arXiv subjects

Xiaohong Li

Publications and source records attributed to Xiaohong Li.

At least 55 records · Page 3Linked to original sources

arXiv2022

Inertia and spectral symmetry of eccentricity matrices of some clique trees

The eccentricity matrix $\mathcal E(G)$ of a connected graph $G$ is obtained from the distance matrix of $G$ by leaving unchanged the largest nonzero entries in each row and each column, and replacing the remaining ones with zeros. In this paper, we consider the set $\mathcal C \mathcal T$ of clique trees whose blocks have at most two cut-vertices \textcolor{blue}{of the clique tree}. After proving the irreducibility of the eccentricity matrix of a clique tree in $\mathcal C \mathcal T$ and finding its inertia indices, we show that every graph in $\mathcal C \mathcal T$ with more than $4$ vertices and odd diameter has two positive and two negative $\mathcal E$-eigenvalues. Positive $\mathcal E$-eigenvalues and negative $\mathcal E$-eigenvalues turn out to be equal in number even for graphs in $\mathcal C \mathcal T$ with even diameter; that shared cardinality also counts the \textcolor{blue}{`diametrally distinguished'} vertices. Finally, we prove that the spectrum of the eccentricity matrix of a clique tree $G$ in $\mathcal C \mathcal T$ is symmetric with respect to the origin if and only if $G$ has an odd diameter and exactly two adjacent central vertices.

math.CO↗

arXiv2022

Towards Understanding the Faults of JavaScript-Based Deep Learning Systems

Quality assurance is of great importance for deep learning (DL) systems, especially when they are applied in safety-critical applications. While quality issues of native DL applications have been extensively analyzed, the issues of JavaScript-based DL applications have never been systematically studied. Compared with native DL applications, JavaScript-based DL applications can run on major browsers, making the platform- and device-independent. Specifically, the quality of JavaScript-based DL applications depends on the 3 parts: the application, the third-party DL library used and the underlying DL framework (e.g., TensorFlow.js), called JavaScript-based DL system. In this paper, we conduct the first empirical study on the quality issues of JavaScript-based DL systems. Specifically, we collect and analyze 700 real-world faults from relevant GitHub repositories, including the official TensorFlow.js repository, 13 third-party DL libraries, and 58 JavaScript-based DL applications. To better understand the characteristics of these faults, we manually analyze and construct taxonomies for the fault symptoms, root causes, and fix patterns, respectively. Moreover, we also study the fault distributions of symptoms and root causes, in terms of the different stages of the development lifecycle, the 3-level architecture in the DL system, and the 4 major components of TensorFlow.js framework. Based on the results, we suggest actionable implications and research avenues that can potentially facilitate the development, testing, and debugging of JavaScript-based DL systems.

cs.SE↗

arXiv2022

Saliency-Driven Active Contour Model for Image Segmentation

Active contour models have achieved prominent success in the area of image segmentation, allowing complex objects to be segmented from the background for further analysis. Existing models can be divided into region-based active contour models and edge-based active contour models. However, both models use direct image data to achieve segmentation and face many challenging problems in terms of the initial contour position, noise sensitivity, local minima and inefficiency owing to the in-homogeneity of image intensities. The saliency map of an image changes the image representation, making it more visual and meaningful. In this study, we propose a novel model that uses the advantages of a saliency map with local image information (LIF) and overcomes the drawbacks of previous models. The proposed model is driven by a saliency map of an image and the local image information to enhance the progress of the active contour models. In this model, the saliency map of an image is first computed to find the saliency driven local fitting energy. Then, the saliency-driven local fitting energy is combined with the LIF model, resulting in a final novel energy functional. This final energy functional is formulated through a level set formulation, and regulation terms are added to evolve the contour more precisely across the object boundaries. The quality of the proposed method was verified on different synthetic images, real images and publicly available datasets, including medical images. The image segmentation results, and quantitative comparisons confirmed the contour initialization independence, noise insensitivity, and superior segmentation accuracy of the proposed model in comparison to the other segmentation models.

cs.CV↗

arXiv2022

Short-term passenger flow prediction for multi-traffic modes: A Transformer and residual network based multi-task learning method

With the prevailing of mobility as a service (MaaS), it becomes increasingly important to manage multi-traffic modes simultaneously and cooperatively. As an important component of MaaS, short-term passenger flow prediction for multi-traffic modes has thus been brought into focus. It is a challenging problem because the spatiotemporal features of multi-traffic modes are critically complex. Moreover, the passenger flows of multi-traffic modes differentiate and fluctuate significantly. To solve these problems, this paper proposes a multitask learning-based model, called Res-Transformer, for short-term inflow prediction of multi-traffic modes (subway, taxi, and bus). Each traffic mode is treated as a single task in the model. The Res-Transformer consists of two parts: (1) several modified Transformer layers comprising the conv-Transformer layer and the multi-head attention mechanism, which helps to extract the spatial and temporal features of multi-traffic modes, (2) the structure of residual network is utilized to obtain the correlations of different traffic modes and prevent gradient vanishing, gradient explosion, and overfitting. The Res-Transformer model is evaluated on two large-scale real-world datasets from Beijing, China. One is the region of a traffic hub and the other is the region of a residential area. Experiments are conducted to compare the performance of the proposed model with several baseline models. Results prove the effectiveness and robustness of the proposed method. This paper can give critical insights into the short-term inflow prediction for multi-traffic modes.

cs.LG↗

arXiv2022

A Novel Speech-Driven Lip-Sync Model with CNN and LSTM

Generating synchronized and natural lip movement with speech is one of the most important tasks in creating realistic virtual characters. In this paper, we present a combined deep neural network of one-dimensional convolutions and LSTM to generate vertex displacement of a 3D template face model from variable-length speech input. The motion of the lower part of the face, which is represented by the vertex movement of 3D lip shapes, is consistent with the input speech. In order to enhance the robustness of the network to different sound signals, we adapt a trained speech recognition model to extract speech feature, and a velocity loss term is adopted to reduce the jitter of generated facial animation. We recorded a series of videos of a Chinese adult speaking Mandarin and created a new speech-animation dataset to compensate the lack of such public data. Qualitative and quantitative evaluations indicate that our model is able to generate smooth and natural lip movements synchronized with speech.

cs.SD↗

arXiv2021

Coronal rain in randomly heated arcades

Adopting the MPI-AMRVAC code, we present a 2.5-dimensional magnetohydrodynamic (MHD) simulation, which includes thermal conduction and radiative cooling, to investigate the formation and evolution of the coronal rain phenomenon. We perform the simulation in initially linear force-free magnetic fields which host chromospheric, transition region, and coronal plasma, with turbulent heating localized on their footpoints. Due to thermal instability, condensations start to occur at the loop top, and rebound shocks are generated by the siphon inflows. Condensations fragment into smaller blobs moving downwards and as they hit the lower atmosphere, concurrent upflows are triggered. Larger clumps show us clear "coronal rain showers" as dark structures in synthetic EUV hot channels and bright blobs with cool cores in the 304 Å channel, well resembling real observations. Following coronal rain dynamics for more than 10 hours, we carry out a statistical study of all coronal rain blobs to quantify their widths, lengths, areas, velocity distributions, and other properties. The coronal rain shows us continuous heating-condensation cycles, as well as cycles in EUV emissions. Compared to previous studies adopting steady heating, the rain happens faster and in more erratic cycles. Although most blobs are falling downward, upward-moving blobs exist at basically every moment. We also track the movement of individual blobs to study their dynamics and the forces driving their movements. The blobs have a prominence-corona transition-region-like structure surrounding them, and their movements are dominated by the pressure evolution in the very dynamic loop system.

astro-ph.SR↗

arXiv2021

IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation

Natural language generation (NLG) benchmarks provide an important avenue to measure progress and develop better NLG systems. Unfortunately, the lack of publicly available NLG benchmarks for low-resource languages poses a challenging barrier for building NLG systems that work well for languages with limited amounts of data. Here we introduce IndoNLG, the first benchmark to measure natural language generation (NLG) progress in three low-resource -- yet widely spoken -- languages of Indonesia: Indonesian, Javanese, and Sundanese. Altogether, these languages are spoken by more than 100 million native speakers, and hence constitute an important use case of NLG systems today. Concretely, IndoNLG covers six tasks: summarization, question answering, chit-chat, and three different pairs of machine translation (MT) tasks. We collate a clean pretraining corpus of Indonesian, Sundanese, and Javanese datasets, Indo4B-Plus, which is used to pretrain our models: IndoBART and IndoGPT. We show that IndoBART and IndoGPT achieve competitive performance on all tasks -- despite using only one-fifth the parameters of a larger multilingual model, mBART-LARGE (Liu et al., 2020). This finding emphasizes the importance of pretraining on closely related, local languages to achieve more efficient learning and faster inference for very low-resource languages like Javanese and Sundanese.

cs.CL↗

arXiv2021

Realization of ultrabroadband THz/IR photoresponse in a bias-tunable ratchet photodetector

High performance Terahertz (THz) photodetector has drawn wide attention and got great improvement due to its significant application in biomedical, astrophysics, nondestructive inspection, 6th generation communication system as well as national security application. Here we demonstrate a novel broadband photon-type THz/infrared (IR) photodetector based on the GaAs/AlxGa1-xAs ratchet structure. This kind of photodetector realizes a THz photon-response based on the electrically pumped hot hole injection and overcomes the internal workfunction related spectral response limit. An ultrabroadband photoresponse from 4 THz to 300 THz and a peak responsivity of 50.3 mA/W are realized at negative bias voltage of -1 V. The photodetector also presents a bias-tunable photon-response characteristic due to the asymmetric structure. The ratchet structure also induces an evident photocurrent even at zero bias voltage, which indicates the detector can be regard as a broadband photovoltaic-like detector. The rectification characteristic and high temperature operation possibility of the photodetector are also discussed. This work not only demonstrates a novel ultrabroadband THz/IR photodetector, but also provides a new method to study the light-responsive ratchet.

physics.app-ph↗

arXiv2021

AVA: Adversarial Vignetting Attack against Visual Recognition

Vignetting is an inherited imaging phenomenon within almost all optical systems, showing as a radial intensity darkening toward the corners of an image. Since it is a common effect for photography and usually appears as a slight intensity variation, people usually regard it as a part of a photo and would not even want to post-process it. Due to this natural advantage, in this work, we study vignetting from a new viewpoint, i.e., adversarial vignetting attack (AVA), which aims to embed intentionally misleading information into vignetting and produce a natural adversarial example without noise patterns. This example can fool the state-of-the-art deep convolutional neural networks (CNNs) but is imperceptible to humans. To this end, we first propose the radial-isotropic adversarial vignetting attack (RI-AVA) based on the physical model of vignetting, where the physical parameters (e.g., illumination factor and focal length) are tuned through the guidance of target CNN models. To achieve higher transferability across different CNNs, we further propose radial-anisotropic adversarial vignetting attack (RA-AVA) by allowing the effective regions of vignetting to be radial-anisotropic and shape-free. Moreover, we propose the geometry-aware level-set optimization method to solve the adversarial vignetting regions and physical parameters jointly. We validate the proposed methods on three popular datasets, i.e., DEV, CIFAR10, and Tiny ImageNet, by attacking four CNNs, e.g., ResNet50, EfficientNet-B0, DenseNet121, and MobileNet-V2, demonstrating the advantages of our methods over baseline methods on both transferability and image quality.

eess.IV↗

arXiv2021

Bias Field Poses a Threat to DNN-based X-Ray Recognition

The chest X-ray plays a key role in screening and diagnosis of many lung diseases including the COVID-19. More recently, many works construct deep neural networks (DNNs) for chest X-ray images to realize automated and efficient diagnosis of lung diseases. However, bias field caused by the improper medical image acquisition process widely exists in the chest X-ray images while the robustness of DNNs to the bias field is rarely explored, which definitely poses a threat to the X-ray-based automated diagnosis system. In this paper, we study this problem based on the recent adversarial attack and propose a brand new attack, i.e., the adversarial bias field attack where the bias field instead of the additive noise works as the adversarial perturbations for fooling the DNNs. This novel attack posts a key problem: how to locally tune the bias field to realize high attack success rate while maintaining its spatial smoothness to guarantee high realisticity. These two goals contradict each other and thus has made the attack significantly challenging. To overcome this challenge, we propose the adversarial-smooth bias field attack that can locally tune the bias field with joint smooth & adversarial constraints. As a result, the adversarial X-ray images can not only fool the DNNs effectively but also retain very high level of realisticity. We validate our method on real chest X-ray datasets with powerful DNNs, e.g., ResNet50, DenseNet121, and MobileNet, and show different properties to the state-of-the-art attacks in both image realisticity and attack transferability. Our method reveals the potential threat to the DNN-based X-ray automated diagnosis and can definitely benefit the development of bias-field-robust automated diagnosis system.

eess.IV↗

arXiv2021

Stereo Correspondence and Reconstruction of Endoscopic Data Challenge

The stereo correspondence and reconstruction of endoscopic data sub-challenge was organized during the Endovis challenge at MICCAI 2019 in Shenzhen, China. The task was to perform dense depth estimation using 7 training datasets and 2 test sets of structured light data captured using porcine cadavers. These were provided by a team at Intuitive Surgical. 10 teams participated in the challenge day. This paper contains 3 additional methods which were submitted after the challenge finished as well as a supplemental section from these teams on issues they found with the dataset.

cs.CV↗

arXiv2021

Generating Informative CVE Description From ExploitDB Posts by Extractive Summarization

ExploitDB is one of the important public websites, which contributes a large number of vulnerabilities to official CVE database. Over 60\% of these vulnerabilities have high- or critical-security risks. Unfortunately, over 73\% of exploits appear publicly earlier than the corresponding CVEs, and about 40\% of exploits do not even have CVEs. To assist in documenting CVEs for the ExploitDB posts, we propose an open information method to extract 9 key vulnerability aspects (vulnerable product/version/component, vulnerability type, vendor, attacker type, root cause, attack vector and impact) from the verbose and noisy ExploitDB posts. The extracted aspects from an ExploitDB post are then composed into a CVE description according to the suggested CVE description templates, which is must-provided information for requesting new CVEs. Through the evaluation on 13,017 manually labeled sentences and the statistically sampling of 3,456 extracted aspects, we confirm the high accuracy of our extraction method. Compared with 27,230 reference CVE descriptions. Our composed CVE descriptions achieve high ROUGH-L (0.38), a longest common subsequence based metric for evaluating text summarization methods.

cs.LG↗

arXiv2020

Laser Assisted Solution Synthesis of High Performance Graphene Supported Electrocatalysts

Simple, yet versatile, methods to functionalize graphene flakes with metal (oxide) nanoparticles are in demand, particularly for the development of advanced catalysts. Herein, based on light-induced electrochemistry, a laser-assisted, continuous, solution route for the simultaneous reduction and modification of graphene oxide with catalytic nanoparticles is reported. Electrochemical graphene oxide (EGO) is used as starting material and electron-hole pair source due to its low degree of oxidation, which imparts structural integrity and an ability to withstand photodegradation. Simply illuminating a solution stream containing EGO and metal salt (e.g., H2PtCl6 or RuCl3) with a 248 nm wavelength laser produces reduced EGO (rEGO, oxygen content 4.0 at%) flakes, decorated with Pt (~2.0 nm) or RuO2 (~2.8 nm) nanoparticles. The RuO2-rEGO flakes exhibit superior catalytic activity for the oxygen evolution reaction, requiring a small overpotential of 225 mV to reach a current density of 10 mA cm-2. The Pt-rEGO flakes (10.2 wt% of Pt) show enhanced mass activity for the hydrogen evolution reaction, and similar performance for oxygen reduction reaction compared to a commercial 20 wt% Pt/C catalyst. This simple production method is also used to deposit PtPd alloy and MnOx nanoparticles on rEGO, demonstrating its versatility in synthesizing functional nanoparticle-modified graphene materials.

cond-mat.mtrl-sci↗

arXiv2020

IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding

Although Indonesian is known to be the fourth most frequently used language over the internet, the research progress on this language in the natural language processing (NLP) is slow-moving due to a lack of available resources. In response, we introduce the first-ever vast resource for the training, evaluating, and benchmarking on Indonesian natural language understanding (IndoNLU) tasks. IndoNLU includes twelve tasks, ranging from single sentence classification to pair-sentences sequence labeling with different levels of complexity. The datasets for the tasks lie in different domains and styles to ensure task diversity. We also provide a set of Indonesian pre-trained models (IndoBERT) trained from a large and clean Indonesian dataset Indo4B collected from publicly available sources such as social media texts, blogs, news, and websites. We release baseline models for all twelve tasks, as well as the framework for benchmark evaluation, and thus it enables everyone to benchmark their system performances.

cs.CL↗

arXiv2020

A3Ident: A Two-phased Approach to Identify the Leading Authors of Android Apps

Authorship identification is the process of identifying and classifying authors through given codes. Authorship identification can be used in a wide range of software domains, e.g., code authorship disputes, plagiarism detection, exposure of attackers' identity. Besides the inherent challenges from legacy software development, framework programming and crowdsourcing mode in Android raise the difficulties of authorship identification significantly. More specifically, widespread third party libraries and inherited components (e.g., classes, methods, and variables) dilute the primary code within the entire Android app and blur the boundaries of code written by different authors. However, prior research has not well addressed these challenges. To this end, we design a two-phased approach to attribute the primary code of an Android app to the specific developer. In the first phase, we put forward three types of strategies to identify the relationships between Java packages in an app, which consist of context, semantic and structural relationships. A package aggregation algorithm is developed to cluster all packages that are of high probability written by the same authors. In the second phase, we develop three types of features to capture authors' coding habits and code stylometry. Based on that, we generate fingerprints for an author from its developed Android apps and employ several machine learning algorithms for authorship classification. We evaluate our approach in three datasets that contain 15,666 apps from 257 distinct developers and achieve a 92.5% accuracy rate on average. Additionally, we test it on 2,900 obfuscated apps and our approach can classify apps with an accuracy rate of 80.4%.

cs.SE↗

arXiv2020

Multi-graph convolutional network for short-term passenger flow forecasting in urban rail transit

Short-term passenger flow forecasting is a crucial task for urban rail transit operations. Emerging deep-learning technologies have become effective methods used to overcome this problem. In this study, the authors propose a deep-learning architecture called Conv-GCN that combines a graph convolutional network (GCN) and a three-dimensional (3D) convolutional neural network (3D CNN). First, they introduce a multi-graph GCN to deal with three inflow and outflow patterns (recent, daily, and weekly) separately. Multi-graph GCN networks can capture spatiotemporal correlations and topological information within the entire network. A 3D CNN is then applied to deeply integrate the inflow and outflow information. High-level spatiotemporal features between different inflow and outflow patterns and between stations that are nearby and far away can be extracted by 3D CNN. Finally, a fully connected layer is used to output results. The Conv-GCN model is evaluated on smart card data of the Beijing subway under the time interval of 10, 15, and 30 min. Results show that this model yields the best performance compared with seven other models. In terms of the root-mean-square errors, the performances under three time intervals have been improved by 9.402, 7.756, and 9.256%, respectively. This study can provide critical insights for subway operators to optimise urban rail transit operations.

physics.soc-ph↗

arXiv2020

Predicting Missing Information of Key Aspects in Vulnerability Reports

Software vulnerabilities have been continually disclosed and documented. An important practice in documenting vulnerabilities is to describe the key vulnerability aspects, such as vulnerability type, root cause, affected product, impact, attacker type and attack vector, for the effective search and management of fast-growing vulnerabilities. We investigate 120,103 vulnerability reports in the Common Vulnerabilities and Exposures (CVE) over the past 20 years. We find that 56%, 85%, 38% and 28% of CVEs miss vulnerability type, root causes, attack vector and attacker type respectively. To help to complete the missing information of these vulnerability aspects, we propose a neural-network based approach for predicting the missing information of a key aspect of a vulnerability based on the known aspects of the vulnerability. We explore the design space of the neural network models and empirically identify the most effective model design. Using a large-scale vulnerability datas\-et from CVE, we show that we can effectively train a neural-network based classifier with less than 20% of historical CVEs. Our model achieves the prediction accuracy 94%, 79%, 89%and 70% for vulnerability type, root cause, attacker type and attack vector, respectively. Our ablation study reveals the prominent correlations among vulnerability aspects and further confirms the practicality of our approach.

cs.SE↗

arXiv2019

An Empirical Study towards Characterizing Deep Learning Development and Deployment across Different Frameworks and Platforms

Deep Learning (DL) has recently achieved tremendous success. A variety of DL frameworks and platforms play a key role to catalyze such progress. However, the differences in architecture designs and implementations of existing frameworks and platforms bring new challenges for DL software development and deployment. Till now, there is no study on how various mainstream frameworks and platforms influence both DL software development and deployment in practice. To fill this gap, we take the first step towards understanding how the most widely-used DL frameworks and platforms support the DL software development and deployment. We conduct a systematic study on these frameworks and platforms by using two types of DNN architectures and three popular datasets. (1) For development process, we investigate the prediction accuracy under the same runtime training configuration or same model weights/biases. We also study the adversarial robustness of trained models by leveraging the existing adversarial attack techniques. The experimental results show that the computing differences across frameworks could result in an obvious prediction accuracy decline, which should draw the attention of DL developers. (2) For deployment process, we investigate the prediction accuracy and performance (refers to time cost and memory consumption) when the trained models are migrated/quantized from PC to real mobile devices and web browsers. The DL platform study unveils that the migration and quantization still suffer from compatibility and reliability issues. Meanwhile, we find several DL software bugs by using the results as a benchmark. We further validate the results through bug confirmation from stakeholders and industrial positive feedback to highlight the implications of our study. Through our study, we summarize practical guidelines, identify challenges and pinpoint new research directions.

cs.LG↗