arXiv subjects

Ying Chen

Publications and source records attributed to Ying Chen.

At least 325 records · Page 18Linked to original sources

arXiv2021

Integrated Communication and Navigation for Ultra-Dense LEO Satellite Networks: Vision, Challenges and Solutions

Next generation beyond 5G networks are expected to provide both Terabits per second data rate communication services and centimeter-level accuracy localization services in an efficient, seamless and cost-effective manner. However, most of the current communication and localization systems are separately designed, leading to an under-utilization of radio resources and network performance degradation. In this paper, we propose an integrated communication and navigation (ICAN) framework to fully unleash the potential of ultra-dense LEO satellite networks for optimal provisioning of differentiated services. The specific benefits, feasibility analysis and challenges for ICAN enabled satellite system are explicitly discussed. In particular, a novel beam hopping based ICAN satellite system solution is devised to adaptively tune the network beam layout for dual functional communication and positioning purposes. Furthermore, a thorough experimental platform is built following the Third Generation Partnership Project (3GPP) defined non-terrestrial network simulation parameters to validate the performance gain of the ICAN satellite system

eess.SP↗

arXiv2021

KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation

Knowledge distillation (KD) has recently emerged as an efficacious scheme for learning compact deep neural networks (DNNs). Despite the promising results achieved, the rationale that interprets the behavior of KD has yet remained largely understudied. In this paper, we introduce a novel task-oriented attention model, termed as KDExplainer, to shed light on the working mechanism underlying the vanilla KD. At the heart of KDExplainer is a Hierarchical Mixture of Experts (HME), in which a multi-class classification is reformulated as a multi-task binary one. Through distilling knowledge from a free-form pre-trained DNN to KDExplainer, we observe that KD implicitly modulates the knowledge conflicts between different subtasks, and in reality has much more to offer than label smoothing. Based on such findings, we further introduce a portable tool, dubbed as virtual attention module (VAM), that can be seamlessly integrated with various DNNs to enhance their performance under KD. Experimental results demonstrate that with a negligible additional cost, student models equipped with VAM consistently outperform their non-VAM counterparts across different benchmarks. Furthermore, when combined with other KD methods, VAM remains competent in promoting results, even though it is only motivated by vanilla KD. The code is available at https://github.com/zju-vipa/KDExplainer.

cs.CV↗

arXiv2021

Quantum Simulations of the Non-Unitary Time Evolution and Applications to Neutral-Kaon Oscillations

In light of recent exciting progress in building up quantum computing facilities based on both optical and cold-atom techniques, the algorithms for quantum simulations of particle-physics systems are in rapid progress. In this paper, we propose an efficient algorithm for simulating the non-unitary time evolution of neutral-kaon oscillations $K^0 \leftrightarrow \overline{K}^0$, with or without CP conservation, on the quantum computers provided by the IBM company. The essential strategy is to realize the time-evolution operator with basic quantum gates and an extra qubit corresponding to some external environment. The final results are well consistent with theoretical expectations, and the algorithm can also be applied to open systems beyond elementary particles.

hep-ph↗

arXiv2021

Gluons in charmoniumlike states

The mass components of charmoniumlike states are investigated through the decomposition of QCD energy-momentum tensor (EMT) on lattice. The quark mass contribution $\langle H_m\rangle$ and the momentum fraction $\langle x\rangle$ of valence charm quark and antiquark are calculated for conventional $1S,1P,1D$ charmonia and the exotic $1^{-+}$ charmoniumlike state, based on the $N_f=2+1$ gauge configurations generated by the RBC/UKQCD collaboration. It is found that $\langle H_m\rangle$ is close to each other and around 2.0 to 2.2 GeV for these states, which implies that the mass splittings among these states come almost from the gluon contribution of QCD trace anomaly. The $\langle x\rangle$ of the $1^{-+}$ state is only around 0.55, while that in conventional charmonia is around 0.7 to 0.8. This difference manifests that the proportion of light quarks and gluons in the $1^{-+}$ charmoniumlike state is significantly larger than conventional states.

hep-lat↗

arXiv2021

Spectral Machine Learning for Pancreatic Mass Imaging Classification

We present a novel spectral machine learning (SML) method in screening for pancreatic mass using CT imaging. Our algorithm is trained with approximately 30,000 images from 250 patients (50 patients with normal pancreas and 200 patients with abnormal pancreas findings) based on public data sources. A test accuracy of 94.6 percents was achieved in the out-of-sample diagnosis classification based on a total of approximately 15,000 images from 113 patients, whereby 26 out of 32 patients with normal pancreas and all 81 patients with abnormal pancreas findings were correctly diagnosed. SML is able to automatically choose fundamental images (on average 5 or 9 images for each patient) in the diagnosis classification and achieve the above mentioned accuracy. The computational time is 75 seconds for diagnosing 113 patients in a laptop with standard CPU running environment. Factors that influenced high performance of a well-designed integration of spectral learning and machine learning included: 1) use of eigenvectors corresponding to several of the largest eigenvalues of sample covariance matrix (spike eigenvectors) to choose input attributes in classification training, taking into account only the fundamental information of the raw images with less noise; 2) removal of irrelevant pixels based on mean-level spectral test to lower the challenges of memory capacity and enhance computational efficiency while maintaining superior classification accuracy; 3) adoption of state-of-the-art machine learning classification, gradient boosting and random forest. Our methodology showcases practical utility and improved accuracy of image diagnosis in pancreatic mass screening in the era of AI.

cs.CV↗

arXiv2021

BSTC: A Large-Scale Chinese-English Speech Translation Dataset

This paper presents BSTC (Baidu Speech Translation Corpus), a large-scale Chinese-English speech translation dataset. This dataset is constructed based on a collection of licensed videos of talks or lectures, including about 68 hours of Mandarin data, their manual transcripts and translations into English, as well as automated transcripts by an automatic speech recognition (ASR) model. We have further asked three experienced interpreters to simultaneously interpret the testing talks in a mock conference setting. This corpus is expected to promote the research of automatic simultaneous translation as well as the development of practical systems. We have organized simultaneous translation tasks and used this corpus to evaluate automatic simultaneous translation systems.

cs.CL↗

arXiv2021

Cooperative Beam Hopping for Accurate Positioning in Ultra-Dense LEO Satellite Networks

In ultra-dense LEO satellite networks, conventional communication-oriented beam pattern design cannot provide multiple favorable signals from different satellites simultaneously, and thus leads to poor positioning performance. To tackle this issue, in this paper, we propose a novel cooperative beam hopping (BH) framework to adaptively tune beam layouts suitable for multi-satellite coordinated positioning. On this basis, a joint user association, BH design and power allocation optimization problem is formulated to minimize average Cramér-Rao lower bound (CRLB). An efficient flexible BH control algorithm (FBHCA) is then proposed to solve the problem. Finally, a thorough experimental platform is built following the Third Generation Partnership Project (3GPP) defined non-terrestrial network (NTN) simulation parameters to validate the performance gain of the devised algorithm. The numerical results demonstrate that FBHCA can significantly improve CRLB performance over the benchmark scheme.

cs.NI↗

arXiv2021

Deep Stochastic Volatility Model

Volatility for financial assets returns can be used to gauge the risk for financial market. We propose a deep stochastic volatility model (DSVM) based on the framework of deep latent variable models. It uses flexible deep learning models to automatically detect the dependence of the future volatility on past returns, past volatilities and the stochastic noise, and thus provides a flexible volatility model without the need to manually select features. We develop a scalable inference and learning algorithm based on variational inference. In real data analysis, the DSVM outperforms several popular alternative volatility models. In addition, the predicted volatility of the DSVM provides a more reliable risk measure that can better reflex the risk in the financial market, reaching more quickly to a higher level when the market becomes more risky and to a lower level when the market is more stable, compared with the commonly used GARCH type model with a huge data set on the U.S. stock market.

cs.LG↗

arXiv2021

The Variational Bayesian Inference for Network Autoregression Models

We develop a variational Bayesian (VB) approach for estimating large-scale dynamic network models in the network autoregression framework. The VB approach allows for the automatic identification of the dynamic structure of such a model and obtains a direct approximation of the posterior density. Compared to Markov Chain Monte Carlo (MCMC) based sampling approaches, the VB approach achieves enhanced computational efficiency without sacrificing estimation accuracy. In the simulation study conducted here, the proposed VB approach detects various types of proper active structures for dynamic network models. Compared to the alternative approach, the proposed method achieves similar or better accuracy, and its computational time is halved. In a real data analysis scenario of day-ahead natural gas flow prediction in the German gas transmission network with 51 nodes between October 2013 and September 2015, the VB approach delivers promising forecasting accuracy along with clearly detected structures in terms of dynamic dependence.

stat.ME↗

arXiv2021

Exclusive Topic Modeling

We propose an Exclusive Topic Modeling (ETM) for unsupervised text classification, which is able to 1) identify the field-specific keywords though less frequently appeared and 2) deliver well-structured topics with exclusive words. In particular, a weighted Lasso penalty is imposed to reduce the dominance of the frequently appearing yet less relevant words automatically, and a pairwise Kullback-Leibler divergence penalty is used to implement topics separation. Simulation studies demonstrate that the ETM detects the field-specific keywords, while LDA fails. When applying to the benchmark NIPS dataset, the topic coherence score on average improves by 22% and 10% for the model with weighted Lasso penalty and pairwise Kullback-Leibler divergence penalty, respectively.

stat.ML↗

arXiv2021

Concentrated Document Topic Model

We propose a Concentrated Document Topic Model(CDTM) for unsupervised text classification, which is able to produce a concentrated and sparse document topic distribution. In particular, an exponential entropy penalty is imposed on the document topic distribution. Documents that have diverse topic distributions are penalized more, while those having concentrated topics are penalized less. We apply the model to the benchmark NIPS dataset and observe more coherent topics and more concentrated and sparse document-topic distributions than Latent Dirichlet Allocation(LDA).

stat.ML↗

arXiv2021

Mask-based Data Augmentation for Semi-supervised Semantic Segmentation

Semantic segmentation using convolutional neural networks (CNN) is a crucial component in image analysis. Training a CNN to perform semantic segmentation requires a large amount of labeled data, where the production of such labeled data is both costly and labor intensive. Semi-supervised learning algorithms address this issue by utilizing unlabeled data and so reduce the amount of labeled data needed for training. In particular, data augmentation techniques such as CutMix and ClassMix generate additional training data from existing labeled data. In this paper we propose a new approach for data augmentation, termed ComplexMix, which incorporates aspects of CutMix and ClassMix with improved performance. The proposed approach has the ability to control the complexity of the augmented data while attempting to be semantically-correct and address the tradeoff between complexity and correctness. The proposed ComplexMix approach is evaluated on a standard dataset for semantic segmentation and compared to other state-of-the-art techniques. Experimental results show that our method yields improvement over state-of-the-art methods on standard datasets for semantic image segmentation.

cs.CV↗

arXiv2021

Dense U-net for super-resolution with shuffle pooling layer

Recent researches have achieved great progress on single image super-resolution(SISR) due to the development of deep learning in the field of computer vision. In these method, the high resolution input image is down-scaled to low resolution space using a single filter, commonly max-pooling, before feature extraction. This means that the feature extraction is performed in biased filtered feature space. We demonstrate that this is sub-optimal and causes information loss. In this work, we proposed a state-of-the-art convolutional neural network method called Dense U-net with shuffle pooling. To achieve this, a modified U-net with dense blocks, called dense U-net, is proposed for SISR. Then, a new pooling strategy called shuffle pooling is designed, which is aimed to replace the dense U-Net for down-scale operation. By doing so, we effectively replace the handcrafted filter in the SISR pipeline with more lossy down-sampling filters specifically trained for each feature map, whilst also reducing the information loss of the overall SISR operation. In addition, a mix loss function, which combined with Mean Square Error(MSE), Structural Similarity Index(SSIM) and Mean Gradient Error (MGE), comes up to reduce the perception loss and high-level information loss. Our proposed method achieves superior accuracy over previous state-of-the-art on the three benchmark datasets: SET14, BSD300, ICDAR2003. Code is available online.

eess.IV↗

arXiv2020

CloudPSS: A High-Performance Power System Simulator Based on Cloud Computing

With the increasing computations in power system simulations, high-performance and cost-effective power system simulator is highly required. In this paper, a cloud-computing based power system simulator, namely CloudPSS, is designed. Based on an open service integrating framework, a self-developed electromagnetic transients (EMT) simulator with an automatic code generator is provided to accelerate EMT simulations using heterogeneous devices in the cloud, such as CPU and GPU. Test results show that CloudPSS can achieve significant speedups for both large-scale simulation tasks and multi-scenario tasks. Moreover, benefit from the time-sharing of cloud computing resources, the computational cost can be greatly reduced.

cs.DC↗

arXiv2020

Domain Adaptation on Semantic Segmentation for Aerial Images

Semantic segmentation has achieved significant advances in recent years. While deep neural networks perform semantic segmentation well, their success rely on pixel level supervision which is expensive and time-consuming. Further, training using data from one domain may not generalize well to data from a new domain due to a domain gap between data distributions in the different domains. This domain gap is particularly evident in aerial images where visual appearance depends on the type of environment imaged, season, weather, and time of day when the environment is imaged. Subsequently, this distribution gap leads to severe accuracy loss when using a pretrained segmentation model to analyze new data with different characteristics. In this paper, we propose a novel unsupervised domain adaptation framework to address domain shift in the context of aerial semantic image segmentation. To this end, we solve the problem of domain shift by learn the soft label distribution difference between the source and target domains. Further, we also apply entropy minimization on the target domain to produce high-confident prediction rather than using high-confident prediction by pseudo-labeling. We demonstrate the effectiveness of our domain adaptation framework using the challenge image segmentation dataset of ISPRS, and show improvement over state-of-the-art methods in terms of various metrics.

cs.CV↗

arXiv2020

Cascade Attentive Dropout for Weakly Supervised Object Detection

Weakly supervised object detection (WSOD) aims to classify and locate objects with only image-level supervision. Many WSOD approaches adopt multiple instance learning as the initial model, which is prone to converge to the most discriminative object regions while ignoring the whole object, and therefore reduce the model detection performance. In this paper, a novel cascade attentive dropout strategy is proposed to alleviate the part domination problem, together with an improved global context module. We purposely discard attentive elements in both channel and space dimensions, and capture the inter-pixel and inter-channel dependencies to induce the model to better understand the global context. Extensive experiments have been conducted on the challenging PASCAL VOC 2007 benchmarks, which achieve 49.8% mAP and 66.0% CorLoc, outperforming state-of-the-arts.

cs.CV↗

arXiv2020

Probabilistic Forecasting for Daily Electricity Loads and Quantiles for Curve-to-Curve Regression

Probabilistic forecasting of electricity load curves is of fundamental importance for effective scheduling and decision making in the increasingly volatile and competitive energy markets. We propose a novel approach to construct probabilistic predictors for curves (PPC), which leads to a natural and new definition of quantiles in the context of curve-to-curve linear regression. There are three types of PPC: a predictive set, a predictive band and a predictive quantile, all of which are defined at a pre-specified nominal probability level. In the simulation study, the PPC achieve promising coverage probabilities under a variety of data generating mechanisms. When applying to one day ahead forecasting for the French daily electricity load curves, PPC outperform several state-of-the-art predictive methods in terms of forecasting accuracy, coverage rate and average length of the predictive bands. The predictive quantile curves provide insightful information which is highly relevant to hedging risks in electricity supply management.

stat.ME↗

arXiv2020

Charmed and $ϕ$ meson decay constants from 2+1-flavor lattice QCD

On a lattice with 2+1-flavor dynamical domain-wall fermions at the physical pion mass, we calculate the decay constants of $D_{s}^{(*)}$, $D^{(*)}$ and $ϕ$. The lattice size is $48^3\times96$, which corresponds to a spatial extension of $\sim5.5$ fm with the lattice spacing $a\approx 0.114$ fm. For the valence light, strange and charm quarks, we use overlap fermions at several mass points close to their physical values. Our results at the physical point are $f_D=213(5)$ MeV, $f_{D_s}=249(7)$ MeV, $f_{D^*}=234(6)$ MeV, $f_{D_s^*}=274(7)$ MeV, and $f_ϕ=241(9)$ MeV. The couplings of $D^*$ and $D_s^*$ to the tensor current ($f_V^T$) can be derived, respectively, from the ratios $f_{D^*}^T/f_{D^*}=0.91(4)$ and $f_{D_s^*}^T/f_{D_s^*}=0.92(4)$, which are the first lattice QCD results. We also obtain the ratios $f_{D^*}/f_D=1.10(3)$ and $f_{D_s^*}/f_{D_s}=1.10(4)$, which reflect the size of heavy quark symmetry breaking in charmed mesons. The ratios $f_{D_s}/f_{D}=1.16(3)$ and $f_{D_s^*}/f_{D^*}=1.17(3)$ can be taken as a measure of SU(3) flavor symmetry breaking.

hep-lat↗