arXiv subjects

Zhe Gao

Publications and source records attributed to Zhe Gao.

29 records · Page 2Linked to original sources

arXiv2024

C$^3$DG: Conditional Domain Generalization for Hyperspectral Imagery Classification with Convergence and Constrained-risk Theories

Hyperspectral imagery (HSI) classification may suffer the challenge of hyperspectral-monospectra, where different classes present similar spectra. Joint spatial-spectral feature extraction is a popular solution for the problem, but this strategy tends to inflate accuracy since test pixels may exist in training patches. Domain generalization methods show promising potential, but they still fail to distinguish similar spectra across varying domains, in addition, the theoretical support is usually ignored. In this paper, we only rely on spectral information to solve the hyperspectral-monospectra problem, and propose a Convergence and Error-Constrained Conditional Domain Generalization method for Hyperspectral Imagery Classification (C$^3$DG). The major contributions of this paper include two aspects: the Conditional Revising Inference Block (CRIB), and the corresponding theories for model convergence and generalization errors. CRIB is the kernel structure of the proposed method, which employs a shared encoder and multi-branch decoders to fully leverage the conditional distribution during training, achieving a decoupling that aligns with the generation mechanisms of HSI. Moreover, to ensure model convergence and maintain controllable error, we propose the optimization convergence theorem and risk upper bound theorem. In the optimization convergence theorem, we ensure the model convergence by demonstrating that the gradients of the loss terms are not contradictory. In the risk upper bound theorem, our theoretical analysis explores the relationship between test-time training and recent related work to establish a concrete bound for error. Experimental results on three benchmark datasets indicate the superiority of C$^3$DG.

cs.CV↗

arXiv2024

Polarized $γ$-photon beams produced by collision of two ultrarelativistic electron beams

Many studies have shown that high-energy $γ$-photon beams can be efficiently generated via nonlinear Compton scattering driven by laser pulses with intensities $> 10^{22}\rm{W/cm^2}$ recently available in laboratories. Here, we propose a laserless scheme to efficiently generate high-energy polarized $γ$-photon beams by collision of two ultrarelativistic electron beams. The self-generated field of a dense driving electron beam provides the strong deflection field for the other ultrarelativistic seeding electron beam. A QED Monte Carlo code based on the locally constant field approximation is employed to simulate the collision process, and the polarization properties of produced $γ$ photons are investigated. The simulation results and theoretical analysis indicate that the photon polarization, including both linear and circular polarizations, can be tuned by changing the initial polarization of the seeding beam. If an unpolarized seeding beam is used, linearly polarized photons with an average polarization of 55\% can be obtained. If the seeding beam is transversely (longitudinally) polarized, the linear (circular) polarization of photons above 3 GeV can reach 90\% (67\%), which is favorable for highly polarized, high-energy $γ$ photon sources.

physics.acc-ph↗

arXiv2021

On two approaches to the third-order solution of surface gravity waves

Third-order approximate solutions for surface gravity waves in the finite water depth are studied in the context of potential flow theory. This solution provides explicit expressions for the surface elevation, free-surface velocity potential and velocity potential. The amplitude dispersion relation is also provided. Two approaches are used to derive the third order analytical solution, resulting in two types of approximate solutions: the perturbation solution and the Hamiltonian solution. The perturbation solution is obtained by classical perturbation technique in which the time variable is expanded in multiscale to eliminate secular terms. The Hamiltonian solution is derived from the canonical transformation in the Hamiltonian theory of water waves. By comparing the two types of solutions, it is found that they are completely equivalent for the first to second order solutions and the nonlinear dispersion, but for the third order part only the sum-sum terms are the same. Due to the canonical transformation that could completely separate the dynamic and bound harmonics, the Hamiltonian solutions break through the difficulty that the perturbation theory breaks down due to singularities in the transfer functions when quartet resonance criterion is satisfied. Furthermore, it is also found that some time-averaged quantities based on the Hamiltonian solution, such as mean potential energy and mean kinetic energy, are equal to those in the initial state in which sea surface is assumed to be a Gaussian random process. This is because there are associated conserved quantities in the Hamiltonian form. All of these show that the Hamiltonian solution is more reasonable and accurate to describe the third order steady-state wave field. Finally, based on the Hamiltonian solution, some statistics are given such as the volume flux, skewness, and excess kurtosis.

physics.flu-dyn↗

arXiv2020

Time to Transfer: Predicting and Evaluating Machine-Human Chatting Handoff

Is chatbot able to completely replace the human agent? The short answer could be - "it depends...". For some challenging cases, e.g., dialogue's topical spectrum spreads beyond the training corpus coverage, the chatbot may malfunction and return unsatisfied utterances. This problem can be addressed by introducing the Machine-Human Chatting Handoff (MHCH), which enables human-algorithm collaboration. To detect the normal/transferable utterances, we propose a Difficulty-Assisted Matching Inference (DAMI) network, utilizing difficulty-assisted encoding to enhance the representations of utterances. Moreover, a matching inference mechanism is introduced to capture the contextual matching features. A new evaluation metric, Golden Transfer within Tolerance (GT-T), is proposed to assess the performance by considering the tolerance property of the MHCH. To provide insights into the task and validate the proposed model, we collect two new datasets. Extensive experimental results are presented and contrasted against a series of baseline models to demonstrate the efficacy of our model on MHCH.

cs.CL↗

arXiv2020

Read Beyond the Lines: Understanding the Implied Textual Meaning via a Skim and Intensive Reading Model

The nonliteral interpretation of a text is hard to be understood by machine models due to its high context-sensitivity and heavy usage of figurative language. In this study, inspired by human reading comprehension, we propose a novel, simple, and effective deep neural framework, called Skim and Intensive Reading Model (SIRM), for figuring out implied textual meaning. The proposed SIRM consists of two main components, namely the skim reading component and intensive reading component. N-gram features are quickly extracted from the skim reading component, which is a combination of several convolutional neural networks, as skim (entire) information. An intensive reading component enables a hierarchical investigation for both local (sentence) and global (paragraph) representation, which encapsulates the current embedding and the contextual information with a dense connection. More specifically, the contextual information includes the near-neighbor information and the skim information mentioned above. Finally, besides the normal training loss function, we employ an adversarial loss function as a penalty over the skim reading component to eliminate noisy information arisen from special figurative words in the training data. To verify the effectiveness, robustness, and efficiency of the proposed architecture, we conduct extensive comparative experiments on several sarcasm benchmarks and an industrial spam dataset with metaphors. Experimental results indicate that (1) the proposed model, which benefits from context modeling and consideration of figurative language, outperforms existing state-of-the-art solutions, with comparable parameter scale and training speed; (2) the SIRM yields superior robustness in terms of parameter size sensitivity; (3) compared with ablation and addition variants of the SIRM, the final framework is efficient enough.

cs.CL↗

arXiv2019

Detect Camouflaged Spam Content via StoneSkipping: Graph and Text Joint Embedding for Chinese Character Variation Representation

The task of Chinese text spam detection is very challenging due to both glyph and phonetic variations of Chinese characters. This paper proposes a novel framework to jointly model Chinese variational, semantic, and contextualized representations for Chinese text spam detection task. In particular, a Variation Family-enhanced Graph Embedding (VFGE) algorithm is designed based on a Chinese character variation graph. The VFGE can learn both the graph embeddings of the Chinese characters (local) and the latent variation families (global). Furthermore, an enhanced bidirectional language model, with a combination gate function and an aggregation learning function, is proposed to integrate the graph and text information while capturing the sequential information. Extensive experiments have been conducted on both SMS and review datasets, to show the proposed method outperforms a series of state-of-the-art models for Chinese spam detection.

cs.CL↗

arXiv2018

Automatic Clone Recommendation for Refactoring Based on the Present and the Past

When many clones are detected in software programs, not all clones are equally important to developers. To help developers refactor code and improve software quality, various tools were built to recommend clone-removal refactorings based on the past and the present information, such as the cohesion degree of individual clones or the co-evolution relations of clone peers. The existence of these tools inspired us to build an approach that considers as many factors as possible to more accurately recommend clones. This paper introduces CREC, a learning-based approach that recommends clones by extracting features from the current status and past history of software projects. Given a set of software repositories, CREC first automatically extracts the clone groups historically refactored (R-clones) and those not refactored (NR-clones) to construct the training set. CREC extracts 34 features to characterize the content and evolution behaviors of individual clones, as well as the spatial, syntactical, and co-change relations of clone peers. With these features, CREC trains a classifier that recommends clones for refactoring. We designed the largest feature set thus far for clone recommendation, and performed an evaluation on six large projects. The results show that our approach suggested refactorings with 83% and 76% F-scores in the within-project and cross-project settings. CREC significantly outperforms a state-of-the-art similar approach on our data set, with the latter one achieving 70% and 50% F-scores. We also compared the effectiveness of different factors and different learning algorithms.

cs.SE↗

arXiv2016

Observation of Toroidal Alfven Eigenmodes during Minor Disruptions in Ohmic Plasmas

Toroidal Alfven eigenmodes (TAEs) excited in purely ohmically heated plasmas without any auxiliary heating have been identified for the first time in the SUNIST spherical tokamak. The TAE modes are observed during minor disruptions and have a frequency range of 150-500 kHz. The mode structure analysis indicates the existence of both m/n=-3/-1 and -4/-1 harmonics, propagating in the electron diamagnetic direction in the laboratory frame of reference. These TAEs appear simultaneously with the generation of runaway electrons in the current quench phase, accompanying with the density sweeping during the minor disruption. Possible driving mechanisms and potential applications of these TAEs are discussed.

physics.plasm-ph↗

arXiv2008

Time-dependent energetic laser-ion acceleration by strong charge separation field

The laser-ion acceleration in the ultra-short and ultra-intense laser-matter interactions attracts more and more interest nowadays. Since electrons gain relativistic energy from laser pulse in a period of several femtoseconds and driven away by the ponderomotive force of laser pulse, a huge charge-separation field pulse is generated. In general cases, the ion acceleration is determined by this charge-separation field. A novel general time-dependent solution for laser-plasma isothermal expansions into a vacuum with different types of the scale length of the density gradient which correspond to different charge separation forms is obtained. The previous solutions are some special cases of our general solution. A series of new solutions have been proposed and may be used to predict new mechanisms of ion acceleration. However, many unaccounted idiographic solutions that may be used to reveal new acceleration mode of ions such as shock wave acceleration, may be deduced from our general solutions.

physics.plasm-ph↗

arXiv2008

Time-dependent energetic proton acceleration and scaling laws in ultra-intense laser pulses interactions with thin foils

A two-phase model, where the plasma expansion is an isothermal one when laser irradiates and a following adiabatic one after laser ends, has been proposed to predict the maximum energy of the proton beams induced in the ultra-intense laser-foil interactions. The hot-electron recirculation in the ultra-intense laser-solid interactions has been accounted in and described by the time-dependent hot-electron density continuously in this model. The dilution effect of electron density as electrons recirculate and spread laterally has been considered. With our model, the scaling laws of maximum ion energy have been achieved and the dependence of the scaling coefficients on laser intensity, pulse duration and target thickness have been obtained. Some interesting results have been predicted: the adiabatic expansion is an important process of the ion acceleration and cannot be neglected; the whole acceleration time is about 10-20 times of laser pulse duration; the larger the laser intensity, the more sensitive the maximum ion energy to the change of focus radius, and so on.

physics.plasm-ph↗

arXiv2008

Two-dimension plasma expansions with anisotropic pressure

A two-dimension self-similar solution is proposed for a plasma expansion with anisotropic pressure. With the solution, it depends on the relationship between the ratio of the longitudinal and the transverse temperature of the plasma, $κ^2$ and the electron-ion mass ratio, $μ$, that the plasma front is composed by a part of hyperbolic (or a plane) and a small pointed projection at the center or a part of an ellipse. Zhang and coworkers's experiments (PRL, 99, 167602 (2007))support our results for $κ^2\in(τ,1]$. For $κ^2\leqτ$, there is an anomalous high-energy plasma emission at the angle of near $90^{\text{o}}$ due to longitudinal Coulomb explosion.

physics.plasm-ph↗