or surpassing those of models trained on matched realistic datasets, reducing the reliance on real-world MRI data by up to 96%. Additionally, PISF exhibits remarkable generalizability across multiple vendors and imaging centers. Its adaptability to diverse patient populations has been validated through evaluations by ten experienced medical professionals. PISF presents a feasible and cost-effective way to significantly boost the widespread adoption of DL in various fast MRI applications.

eess.IV↗

arXiv2024

Expansion dynamics of Bose-Einstein condensates in a synthetic magnetic field

We investigate the expansion dynamics of spin-orbit-coupled Bose-Einstein condensates subjected to a synthetic magnetic field, after their release from an external harmonic trap. Our findings reveal that the condensate experiences a spin-dependent rotation and separation due to the rigid-like rotational velocity field, which leads to a spin density deflection. The deflection angle reaches a peak at a time that is inversely related to the frequency of the harmonic trap. When the detuning gradient is below a critical value for vortex nucleation, our analytical results derived from a spinor hydrodynamic theory align closely with numerical results using the coupled Gross-Pitaevskii equations. Beyond this critical value, we also numerically simulated the expansion dynamics of the condensates containing vortices with negative circulation. Our findings highlight the pivotal role of the rigid-like rotational velocity field on the dynamics of the condensate and may stimulate further experimental investigations into the rich superfluid dynamics induced by synthetic magnetic fields.

cond-mat.quant-gas↗

arXiv2024

Divide-Conquer-and-Merge: Memory- and Time-Efficient Holographic Displays

Recently, deep learning-based computer-generated holography (CGH) has demonstrated tremendous potential in three-dimensional (3D) displays and yielded impressive display quality. However, most existing deep learning-based CGH techniques can only generate holograms of 1080p resolution, which is far from the ultra-high resolution (16K+) required for practical virtual reality (VR) and augmented reality (AR) applications to support a wide field of view and large eye box. One of the major obstacles in current CGH frameworks lies in the limited memory available on consumer-grade GPUs which could not facilitate the generation of higher-definition holograms. To overcome the aforementioned challenge, we proposed a divide-conquer-and-merge strategy to address the memory and computational capacity scarcity in ultra-high-definition CGH generation. This algorithm empowers existing CGH frameworks to synthesize higher-definition holograms at a faster speed while maintaining high-fidelity image display quality. Both simulations and experiments were conducted to demonstrate the capabilities of the proposed framework. By integrating our strategy into HoloNet and CCNNs, we achieved significant reductions in GPU memory usage during the training period by 64.3\% and 12.9\%, respectively. Furthermore, we observed substantial speed improvements in hologram generation, with an acceleration of up to 3$\times$ and 2 $\times$, respectively. Particularly, we successfully trained and inferred 8K definition holograms on an NVIDIA GeForce RTX 3090 GPU for the first time in simulations. Furthermore, we conducted full-color optical experiments to verify the effectiveness of our method. We believe our strategy can provide a novel approach for memory- and time-efficient holographic displays.

eess.IV↗

arXiv2024

Variational structure and two-dimensional subsonic jet flows for compressible Euler system with general incoming flows

In this paper, we proved the well-posedness theory of compressible subsonic jet flows for two-dimensional steady Euler system with {\it general} incoming horizontal velocity as long as the flux is larger than a critical value. One of the key observations is that the stream function formulation for two-dimensional compressible steady Euler system enjoys a variational structure even when the flows have nontrivial vorticity, so that the jet problem can be reformulated as a domain variation problem. This variational structure helps to adapt the framework developed by Alt, Caffarelli, and Friedman to study {the jet problem, which is a Bernoulli type free boundary problem. A major technical point to analyze the jet flows is that the inhomogeneous terms in the rescaled equation near the free boundary are always small, even when the vorticity of the flows is big.

math.AP↗

arXiv2024

Interpretable Short-Term Load Forecasting via Multi-Scale Temporal Decomposition

Rapid progress in machine learning and deep learning has enabled a wide range of applications in the electricity load forecasting of power systems, for instance, univariate and multivariate short-term load forecasting. Though the strong capabilities of learning the non-linearity of the load patterns and the high prediction accuracy have been achieved, the interpretability of typical deep learning models for electricity load forecasting is less studied. This paper proposes an interpretable deep learning method, which learns a linear combination of neural networks that each attends to an input time feature. We also proposed a multi-scale time series decomposition method to deal with the complex time patterns. Case studies have been carried out on the Belgium central grid load dataset and the proposed model demonstrated better accuracy compared to the frequently applied baseline model. Specifically, the proposed multi-scale temporal decomposition achieves the best MSE, MAE and RMSE of 0.52, 0.57 and 0.72 respectively. As for interpretability, on one hand, the proposed method displays generalization capability. On the other hand, it can demonstrate not only the feature but also the temporal interpretability compared to other baseline methods. Besides, the global time feature interpretabilities are also obtained. Obtaining global feature interpretabilities allows us to catch the overall patterns, trends, and cyclicality in load data while also revealing the significance of various time-related features in forming the final outputs.

cs.LG↗

arXiv2024

A Quantum Algorithm Based Heuristic to Hide Sensitive Itemsets

Quantum devices use qubits to represent information, which allows them to exploit important properties from quantum physics, specifically superposition and entanglement. As a result, quantum computers have the potential to outperform the most advanced classical computers. In recent years, quantum algorithms have shown hints of this promise, and many algorithms have been proposed for the quantum domain. There are two key hurdles to solving difficult real-world problems on quantum computers. The first is on the hardware front -- the number of qubits in the most advanced quantum systems is too small to make the solution of large problems practical. The second involves the algorithms themselves -- as quantum computers use qubits, the algorithms that work there are fundamentally different from those that work on traditional computers. As a result of these constraints, research has focused on developing approaches to solve small versions of problems as proofs of concept -- recognizing that it would be possible to scale these up once quantum devices with enough qubits become available. Our objective in this paper is along the same lines. We present a quantum approach to solve a well-studied problem in the context of data sharing. This heuristic uses the well-known Quantum Approximate Optimization Algorithm (QAOA). We present results on experiments involving small datasets to illustrate how the problem could be solved using quantum algorithms. The results show that the method has potential and provide answers close to optimal. At the same time, we realize there are opportunities for improving the method further.

quant-ph↗

arXiv2024

Two high-amplitude $δ$ Scuti-$γ$ Doradus hybrids constrained by the radial fundamental p and equally spaced g modes

Based on 2-minute cadence TESS data, we investigate pulsations of TIC 65138566 and TIC 139729335 and discover them to be two new HADS stars with equally spaced g modes. We recognize the radial fundamental mode $f_1$ = 18.3334 c/d and the first overtone $f_3$ = 23.6429 c/d for TIC 65138566, and identify the highest peak $f_1$ = 19.0955 c/d as the radial fundamental mode for TIC 139729335. For g modes, both stars display a regular period spacing of 2413 s. Through detailed seismological analysis, we deduce that these period spacing patterns correspond to modes with $\ell$ = 1. Moreover, our analysis reveals that with the increase in masses and metallicities, the star should display a higher degree of evolution to match a specific period spacing $Π_0$. Conversely, the star should have a lower extent of evolution to match the radial fundamental mode. These two contradictory behaviors allow us to precisely obtain stellar physical parameters. TIC 65138566 and TIC 139729335 are determined to be two main sequence stars that have almost the same range of masses and metallicities, with $M$ = 1.36 $\pm$ 0.06 $M_{\odot}$ and $Z$ = 0.005 $\pm$ 0.002. The hydrogen abundance in the core of TIC 65138566 is estimated to be about 0.28, while TIC 139729335 has a slightly higher value of around 0.31. Finally, we suggest that the HADS $δ$ Scuti-$γ$ Doradus star TIC 308396022 is a main sequence star with $M$ = 1.54 $\pm$ 0.08 $M_{\odot}$, $Z$ = 0.007 $\pm$ 0.001, and $X_{\rm c}$ = 0.18 $\pm$ 0.02.

astro-ph.SR↗