Search arXiv⌕ Search

arXiv subjects

Chao Wang

Publications and source records attributed to Chao Wang.

At least 613 records · Page 34Linked to original sources
arXiv2020

A Comparison of Pooling Methods on LSTM Models for Rare Acoustic Event Classification

Acoustic event classification (AEC) and acoustic event detection (AED) refer to the task of detecting whether specific target events occur in audios. As long short-term memory (LSTM) leads to state-of-the-art results in various speech related tasks, it is employed as a popular solution for AEC as well. This paper focuses on investigating the dynamics of LSTM model on AEC tasks. It includes a detailed analysis on LSTM memory retaining, and a benchmarking of nine different pooling methods on LSTM models using 1.7M generated mixture clips of multiple events with different signal-to-noise ratios. This paper focuses on understanding: 1) utterance-level classification accuracy; 2) sensitivity to event position within an utterance. The analysis is done on the dataset for the detection of rare sound events from DCASE 2017 Challenge. We find max pooling on the prediction level to perform the best among the nine pooling approaches in terms of classification accuracy and insensitivity to event position within an utterance. To authors' best knowledge, this is the first kind of such work focused on LSTM dynamics for AEC tasks.

eess.AS↗
arXiv2020

QCD calculations of radiative heavy meson decays with subleading power corrections

We revisit QCD calculations of radiative heavy meson decay form factors by including the subleading power corrections from the twist-two photon distribution amplitude at next-to-leading-order in $α_s$ with the method of the light-cone sum rules (LCSR). The desired hard-collinear factorization formula for the vacuum-to-photon correlation function with the interpolating currents for two heavy mesons is constructed with the operator-product-expansion technique in the presence of evanescent operators. Applying the background field approach, the higher twist corrections from both the two-particle and three-particle photon distribution amplitudes are further computed in the LCSR framework at leading-order in QCD, up to the twist-four accuracy. Combining the leading power "point-like" photon contribution at tree level and the subleading power resolved photon corrections from the newly derived LCSR, we update theory predictions for the nonperturbative couplings describing the electromagnetic decay processes of the heavy mesons $H^{\ast \, \pm} \to H^{\pm} \, γ$, $H^{\ast \, 0} \to H^{0} \, γ$, $H_s^{\ast \, \pm} \to H_s^{\pm} \, γ$ (with $H=D, \, B$). Furthermore, we perform an exploratory comparisons of our sum rule computations of the heavy-meson magnetic couplings with the previous determinations based upon different QCD approaches and phenomenological models.

hep-ph↗
arXiv2020

ReluDiff: Differential Verification of Deep Neural Networks

As deep neural networks are increasingly being deployed in practice, their efficiency has become an important issue. While there are compression techniques for reducing the network's size, energy consumption and computational requirement, they only demonstrate empirically that there is no loss of accuracy, but lack formal guarantees of the compressed network, e.g., in the presence of adversarial examples. Existing verification techniques such as Reluplex, ReluVal, and DeepPoly provide formal guarantees, but they are designed for analyzing a single network instead of the relationship between two networks. To fill the gap, we develop a new method for differential verification of two closely related networks. Our method consists of a fast but approximate forward interval analysis pass followed by a backward pass that iteratively refines the approximation until the desired property is verified. We have two main innovations. During the forward pass, we exploit structural and behavioral similarities of the two networks to more accurately bound the difference between the output neurons of the two networks. Then in the backward pass, we leverage the gradient differences to more accurately compute the most beneficial refinement. Our experiments show that, compared to state-of-the-art verification tools, our method can achieve orders-of-magnitude speedup and prove many more properties than existing tools.

cs.LG↗
arXiv2020

A Study of the Tasks and Models in Machine Reading Comprehension

To provide a survey on the existing tasks and models in Machine Reading Comprehension (MRC), this report reviews: 1) the dataset collection and performance evaluation of some representative simple-reasoning and complex-reasoning MRC tasks; 2) the architecture designs, attention mechanisms, and performance-boosting approaches for developing neural-network-based MRC models; 3) some recently proposed transfer learning approaches to incorporating text-style knowledge contained in external corpora into the neural networks of MRC models; 4) some recently proposed knowledge base encoding approaches to incorporating graph-style knowledge contained in external knowledge bases into the neural networks of MRC models. Besides, according to what has been achieved and what are still deficient, this report also proposes some open problems for the future research.

cs.CL↗
arXiv2020

PolSAR Image Classification Based on Dilated Convolution and Pixel-Refining Parallel Mapping network in the Complex Domain

Efficient and accurate polarimetric synthetic aperture radar (PolSAR) image classification with a limited number of prior labels is always full of challenges. For general supervised deep learning classification algorithms, the pixel-by-pixel algorithm achieves precise yet inefficient classification with a small number of labeled pixels, whereas the pixel mapping algorithm achieves efficient yet edge-rough classification with more prior labels required. To take efficiency, accuracy and prior labels into account, we propose a novel pixel-refining parallel mapping network in the complex domain named CRPM-Net and the corresponding training algorithm for PolSAR image classification. CRPM-Net consists of two parallel sub-networks: a) A transfer dilated convolution mapping network in the complex domain (C-Dilated CNN) activated by a complex cross-convolution neural network (Cs-CNN), which is aiming at precise localization, high efficiency and the full use of phase information; b) A complex domain encoder-decoder network connected parallelly with C-Dilated CNN, which is to extract more contextual semantic features. Finally, we design a two-step algorithm to train the Cs-CNN and CRPM-Net with a small number of labeled pixels for higher accuracy by refining misclassified labeled pixels. We verify the proposed method on AIRSAR and E-SAR datasets. The experimental results demonstrate that CRPM-Net achieves the best classification results and substantially outperforms some latest state-of-the-art approaches in both efficiency and accuracy for PolSAR image classification. The source code and trained models for CRPM-Net is available at: https://github.com/PROoshio/CRPM-Net.

cs.CV↗
arXiv2020

NEW: A Generic Learning Model for Tie Strength Prediction in Networks

Tie strength prediction, sometimes named weight prediction, is vital in exploring the diversity of connectivity pattern emerged in networks. Due to the fundamental significance, it has drawn much attention in the field of network analysis and mining. Some related works appeared in recent years have significantly advanced our understanding of how to predict the strong and weak ties in the social networks. However, most of the proposed approaches are scenario-aware methods heavily depending on some special contexts and even exclusively used in social networks. As a result, they are less applicable to various kinds of networks. In contrast to the prior studies, here we propose a new computational framework called Neighborhood Estimating Weight (NEW) which is purely driven by the basic structure information of the network and has the flexibility for adapting to diverse types of networks. In NEW, we design a novel index, i.e., connection inclination, to generate the representative features of the network, which is capable of capturing the actual distribution of the tie strength. In order to obtain the optimized prediction results, we also propose a parameterized regression model which approximately has a linear time complexity and thus is readily extended to the implementation in large-scale networks. The experimental results on six real-world networks demonstrate that our proposed predictive model outperforms the state of the art methods, which is powerful for predicting the missing tie strengths when only a part of the network's tie strength information is available.

cs.SI↗
arXiv2020

The influence of anti-chiral edge states on Andreev reflection in graphene-superconductor junction

Using the tight binding model and the non-equilibrium Green function method, we study Andreev reflection in graphene-superconductor junction, where graphene has two nonequal Dirac Cones split in energy and therefore time reversal symmetry is broken. Due to the anti-chiral edge states of the current graphene model, an incident electron travelling along the edges makes distinct contribution to Andreev reflections. In a two-terminal device, because Andreev retro-reflection is not allowed for just the anti-chiral edges, in this case the mutual scattering between edge and bulk states is necessary, which leads that the coefficient of Andreev retro-reflection is always symmetrical about the incident energy. In a four-terminal junction, however, the edges are parallel to the interface of superconductor and graphene, so at the interface an incident electron travelling along the edges can be retro-reflected as a hole into bulk modes, or specularly reflected as a hole into anti-chiral edge states again. It is noted that, the coefficient of specular Andreev reflection keeps symmetric as to the incident energy of electron which is consistent with the reported results before, however the coefficient of Andreev retro-reflection shows an unexpected asymmetrical behavior due to the presence of anti-chiral edge states. Our results present some new ideas to study the anti-chiral edge modes and Andreev reflection for a graphene model with the broken time reversal symmetry.

cond-mat.supr-con↗
arXiv2020

Stability of large solutions for full compressible Navier-Stokes equations in the whole spaces

The current paper is devoted to the investigation of the global-in-time stability of large solutions for the full Navier-Stokes-Fourier system in the whole space. Suppose that the density and the temperature are bounded from above uniformly in time in the Holder space $C^α$ with $α$ sufficiently small and in $L^\infty$ space respectively. Then we prove two results: (1). Such kind of the solution will converge to its associated equilibrium with a rate which is the same as that for the heat equation if we impose the same condition on the initial data. As a result, we obtain the propagation of positive lower bounds of the density and the temperature. (2). Such kind of the solution is stable, that is, any perturbed solution will remain close to the reference solution if initially they are close to each other. This shows that the set of the smooth and bounded solutions is open.

math.AP↗
arXiv2020

FCNC transitions of $Λ_b$ to neutron in Bethe-Salpeter equation approach

In a covariant quark-diquark model, we investigate the rare decay of $Λ_b \rightarrow n l^+ l^-$ and $Λ_b \rightarrow n γ$ in the Bethe-Salpeter equation approach. In this model the baryons are treated as bound states of a constituent quark and a diquark interacting via a gluon exchange and the linear confinement. We find that the ratio of form factors $R$ is varies from $-0.90$ to $-0.25$ and the branching ratios $Br(Λ_b \rightarrow n l^+ l^-)\times 10^{8}$ are $6.79(l=e),~4.08 ~ (l=μ),~2.9 ~(l=τ) $ and the branching ratio $Br(Λ_b \rightarrow γ)\times 10^{7} )=3.69$ in central values of parameters.

hep-ph↗
arXiv2019

A Survey of FPGA Based Deep Learning Accelerators: Challenges and Opportunities

With the rapid development of in-depth learning, neural network and deep learning algorithms have been widely used in various fields, e.g., image, video and voice processing. However, the neural network model is getting larger and larger, which is expressed in the calculation of model parameters. Although a wealth of existing efforts on GPU platforms currently used by researchers for improving computing performance, dedicated hardware solutions are essential and emerging to provide advantages over pure software solutions. In this paper, we systematically investigate the neural network accelerator based on FPGA. Specifically, we respectively review the accelerators designed for specific problems, specific algorithms, algorithm features, and general templates. We also compared the design and implementation of the accelerator based on FPGA under different devices and network models and compared it with the versions of CPU and GPU. Finally, we present to discuss the advantages and disadvantages of accelerators on FPGA platforms and to further explore the opportunities for future research.

cs.DC↗
arXiv2019

Water harvesting from Soils by Solar-to-Heat Induced Evaporation and Capillary Water Migration

Fresh water scarcity is one of the critical challenges for global sustainable development. Several novel water resources such as passive seawater solar desalination and atmospheric water harvesting have made some progress in recent years. However, no investigation has referred to harvesting water from shallow subsurface soils, which are potential huge water reservoirs. Here, we introduce a method of solar-driven water harvesting from soils, which can provide cheap fresh water in impoverished, arid and decentralized areas. The concentrated solar energy is used to heat the soils to evaporate the soil moisture. Then vapors flow to the condenser through tubes and condense as freshwater. Sustainable water harvesting is realized by water migration due to capillary pumping effect within soils. In the laboratory condition, an experimental setup is designed and its water-harvesting ability from soils is investigated. The maximum water mass harvesting rate was 99.8 g h-1. In about 12 h, the total harvesting water could be as high as about 900 ml. The whole process is solar-driven and spontaneous without other mechanical or electrical ancillaries. The water harvesting rate under one sun energy flux (1 kW m-2) is estimated to be about 360 g h-1 with a 1 m2 solar concentrator. Our proposal provides a potential onsite and sustainable fresh water supply solution to deal with the water scarcity problem.

physics.app-ph↗
arXiv2019

Vision-Based Lane-Changing Behavior Detection Using Deep Residual Neural Network

Accurate lane localization and lane change detection are crucial in advanced driver assistance systems and autonomous driving systems for safer and more efficient trajectory planning. Conventional localization devices such as Global Positioning System only provide road-level resolution for car navigation, which is incompetent to assist in lane-level decision making. The state of art technique for lane localization is to use Light Detection and Ranging sensors to correct the global localization error and achieve centimeter-level accuracy, but the real-time implementation and popularization for LiDAR is still limited by its computational burden and current cost. As a cost-effective alternative, vision-based lane change detection has been highly regarded for affordable autonomous vehicles to support lane-level localization. A deep learning-based computer vision system is developed to detect the lane change behavior using the images captured by a front-view camera mounted on the vehicle and data from the inertial measurement unit for highway driving. Testing results on real-world driving data have shown that the proposed method is robust with real-time working ability and could achieve around 87% lane change detection accuracy. Compared to the average human reaction to visual stimuli, the proposed computer vision system works 9 times faster, which makes it capable of helping make life-saving decisions in time.

cs.CV↗
arXiv2019

Data-Driven Multi-step Demand Prediction for Ride-hailing Services Using Convolutional Neural Network

Ride-hailing services are growing rapidly and becoming one of the most disruptive technologies in the transportation realm. Accurate prediction of ride-hailing trip demand not only enables cities to better understand people's activity patterns, but also helps ride-hailing companies and drivers make informed decisions to reduce deadheading vehicle miles traveled, traffic congestion, and energy consumption. In this study, a convolutional neural network (CNN)-based deep learning model is proposed for multi-step ride-hailing demand prediction using the trip request data in Chengdu, China, offered by DiDi Chuxing. The CNN model is capable of accurately predicting the ride-hailing pick-up demand at each 1-km by 1-km zone in the city of Chengdu for every 10 minutes. Compared with another deep learning model based on long short-term memory, the CNN model is 30% faster for the training and predicting process. The proposed model can also be easily extended to make multi-step predictions, which would benefit the on-demand shared autonomous vehicles applications and fleet operators in terms of supply-demand rebalancing. The prediction error attenuation analysis shows that the accuracy stays acceptable as the model predicts more steps.

cs.LG↗
arXiv2019

Acoustic scene analysis with multi-head attention networks

Acoustic Scene Classification (ASC) is a challenging task, as a single scene may involve multiple events that contain complex sound patterns. For example, a cooking scene may contain several sound sources including silverware clinking, chopping, frying, etc. What complicates ASC more is that classes of different activities could have overlapping sounds patterns (e.g. both cooking and dishwashing could have silverware clinking sound). In this paper, we propose a multi-head attention network to model the complex temporal input structures for ASC. The proposed network takes the audio's time-frequency representation as input, and it leverages standard VGG plus LSTM layers to extract high-level feature representation. Further more, it applies multiple attention heads to summarize various patterns of sound events into fixed dimensional representation, for the purpose of final scene classification. The whole network is trained in an end-to-end fashion with back-propagation. Experimental results confirm that our model discovers meaningful sound patterns through the attention mechanism, without using explicit supervision in the alignment. We evaluated our proposed model using DCASE 2018 Task 5 dataset, and achieved competitive performance on par with previous winner's results.

eess.AS↗
arXiv2019

Debreach: Mitigating Compression Side Channels via Static Analysis and Transformation

Compression is an emerging source of exploitable side-channel leakage that threatens data security, particularly in web applications where compression is indispensable for performance reasons. Current approaches to mitigating compression side channels have drawbacks in that they either degrade compression ratio drastically or require too much effort from developers to be widely adopted. To bridge the gap, we develop Debreach, a static analysis and program transformation based approach to mitigating compression side channels. Debreach consists of two steps. First, it uses taint analysis to soundly identify flows of sensitive data in the program and uses code instrumentation to annotate data before feeding them to the compressor. Second, it enhances the compressor to exploit the freedom to not compress of standard compression protocols, thus removing the dependency between sensitive data and the size of the compressor's output. Since Debreach automatically instruments applications and does not change the compression protocols, it has the advantage of being non-disruptive and compatible with existing systems. We have evaluated Debreach on a set of web server applications written in PHP. Our experiments show that, while ensuring leakage-freedom, Debreach can achieve significantly higher compression performance than state-of-the-art approaches.

cs.CR↗
arXiv2019

Improving Back-Translation with Uncertainty-based Confidence Estimation

While back-translation is simple and effective in exploiting abundant monolingual corpora to improve low-resource neural machine translation (NMT), the synthetic bilingual corpora generated by NMT models trained on limited authentic bilingual data are inevitably noisy. In this work, we propose to quantify the confidence of NMT model predictions based on model uncertainty. With word- and sentence-level confidence measures based on uncertainty, it is possible for back-translation to better cope with noise in synthetic bilingual corpora. Experiments on Chinese-English and English-German translation tasks show that uncertainty-based confidence estimation significantly improves the performance of back-translation.

cs.CL↗
arXiv2019

Stable diagonal stripes in the t-J model at $\bar{n}_h$=1/8 doping from fPEPS calculations

We investigate the 2D t-J model at a hole doping of $\bar{n}_h$=1/8 using recently developed high accuracy fermionic projected entangled pair states(fPEPS) method. By applying stochastic gradient descent method combined with Monte Carlo sampling technique, we obtain the ground state hole energy $E_{\rm hole}$=-1.6186 for $J/t$=0.4. We show that the ground state has stable diagonal stripes instead of vertical stripes with width of 4 unit cells, and stripe filling $ρ_l$=0.5. We further show that the long range superconductivity order is suppressed at this point.

cond-mat.str-el↗