arXiv subjects

Yuhang Wang

Publications and source records attributed to Yuhang Wang.

120 records · Page 7Linked to original sources

arXiv2022

Detecting fake news by enhanced text representation with multi-EDU-structure awareness

Since fake news poses a serious threat to society and individuals, numerous studies have been brought by considering text, propagation and user profiles. Due to the data collection problem, these methods based on propagation and user profiles are less applicable in the early stages. A good alternative method is to detect news based on text as soon as they are released, and a lot of text-based methods were proposed, which usually utilized words, sentences or paragraphs as basic units. But, word is a too fine-grained unit to express coherent information well, sentence or paragraph is too coarse to show specific information. Which granularity is better and how to utilize it to enhance text representation for fake news detection are two key problems. In this paper, we introduce Elementary Discourse Unit (EDU) whose granularity is between word and sentence, and propose a multi-EDU-structure awareness model to improve text representation for fake news detection, namely EDU4FD. For the multi-EDU-structure awareness, we build the sequence-based EDU representations and the graph-based EDU representations. The former is gotten by modeling the coherence between consecutive EDUs with TextCNN that reflect the semantic coherence. For the latter, we first extract rhetorical relations to build the EDU dependency graph, which can show the global narrative logic and help deliver the main idea truthfully. Then a Relation Graph Attention Network (RGAT) is set to get the graph-based EDU representation. Finally, the two EDU representations are incorporated as the enhanced text representation for fake news detection, using a gated recursive unit combined with a global attention mechanism. Experiments on four cross-source fake news datasets show that our model outperforms the state-of-the-art text-based methods.

cs.CL↗

arXiv2022

Three-dimensional discontinuous Galerkin based high-order gas-kinetic scheme and GPU implementation

In this paper, the discontinuous Galerkin based high-order gas-kinetic schemes (DG-HGKS) are developed for the three-dimensional Euler and Navier-Stokes equations. Different from the traditional discontinuous Galerkin (DG) methods with Riemann solvers, the current method adopts a kinetic evolution process, which is provided by the integral solution of Bhatnagar-Gross-Krook (BGK) model. In the weak formulation of DG method, a time-dependent evolution function is provided, and both inviscid and viscous fluxes can be calculated uniformly. The temporal accuracy is achieved by the two-stage fourth-order discretization, and the second-order gas-kinetic solver is adopted for the fluxes over the cell interface and the fluxes inside a cell. Numerical examples, including accuracy tests and Taylor-Green vortex problem, are presented to validate the efficiency and accuracy of DG-HGKS. Both optimal convergence and super-convergence are achieved by the current scheme. The comparison between DG-HGKS and high-order gas-kinetic scheme with weighted essential non-oscillatory reconstruction (WENO-HGKS) is also given, and the numerical performances are comparable with the approximate number of degree of freedom. To accelerate the computation, the DG-HGKS is implemented with the graphics processing unit (GPU) using compute unified device architecture (CUDA). The obtained results are also compared with those calculated by the central processing units (CPU) code in terms of the computational efficiency. The speedup of GPU code suggests the potential of high-order gas-kinetic schemes for the large scale computation.

math.NA↗

arXiv2021

Analysis for full face mechanical behaviors through spatial deduction model with real-time monitoring data

Mechanical analysis for the full face of tunnel structure is crucial to maintain stability, which is a challenge in classical analytical solutions and data analysis. Along this line, this study aims to develop a spatial deduction model to obtain the full-faced mechanical behaviors through integrating mechanical properties into pure data-driven model. The spatial tunnel structure is divided into many parts and reconstructed in a form of matrix. Then, the external load applied on structure in the field was considered to study the mechanical behaviors of tunnel. Based on the limited observed monitoring data in matrix and mechanical analysis results, a double-driven model was developed to obtain the full-faced information, in which the data-driven model was the dominant one and the mechanical constraint was the secondary one. To verify the presented spatial deduction model, cross-test was conducted through assuming partial monitoring data are unknown and regarding them as testing points. The well agreement between deduction results with actual monitoring results means the proposed model is reasonable. Therefore, it was employed to deduct both the current and historical performance of tunnel full face, which is crucial to prevent structural disasters.

cs.LG↗

arXiv2021

Path-specific Underwater Acoustic Channel Tracking and its Application in Passive Time Reversal Mirror

We consider the underwater acoustic channel which is time-variant and doubly-spread in this work. Since conventional channel estimation and decision feedback equalizer (DFE) can not work well for this type of channel, a path-specific underwater acoustic channel tracking is proposed. It is based on the framework of Kalman filter. We provide a simplified sound propagation model as the state transition model. A multipath tracker is proposed which is tolerant of the model-mismatch. Then we can obtain the time-variant path number and path-specific parameters such as delay and Doppler scaling factor. We also consider the application of the proposed path-specific underwater acoustic channel tracking. We propose two types of passive time reversal mirror (PTRM) with our path-specific parameters for time-variant and doubly-spread underwater acoustic channel. With the path-specific parameters obtained by the proposed channel tracking, the proposed PTRM can not only match the time dispersion as conventional PTRM, but also the doubly-spread channel, since the path-specific delay and Doppler scaler factor can help to match the channel in both time and frequency domain. For extensive doubly-spread channel, we can further apply the path-specific compensation to the PTRM. Both simulations and experimental results by data from 2016 Qiandao Lake experiment show the efficiency of proposed path-specific channel tracking and proposed PTRMs with path-specific parameters.

eess.SP↗

arXiv2021

Dynamic Underwater Acoustic Channel Tracking for Correlated Rapidly Time-varying Channels

In this work, we focus on the model-mismatch problem for model-based subspace channel tracking in the correlated underwater acoustic channel. A model based on the underwater acoustic channel's correlation can be used as the state-space model in the Kalman filter to improve the underwater acoustic channel tracking compared that without a model. Even though the data support the assumption that the model is slow-varying and uncorrelated to some degree, to improve the tracking performance further, we can not ignore the model-mismatch problem because most channel models encounter this problem in the underwater acoustic channel. Therefore, in this work, we provide a dynamic time-variant state-space model for underwater acoustic channel tracking. This model is tolerant to the slight correlation after decorrelation. Moreover, a forward-backward Kalman filter is combined to further improve the tracking performance. The performance of our proposed algorithm is demonstrated with the same at-sea data as that used for conventional channel tracking. Compared with the conventional algorithms, the proposed algorithm shows significant improvement, especially in rough sea conditions in which the channels are fast-varying.

eess.SP↗

arXiv2020

Quantum Simulations of SARS-CoV-2 Main Protease Mpro Enable Accurate Scoring of Diverse Ligands

The COVID-19 pandemic has led to unprecedented efforts to identify drugs that can reduce its associated morbidity/mortality rate. Computational chemistry approaches hold the potential for triaging potential candidates far more quickly than their experimental counterparts. These methods have been widely used to search for small molecules that can inhibit critical proteins involved in the SARS-CoV-2 replication cycle. An important target is the SARS-CoV-2 main protease Mpro, an enzyme that cleaves the viral polyproteins into individual proteins required for viral replication and transcription. Unfortunately, standard computational screening methods face difficulties in ranking diverse ligands to a receptor due to disparate ligand scaffolds and varying charge states. Here, we describe full density functional quantum mechanical (DFT/QM) simulations of Mpro in complex with various ligands to obtain absolute ligand binding energies. Our calculations are enabled by a new cloud-native parallel DFT/QM implementation running on computational resources from Amazon Web Services (AWS). The results we obtain are promising: the approach is quite capable of scoring a very diverse set of existing drug compounds for their affinities to Mpro and suggest the DFT/QM approach is potentially more broadly applicable to repurpose screening against this target. In addition, each DFT/QM simulation required only ~1 hour (wall clock time) per ligand. The fast turnaround time raises the practical possibility of a broad application of large-scale quantum mechanics in the drug discovery pipeline at stages where ligand diversity is essential.

physics.chem-ph↗

arXiv2020

Novel algorithms and high-performance cloud computing enable efficient fully quantum mechanical protein-ligand scoring

Ranking the binding of small molecules to protein receptors through physics-based computation remains challenging. Though inroads have been made using free energy methods, these fail when the underlying classical mechanical force fields are insufficient. In principle, a more accurate approach is provided by quantum mechanical density functional theory (DFT) scoring, but even with approximations, this has yet to become practical on drug discovery-relevant timescales and resources. Here, we describe how to overcome this barrier using algorithms for DFT calculations that scale on widely available cloud architectures, enabling full density functional theory, without approximations, to be applied to protein-ligand complexes with approximately 2500 atoms in tens of minutes. Applying this to a realistic example of 22 ligands binding to MCL1 reveals that density functional scoring outperforms classical free energy perturbation theory for this system. This raises the possibility of broadly applying fully quantum mechanical scoring to real-world drug discovery pipelines.

physics.chem-ph↗

arXiv2019

Adaptive Context Network for Scene Parsing

Recent works attempt to improve scene parsing performance by exploring different levels of contexts, and typically train a well-designed convolutional network to exploit useful contexts across all pixels equally. However, in this paper, we find that the context demands are varying from different pixels or regions in each image. Based on this observation, we propose an Adaptive Context Network (ACNet) to capture the pixel-aware contexts by a competitive fusion of global context and local context according to different per-pixel demands. Specifically, when given a pixel, the global context demand is measured by the similarity between the global feature and its local feature, whose reverse value can be used to measure the local context demand. We model the two demand measurements by the proposed global context module and local context module, respectively, to generate adaptive contextual features. Furthermore, we import multiple such modules to build several adaptive context blocks in different levels of network to obtain a coarse-to-fine result. Finally, comprehensive experimental evaluations demonstrate the effectiveness of the proposed ACNet, and new state-of-the-arts performances are achieved on all four public datasets, i.e. Cityscapes, ADE20K, PASCAL Context, and COCO Stuff.

cs.CV↗

arXiv2019

Real Time Lateral Movement Detection based on Evidence Reasoning Network for Edge Computing Environment

Edge computing is providing higher class intelligent service and computing capabilities at the edge of the network. The aim is to ease the backhaul impacts and offer an improved user experience, however, the edge artificial intelligence exacerbates the security of the cloud computing environment due to the dissociation of data, access control and service stages. In order to prevent users from using the edge-cloud computing environment to carry out lateral movement attacks, we proposed a method named CloudSEC meaning real time lateral movement detection based on evidence reasoning network for the edge-cloud environment. The concept of vulnerability correlation is introduced. Based on the vulnerability knowledge and environmental information of the network system, the evidence reasoning network is constructed, and the lateral movement reasoning ability provided by the evidence reasoning network is used. CloudSEC realizes the reconfiguration of the efficient real-time attack process. The experiment shows that the results are complete and credible.

cs.CR↗

arXiv2018

Preserving Location Privacy in Mobile Edge Computing

The burgeoning technology of Mobile Edge Computing is attracting the traditional LBS and LS to deploy due to its nature characters such as low latency and location awareness. Although this transplant will avoid the location privacy threat from the central cloud provider, there still exists the privacy concerns in the LS of MEC scenario. Location privacy threat arises during the procedure of the fingerprint localization, and the previous studies on location privacy are ineffective because of the different threat model and information semantic. To address the location privacy in MEC environment, we designed LoPEC, a novel and effective scheme for protecting location privacy for the MEC devices. By the proper model of the RAN access points, we proposed the noise-addition method for the fingerprint data, and successfully induce the attacker from recognizing the real location. Our evaluation proves that LoPEC effectively prevents the attacker from obtaining the user's location precisely in both single-point and trajectory scenarios.

cs.CR↗

arXiv2017

Stacked Deconvolutional Network for Semantic Segmentation

Recent progress in semantic segmentation has been driven by improving the spatial resolution under Fully Convolutional Networks (FCNs). To address this problem, we propose a Stacked Deconvolutional Network (SDN) for semantic segmentation. In SDN, multiple shallow deconvolutional networks, which are called as SDN units, are stacked one by one to integrate contextual information and guarantee the fine recovery of localization information. Meanwhile, inter-unit and intra-unit connections are designed to assist network training and enhance feature fusion since the connections improve the flow of information and gradient propagation throughout the network. Besides, hierarchical supervision is applied during the upsampling process of each SDN unit, which guarantees the discrimination of feature representations and benefits the network optimization. We carry out comprehensive experiments and achieve the new state-of-the-art results on three datasets, including PASCAL VOC 2012, CamVid, GATECH. In particular, our best model without CRF post-processing achieves an intersection-over-union score of 86.6% in the test set.

cs.CV↗

arXiv2016

Quantized Convolutional Neural Networks for Mobile Devices

Recently, convolutional neural networks (CNN) have demonstrated impressive performance in various computer vision tasks. However, high performance hardware is typically indispensable for the application of CNN models due to the high computation complexity, which prohibits their further extensions. In this paper, we propose an efficient framework, namely Quantized CNN, to simultaneously speed-up the computation and reduce the storage and memory overhead of CNN models. Both filter kernels in convolutional layers and weighting matrices in fully-connected layers are quantized, aiming at minimizing the estimation error of each layer's response. Extensive experiments on the ILSVRC-12 benchmark demonstrate 4~6x speed-up and 15~20x compression with merely one percentage loss of classification accuracy. With our quantized CNN model, even mobile devices can accurately classify images within one second.

cs.CV↗