arXiv subjects

Wei Xu

Publications and source records attributed to Wei Xu.

At least 487 records · Page 27Linked to original sources

arXiv2021

Deep Reinforcement Learning Based Dynamic Trajectory Control for UAV-assisted Mobile Edge Computing

In this paper, we consider a platform of flying mobile edge computing (F-MEC), where unmanned aerial vehicles (UAVs) serve as equipment providing computation resource, and they enable task offloading from user equipment (UE). We aim to minimize energy consumption of all the UEs via optimizing the user association, resource allocation and the trajectory of UAVs. To this end, we first propose a Convex optimizAtion based Trajectory control algorithm (CAT), which solves the problem in an iterative way by using block coordinate descent (BCD) method. Then, to make the real-time decision while taking into account the dynamics of the environment (i.e., UAV may take off from different locations), we propose a deep Reinforcement leArning based Trajectory control algorithm (RAT). In RAT, we apply the Prioritized Experience Replay (PER) to improve the convergence of the training procedure. Different from the convex optimization based algorithm which may be susceptible to the initial points and requires iterations, RAT can be adapted to any taking off points of the UAVs and can obtain the solution more rapidly than CAT once training process has been completed. Simulation results show that the proposed CAT and RAT achieve the similar performance and both outperform traditional algorithms.

eess.SP↗

arXiv2020

FAWA: Fast Adversarial Watermark Attack on Optical Character Recognition (OCR) Systems

Deep neural networks (DNNs) significantly improved the accuracy of optical character recognition (OCR) and inspired many important applications. Unfortunately, OCRs also inherit the vulnerabilities of DNNs under adversarial examples. Different from colorful vanilla images, text images usually have clear backgrounds. Adversarial examples generated by most existing adversarial attacks are unnatural and pollute the background severely. To address this issue, we propose the Fast Adversarial Watermark Attack (FAWA) against sequence-based OCR models in the white-box manner. By disguising the perturbations as watermarks, we can make the resulting adversarial images appear natural to human eyes and achieve a perfect attack success rate. FAWA works with either gradient-based or optimization-based perturbation generation. In both letter-level and word-level attacks, our experiments show that in addition to natural appearance, FAWA achieves a 100% attack success rate with 60% less perturbations and 78% fewer iterations on average. In addition, we further extend FAWA to support full-color watermarks, other languages, and even the OCR accuracy-enhancing mechanism.

cs.CV↗

arXiv2020

Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting

Object counting aims to estimate the number of objects in images. The leading counting approaches focus on the single category counting task and achieve impressive performance. Note that there are multiple categories of objects in real scenes. Multi-class object counting expands the scope of application of object counting task. The multi-target detection task can achieve multi-class object counting in some scenarios. However, it requires the dataset annotated with bounding boxes. Compared with the point annotations in mainstream object counting issues, the coordinate box-level annotations are more difficult to obtain. In this paper, we propose a simple yet efficient counting network based on point-level annotations. Specifically, we first change the traditional output channel from one to the number of categories to achieve multiclass counting. Since all categories of objects use the same feature extractor in our proposed framework, their features will interfere mutually in the shared feature space. We further design a multi-mask structure to suppress harmful interaction among objects. Extensive experiments on the challenging benchmarks illustrate that the proposed method achieves state-of-the-art counting performance.

cs.CV↗

arXiv2020

Modeling Heterogeneous Statistical Patterns in High-dimensional Data by Adversarial Distributions: An Unsupervised Generative Framework

Since the label collecting is prohibitive and time-consuming, unsupervised methods are preferred in applications such as fraud detection. Meanwhile, such applications usually require modeling the intrinsic clusters in high-dimensional data, which usually displays heterogeneous statistical patterns as the patterns of different clusters may appear in different dimensions. Existing methods propose to model the data clusters on selected dimensions, yet globally omitting any dimension may damage the pattern of certain clusters. To address the above issues, we propose a novel unsupervised generative framework called FIRD, which utilizes adversarial distributions to fit and disentangle the heterogeneous statistical patterns. When applying to discrete spaces, FIRD effectively distinguishes the synchronized fraudsters from normal users. Besides, FIRD also provides superior performance on anomaly detection datasets compared with SOTA anomaly detection methods (over 5% average AUC improvement). The significant experiment results on various datasets verify that the proposed method can better model the heterogeneous statistical patterns in high-dimensional data and benefit downstream applications.

cs.LG↗

arXiv2020

Structural, Electronic, and Vibrational Properties of 2D Graphdiyne-Like Carbon Nanonetwork Synthesized on Au(111): Implications for the Engineering of sp-sp2 Carbon Nanostructures

Graphdiyne, atomically-thin 2D carbon nanostructure based on sp-sp2 hybridization, is an appealing system potentially showing outstanding mechanical and optoelectronic properties. Surface-catalyzed coupling of halogenated sp-carbon-based molecular precursors represents a promising bottom-up strategy to fabricate extended 2D carbon systems with engineered structure on metallic substrates. Here, we investigate the atomic-scale structure and electronic and vibrational properties of an extended graphdiyne-like sp-sp2 carbon nanonetwork grown on Au(111) by means of on-surface synthesis. The formation of such 2D nanonetwork at its different stages as a function of the annealing temperature after the deposition is monitored by scanning tunneling microscopy (STM), Raman spectroscopy and combined with density functional theory (DFT) calculations. High-resolution STM imaging and the high sensitivity of Raman spectroscopy to the bond nature provide a unique strategy to unravel the atomic-scale properties of sp-sp2 carbon nanostructures. We show that hybridization between the 2D carbon nanonetwork and the underlying substrate states strongly affects its electronic and vibrational properties, modifying substantially the density of states and the Raman spectrum compared to the free standing system. This opens the way to the modulation of the electronic properties with significant prospects in future applications as active nanomaterials for catalysis, photoconversion and carbon-based nanoelectronics.

cond-mat.mtrl-sci↗

arXiv2020

WNUT-2020 Task 1 Overview: Extracting Entities and Relations from Wet Lab Protocols

This paper presents the results of the wet lab information extraction task at WNUT 2020. This task consisted of two sub tasks: (1) a Named Entity Recognition (NER) task with 13 participants and (2) a Relation Extraction (RE) task with 2 participants. We outline the task, data annotation process, corpus statistics, and provide a high-level overview of the participating systems for each sub task.

cs.CL↗

arXiv2020

TweeTime: A Minimally Supervised Method for Recognizing and Normalizing Time Expressions in Twitter

We describe TweeTIME, a temporal tagger for recognizing and normalizing time expressions in Twitter. Most previous work in social media analysis has to rely on temporal resolvers that are designed for well-edited text, and therefore suffer from the reduced performance due to domain mismatch. We present a minimally supervised method that learns from large quantities of unlabeled data and requires no hand-engineered rules or hand-annotated training corpora. TweeTIME achieves 0.68 F1 score on the end-to-end task of resolving date expressions, outperforming a broad range of state-of-the-art systems.

cs.IR↗

arXiv2020

Code and Named Entity Recognition in StackOverflow

There is an increasing interest in studying natural language and computer code together, as large corpora of programming texts become readily available on the Internet. For example, StackOverflow currently has over 15 million programming related questions written by 8.5 million users. Meanwhile, there is still a lack of fundamental NLP techniques for identifying code tokens or software-related named entities that appear within natural language sentences. In this paper, we introduce a new named entity recognition (NER) corpus for the computer programming domain, consisting of 15,372 sentences annotated with 20 fine-grained entity types. We trained in-domain BERT representations (BERTOverflow) on 152 million sentences from StackOverflow, which lead to an absolute increase of +10 F-1 score over off-the-shelf BERT. We also present the SoftNER model which achieves an overall 79.10 F$_1$ score for code and named entity recognition on StackOverflow data. Our SoftNER model incorporates a context-independent code token classifier with corpus-level features to improve the BERT-based tagging model. Our code and data are available at: https://github.com/jeniyat/StackOverflowNER/

cs.CL↗

arXiv2020

An Empirical Study of Pre-trained Transformers for Arabic Information Extraction

Multilingual pre-trained Transformers, such as mBERT (Devlin et al., 2019) and XLM-RoBERTa (Conneau et al., 2020a), have been shown to enable the effective cross-lingual zero-shot transfer. However, their performance on Arabic information extraction (IE) tasks is not very well studied. In this paper, we pre-train a customized bilingual BERT, dubbed GigaBERT, that is designed specifically for Arabic NLP and English-to-Arabic zero-shot transfer learning. We study GigaBERT's effectiveness on zero-short transfer across four IE tasks: named entity recognition, part-of-speech tagging, argument role labeling, and relation extraction. Our best model significantly outperforms mBERT, XLM-RoBERTa, and AraBERT (Antoun et al., 2020) in both the supervised and zero-shot transfer settings. We have made our pre-trained models publicly available at https://github.com/lanwuwei/GigaBERT.

cs.CL↗

arXiv2020

Beamforming Optimization for IRS-Aided Communications with Transceiver Hardware Impairments

In this paper, we focus on intelligent reflecting surface (IRS) assisted multi-antenna communications with transceiver hardware impairments encountered in practice. In particular, we aim to maximize the received signal-to-noise ratio (SNR) taking into account the impact of hardware impairments, where the source transmit beamforming and the IRS reflect beamforming are jointly designed under the proposed optimization framework. To circumvent the non-convexity of the formulated design problem, we first derive a closed-form optimal solution to the source transmit beamforming. Then, for the optimization of IRS reflect beamforming, we obtain an upper bound to the optimal objective value via solving a single convex problem. A low-complexity minorization-maximization (MM) algorithm was developed to approach the upper bound. Simulation results demonstrate that the proposed beamforming design is more robust to the hardware impairments than that of the conventional SNR maximized scheme. Moreover, compared to the scenario without deploying an IRS, the performance gain brought by incorporating the hardware impairments is more evident for the IRS-aided communications.

cs.IT↗

arXiv2020

Sliding Differential Evolution Scheduling for Federated Learning in Bandwidth-Limited Networks

Federated learning (FL) in a bandwidth-limited network with energy-limited user equipments (UEs) is under-explored. In this paper, to jointly save energy consumed by the battery-limited UEs and accelerate the convergence of the global model in FL for the bandwidth-limited network, we propose the sliding differential evolution-based scheduling (SDES) policy. To this end, we first formulate an optimization that aims to minimize a weighted sum of energy consumption and model training convergence. Then, we apply the SDES with parallel differential evolution (DE) operations in several small-scale windows, to address the above proposed problem effectively. Compared with existing scheduling policies, the proposed SDES performs well in reducing energy consumption and the model convergence with lower computational complexity.

cs.IT↗

arXiv2020

AI Driven Heterogeneous MEC System with UAV Assistance for Dynamic Environment -- Challenges and Solutions

By taking full advantage of Computing, Communication and Caching (3C) resources at the network edge, Mobile Edge Computing (MEC) is envisioned as one of the key enablers for the next generation networks. However, current fixed-location MEC architecture may not be able to make real-time decision in dynamic environment, especially in large-scale scenarios. To address this issue, in this paper, a Heterogeneous MEC (H-MEC) architecture is proposed, which is composed of fixed unit, i.e., Ground Stations (GSs) as well as moving nodes, i.e., Ground Vehicles (GVs) and Unmanned Aerial Vehicles (UAVs), all with 3C resource enabled. The key challenges in H-MEC, i.e., mobile edge node management, real-time decision making, user association and resource allocation along with the possible Artificial Intelligence (AI)-based solutions are discussed. In addition, the AI-based joint Resource schEduling (ARE) framework with two different AI-based mechanisms, i.e., Deep neural network (DNN)-based and deep reinforcement learning (DRL)-based architectures are proposed. DNN-based solution with online incremental learning applies the global optimizer and therefore has better performance than the DRL-based architecture with online policy updating, but requires longer training time. The simulation results are given to verify the efficiency of our proposed ARE framework.

eess.SP↗

arXiv2020

Robots State Estimation and Observability Analysis Based on Statistical Motion Models

This paper presents a generic motion model to capture mobile robots' dynamic behaviors (translation and rotation). The model is based on statistical models driven by white random processes and is formulated into a full state estimation algorithm based on the error-state extended Kalman filtering framework (ESEKF). Major benefits of this method are its versatility, being applicable to different robotic systems without accurately modeling the robots' specific dynamics, and ability to estimate the robot's (angular) acceleration, jerk, or higher-order dynamic states with low delay. Mathematical analysis with numerical simulations are presented to show the properties of the statistical model-based estimation framework and to reveal its connection to existing low-pass filters. Furthermore, a new paradigm is developed for robots observability analysis by developing Lie derivatives and associated partial differentiation directly on manifolds. It is shown that this new paradigm is much simpler and more natural than existing methods based on quaternion parameterizations. It is also scalable to high dimensional systems. A novel \textbf{\textit{thin}} set concept is introduced to characterize the unobservable subset of the system states, providing the theoretical foundation to observability analysis of robotic systems operating on manifolds and in high dimension. Finally, extensive experiments including full state estimation and extrinsic calibration (both POS-IMU and IMU-IMU) on a quadrotor UAV, a handheld platform and a ground vehicle are conducted. Comparisons with existing methods show that the proposed method can effectively estimate all extrinsic parameters, the robot's translation/angular acceleration and other state variables (e.g., position, velocity, attitude) of high accuracy and low delay.

cs.RO↗

arXiv2020

Learning Pugachev's Cobra Maneuver for Tail-sitter UAVs Using Acceleration Model

The Pugachev's cobra maneuver is a dramatic and demanding maneuver requiring the aircraft to fly at extremely high Angle of Attacks (AOA) where stalling occurs. This paper considers this maneuver on tail-sitter UAVs. We present a simple yet very effective feedback-iterative learning position control structure to regulate the altitude error and lateral displacement during the maneuver. Both the feedback controller and the iterative learning controller are based on the aircraft acceleration model, which is directly measurable by the onboard accelerometer. Moreover, the acceleration model leads to an extremely simple dynamic model that does not require any model identification in designing the position controller, greatly simplifying the implementation of the iterative learning control. Real-world outdoor flight experiments on the "Hong Hu" UAV, an aerobatic yet efficient quadrotor tail-sitter UAV of small-size, are provided to show the effectiveness of the proposed controller.

eess.SY↗

arXiv2020

Cascaded Channel Estimation for IRS-assisted Mmwave Multi-antenna with Quantized Beamforming

In this letter, we optimize the channel estimator of the cascaded channel in an intelligent reflecting surface (IRS)-assisted millimeter wave (mmWave) multi-antenna system. In this system, the receiver is equipped with a hybrid architecture adopting quantized beamforming. Different from traditional multiple-input multiple-output (MIMO) systems, the design of channel estimation is challenging since the IRS is usually a passive array with limited signal processing capability. We derive the optimized channel estimator in a closed form by reformulating the problem of cascaded channel estimation in this system, leveraging the typical mean-squared error (MSE) criterion. Considering the presence of possible channel sparsity in mmWave channels, we generalize the proposed method by exploiting the channel sparsity for further performance enhancement and computational complexity reduction. Simulation results verify that the proposed estimator significantly outperforms the existing ones.

cs.IT↗

arXiv2020

Magnetoactive elastomer based on superparamagnetic nanoparticles with Curie point close to room temperature

A magnetoactive elastomer (MAE) consisting of single-domain La0.8Ag0.2Mn1.2O3 nanoparticles with a Curie temperature close to room temperature (TC = 308 K) in a silicone matrix has been prepared and comprehensively studied. It has been found that at room temperature and above, MAE particles are magnetized superparamagnetically with a low coercivity below 10 Oe, and the influence of magnetic anisotropy on the appearance of a torque is justified. A coupling between magnetization and magnetoelasticity has been also established. The mechanisms of the appearance of magnetoelasticity, including the effect of MAE rearrangement and MAE compression by magnetized particles, have been revealed. It has been found that the magnetoelastic properties of MAE have critical features near TC. The magnetoelastic properties of MAE disappear at T > TC and are restored at T < TC. This makes it possible to use MAE at room temperature as a smart material for devices with self-regulating magnetoelastic properties.

cond-mat.mtrl-sci↗

arXiv2020

Beamforming Design for Multiuser Transmission Through Reconfigurable Intelligent Surface

This paper investigates the problem of resource allocation for multiuser communication networks with a reconfigurable intelligent surface (RIS)-assisted wireless transmitter. In this network, the sum transmit power of the network is minimized by controlling the phase beamforming of the RIS and transmit power of the BS. This problem is posed as a joint optimization problem of transmit power and RIS control, whose goal is to minimize the sum transmit power under signal-to-interference-plus-noise ratio (SINR) constraints of the users. To solve this problem, a dual method is proposed, where the dual problem is obtained as a semidefinite programming problem. After solving the dual problem, the phase beamforming of the RIS is obtained in the closed form, while the optimal transmit power is obtained by using the standard interference function. Simulation results show that the proposed scheme can reduce up to 94% and 27% sum transmit power compared to the maximum ratio transmission (MRT) beamforming and zero-forcing (ZF) beamforming techniques, respectively.

eess.SP↗

arXiv2020

Multi-Agent Deep Reinforcement Learning Based Trajectory Planning for Multi-UAV Assisted Mobile Edge Computing

An unmanned aerial vehicle (UAV)-aided mobile edge computing (MEC) framework is proposed, where several UAVs having different trajectories fly over the target area and support the user equipments (UEs) on the ground. We aim to jointly optimize the geographical fairness among all the UEs, the fairness of each UAV' UE-load and the overall energy consumption of UEs. The above optimization problem includes both integer and continues variables and it is challenging to solve. To address the above problem, a multi-agent deep reinforcement learning based trajectory control algorithm is proposed for managing the trajectory of each UAV independently, where the popular Multi-Agent Deep Deterministic Policy Gradient (MADDPG) method is applied. Given the UAVs' trajectories, a low-complexity approach is introduced for optimizing the offloading decisions of UEs. We show that our proposed solution has considerable performance over other traditional algorithms, both in terms of the fairness for serving UEs, fairness of UE-load at each UAV and energy consumption for all the UEs.

eess.SP↗