检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Wu, Qiming Zou, Zhikang Zhou, Pan Ye, Xiaoqing Wang, Binghui Li, Ang School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan China Baidu Inc. Shenzhen China The Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Department of Computer Science Illinois Institute of Technology Chicago United States Department of Electrical and Computer Engineering Duke University Durham United States

Crowd counting has drawn much attention due to its importance in safety-critical surveillance systems. Especially, deep neural network (DNN) methods have significantly reduced estimation errors for crowd counting missions. Recent studies have demonstrated that DNNs are vulnerable to adversarial attacks, i.e., normal images with human-imperceptible perturbations could mislead DNNs to make false predictions. In this work, we propose a robust attack strategy called Adversarial Patch Attack with Momentum (APAM) to systematically evaluate the robustness of crowd counting models, where the attacker's goal is to create an adversarial perturbation that severely degrades their performances, thus leading to public safety accidents (e.g., stampede accidents). Especially, the proposed attack leverages the extreme-density background information of input images to generate robust adversarial patches via a series of transformations (e.g., interpolation, rotation, etc.). We observe that by perturbing less than 6% of image pixels, our attacks severely degrade the performance of crowd counting systems, both digitally and physically. To better enhance the adversarial robustness of crowd counting models, we propose the first regression model-based Randomized Ablation (RA), which is more sufficient than Adversarial Training (ADT) (Mean Absolute Error of RA is 5 lower than ADT on clean samples and 30 lower than ADT on adversarial examples). Extensive experiments on five crowd counting models demonstrate the effectiveness and generality of the proposed method. Copyright © 2021, The Authors. All rights reserved.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Learning High-Resolution and Efficient Non-local Features for Brain Glioma Segmentation in MR Images 23rd

Learning High-Resolution and Efficient Non-local Features fo...

引用

23rd International Conference on Medical Image Computing and computer-Assisted Intervention, MICCai 2020

作者： Jia, Haozhe Xia, Yong Cai, Weidong Huang, Heng Research and Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen518057 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xian710072 China School of Computer Science University of Sydney SydneyNSW2006 Australia Department of Electrical and Computer Engineering University of Pittsburgh PittsburghPA15261 United States JD Finance America Corporation Mountain ViewCA94043 United States

ISBN: (纸本)9783030597184

Brain glioma segmentation using multi-parametric magnetic resonance (MR) imaging has significant clinical value. Although 3D convolutional neural networks (CNNs) have become increasingly prevalent in delivering this segmentation task, these models still suffer from an insufficient ability to high-resolution feature representation for small and irregular regions, limited local receptive fields, and poor long-range dependencies. In this paper, we propose a 3D High-resolution and Non-local Feature Network (HNF-Net) for brain glioma segmentation using multi-parametric MR imaging. We construct HNF-Net based mainly on the parallel multi-scale fusion (PMF) module, which helps produce strong high-resolution feature representation and aggregate multi-scale contextual information. We also introduce the expectation-maximization attention (EMA) module to HNF-Net, aiming to capture the long-range dependent contextual information and reduce the feature redundancy in a lightweight fashion. We evaluated our HNF-Net on the BraTS 2019 Challenge dataset against eight top-ranking methods listed on the challenge leaderboard. Our results suggest that the proposed HNF-Net achieves improved overall performance over these methods, and our ablation study demonstrates the effectiveness of the PMF module and EMA module. © 2020, Springer Nature Switzerland AG.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

DRL-Based Pricing-Driven for Task Offloading and Dynamic Resource in Vehicle Edge Computing

引用

IEEE Transactions on Mobile Computing 2025年

作者： Wu, Sijun Yang, Liang Li, Junjie Guo, Hongzhi Ahmad, Ishtiaq Da Costa, Daniel Benevides Jiang, Hongbo Niyato, Dusit Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Northwestern Polytechnical University Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Cybersecurity Shaanxi Xi'an710072 China Czech Technical University in Prague Department of Telecommunication Engineering Faculty of Electrical Engineering Prague166 27 Czech Republic Interdisciplinary Research Center for Communication Systems and Sensing Department of Electrical Engineering Dhahran31261 Saudi Arabia Nanyang Technological University School of Computer Science and Engineering Singapore639798 Singapore

Vehicle Edge Computing (VEC) assists vehicles in performing latency-sensitive tasks by deploying resources near the vehicle. Designing an incentive mechanism for vehicles and VEC is crucial for realizing an intelligent transmission system. Considering the rationality of resource allocation, we model the utility functions of the VEC and the vehicle, which are used as optimization objectives. Specifically, the VEC allocates resources through pricing to maximize revenue under resource-constrained conditions, and the vehicle weighs payments against energy consumption to determine offloading and resource allocation. Given the vehicle movement and the variable channel state, we use the Deep Reinforcement Learning (DRL) algorithm to solve these optimization problems. To reduce the learning difficulty of the DRL algorithm in complex VEC scenarios with multiple optimization variables, we propose a Pricing-Driven Resource Allocation (PDRA) algorithm that performs mobility-aware task offloading and calculates the optimal values of the optimization variables in the utility function of the vehicle to reduce the decision dimension. Furthermore, we also propose a DRL-based Pricing-Driven Dynamic Resource Allocation (DPDDRA) algorithm to achieve efficient resource allocation. Extensive experimental results show that the proposed algorithms can reduce the learning difficulty while maximizing VEC and vehicle revenue in complex VEC scenarios. © 2002-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Quantum open system identification via global optimization: optimally accurate Markovian models of open systems from time-series data

arXiv

引用

arXiv 2022年

作者： Popovych, Zakhar Jacobs, Kurt Korpas, Georgios Marecek, Jakub Bondar, Denys I. Department of Physics Tulane University New OrleansLA70118 United States DEVCOM Army Research Laboratory AdelphiMD20783 United States Department of Physics University of Massachusetts at Boston BostonMA02125 United States HSBC Lab Innovation & Ventures 8 Canada Square LondonE14 5HQ United Kingdom Department of Computer Science Czech Technical University in Prague Karlovo nam. 13 Prague 2 Czech Republic Archimedes Research Unit on AI Data Science and Algorithms Athena Research and Innovation Center Maroussi Greece

Accurate models of the dynamics of quantum circuits are essential for optimizing and advancing quantum devices. Since first-principles models of environmental noise and dissipation in real quantum systems are often unavailable, deriving accurate models from measured time-series data is critical. However, identifying open quantum systems poses significant challenges: powerful methods from systems engineering can perform poorly beyond weak damping (as we show) because they fail to incorporate essential constraints required for quantum evolution (e.g., positivity). Common methods that can include these constraints are typically multi-step, fitting linear models to physically grounded master equations, often resulting in non-convex functions in which local optimization algorithms get stuck in local extrema (as we show). In this work, we solve these problems by formulating quantum system identification directly from data as a polynomial optimization problem, enabling the use of recently developed global optimization methods. These methods are essentially guaranteed to reach global optima, allowing us for the first time to efficiently obtain the most accurate Markovian model for a given system. In addition to its practical importance, this allows us to take the error of these Markovian models as an alternative (operational) measure of the non-Markovianity of a system. We test our method with the spin-boson model — a two-level system coupled to a bath of harmonic oscillators — for which we obtain the exact evolution using matrix-product-state techniques. We show that polynomial optimization using moment/sum-of-squares approaches significantly outperforms traditional optimization algorithms, and we show that even for strong damping Lindblad-form master equations can provide accurate models of the spin-boson system (fractional errors at the level of 10−3). Using Breuer’s measure of non-Markovianity as an example we show that there can be large differences between such measur

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

Accuracy vs. Efficiency: Achieving both Through Hardware-Aware Quantization and Reconfigurable Architecture with Mixed Precision

Accuracy vs. Efficiency: Achieving both Through Hardware-Awa...

引用

IEEE International Conference on Big data and Cloud Computing (BdCloud)

作者： Libo Chang Shengbing Zhang Huimin Du Shiyu Wang Meikang Qiu Jihe Wang School of Computer Science Northwestern Polytechnical University and National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an China School of Electronic Engineering Xi'an University of Posts and Telecommunication Xi'an China School of Computer Science Northwestern Polytechnical University and Engineering Research Center of Embedded System Integration Ministry of Education Xi'an China Texas A&M University-Commerce Texas USA

We propose a hardware/software co-design framework, which leverages hardware-aware quantization and a reconfigurable processor to improve the computational efficiency of convolutional neural networks (CNNs) on tiny IoT devices based on reconfigurable platforms. Firstly, we proposed a multi-objective optimization value function that can weigh accuracy, the size of CNN models, and computational delay, to improve the efficiency of the mixed- precision quantization algorithm based on deep reinforcement learning. Secondly, we propose a reconfigurable CNN processor that can adapt to the computing characteristics of various quantized CNN models, as well as a reconfigurable computing array and an on-chip elastic buffer, to improve the performance and computing efficiency on edge equipment. Finally, we demonstrate the effectiveness of the proposed co-design method through an extensive evaluation of the Ultra96-V2 platform. With respect to the well-known CNNs—VGG-16, ResNet-50, and MobileNet-V2, the experimental result shows that the throughput of 216.6 GOPS, 214.0 GOPS, and 53.6 GOPS, the computing efficiency of 0.63GOPS/DSP, 0.64GOPS/DSP, and 0.24 GOPS/DSP, respectively. In addition, achieving a better optimized trade-off between the computing efficiency and accuracy compared with the recently proposed CNN processor with fixed bit-width and mixed-precision.

关键词： Adaptation models Quantization (signal) Computational modeling Reinforcement learning Throughput System-on-chip Reconfigurable architectures

来源：评论

学校读者我要写书评

暂无评论

Co-Designed Communication and Computing for data Reliability in Industrial Cyber-Physical Systems with Cloud-Fog Automation

引用

IEEE Journal on Selected Areas in Communications 2025年

作者： Fan, Xiaoxuan Deng, Xianjun Liu, Shenghao Zhu, Chenlu Zhou, Xinlei Yi, Lingzhi Wu, Libing Park, Jong Hyuk Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering China Wuhan Research Institute of Posts and Telecommunications China Zhongnan University of Economics and Law School of Information Engineering China Wuhan University School of Cyber Science and Engineering China Seoul National University of Science and Technology Department of Computer Science and Engineering Korea Republic of

The Cloud-Fog Automation is a newly proposed digital industrial automation architecture aimed at accelerating the integration and collaboration of communication, computing, and control towards next-generation cyber-physical systems (CPSs). data reliability is one of the key considerations for achieving Cloud-Fog Automation. Sensor nodes serve as infrastructures for data collection within industrial CPSs and are essential for maintaining ultra-high data reliability. However, the underlying sensor nodes communicate frequently, are damage-prone and difficult to identify, which dramatically shortens the network lifetime and poses great challenges to data reliability. Motivated by this fact, this paper co-designs communication architecture, algorithms, and computing models for next-generation industrial CPSs with Cloud-Fog Automation to ensure data reliability and functional security. First, a four-layer energy-efficient communication architecture is proposed and a cluster head computing algorithm based on double deep Q-learning (CH-DDQ) is designed inside the architecture. Besides, a 2-stage hyBrid fault detection scheme (2-Brain) is proposed for underlying sensor nodes. 2-Brain first incorporates the Obstacle Triple Jump Protocol (OTP) and OTP packets to improve hard fault detection performance. Then, an unsupervised sensor reading soft fault detection model (SR-SFD) based on contrastive learning, momentum, and tensor is adopted to learn discriminative representations of sensor readings and identify soft faults. Simulations and a case study in the nuclear power industry manifest CH-DDQ improves the network lifetime by 5.4%484.3% compared to three peer methods, and OTP performs better than baselines by 33.1% on average. Additionally, SR-SFD exhibits high efficiency in sensor soft fault detection and other application scenarios. © 1983-2012 IEEE.

关键词： Cluster computing

来源：评论

学校读者我要写书评

暂无评论

Multimodal Whole Slide Foundation Model for Pathology

arXiv

引用

arXiv 2024年

作者： Ding, Tong Wagner, Sophia J. Song, Andrew H. Chen, Richard J. Lu, Ming Y. Zhang, Andrew Vaidya, Anurag J. Jaume, Guillaume Shaban, Muhammad Kim, Ahrong Williamson, Drew F.K. Chen, Bowen Almagro-Perez, Cristina Doucet, Paul Sahai, Sharifa Chen, Chengkuan Komura, Daisuke Kawabe, Akihiro Ishikawa, Shumpei Gerber, Georg Peng, Tingying Le, Long Phi Mahmood, Faisal Department of Pathology Mass General Brigham Harvard Medical School BostonMA United States Data Science Program Dana-Farber Cancer Institute BostonMA United States Cancer Program Broad Institute of Harvard and MIT CambridgeMA United States John A. Paulson School of Engineering and Applied Sciences Harvard University CambridgeMA United States Helmholtz Munich German Research Center for Environment and Health Munich Germany School of Computation Information and Technology Technical University of Munich Munich Germany Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States Harvard-MIT Division of Health Sciences and Technology Massachusetts Institute of Technology CambridgeMA United States Department of Pathology Pusan National University Busan Korea Republic of Department of Pathology and Laboratory Medicine Emory University School of Medicine AtlantaGA United States Harvard Data Science Initiative Harvard University CambridgeMA United States Department of Systems Biology Harvard Medical School BostonMA United States Department of Preventive Medicine Graduate School of Medicine The University of Tokyo Tokyo Japan Division of Pathology National Cancer Center Exploratory Oncology Research & Clinical Trial Center Chiba Japan

The field of computational pathology has been transformed with recent advances in foundation models that encode histopathology region-of-interests (ROIs) into versatile and transferable feature representations via self-supervised learning (SSL). However, translating these advancements to address complex clinical challenges at the patient and slide level remains constrained by limited clinical data in disease-specific cohorts, especially for rare clinical conditions. We propose TITAN, a multimodal whole slide foundation model pretrained using 335,645 WSIs via visual self-supervised learning and vision-language alignment with corresponding pathology reports and 423,122 synthetic captions generated from a multimodal generative ai copilot for pathology. Without any finetuning or requiring clinical labels, TITAN can extract general-purpose slide representations and generate pathology reports that generalize to resource-limited clinical scenarios such as rare disease retrieval and cancer prognosis. We evaluate TITAN on diverse clinical tasks and find that TITAN outperforms both ROI and slide foundation models across machine learning settings such as linear probing, few-shot and zero-shot classification, rare cancer retrieval and cross-modal retrieval, and pathology report generation. The model is publicly accessible at https://***/mahmoodlab/TITAN © 2024, CC BY-NC-ND.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Grand Challenge on Respiratory Sound Classification for SPRSound dataset

Grand Challenge on Respiratory Sound Classification for SPRS...

引用

IEEE Biomedical Circuits and Systems (BIOCAS)

作者： Qing Zhang Jing Zhang Jiajun Yuan Huajie Huang Yuhang Zhang Changyan Chen Jilei Lin Baoqin Zhang Gaomei Lv Shuzhu Lin Na Wang Xin Liu Mingyu Tang Yahua Wang Lu Liu Hui Ma Dan Xie Lihua Wu Haibo Yang Shuhua Yuan Mengjun Chen Bingxue Zhang Hongyuan Zhou Jian Zhao Yongfu Li Yong Yin Liebin Zhao Guoxing Wang Yong Lian Department of Micro-Nano Electronics and MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China Pediatric AI Clinical Application and Research Center Shanghai Children’s Medical Center Shanghai Jiao Tong University School of Medicine China Department of Respiratory Medicine Shanghai Children’s Medical Center Shanghai Jiao Tong University School of Medicine China Shanghai Engineering Research Center of Intelligence Pediatrics (SERCIP) Shanghai Children’s Medical Center School of Medicine Shanghai Jiao Tong University Shanghai China School of Computer Engineering and Science Shanghai University China Sanya Maternity and Child Care Hospital China Department of Paediatrics Taicang Affiliated Hospital of Soochow University The First People’s Hospital of Taicang China Linyi City People Hospital China Department of Paediatrics Fengcheng Hospital China Linyi City Maternal and Child Health Hospital China Department of Pediatrics Fifth Affiliated Hospital of Harbin Medical University China Fujian Children’s Hospital China The First Affiliated Hospital of Henan University of Traditional Chinese Medicine China Shanghai Tuoxiao Intelligent Technology Co. Ltd China

Globally, respiratory diseases are the leading cause of death, making it essential to develop an automatic respiratory sounds software to speed up diagnosis and reduce physician workload. A recent line of attempts have been proposed to predict accurately, but they have yet been able to provide a satisfactory generalization performance. In this contest, we invited the community to develop more accurate and generalized respiratory sound algorithms. A starter code is provided to standardize the submissions and lower the barrier. New testing set is prepared to evaluate the generalization performance of the submissions. Top 3 teams will present their work at IEEE BioCAS 2023 conference.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GradSA: Gradient Sparsification and Accumulation for Communication-Efficient Distributed Deep Learning 15th

GradSA: Gradient Sparsification and Accumulation for Communi...

引用

15th International Conference on Green, Pervasive, and Cloud Computing, GPC 2020

作者： Liu, Bo Jiang, Wenbin Zhao, Shaofeng Jin, Hai He, Bingsheng National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan China Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Huazhong University of Science and Technology Wuhan China Library Henan University of Economics and Law Zhengzhou China Department of Computer Science School of Computing National University of Singapore Singapore Singapore

ISBN: (纸本)9783030642426

Large-scale distributed deep learning is of great importance in various applications. For distributed training, the inter-node gradient communication often becomes the performance bottleneck. Gradient sparsification has been proposed to reduce the communication overhead. However, the sparsification only arbitrarily selects a small fraction of gradients, while the efficiency of selection dimension has been overlooked. Furthermore, gradient staleness is inevitable after applying the sparsification which will ultimately lead to model divergence. In this paper, we propose a staleness-compensated sparse stochastic gradient descent algorithm, GradSA, to improve the training efficiency. Layer-level gradients are sparsified to reduce the communication overhead, which conform to the characteristics of the network structure, and historical accumulation of the approximated gradients is utilized to speed up convergence. We demonstrate the model convergence acceleration and the efficiency of our layer-level selection over existing state-of-the-art works, such as DGC, TernGrad, and 8-Bit quantization. © 2020, Springer Nature Switzerland AG.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Natural image classification based on multi-parameter optimization in deep convolutional neural network

引用

International Journal of Performability engineering 2019年第9期15卷 2515-2521页

作者： Wang, Lei Zhang, Yanning Xi, Runping Ling, Lu School of Computer Northwestern Polytechnical University Xi'an710072 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an710072 China Jiangxi Engineering Technology Research Center of Nuclear Geoscience Data Science and System East China University of Technology Nanchang330013 China

Traditional machine learning algorithms cannot adequately train the parameters of networks using massive data. A deep convolutional neural network based on multi-parameter optimization by the TensorFlow deep learning framework is designed in this paper. In order to improve the training speed and prevent over-fitting, we improve and optimize the multi-parameters, including the batch value, dropout, and momentum in the network structure. The experiment involves training and testing on the standard natural image data sets in cifar-10 and cifar-100. The experimental results show that the method achieve better classification accuracy in less time compared with other algorithms, such as Conv-KN, ImageNet-2010, SVM, LR, and Boosting. © 2019 Totem Publisher, Inc. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：