检索结果-内蒙古大学图书馆

FISS GAN:A Generative Adversarial Network for Foggy Image Semantic Segmentation

IEEE/CAA Journal of Automatica Sinica 2021年第8期8卷 1428-1439页

作者： Kunhua Liu Zihao Ye Hongyan Guo Dongpu Cao Long Chen Fei-Yue Wang School of Computer Science and Engineering Sun Yat-sen UniversityGuangzhou 510006China State Key Laboratory of Automotive Simulation and Control and the Department of Control Science and Engineering Jilin University(Campus Nanling)Changchun 130025China Mechanical and Mechatronics Engineering Department at the University of Waterloo 200 University Avenue West WaterlooON N2L 3G1Canada State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China

Because pixel values of foggy images are irregularly higher than those of images captured in normal weather(clear images),it is difficult to extract and express their *** method has previously been developed to directly explore the relationship between foggy images and semantic segmentation *** investigated this relationship and propose a generative adversarial network(GAN)for foggy image semantic segmentation(FISS GAN),which contains two parts:an edge GAN and a semantic segmentation *** edge GAN is designed to generate edge information from foggy images to provide auxiliary information to the semantic segmentation *** semantic segmentation GAN is designed to extract and express the texture of foggy images and generate semantic segmentation *** on foggy cityscapes datasets and foggy driving datasets indicated that FISS GAN achieved state-of-the-art performance.

关键词： Edge GAN foggy images foggy image semantic segmentation GAN semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Topological properties and localization transition in a one-dimensional non-Hermitian lattice with a slowly varying potential

引用

Physical Review B 2022年第10期105卷 104201-104201页

作者： Siqing Li Mengyao Li Yi Gao Peiqing Tong Center for Quantum Transport and Thermal Energy Science Jiangsu Key Laboratory on Opto-Electronic Technology School of Physics and Technology Nanjing Normal University Nanjing 210023 China Jiangsu Key Laboratory for Numerical Simulation of Large Scale Complex Systems School of Physics and Technology Nanjing Normal University Nanjing 210023 China

We explore the eigenenergy distribution, localization transition, and topological property of a one-dimensional non-Hermitian lattice with a slowly varying potential, which does not possess parity-time (PT) symmetry. We found that, in contrast to PT-symmetric systems whose eigenenergies can stay real until the PT-symmetry breaking point, the eigenenergies in the present system are fully complex and their distribution in the complex plane depends on the parameters. As non-Hermiticity is introduced into the system, also depending on the parameters, the eigenstates may show a crossover behavior from fully extended to fully localized as non-Hermiticity is increased, or there will be a sharp localization transition at finite non-Hermiticity. Nevertheless, this non-Hermitian system is proven to be topologically trivial, thus we conclude that in general non-Hermitian systems, the localization transition is not always of a topological nature.

关键词： Anderson localization Topological phase transition Non-Hermitean systems PT-symmetry

来源：评论

学校读者我要写书评

暂无评论

Mitigating Over-Trust in Chat Companion Robot Interaction Using Augmented Reality 23

Mitigating Over-Trust in Chat Companion Robot Interaction Us...

引用

Proceedings of the 4th International Conference on Artificial Intelligence and Computer Engineering

作者： Guobao Wang Changshun Zhao Ying Liu Di He Yuqing Wang Kaiyue Zhang Yanshan University/Jiangsu Xuzhou Construction Machinery Group Co. Ltd. China Officers College of PAP China National Key Laboratory for Complex Systems Simulation China University of Electronic Science and Technology of China China Jiangsu Province Tongshan Secondary Vocational School China

ISBN: (纸本)9798400708831

This study aims to explore the effects of different human-machine interfaces, system performance, and robot interaction modalities on over-trust in chat companion robot systems. We designed and implemented three types of interfaces: 2D Virtual Interface + Virtual Robot, 3D Augmented Reality Interface + AR-based Virtual Robot, and 3D Real World + NAO Physical Robot. We also manipulated the system performance (high or low) and the robot interaction modality (language, gesture, or both). We conducted a user study with 30 participants, who interacted with the chat companion robot under different conditions and rated their trust, distrust, and human-robot distance. We also measured the user experience in terms of usefulness and ease of use. The results showed that the type of interface significantly influenced the trust, distrust, and human-robot distance of the users, and that the 3D augmented reality interface was the most effective in enhancing trust and reducing distrust and distance. The performance of the system also affected the trust and distance of the users, and the gesture interface was the most sensitive to the performance variation. The modality of the interaction did not have a significant impact on the dependent variables. The user experience ratings also indicated that the 3D augmented reality interface was the most useful and easy to use. The implications and limitations of these findings are discussed in the paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm 29

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

29th IEEE International Conference on Parallel and Distributed systems, ICPADS 2023

作者： Zeng, Yan Huang, Chengchuang Ni, Yijie Zhou, Chunbao Zhang, Jilin Wang, Jue Zhou, Mingyao Xue, Meiting Zhang, Yunquan Hangzhou Dianzi University School of Computer Science and Technology Hangzhou310018 China Ministry of Education Key Laboratory for Modeling and Simulation of Complex Systems Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China Hangzhou Dianzi University School of ITMO Joint Institute Hangzhou310018 China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing100086 China HuaWei China Institute of Computing Technology of the Chinese Academy of Sciences State Key Laboratory of Computer Architecture Beijing100086 China

ISBN: (纸本)9798350330717

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network's dataflow graph and device cluster's topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method. © 2023 IEEE.

关键词： Auto-Parallel Distributed machine learning Genetic algorithm Integer linear programming Model parallelism

来源：评论

学校读者我要写书评

暂无评论

A Solution Analysis of U.S. Weapon Equipment systems-of-systems Development and Application 7

A Solution Analysis of U.S. Weapon Equipment Systems-of-Syst...

引用

7th International Conference on Information science and Control Engineering, ICISCE 2020

作者： Lin, Menglong Yi, Shuanghui Zhang, Mengmeng Shu, Zhen National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory Changsha China National Key Laboratory for Complex System Simulation Beijing China

ISBN: (纸本)9781728164069

In recent years, the development and deployment of the U.S. weapon equipment systems-of-systems (SoS) have yielded rich research results. However, there are still large gaps in the SoS development, joint testing, and design and acquisition of our own equipment SoS. The barriers of these steps have not yet been opened up. This article mainly analyzes the solutions of the U.S. weapon equipment SoS from three aspects, such as capability-based requirement generation and architecture design technology, interconnected-oriented integration test technology, and weapon equipment design and acquisition technology based on complex adaptive systems. We explore key technologies involved in order to form an overall understanding and explore related research approaches. © 2020 IEEE.

关键词： System of systems

来源：评论

学校读者我要写书评

暂无评论

Investigation of Allopurinol binding mechanism to allele HLA-A∗33:03 by using Molecular Dynamics simulation 46

Investigation of Allopurinol binding mechanism to allele HLA...

引用

46th Vietnam Conference on Theoretical Physics, VCTP 2021

作者： Pham, Oanh P. Lai, Hien T.T. Tran, Duong B. Le, Linh T. P. Nguyen, Anh Thi Van Nguyen, Hang Thi Thu Nguyen, Toan T. Key Laboratory for Multiscale Simulation of Complex Systems VNU University of Science Vietnam National University 334 Nguyen Trai Street Thanh Xuan Dist Hanoi120000 Viet Nam Key Laboratory of Enzyme and Protein Technology VNU University of Science Vietnam National University 334 Nguyen Trai Street Thanh Xuan Dist Hanoi120000 Viet Nam Department of Theoretical Physics VNU University of Science 334 Nguyen Trai Street Thanh Xuan Dist Hanoi120000 Viet Nam

Allopurinol (ALP), a xanthine oxidase inhibitor, is an FDA-approved urate-lowering medication used to treat Gout, prevent tumor lysis syndrome, and prevent recurrent calcium nephrolithiasis in hyperuricosuria patients. However, it has been known as a common cause of severe cutaneous adverse drug reactions (SCAR) including Stevens-Johnson syndrome (SJS) and toxic epidermal necrolysis (TEN), hypersensitivity syndrome/drug reaction with eosinophilia and systemic symptoms (HSS/DRESS), especially in patients carrying the Human Leukocyte Antigens allele HLA-B∗58:01, which is more prevalent in Asian population. However, although patients do not carry the HLA-B∗58:01 allele, they still exhibit allopurinol-induced SCAR. Surprisingly, a large number of these patients have the HLA-A∗33:03 allele. In this research, we investigated the binding of ALP to the HLA-A∗33:03 structure using Molecular Dynamics (MD) simulation. Our results showed that the complex of HLA-A∗33:03 and ALP was stable after 100000 ps simulation time. ALP had strong interactions with three important residues locating in the active site of HLA-A∗33:03, which include the seven amino acid residues Val 76, Asp 77, Leu 81, Ile 95, Gln 96, Asp 116, and Tyr 123. This data suggests that ALP has strong binding affinity for this allele. Thus, in addition to HLA-B∗58:01, HLA-A∗33:03 may be a potential screening marker before prescribing Allopurinol for Gout treatment. © Published under licence by IOP Publishing Ltd.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Exploring the effects of phase modulation on the dynamics of the kicked rotor systems

引用

Physical Review E 2022年第1期105卷 014212-014212页

作者： Mengyao Li Yingying Xiao Yongchun Tao Yi Gao Peiqing Tong Center for Quantum Transport and Thermal Energy Science Jiangsu Key Lab on Opto-Electronic Technology School of Physics and Technology Nanjing Normal University Nanjing 210023 China School of Physics and Technology Jiangsu Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Nanjing 210023 China

Inspired by the recent experimental progress in the time-driven phase transition in quantum chaos, we investigate comprehensively the energy diffusion of a kicked rotor in the presence of phase modulation. In the classical case, we found that there always exists anomalous diffusion as long as the phase is modulated periodically and changes by 0 or π from kick to kick. On the contrary, for quasiperiodic and random phase modulation, anomalous diffusion is suppressed. On the other hand, in the quantum case, there exist only ballistic energy diffusion and dynamical localization in the standard and periodically shifted cases, while random phase modulation destroys the quantum coherence and totally suppresses the dynamical localization. Furthermore, the quasiperiodic phase modulation is an intermediate phase between the standard case and the random one. In both the classical and quantum cases, quasiperiodic phase modulation is inequivalent to random phase modulation at large kicking times (>103), thus caution has to be taken when dealing with these two kinds of phase modulation in experiments.

关键词： Cold atoms & matter waves 1-dimensional systems

来源：评论

学校读者我要写书评

暂无评论

A Survey of Knowledge Enhanced Pre-trained Models

arXiv

引用

arXiv 2021年

作者： Yang, Jian Hu, Xinyu Xiao, Gang Shen, Yulong Computer Science and Technology Xidian University Xi’an China National Key Laboratory for Complex Systems Simulation Beijing China

Pre-trained language models learn informative word representations on a large-scale text corpus through self-supervised learning, which has achieved promising performance in fields of natural language processing (NLP) after fine-tuning. These models, however, suffer from poor robustness and lack of interpretability. We refer to pre-trained language models with knowledge injection as knowledge-enhanced pre-trained language models (KEPLMs). These models demonstrate deep understanding and logical reasoning and introduce interpretability. In this survey, we provide a comprehensive overview of KEPLMs in NLP. We first discuss the advancements in pre-trained language models and knowledge representation learning. Then we systematically categorize existing KEPLMs from three different perspectives. Finally, we outline some potential directions of KEPLMs for future research. Copyright © 2021, The Authors. All rights reserved.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Privacy sensitive large-margin model for face de-identification 1st

Privacy sensitive large-margin model for face de-identifica...

引用

1st International Conference on Neural Computing for Advanced Applications, NCAA 2020

作者： Guo, Zhiqiang Liu, Huigui Kuang, Zhenzhong Nakashima, Yuta Babaguchi, Noboru Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Osaka University Osaka Japan

ISBN: (纸本)9789811576690

There is an increasing concern of face privacy protection along with the wide application of big media data and social networks due to free online data release. Although some pioneering works obtained some achievements, they are not sufficient enough for sanitizing the sensitive identity information. In this paper, we propose a generative approach to de-identify face images yet preserving the non-sensitive information for data reusability. To ensure a high privacy level, we introduce a large-margin model for the synthesized new identities by keeping a safe distance with both the input identity and existing identities. Besides, we show that our face de-identification operation follows the (Formula Presented)-differential privacy rule which can provide a rigorous privacy notion in theory. We evaluate the proposed approach using the vggface dataset and compare with several state-of-the-art methods. The results show that our approach outperforms previous solutions for effective face privacy protection while preserving the major utilities. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Privacy-preserving techniques

来源：评论

学校读者我要写书评

暂无评论

FedAG:A Federated Learning Method Based on Data Importance Weighted Aggregation

FedAG:A Federated Learning Method Based on Data Importance W...

引用

IEEE International Conference on Communications in China (ICCC)

作者： Mengchu Xu Yan Zeng Meiting Xue Ji-Lin Zhang Jian Wan Mingyao Zhou Yilin Wen Yukun Shi School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education Hangzhou China Zhejiang Engineering Research Center of Data Security Governance Hangzhou China School of Cyberspace Hangzhou Dianzi University Hangzhou China Huawei Enterprise Communication Technology Co Hangzhou China

Federated learning is a distributed machine learning approach that trains models with multiple clients and data locally. However, the existing methods ignore the differences between local models caused by the data heterogeneity, and give a high aggregation weight for the low-quality local model, which leads to low accuracy of the global model. For this problem, we propose a federated learning method based on data importance weighted aggregation, FedAG. It constructs an evaluation model of data importance based on the data distribution skewness, data volume, and data quality of clients, and aggregates local models with different weights computed by the evaluation model of data importance into a global model. We make experiments on five datasets including EMNIST, MNIST, and CIFAR-10. The results show that the accuracy of FedAG is respectively improved by 6.5%, 1.8%, 1.3% and 2.1%, compared with FedAvg, FedProx, FedVar, and Scaffold algorithms.

关键词：

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：