检索结果-内蒙古大学图书馆

2022 International Conference on Environmental science and Green Energy, ICESGE 2022

作者： Dai, Hongbin Huang, Guangqiu Zeng, Huibin Yu, Rongchuan Wang, Jingjing School of Management Xi'an University of Architecture and Technology Xi'an China School of Mathematics and Computer Science Guangxi Science & Technology Normal University Laibin546199 China

ISBN: (纸本)9781665453165

According to the regional disaster system theory, haze risk assessment indicators for the Fenwei Plain were chosen to effectively study the urban haze hazards in terms of the sensitivity of the disaster-causing environment, the hazard of haze components, and the vulnerability of disaster-bearing bodies. The risk level of haze hazards in Fenwei Plain cities was calculated using Principal Component Analysis (PCA). A quantitative assessment of the haze risk in the Fenwei Plain urban agglomeration was carried out using the extreme gradient boosting method (XGBoost) to investigate the spatial and temporal distribution patterns of PM2.5 and its trends. The results show that Xi'an exhibited the highest haze risk index and the PCA-XGBoost model performed best in the three evaluation indicators. The main factors affecting haze are the economy and population density. © 2022 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

MetaCity: Data-driven sustainable development of complex cities

引用

The Innovation 2025年第2期6卷 88-103,87页

作者： Yunke Zhang Yuming Lin Guanjie Zheng Yu Liu Nicholas Sukiennik Fengli Xu Yongjun Xu Feng Lu Qi Wang Yuan Lai Li Tian Nan Li Dongping Fang Fei Wang Tao Zhou Yong Li Yu Zheng Zhiqiang Wu Huadong Guo Department of Electronic Engineering Beijing National Research Center for Information Science and Technology(BNRist)Tsinghua UniversityBeijing 100084China John Hopcroft Center for Computer Science Shanghai Jiao Tong UniversityShanghai 200240China University of Chinese Academy of Sciences Beijing 100049China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China Institute of Geographic Sciences and Natural Resources Research Chinese Academy of SciencesBeijing 100101China Department of Civil and Environmental Engineering Northeastern UniversityBostonMA 02115USA School of Architecture Tsinghua UniversityBeijing 100084China School of Civil Engineering Tsinghua UniversityBeijing 100084China Big Data Research Center University of Electronic Science and Technology of ChinaChengdu 611731China JD iCity JD Technology&JD Intelligent Cities ResearchBeijing 100176China College of Architecture and Urban Planning Tongji UniversityShanghai 200292China International Research Center of Big Data for Sustainable Development Goals Beijing 100094China Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China These authors contributed equally

Cities are complex systems that develop under complicated interactions among their human and environmental *** generates substantial outcomes and opportunities while raising challenges including congestion,air pollution,inequality,etc.,calling for efficient and reasonable solutions to sustainable ***,booming technologies generate large-scale data of complex cities,providing a chance to propose data-driven solutions for sustainable urban *** paper provides a comprehensive overview of data-driven urban sustainability *** this review article,we conceptualize MetaCity,a general framework for optimizing resource usage and allocation problems in complex cities with data-driven *** this framework,we decompose specific urban sustainable goals,e.g.,efficiency and resilience,review practical urban problems under these goals,and explore the probability of using data-driven technologies as potential solutions to the challenge of *** the basis of extensive urban data,we integrate urban problem discovery,operation of urban systems simulation,and complex decision-making problem solving into an entire cohesive framework to achieve sustainable development goals by optimizing resource allocation problems in complex cities.

关键词： resource usage sustainable development urbanization resilience data driven urban systems simulation complex cities complexity

来源：评论

学校读者我要写书评

暂无评论

Recommending Online Course Resources Based on Knowledge Graph 19th

Recommending Online Course Resources Based on Knowledge Grap...

引用

19th International Conference on Web Information Systems and Applications, WISA 2022

作者： Chen, Xin Sun, Yuhong Zhou, Tong Wen, Yan Zhang, Feng Zeng, Qingtian College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China College of Civil Engineering and Architecture Shandong University of Science and Technology Qingdao266590 China

ISBN: (纸本)9783031203084

Nowadays, it is challenging for college students or lifelong education learners to choose the courses they need under the constant growth of massive online course resources. Therefore the recommendation systems are used to meet their personalized interests. In the scenario of course recommendation, traditional collaborative filtering (CF) is not applicable because of the sparsity of user-item interactions and the cold start problem. Learned from MKR, MKCR is proposed to enhance online courses sources recommendation when the interaction between students and courses is extremely sparse. MKCR is an end-to-end framework that utilizes a knowledge graph embedding task to assist recommendation tasks. The experiment data partially come from the MOOC platform of Chinese universities. The results show MKCR is better performance than other methods in the experiments. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Method on Online Learning Video Recommendation Method Based on Knowledge Graph 12th

A Method on Online Learning Video Recommendation Method Base...

引用

12th IFIP TC 12 International Conference on Intelligent Information Processing, IIP 2022

作者： Chen, Xin Sun, Yuhong Zhou, Tong Zeng, Qingtian Qi, Huafang College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China College of Civil Engineering and Architecture Shandong University of Science and Technology Qingdao266590 China

ISBN: (纸本)9783031039478

The MOOC platforms usually recommend online course resources to users among a large number of courses on platform whose users are almost college students or students by selves. However, the entire course as the recommendation results may ignore student interests in some specific knowledge points, and so may reduce student learning interests. The recommendation not courses but online learning videos of course are researched. The connection between a single learning video and other entities is considered to construct learning video knowledge graph. Based on the end-to-end deep learning framework, a convolutional neural network KGCN-LV is applied in learning videos recommendation, which is integrated learning video knowledge graph. Experimental results on public data set MOOCCube show that the learning video recommendation method based on knowledge graph is up to 5% better than the traditional collaborative filtering method. The recommendation performance is effectively improved, and the recommendation effect is interpretable. © 2022, IFIP International Federation for Information Processing.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

LIAS: A Lightweight Incentive Authentication Scheme for Forensic Services in IoV

LIAS: A Lightweight Incentive Authentication Scheme for Fore...

引用

作者： Zhang, Mingyue Zhou, Junlong Cong, Peijin Zhang, Gongxuan Zhuo, Cheng Hu, Shiyan Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Institute of Computing Technology Chinese Academy of Sciences State Key Laboratory of Computer Architecture Beijing100190 China Zhejiang University Department of Information Science and Electronic Engineering Hangzhou310027 China University of Southampton School of Electronics and Computer Science SouthamptonSO17 1BJ United Kingdom

Internet of Vehicles (IoV) has become an indispensable data sensing and processing platform in Internet of Things (IoT) for intelligent transportation. The mounted cameras on the vehicles along with the fixed roadside cameras are utilized to provide pictorial services for IoV users and law enforcement agencies. For such forensic services, ensuring the security and privacy of vehicles while guaranteeing the efficiency of data transmission among vehicles is important. In this paper, we propose a lightweight incentive authentication scheme (LIAS) for forensic services in IoV. LIAS is developed on a three-tier architecture containing cloud layer, fog layer, and user layer. LIAS uses pairing-free certificateless signcryption, pseudonym update mechanism, and incentive mechanism to realize a secure anonymous authentication efficiently. We conduct correctness and security analysis, as well as performance analysis and evaluation to validate the high security and efficiency of LIAS. Experimental results reveal that, the communication and computation overheads as well as the message delay and packet loss of LIAS are much lower than those of state-of-the-art techniques. Note to Practitioners - This paper is motivated by the security and privacy issues of forensic services in IoV for intelligent transportation. Our goal is to improve the security and privacy of vehicles while guaranteeing the lightweight and incentive of data transmission among the vehicles. Fog-assisted IoV is introduced to fully utilize the capacities of near-user edge devices as well as the connections between fog nodes and devices. However, it still faces the difficulties in ensuring vehicles' security and privacy. Moreover, vehicles' information dissemination could be easily monitored because of the unavoidable defect of wireless communication. Thereby, it is essential to guarantee the security and privacy of vehicles while enhancing the efficiency of vehicles' data transmission during the forensic service.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Efficient adaptation of pre-trained vision transformer via householder transformation 24

Efficient adaptation of pre-trained vision transformer via h...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Wei Dong Yuan Sun Yiting Yang Xing Zhang Zhijun Lin Qingsen Yan Haokui Zhang Peng Wang Yang Yang Hengtao Shen College of Information and Control Engineering Xi'an University of Architecture and Technology School of Computer Science Northwestern Polytechnical University School of Computer Science and Engineering University of Electronic Science and Technology of China School of Computer Science and Engineering University of Electronic Science and Technology of China and School of Computer Science and Technology Tongji University

ISBN: (纸本)9798331314385

A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix. This matrix is decomposed into a product of down-projection and up-projection matrices, with the bottleneck dimensionality being crucial for reducing the number of learnable parameters, as exemplified by prevalent methods like LoRA and Adapter. However, these low-rank strategies typically employ a fixed bottleneck dimensionality, which limits their flexibility in handling layer-wise variations. To address this limitation, we propose a novel PEFT approach inspired by Singular Value Decomposition (SVD) for representing the adaptation matrix. SVD decomposes a matrix into the product of a left unitary matrix, a diagonal matrix of scaling values, and a right unitary matrix. We utilize Householder transformations to construct orthogonal matrices that efficiently mimic the unitary matrices, requiring only a vector. The diagonal values are learned in a layer-wise manner, allowing them to flexibly capture the unique properties of each layer. This approach enables the generation of adaptation matrices with varying ranks across different layers, providing greater flexibility in adapting pre-trained models. Experiments on standard downstream vision tasks demonstrate that our method achieves promising fine-tuning performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Digital Twin in Bridge Rotation Construction 6

Research on the Application of Digital Twin in Bridge Rotati...

引用

6th International Conference on computer Network, Electronic and Automation, ICCNEA 2023

作者： Liu, Yanming Xu, Fei Yang, Zhenghua Deng, Yan Wang, Xing State Key Laboratory of Rail Xi'an China Xi'an Technological University School of Computer Science and Engineering Xi'an China Xi'an Technological University School of Architecture and Engineering Xi'an China Xi'an Technological University School of Ordnance Science and Technology Xi'an China

ISBN: (纸本)9798350305388

With the continuous expansion of china's high-speed railway network, the construction of bridges spanning existing railway lines has become increasingly common. Bridge transition, as a solution for constructing bridges on existing tracks, is crucial for ensuring safety during the construction phase. This research aims to utilize digital twin technology to monitor the construction of bridge transitions and address the limitations of traditional bridge monitoring methods. We employed the Unity3D game engine to create a digital twin virtual scene and facilitated seamless data exchange between the physical and virtual domains using the OPC UA data exchange mechanism. Ultimately, we developed a prototype system for monitoring bridge transition construction. This system effectively monitors critical information and activities during bridge construction, providing early warning capabilities and decision support throughout the construction process. Through the design and implementation of the system prototype, we have confirmed the feasibility of applying digital twin technology in bridge transition construction. © 2023 IEEE.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Removal of Ocular Artifacts from Electroencephalo-Graph by Improving Variational Mode Decomposition

引用

china Communications 2022年第2期19卷 47-61页

作者： Miao Shi Chao Wang Wei Zhao Xinshi Zhang Ye Ye Nenggang Xie Department of Mechanical Engineering Anhui University of TechnologyAnhuiMa’anshan 243002PR China College of Civil Engineering and Architecture Anhui Polytechnic UniversityAnhuiWuhu 241000PR China Department of Computer Science and Technology Anhui University of TechnologyAnhuiMa’anshan 243002PR China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterAnhuiHefei230000PR China Department of Management science and Engineering Anhui University of TechnologyAnhuiMa’anshan 243002PR China

Ocular artifacts in Electroencephalography(EEG)recordings lead to inaccurate results in signal analysis and *** Mode Decomposition(VMD)is an adaptive and completely nonrecursive signal processing *** are two parameters in VMD that have a great influence on the result of signal ***,this paper studies a signal decomposition by improving VMD based on squirrel search algorithm(SSA).It’s improved with abilities of global optimal guidance and opposition based *** original seasonal monitoring condition in SSA is *** feedback of whether the optimal solution is successfully updated is used to establish new seasonal monitoring ***-based learning is introduced to reposition the position of the population in this *** is applied to optimize the important parameters of ***-VMD model is established to remove ocular artifacts from EEG *** have verified the effectiveness of our proposal in a public dataset compared with other *** proposed method improves the SNR of the dataset from-2.03 to 2.30.

关键词： ocular artifact variational mode decomposition squirrel search algorithm global guidance ability opposition-based learning

来源：评论

学校读者我要写书评

暂无评论

Conceptual Reinforcement Learning for Language-Conditioned Tasks

arXiv

引用

arXiv 2023年

作者： Peng, Shaohui Hu, Xing Zhang, Rui Guo, Jiaming Yi, Qi Chen, Ruizhi Du, Zidong Li, Ling Guo, Qi Chen, Yunji SKL of Processors Institute of Computing Technology CAS United States University of Chinese Academy of Sciences China Cambricon Technologies China University of Science and Technology of China China SKL of Computer Science Institute of Software CAS United States

Despite the broad application of deep reinforcement learning (RL), transferring and adapting the policy to unseen but similar environments is still a significant challenge. Recently, the language-conditioned policy is proposed to facilitate policy transfer through learning the joint representation of observation and text that catches the compact and invariant information across environments. Existing studies of language-conditioned RL methods often learn the joint representation as a simple latent layer for the given instances (episode-specific observation and text), which inevitably includes noisy or irrelevant information and cause spurious correlations that are dependent on instances, thus hurting generalization performance and training efficiency. To address this issue, we propose a conceptual reinforcement learning (CRL) framework to learn the concept-like joint representation for language-conditioned policy. The key insight is that concepts are compact and invariant representations in human cognition through extracting similarities from numerous instances in real-world. In CRL, we propose a multi-level attention encoder and two mutual information constraints for learning compact and invariant concepts. Verified in two challenging environments, RTFM and Messenger, CRL significantly improves the training efficiency (up to 70%) and generalization ability (up to 30%) to the new environment dynamics. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Serverless Computation and Related Analysis Based on Matrix Multiplication 1

引用

2nd International Conference on Artificial Intelligence, Robotics, and Communication, ICAIRC 2022

作者： Gong, Jiajun Sun, Haotian Wang, Yilin College of Architecture and Urban Planning Shenyang Jianzhu University Shenyang110000 China College of Stomatology ChongQing Medical University Chengdu610066 China Department of Computer Science and Technology Tsinghua University Beijing100084 China

ISBN: (数字)9789819945542

ISBN: (纸本)9789819945535

This paper investigates the effect of the change in matrix dimensionality and the relationship between function communication time and execution time, as well as the relationship between memory parameters and execution time, on the efficiency and economic cost of computation when using a serverless platform for high-dimensional matrix data. AWS Lambda was used to create the functions, AWS S3 to store the data, perform the high-dimensional matrix fork multiplication and matrix convolution operations, respectively, and S3 to design the monitoring and data analysis interface, and finally, analyze the statistical data. According to the analysis, the average communication time consumption ratio decreases gradually as the number of matrix dimensions increases. The computation time decreases by increasing the number of nodes as far as concurrency allows. As the memory parameter increases, the computation time decreases, and the total cost decreases and then increases. The experimental results show that the impact of communication costs on serverless computing decreases as the size of the data increases. When the concurrency limit is not reached, there is a significant increase in computational efficiency, reducing the time consumed by individual nodes and the overall computing process. Increased memory improves computational efficiency but does not necessarily result in total cost savings. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Matrix algebra

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：