arXiv subjects

Zhe Zhang

Publications and source records attributed to Zhe Zhang.

At least 181 records · Page 10Linked to original sources

arXiv2022

ATASI-Net: An Efficient Sparse Reconstruction Network for Tomographic SAR Imaging with Adaptive Threshold

Tomographic SAR technique has attracted remarkable interest for its ability of three-dimensional resolving along the elevation direction via a stack of SAR images collected from different cross-track angles. The emerged compressed sensing (CS)-based algorithms have been introduced into TomoSAR considering its super-resolution ability with limited samples. However, the conventional CS-based methods suffer from several drawbacks, including weak noise resistance, high computational complexity, and complex parameter fine-tuning. Aiming at efficient TomoSAR imaging, this paper proposes a novel efficient sparse unfolding network based on the analytic learned iterative shrinkage thresholding algorithm (ALISTA) architecture with adaptive threshold, named Adaptive Threshold ALISTA-based Sparse Imaging Network (ATASI-Net). The weight matrix in each layer of ATASI-Net is pre-computed as the solution of an off-line optimization problem, leaving only two scalar parameters to be learned from data, which significantly simplifies the training stage. In addition, adaptive threshold is introduced for each azimuth-range pixel, enabling the threshold shrinkage to be not only layer-varied but also element-wise. Moreover, the final learned thresholds can be visualized and combined with the SAR image semantics for mutual feedback. Finally, extensive experiments on simulated and real data are carried out to demonstrate the effectiveness and efficiency of the proposed method.

eess.SP↗

arXiv2022

Inclusive and semi-inclusive production of spin-3/2 hadrons in $e^+e^-$ annihilation

We investigate the inclusive and semi-inclusive productions of spin-3/2 hadrons, such as $Ω$, in unpolarized $e^+ e^-$ annihilation. The general differential cross sections are expressed in terms of structure functions in accordance to the polarization of the hadron and the azimuthal modulations. We derive a complete definition of quark transverse momentum dependent (TMD) fragmentation functions (FFs) to spin-3/2 hadrons for the first time from the decomposition of the quark-quark correlation matrix at leading twist, 14 of which are newly defined corresponding to rank-3 tensor polarized hadron. The collinear FFs are obtained from the $k_T$-integrated correlation matrix, and only two TMD FFs with rank-3 tensor polarization have nonvanishing collinear counterparts. Then we perform a leading order calculation of the unpolarized differential cross sections. In the single-hadron inclusive production, only two structure functions are found nonzero and none of the rank-3 tensor polarized FFs contributes. For the nearly back-to-back two-hadron production, half of the 48 structure functions are found nonzero even if the spin of the second hadron is not analyzed, and ten of the rank-3 tensor polarized TMD FFs contribute. Therefore, one can study the rank-3 tensor polarized FFs via the production of a spin-3/2 hadron and an unpolarized hadron in unpolarized $e^+ e^-$ collision experiments. These newly defined FFs can be further applied in semi-inclusive deep inelastic scattering processes for the study of nucleon structures.

hep-ph↗

arXiv2022

Fault Diagnosis for Power Electronics Converters based on Deep Feedforward Network and Wavelet Compression

A fault diagnosis method for power electronics converters based on deep feedforward network and wavelet compression is proposed in this paper. The transient historical data after wavelet compression are used to realize the training of fault diagnosis classifier. Firstly, the correlation analysis of the voltage or current data running in various fault states is performed to remove the redundant features and the sampling point. Secondly, the wavelet transform is used to remove the redundant data of the features, and then the training sample data is greatly compressed. The deep feedforward network is trained by the low frequency component of the features, while the training speed is greatly accelerated. The average accuracy of fault diagnosis classifier can reach over 97%. Finally, the fault diagnosis classifier is tested, and final diagnosis result is determined by multiple-groups transient data, by which the reliability of diagnosis results is improved. The experimental result proves that the classifier has strong generalization ability and can accurately locate the open-circuit faults in IGBTs.

eess.SP↗

arXiv2022

Review for AI-based Open-Circuit Faults Diagnosis Methods in Power Electronics Converters

Power electronics converters have been widely used in aerospace system, DC transmission, distributed energy, smart grid and so forth, and the reliability of power electronics converters has been a hotspot in academia and industry. It is of great significance to carry out power electronics converters open-circuit faults monitoring and intelligent fault diagnosis to avoid secondary faults, reduce time and cost of operation and maintenance, and improve the reliability of power electronics system. Firstly, the faults features of power electronic converters are analyzed and summarized. Secondly, some AI-based fault diagnosis methods and application examples in power electronics converters are reviewed, and a fault diagnosis method based on the combination of random forests and transient fault features is proposed for three-phase power electronics converters. Finally, the future research challenges and directions of AI-based fault diagnosis methods are pointed out.

eess.SY↗

arXiv2022

M$^2$DQN: A Robust Method for Accelerating Deep Q-learning Network

Deep Q-learning Network (DQN) is a successful way which combines reinforcement learning with deep neural networks and leads to a widespread application of reinforcement learning. One challenging problem when applying DQN or other reinforcement learning algorithms to real world problem is data collection. Therefore, how to improve data efficiency is one of the most important problems in the research of reinforcement learning. In this paper, we propose a framework which uses the Max-Mean loss in Deep Q-Network (M$^2$DQN). Instead of sampling one batch of experiences in the training step, we sample several batches from the experience replay and update the parameters such that the maximum TD-error of these batches is minimized. The proposed method can be combined with most of existing techniques of DQN algorithm by replacing the loss function. We verify the effectiveness of this framework with one of the most widely used techniques, Double DQN (DDQN), in several gym games. The results show that our method leads to a substantial improvement in both the learning speed and performance.

cs.LG↗

arXiv2022

Glassy crystals with colossal multi-baroresponsivities

As a nontrivial solid state of matter, the glassy-crystal state embraces physical features of both crystalline and amorphous solids, where a long-range ordered periodic structure formed by the mass centers of constituent molecules accommodates orientational glasses. Here, we discover and validate a glassy-crystal state in 2-amino-2-methyl-1,3-propanediol (AMP, C4H11NO2) by neutron scattering and complementary broadband dielectric spectroscopy (BDS) measurements. The freezing process of the dynamic orientational disorder is manifested at relaxation times well described by the Vogel-Fulcher-Tammann (VFT) law and the strongly frequency-dependent freezing temperature ranging from around 225 K at 0.1 Hz to above room temperature in the GHz region. At room temperature, the supercooled state is extremely sensitive to pressure such that a few MPa pressure can induce crystallization to the ordered crystal state, eventually leading to a temperature increase by 48 K within 20 s, a significant reduction of visible light transmittance from about 95% to a few percentages, and a remarkable decrease of electrical conductivity by three orders of magnitude. These ultrasensitive baroresponsivities might find their applications in low-grade waste heat recycling, pressure sensors and non-volatile memory devices. It is expected that glassy crystals serve as an emerging platform for exploiting exotic states of matter and the associated fantastic applications.

cond-mat.mtrl-sci↗

arXiv2022

Nanoscale crack propagation in clay with water adsorption through reactive MD modeling

The atomic-scale cracking mechanism in clay is vital in discovering the cracking mechanism of clay at the continuum scale in that clay is a nanomaterial. In this article, we investigate mechanisms of mode I and mode II crack propagations in pyrophyllite and Ca-montmorillonite with water adsorption through reactive molecular dynamics with a bond-order force field. Clay water adsorption is considered by adding water molecules to the clay surface. During the equilibration stage, water adsorption could cause bending deformation of the pre-defined edge crack region. The relatively small orientating angle of water molecules indicates the formation of hydrogen bonds in the crack propagation process. The peak number density of adsorbed water decreases with the increasing strains. The atomistic structure evolution of the crack tip under loading is analyzed to interpret the nanoscale crack propagation mechanism. The numerical results show that the crack tip first gets blunted with a significant increase in the radius of the curvature of the crack tip and a slight change in crack length. The crack tip blunting is studied by tracking the crack tip opening distance and O-Si-O angle in the tetrahedral Si-O cell in mode I and II cracks. We compare bond-breaking behaviors between Al-O and Si-O. It is found that Si-O bond breaking is primarily responsible for crack propagation. The critical stress intensity factor and critical energy release rate are determined from MD simulation results.

cond-mat.mtrl-sci↗

arXiv2022

On joint training with interfaces for spoken language understanding

Spoken language understanding (SLU) systems extract both text transcripts and semantics associated with intents and slots from input speech utterances. SLU systems usually consist of (1) an automatic speech recognition (ASR) module, (2) an interface module that exposes relevant outputs from ASR, and (3) a natural language understanding (NLU) module. Interfaces in SLU systems carry information on text transcriptions or richer information like neural embeddings from ASR to NLU. In this paper, we study how interfaces affect joint-training for spoken language understanding. Most notably, we obtain the state-of-the-art results on the publicly available 50-hr SLURP dataset. We first leverage large-size pretrained ASR and NLU models that are connected by a text interface, and then jointly train both models via a sequence loss function. For scenarios where pretrained models are not utilized, the best results are obtained through a joint sequence loss training using richer neural interfaces. Finally, we show the overall diminishing impact of leveraging pretrained models with increased training data size.

cs.CL↗

arXiv2022

Interpretable Melody Generation from Lyrics with Discrete-Valued Adversarial Training

Generating melody from lyrics is an interesting yet challenging task in the area of artificial intelligence and music. However, the difficulty of keeping the consistency between input lyrics and generated melody limits the generation quality of previous works. In our proposal, we demonstrate our proposed interpretable lyrics-to-melody generation system which can interact with users to understand the generation process and recreate the desired songs. To improve the reliability of melody generation that matches lyrics, mutual information is exploited to strengthen the consistency between lyrics and generated melodies. Gumbel-Softmax is exploited to solve the non-differentiability problem of generating discrete music attributes by Generative Adversarial Networks (GANs). Moreover, the predicted probabilities output by the generator is utilized to recommend music attributes. Interacting with our lyrics-to-melody generation system, users can listen to the generated AI song as well as recreate a new song by selecting from recommended music attributes.

cs.SD↗

arXiv2022

Optimal Algorithms for Convex Nested Stochastic Composite Optimization

Recently, convex nested stochastic composite optimization (NSCO) has received considerable attention for its applications in reinforcement learning and risk-averse optimization. The current NSCO algorithms have worse stochastic oracle complexities, by orders of magnitude, than those for simpler stochastic composite optimization problems (e.g., sum of smooth and nonsmooth functions) without the nested structure. Moreover, they require all outer-layer functions to be smooth, which is not satisfied by some important applications. These discrepancies prompt us to ask: ``does the nested composition make stochastic optimization more difficult in terms of the order of oracle complexity?" In this paper, we answer the question by developing order-optimal algorithms for the convex NSCO problem constructed from an arbitrary composition of smooth, structured non-smooth and general non-smooth layer functions. When all outer-layer functions are smooth, we propose a stochastic sequential dual (SSD) method to achieve an oracle complexity of $\mathcal{O}(1/ε^2)$ ($\mathcal{O}(1/ε)$) when the problem is non-strongly (strongly) convex. When there exists some structured non-smooth or general non-smooth outer-layer function, we propose a nonsmooth stochastic sequential dual (nSSD) method to achieve an oracle complexity of $\mathcal{O}(1/ε^2)$. We provide a lower complexity bound to show the latter $\mathcal{O}(1/ε^2)$ complexity to be unimprovable even under a strongly convex setting. All these complexity results seem to be new in the literature and they indicate that the convex NSCO problem has the same order of oracle complexity as those without the nested composition in all but the strongly convex and outer-non-smooth problem.

math.OC↗

arXiv2022

Efficient Federated Learning with Spike Neural Networks for Traffic Sign Recognition

With the gradual popularization of self-driving, it is becoming increasingly important for vehicles to smartly make the right driving decisions and autonomously obey traffic rules by correctly recognizing traffic signs. However, for machine learning-based traffic sign recognition on the Internet of Vehicles (IoV), a large amount of traffic sign data from distributed vehicles is needed to be gathered in a centralized server for model training, which brings serious privacy leakage risk because of traffic sign data containing lots of location privacy information. To address this issue, we first exploit privacy-preserving federated learning to perform collaborative training for accurate recognition models without sharing raw traffic sign data. Nevertheless, due to the limited computing and energy resources of most devices, it is hard for vehicles to continuously undertake complex artificial intelligence tasks. Therefore, we introduce powerful Spike Neural Networks (SNNs) into traffic sign recognition for energy-efficient and fast model training, which is the next generation of neural networks and is practical and well-fitted to IoV scenarios. Furthermore, we design a novel encoding scheme for SNNs based on neuron receptive fields to extract information from the pixel and spatial dimensions of traffic signs to achieve high-accuracy training. Numerical results indicate that the proposed federated SNN outperforms traditional federated convolutional neural networks in terms of accuracy, noise immunity, and energy efficiency as well.

cs.LG↗

arXiv2022

PERT: A New Solution to Pinyin to Character Conversion Task

Pinyin to Character conversion (P2C) task is the key task of Input Method Engine (IME) in commercial input software for Asian languages, such as Chinese, Japanese, Thai language and so on. It's usually treated as sequence labelling task and resolved by language model, i.e. n-gram or RNN. However, the low capacity of the n-gram or RNN limits its performance. This paper introduces a new solution named PERT which stands for bidirectional Pinyin Encoder Representations from Transformers. It achieves significant improvement of performance over baselines. Furthermore, we combine PERT with n-gram under a Markov framework, and improve performance further. Lastly, the external lexicon is incorporated into PERT so as to resolve the OOD issue of IME.

cs.CL↗

arXiv2022

Model-Free Statistical Inference on High-Dimensional Data

This paper aims to develop an effective model-free inference procedure for high-dimensional data. We first reformulate the hypothesis testing problem via sufficient dimension reduction framework. With the aid of new reformulation, we propose a new test statistic and show that its asymptotic distribution is $χ^2$ distribution whose degree of freedom does not depend on the unknown population distribution. We further conduct power analysis under local alternative hypotheses. In addition, we study how to control the false discovery rate of the proposed $χ^2$ tests, which are correlated, to identify important predictors under a model-free framework. To this end, we propose a multiple testing procedure and establish its theoretical guarantees. Monte Carlo simulation studies are conducted to assess the performance of the proposed tests and an empirical analysis of a real-world data set is used to illustrate the proposed methodology.

stat.ME↗

arXiv2022

An optimization method to compensate accelerator performance drifts

Accelerator performance often deteriorates with time during a long period of operation due to secular changes in the machine components or the surrounding environment. In many cases some tuning knobs are effective in compensating the performance drifts and optimization methods can be used to find the ideal machine setting. However, such intervention usually cannot be done without interrupting user operation as the optimization algorithms can substantially impact the machine performance. We propose an optimization algorithm, Safe Robust Conjugate Direction Search (RCDS-S), which can perform accelerator tuning while keeping the machine performance within a designated safe envelope. The algorithm builds probability models of the objective function using Lipschitz continuity of the function as well as characteristics of the drifts and applies to the selection of trial solutions to ensure the machine operates safely during tuning. The algorithm can run during normal user operation constantly, or periodically, to compensate the performance drifts. Simulation and online tests have been done to validate the performance of the algorithm.

physics.acc-ph↗

arXiv2022

TomoSAR-ALISTA: Efficient TomoSAR Imaging via Deep Unfolded Network

Synthetic aperture radar (SAR) tomography (TomoSAR) has attracted remarkable interest for its ability in achieving three-dimensional reconstruction along the elevation direction from multiple observations. In recent years, compressed sensing (CS) technique has been introduced into TomoSAR considering for its super-resolution ability with limited samples. Whereas, the CS-based methods suffer from several drawbacks, including weak noise resistance, high computational complexity and complex parameter fine-tuning. Among the different CS algorithms, iterative soft-thresholding algorithm (ISTA) is widely used as a robust reconstruction approach, however, the parameters in the ISTA algorithm are manually chosen, which usually requires a time-consuming fine-tuning process to achieve the best performance. Aiming at efficient TomoSAR imaging, a novel sparse unfolding network named analytic learned ISTA (ALISTA) is proposed towards the TomoSAR imaging problem in this paper, and the key parameters of ISTA are learned from training data via deep learning to avoid complex parameter fine-tuning and significantly relieves the training burden. In addition, experiments verify that it is feasible to use traditional CS algorithms as training labels, which provides a tangible supervised training method to achieve better 3D reconstruction performance even in the absence of labeled data in real applications.

eess.SP↗

arXiv2022

A Novel Gradient Descent Least Squares (GDLS) Algorithm for Efficient SMV Gridless Line Spectrum Estimation with Applications in Tomographic SAR Imaging

This paper presents a novel efficient method for gridless line spectrum estimation problem with single snapshot, namely the gradient descent least squares (GDLS) method. Conventional single snapshot (a.k.a. single measure vector or SMV) line spectrum estimation methods either rely on smoothing techniques that sacrifice the array aperture, or adopt the sparsity constraint and utilize compressed sensing (CS) method by defining prior grids and resulting in the off-grid problem. Recently emerged atomic norm minimization (ANM) methods achieved gridless SMV line spectrum estimation, but its computational complexity is extremely high; thus it is practically infeasible in real applications with large problem scales. Our proposed GDLS method reformulates the line spectrum estimations problem into a least squares (LS) estimation problem and solves the corresponding objective function via gradient descent algorithm in an iterative fashion with efficiency. The convergence guarantee, computational complexity, as well as performance analysis are discussed in this paper. Numerical simulations and real data experiments show that the proposed GDLS algorithm outperforms the state-of-the-art methods e.g., CS and ANM, in terms of estimation performances. It can completely avoid the off-grid problem, and its computational complexity is significantly lower than ANM. Our method has been tested in tomographic SAR (TomoSAR) imaging applications via simulated and real experiment data. Results show great potential of the proposed method in terms of better cloud point performance and eliminating the gridding effect.

eess.SP↗

arXiv2022

Gridless Tomographic SAR Imaging Based on Accelerated Atomic Norm Minimization with Efficiency

Synthetic aperture radar (SAR) tomography (TomoSAR) enables the reconstruction and three-dimensional (3D) localization of targets based on multiple two-dimensional (2D) observations of the same scene. The resolving along the elevation direction can be treated as a line spectrum estimation problem. However, traditional super-resolution spectrum estimation algorithms require multiple snapshots and uncorrelated targets. Meanwhile, as the most popular TomoSAR imaging method in modern years, compressed sensing (CS) based methods suffer from the gridding mismatch effect which markedly degrades the imaging performance. As a gridless CS approach, atomic norm minimization can avoid the gridding effect but requires enormous computing resources. Addressing the above issues, this paper proposes an improved fast ANM algorithm to TomoSAR elevation focusing by introducing the IVDST-ANM algorithm, which reduces the huge computational complexity of the conventional time-consuming semi-positive definite programming (SDP) by the iterative Vandermonde decomposition and shrinkage-thresholding (IVDST) approach, and retains the benefits of ANM in terms of gridless imaging and single snapshot recovery. We conducted experiments using simulated data to evaluate the performance of the proposed method, and reconstruction results of an urban area from the SARMV3D-Imaging 1.0 dataset are also presented.

eess.SP↗

arXiv2022

6G-enabled Edge AI for Metaverse: Challenges, Methods, and Future Research Directions

6G-enabled edge intelligence opens up a new era of Internet of Everything and makes it possible to interconnect people-devices-cloud anytime, anywhere. More and more next-generation wireless network smart service applications are changing our way of life and improving our quality of life. As the hottest new form of next-generation Internet applications, Metaverse is striving to connect billions of users and create a shared world where virtual and reality merge. However, limited by resources, computing power, and sensory devices, Metaverse is still far from realizing its full vision of immersion, materialization, and interoperability. To this end, this survey aims to realize this vision through the organic integration of 6G-enabled edge AI and Metaverse. Specifically, we first introduce three new types of edge-Metaverse architectures that use 6G-enabled edge AI to solve resource and computing constraints in Metaverse. Then we summarize technical challenges that these architectures face in Metaverse and the existing solutions. Furthermore, we explore how the edge-Metaverse architecture technology helps Metaverse to interact and share digital data. Finally, we discuss future research directions to realize the true vision of Metaverse with 6G-enabled edge AI.

cs.NI↗