检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2023年第4期4卷 754-763页

作者： Wu, Guohua Fan, Mingfeng Shi, Jianmai Feng, Yanghe Central South University School of Traffic Transportation Engineering Changsha410073 China National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory College of System Engineering Changsha410073 China National University of Defense Technology College of Systems Engineering Changsha410073 China

Coronavirus disease 2019 has brought a great challenge to the supply of daily necessities and medical items for home-quarantined people. Considering the unmanned operation, agility, and use of clean energy of drones, we propose a novel truck-and-drone coordinated delivery system that does not require direct human contact during the delivery process. All final deliveries are completed by the drone while the truck acts as a movable charging station and a carrier, so that the contagion risks are reduced. Moreover, we spilt the whole delivery problem into the customer-clustering problem and the routing problems of both the truck and the drone. An encoder-decoder framework combined with reinforcement learning is created to solve the routing problems without handcrafted designed heuristics. We design the different problem contexts specific to the truck routing problem and the drone routing problem. The experimental results show that the proposed approach has good generality and can consequently be applied to problems of different scales with high time efficiency. © 2020 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Driving into Danger: Adversarial Patch Attack on End-To-End Autonomous Driving systems Using Deep Learning 28

Driving into Danger: Adversarial Patch Attack on End-To-End ...

引用

28th IEEE Symposium on Computers and Communications, ISCC 2023

作者： Wang, Tong Kuang, Xiaohui Li, Hu Du, Qianjin Hu, Zhanhao Deng, Huan Zhao, Gang Institute of System Engineering Academy of Military Sciences Beijing China National Key Laboratory of Science and Technology on Information System Security Beijing China

ISBN: (纸本)9798350300482

Deep learning-based autonomous driving systems have been extensively researched due to their superior performance compared to traditional methods. Specifically, end-To-end deep learning systems have been developed, which directly output control signals for vehicles using various sensor inputs. However, deep learning techniques are vulnerable to security issues, generating adversarial examples that can attack the output of the relevant model. This paper proposes an adversarial example generation method that applies a patch to pedestrians' clothing, which can generate dangerous behaviors when the pedestrian appears within the camera lens, thereby attacking the end-To-end autonomous driving system. The proposed method is validated using the CARLA simulator, and the results demonstrate successful attacks in various weather and lighting conditions, exposing the security vulnerabilities of this type of system. This study highlights the need for further research to address these vulnerabilities and ensure the safety of autonomous driving systems. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

WaveCRNet: Wavelet Transform-Guided Learning for Semantic Segmentation in Adverse Railway Scenes

引用

IEEE Transactions on Intelligent Transportation systems 2025年第6期26卷 8794-8809页

作者： Wang, Zhangyu Liao, Zhihao Wang, Pengcheng Chen, Peng Luo, Wenwen Beihang University State Key Laboratory of Intelligent Transportation System School of Transportation Science and Engineering Beijing100191 China Beihang University School of Cyber Science and Technology Beijing100191 China

Semantic segmentation is pivotal in autonomous train perception, significantly impacting the system's intelligence and reliability. However, its performance in railway scenes is hindered by various challenges, including severe weather conditions, low-light situations, tunnel settings, and diverse and dynamic unstructured scenes. To address these challenges, this study proposes WaveCRNet, a novel architecture for real-time semantic segmentation in challenging conditions, simulating wavelet-constrained PID controller in feature and wavelet space. This study first designs an effective wavelet information enhancement algorithm using a differentiable wavelet transform to bridge the gap between the wavelet and feature information domains. Then, the wavelet-guided attention pag module (WAPM) is introduced to guide the learning and fusion of detailed features based on wavelet priors. Moreover, the traditional wavelet transforms are spectral aliasing and shift sensitivity. Inspired by dual-tree complex wavelet transform (DTCWT), the DTCWT-based channel reconstruction module (DCRM) is designed to assist the channel-based learning of boundary information from coarse to fine. Finally, the proposed architecture is evaluated by the public dataset RailSem19. The experimental results validate the consistent performance gains between accuracy and inference speed, improving by 63.7% mIoU and 87 FPS, surpassing those of the advanced methods for real-time segmentation. © 2000-2011 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Adversarial Example Detection for Deep Neural Networks: A Review 8

Adversarial Example Detection for Deep Neural Networks: A Re...

引用

8th International Conference on Data science in Cyberspace, DSC 2023

作者： Zhao, Chongyang Li, Hu Wang, Dongxia Liu, Ruiqi National Key Laboratory of Science and Technology on Information System Security Beijing China

ISBN: (纸本)9798350331035

Deep neural networks have been widely applied in various critical domains. However, they are vulnerable to the threat of adversarial examples. It is challenging to make deep neural networks inherently robust to adversarial examples, while adversarial example detection offers advantages such as not affecting model classification accuracy. This paper introduces common adversarial attack methods and provides an explanation of adversarial example detection. Recent advances in adversarial example detection methods are categorized into two major classes: statistical methods and adversarial detection networks. The evolutionary relationship among different detection methods is discussed. Finally, the current research status in this field is summarized, and potential future directions are highlighted. © 2023 IEEE.

关键词： adversarial detection adversarial example deep neural network

来源：评论

学校读者我要写书评

暂无评论

Graphene photodetectors integrated with silicon and perovskite quantum dots

引用

Microsystems & Nanoengineering 2024年第3期10卷 21-33页

作者： Kashif Abbas Peirui Ji Naveed Ullah Shareen Shafique Ze Zhang Muhammad Faizan Ameer Shenghan Qin Shuming Yang State Key Laboratory for Manufacturing Systems Engineering Xi’an Jiaotong UniversityXi’an 710049China Department of Microelectronic Science and Engineering Laboratory of Clean Energy Storage and ConversionSchool of Physical Science and TechnologyNingbo Collaborative Innovation Center of Nonlinear Calamity System of Ocean and AtmosphereNingbo UniversityNingbo 315211China

Photodetectors(PDs)play a crucial role in imaging,sensing,communication systems,***(Gr),a leading two-dimensional material,has demonstrated significant potential for photodetection in recent ***,its relatively weak interaction with light poses challenges for practical *** integration of silicon(Si)and perovskite quantum dots(PQDs)has opened new avenues for Gr in the realm of next-generation *** review provides a comprehensive investigation of Gr/Si Schottky junction PDs and Gr/PQD hybrid PDs as well as their *** operating principles,design,fabrication,optimization strategies,and typical applications of these devices are studied and *** these discussions,we aim to illuminate the current challenges and offer insights into future directions in this rapidly evolving field.

关键词： quantum discussions summarized

来源：评论

学校读者我要写书评

暂无评论

Heteronuclear Magnetisms with Ultracold Spinor Bosonic Gases in Optical Lattices

引用

Chinese Physics Letters 2024年第2期41卷 69-82页

作者： Yongqiang Li Chengkun Xing Ming Gong Guangcan Guo Jianmin Yuan Department of Physics National University of Defense TechnologyChangsha 410073China Hunan Key Laboratory of Extreme Matter and Applications National University of Defense TechnologyChangsha 410073China Key Lab of Quantum Information(CAS) University of Science and Technology of ChinaHefei 230026China CAS Key Laboratory of Quantum Information University of Science and Technology of ChinaHefei 230026China Synergetic Innovation Center of Quantum Information and Quantum Physics University of Science and Technology of ChinaHefei 230026China Hefei National Laboratory University of Science and Technology of ChinaHefei 230088China Department of Physics Graduate School of China Academy of Engineering PhysicsBeijing 100193China

Motivated by recent realizations of spin-1 NaRb mixtures in the experiments[***.114,255301(2015);***.128,223201(2022)],we investigate heteronuclear magnetism in the Mott-insulating *** from the identical mixtures where the boson statistics only admits even parity states from angular momentum composition,for heteronuclear atoms in principle all angular momentum states are allowed,which can give rise to new magnetic *** various magnetic phases can be developed over these degenerate spaces,the concrete symmetry breaking phases depend on not only the degree of degeneracy but also the competitions from many-body *** unveil these rich phases using the bosonic dynamical mean-field theory *** phases are characterized by various orders,including spontaneous magnetization order,spin magnitude order,singlet pairing order,and nematic order,which may coexist specially in the regime with odd *** we address the possible parameter regimes for observing these spin-ordered Mott phases.

关键词： parity momentum allowed

来源：评论

学校读者我要写书评

暂无评论

Sequence structure controllable polymerization-induced self-assembly

引用

science China Chemistry 2024年第1期67卷 390-397页

作者： Zi-Xuan Chang Ren-Man Zhu Chun-Yan Hong Wen-Jian Zhang Department of Polymer Science and Engineering University of Science and Technology of ChinaHefei 230026China Institute of Physical Science and Information Technology Anhui UniversityHefei 230601China Key Laboratory of Environment-Friendly Polymeric Materials of Anhui Province Anhui UniversityHefei 230601China

Polymerization-induced self-assembly(PISA)combines synthesis and self-assembly of artificial polymers in one-pot,which brings us one step closer to emulating ***,the reported PISA formulations primarily focus on developing nano-objects with new chemical compositions and rarely on structural regulation of polymers with specific ***,sequence structure controllable polymerization-induced self-assembly(SCPISA)is reported by using 7-(2-methacryloyloxyethoxy)-4-methylcoumarin(CMA)as a *** the copolymerization of 2-hydroxyethyl methacrylate(HEMA)and CMA,controlled incorporation of CMA units into the polymer chains can be realized by programmable light/heat ***-based P(HEMA-co-CMA)copolymers with the same composition but different sequence structures generate a range of ***,the morphologies of the resultant nano-objects can also be controlled by regulating the feed molar ratio of CMA and HEMA,which is similar to the conventional PISA,but the synthesis procedure is obviously simplified in *** versatility of the methodology is further demonstrated by the fabrication of different functional nano-objects with sequence structure-dependent morphologies in SCPISA systems with different functional monomers.

关键词： polymerization-induced self-assembly sequence-controlled polymers PET-RAFT polymerization

来源：评论

学校读者我要写书评

暂无评论

Boosting bulk photovoltaic effect in transition metal dichalcogenide by edge semimetal contact

引用

Light(science & Applications) 2025年第1期14卷 197-205页

作者： Shuang Qiao Jihong Liu Chengdong Yao Ni Yang Fangyuan Zheng Wanqing Meng Yi Wan Philip C.Y.Chow Dong-Keun Ki Lijie Zhang Yumeng Shi Lain-Jong Li Hebei Key Laboratory of Optic-Electronic Information and Materials College of Physics Science and TechnologyHebei University071002BaodingChina Department of Mechanical Engineering The University of Hong KongHong KongChina Department of Physics and HK Institute of Quantum Science&Technology The University of Hong KongHong KongChina Key Laboratory of Carbon Materials of Zhejiang Province College of Chemistry and Materials EngineeringWenzhou UniversityWenzhouChina Key Laboratory of Luminescence and Optical Information Ministry of EducationSchool of Physical Science and EngineeringBeijing Jiaotong University100044BeijingChina

Oxide materials with a non-centrosymmetric structure exhibit bulk photovoltaic effect(BPVE)but with a low cell *** the past few years,relatively larger BPVE coefficients have been reported for two-dimensional(2D)layers and stacks with asymmety-induced spontaneous ***,we report a crucial breakthrough in boosting the BPVE in 3R-MoS2 by adopting edge contact(EC)geometry using bismuth semimetal *** clear contrast to the typically used top contact(TC)geometry,the EC metal which strongly adheres to the edges and the subtrates can induce a pronounced tensile strain to the 3R-MoS2,and the lateral contact geometry allows to completely access to in-plane polarization from underneath layers reachable by light,leading to>100 times of BPVE enhancement in *** further design a 3R-MoS2/WSe2 heterojunction to demonstrate constructive coupling of BPVE with the conventional photovoltaic effect,indicating their potential in photodetectors and photovoltaic devices.

关键词： effect geometry breakthrough

来源：评论

学校读者我要写书评

暂无评论

PBCounter:weighted model counting on pseudo-boolean formulas

引用

Frontiers of Computer science 2025年第3期19卷 55-63页

作者： Yong LAI Zhenghang XU Minghao YIN College of Computer Science and Technology Jilin UniversityChangchun 130012China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin UniversityChangchun 130012China School of Computer Science and Information Technology Northeast Normal UniversityChangchun 130017China

In Weighted Model Counting(WMC),we assign weights to literals and compute the sum of the weights of the models of a given propositional formula where the weight of an assignment is the product of the weights of its *** current WMC solvers work on Conjunctive Normal Form(CNF)***,CNF is not a natural representation for human-being in many *** by the stronger expressive power of Pseudo-Boolean(PB)formulas than CNF,we propose to perform WMC on PB *** on a recent dynamic programming algorithm framework called ADDMC for WMC,we implement a weighted PB counting tool *** compare PBCounter with the state-of-the-art weighted model counters SharpSAT-TD,ExactMC,D4,and ADDMC,where the latter tools work on CNF with encoding methods that convert PB constraints into a CNF *** experiments on three domains of benchmarks show that PBCounter is superior to the model counters on CNF formulas.

关键词： weighted model counting pseudo-boolean constraint algebraic decision diagrams preprocessing techniques

来源：评论

学校读者我要写书评

暂无评论

Multi-View Graph Embedding Learning for Image Co-Segmentation and Co-Localization

引用

IEEE Transactions on Circuits and systems for Video technology 2024年第6期34卷 4942-4956页

作者： Huang, Aiping Li, Lijian Zhang, Le Niu, Yuzhen Zhao, Tiesong Lin, Chia-Wen Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou350108 China Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou350108 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering The Fujian Science and Technology Innovation Laboratory for Optoelectronic Information Fuzhou350108 China Institute of Communications Engineering National Tsing Hua University Department of Electrical Engineering Hsinchu30013 Taiwan

Image co-segmentation and co-localization exploit inter-image information to identify and extract foreground objects with a batch mode. However, they remain challenging when confronted with large object variations or complex backgrounds. This paper proposes a multi-view graph embedding (MV-Gem) learning scheme which integrates diversity, robustness and discernibility of object features to alleviate this phenomenon. To encourage the diversity, the deep co-information containing both low-layer general representations and high-layer semantic information is generated to form a multi-view feature pool for comprehensive co-object description. To enhance the robustness, a multi-view adaptive weighted learning is formulated to fuse the deep co-information for feature complementation. To ensure the discernibility, the graph embedding and sparse constraint are embedded into the fusion formulation for feature selection. The former aims to inherit important structures from multiple views, and the latter further selects important features to restrain irrelevant backgrounds. With these techniques, MV-Gem gradually recovers all co-objects through optimization iterations. Extensive experimental results on real-world datasets demonstrate that MV-Gem is capable of locating and delineating co-objects in an image group. © 1991-2012 IEEE.

关键词： Semantics

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：