检索结果-内蒙古大学图书馆

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Bai, Ruina Bai, Qi Huang, Ruizhang Chen, Yanping Qin, Yongbin Text Computing & Cognitive Intelligence Engineering Research Center National Education Ministry College of Computer Science and Technology Guizhou University Guiyang550025 China State Key Laboratory of Public Big Data Guizhou University Guiyang550025 China School of Mathematical Sciences Zhejiang University Hangzhou310058 China

ISBN: (纸本)9782493814104

We introduce a multi-view document clustering model called DMsECN (Deep Multi-structure Ensemble Clustering Network), comprising a multi-structure processor and a hybrid ensemble clustering module. Unlike existing models, DMsECN distinguishes itself by creating a consensus structure from multiple clustering structures. The multi-structure processor comprises two stages, each contributing to the extraction of clustering structures that preserve both consistency and complementarity across multiple views. Representation learning extracts both view and view-fused representations from multi-views through the use of contrastive learning. Subsequently, multi-structure learning employs distinct view clustering guidance to generate the corresponding clustering structures. The hybrid ensemble clustering module merges two ensemble methods to amalgamate multiple structures, producing a consensus structure that guarantees both the separability and compactness of clusters within the clustering results. The attention-based ensemble primarily concentrates on learning the contribution weights of diverse clustering structures, while the similarity-based ensemble employs cluster assignment similarity and cluster classification dissimilarity to guide the refinement of the consensus structure. Experimental results demonstrate that DMsECN outperforms other models, achieving new state-of-the-art results on four multi-view document clustering datasets. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Structure (composition)

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Order Variation Mathematical Modeling of Ship Maneuvering Motion Under Environmental Changes

An Adaptive Order Variation Mathematical Modeling of Ship Ma...

引用

OCEANS

作者： Qi Dong Ning Wang Cunlong Zou Lizhu Hao Kai Qu School of Marine Engineering Dalian Maritime University Dalian China State Key Laboratory of Hydrodynamics China Ship Scientific Research Center Wuxi China

ISBN: (数字)9798350362077

ISBN: (纸本)9798350362084

The prediction of ship motion under complex sea conditions not only plays a guiding role in the overall design of the ship but also is important for the ship's maneuverability and safety. Considering that ship motion state and trajectory prediction in wind and wave environments can support ship control and decision-making and reduce the overall operational risk of smart ships. In this paper, an adaptive order variation mathematical modeling (AOVMM) is developed for ship maneuvering motions under environmental changes by using the Taylor expansion and extended Kalman filter (EKF). To improve the prediction accuracy of the model, the order change of the hydrodynamic coefficients in the model is adapted to the environmental changes by the goodness of fit $(\boldsymbol{R}^{2})$ . The various maneuvers are cross-tested in different environments, using the optimal prediction model with calm water and wind and wave environments for predicting motion states and trajectories, respectively. The prediction results show that the proposed AOVMM can weaken the influence of the environment and significantly improve the accuracy of ship maneuvering motion prediction.

关键词： Adaptation models Accuracy Predictive models Turning Hydrodynamics Taylor series Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Research on water heat coupling model of riparian zone based on soil thermal conductivity model 6

Research on water heat coupling model of riparian zone based...

引用

2022 6th International Conference on Hydrodynamics, Energy and Electric Power System, HEEPS 2022

作者： Ma, Chen Ren, Jie Dai, Juan Ma, Zhaoyang Wang, Fan State Key Laboratory of Eco-hydraulics in Northwest Arid Region Xi'An University of Technology shaanxi Xi'an710048 China State Key Laboratory of Hydraulics and Mountain River Engineering Sichuan University Sichuan Chengdu610065 China Changjiang River Scientific Research Institute Hubei Wuhan430010 China

In recent years, the research on the process of water and heat transfer in the riparian zone has become more and more extensive, a more accurate riparian water and heat coupling model is helpful for us to understand the law of water and heat transfer in the riparian zone. The hydro thermal coupling model of riparian zone is constructed based on different soil thermal conductivity models, the simulation effects of different models are verified and compared by using the experimental data, the parameter sensitivity analysis of the built model is carried out to determine the main parameters affecting the output of model temperature field, and the influence of revetment structure on the process of hydro thermal transport in riparian zone is simulated. The results show that: 1. the Hydrothermal Coupling Model of riparian zone based on Johansen thermal conductivity model has the best simulation effect and high reliability. 2. The permeability coefficient (ks ) and porosity (n) have the most significant influence on the temperature simulation results, and the parameter sensitivity is the highest. 3. The revetment structure hinders the infiltration of surface water into the riparian zone in the horizontal direction, reduces the infiltration water level and temperature fluctuation in the riparian zone. © Published under licence by IOP Publishing Ltd.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning-based controller for obstacle avoidance of deep sea mining vehicles 33rd

Deep reinforcement learning-based controller for obstacle av...

引用

33rd International Ocean and Polar engineering Conference, ISOPE 2023

作者： Chen, Qihang Yang, Jianmin Wang, Peng Liang, Zhixuan Lu, Changyu State Key Laboratory of Ocean Engineering Shanghai Jiao Tong University Shanghai China Yazhou Bay Institute of Deepsea SCI-TECH Shanghai Jiao Tong University Hainan Sanya China Department of Computing The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9781880653807

Research on deep-sea mining vehicles (DSMVs) is being actively conducted for deep-sea resource development. Developing the obstacle avoidance performance of DSMV will effectively improve the mobility and safety of the DSMV operation process. In this paper, the Modified Twin Delayed Deep Deterministic Policy Gradient (MTD3) algorithm is adapted to train a controller for obstacle avoidance. A Markov decision process model including state, action, and reward functions is designed, and a suitable reinforcement-learning training environment is designed. The obstacle-avoidance ability of the controller is verified by the simulation tests of avoiding the randomly generated one to five obstacles in each episode. © 2023 by the International Society of Offshore and Polar Engineers (ISOPE).

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

High-performance optimization of SM4-GCM based on FPGA

High-performance optimization of SM4-GCM based on FPGA

引用

2021 International Conference on Advanced computing and Endogenous Security, ICACES 2021

作者： Lv, Shun Sen Li, Bin Chen, Xiaojie Zhou, Qinglei School of Information Engineering Zhengzhou University Zhengzhou China State Key Laboratory of Mathmatical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781665424493

SM4-GCM is an encryption algorithm with authentication function. The algorithm achieves the purpose of data security and information integrity. The SM4-GCM algorithm, implemented using traditional software methods, has low throughput and high resource consumption. In order to further improve the algorithm performance, this paper uses FPGA to optimize the SM4-GCM algorithm to achieve full-pipeline parallel acceleration. Firstly, the SM4 module is optimized using pipelining techniques. Then, the GHASH module is optimized using the Karatsuba algorithm and fast reduction. Finally, a loosely coupled architecture is used to connect various modules with asynchronous FIFOs, which improves the resource utilization and throughput of the FPGA circuit. The experimental results show that the throughput of the optimized SM4-GCM algorithm reaches 28.8 Gbps. It is better than other schemes, has a higher throughput, and meets the actual application requirements. © 2022 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Dendritic integration inspired artificial neural networks capture data correlation 24

Dendritic integration inspired artificial neural networks ca...

引用

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

作者： Chongming Liu Jingyang Ma Songting Li Douglas Zhou School of Mathematical Sciences and Institute of Natural Sciences Shanghai Jiao Tong University Shanghai China School of Mathematical Sciences and Institute of Natural Sciences and Ministry of Education Key Laboratory of Scientific and Engineering Computing Shanghai Jiao Tong University Shanghai China School of Mathematical Sciences and Institute of Natural Sciences and Ministry of Education Key Laboratory of Scientific and Engineering Computing and Shanghai Frontier Science Center of Modern Analysis Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798331314385

Incorporating biological neuronal properties into Artificial Neural Networks (ANNs) to enhance computational capabilities is under active investigation in the field of deep learning. Inspired by recent findings indicating that dendrites adhere to quadratic integration rule for synaptic inputs, this study explores the computational benefits of quadratic neurons. We theoretically demonstrate that quadratic neurons inherently capture correlation within structured data, a feature that grants them superior generalization abilities over traditional neurons. This is substantiated by few-shot learning experiments. Furthermore, we integrate the quadratic rule into Convolutional Neural Networks (CNNs) using a biologically plausible approach, resulting in innovative architectures—Dendritic integration inspired CNNs (Dit-CNNs). Our Dit-CNNs compete favorably with state-of-the-art models across multiple classification benchmarks, e.g., ImageNet-1K, while retaining the simplicity and efficiency of traditional CNNs. All source code are available at https://***/liuchongming1999/Dendritic-integration-inspired-CNN-NeurIPS-2024.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Risk-Aware SDN Defense Framework Against Anti-Honeypot Attacks Using Safe Reinforcement Learning

Risk-Aware SDN Defense Framework Against Anti-Honeypot Attac...

引用

作者： Gao, Dongying Guo, Caiwei Zhang, Yi Ji, Wen Lv, Zhilei Li, Zheng Zhang, Kunsan Lin, Ruibin State Grid Fujian Information & Telecommunication Company Fuzhou China Department of Information and Communication Engineering & Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Xiamen China State Grid Zhangzhou Power Supply Company Zhangzhou China State Grid Info-Telecom Great Power Science and Technology Co. Ltd. Fuzhou China

The development of multiple attack methods by external attackers in recent years poses a huge challenge to the security and efficient operation of software-defined networks (SDN), which are the core of operational controllers and data storage. Therefore, it is critical to ensure that the normal process of network interaction between SDN servers and users is protected from external attacks. In this paper, we propose a risk-aware SDN defense framework based on safe reinforcement learning (SRL) to counter multiple attack actions. Specifically, the defender uses SRL to maximize the utility by choosing to provide a honeypot service or pseudo-honeypot service within predefined security constraints, while the external attacker maximizes the utility by choosing an anti-honeypot attack or masquerade attack. To describe the system risk in detail, we introduce the risk level function to model the simultaneous dynamic attack and defense processes. Simulation results demonstrate that our proposed risk-aware scheme improves the defense utility by 17.5% and 142.4% and reduces the system risk by 42.7% and 59.6% compared to the QLearning scheme and the Random scheme, respectively. © 2024 John Wiley & Sons Ltd.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

LinNet: Linear Network for Efficient Point Cloud Representation Learning 38

LinNet: Linear Network for Efficient Point Cloud Representat...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Deng, Hao Jing, Kunlei Cheng, Shengmei Liu, Cheng Ru, Jiawei Bo, Jiang Wang, Lin State-Province Joint Engineering and Research Center of Advanced Networking and Intelligent Information Services School of Information Science and Technology Northwest University China Shaanxi Key Laboratory of Higher Education Institution of Generative Artificial Intelligence and Mixed Reality China School of Software Engineering Xi'an Jiaotong University China Department of Computing The Hong Kong Polytechnic University Hong Kong

Point-based methods have made significant progress, but improving their scalability in large-scale 3D scenes is still a challenging problem. In this paper, we delve into the point-based method and develop a simpler, faster, stronger variant model, dubbed as LinNet. In particular, we first propose the disassembled set abstraction (DSA) module, which is more effective than the previous version of set abstraction. It achieves more efficient local aggregation by leveraging spatial anisotropy and channel anisotropy separately. Additionally, by mapping 3D point clouds onto 1D space-filling curves, we enable parallelization of downsampling and neighborhood queries on GPUs with linear complexity. LinNet, as a purely point-based method, outperforms most previous methods in both indoor and outdoor scenes without any extra attention, and sparse convolution but merely relying on a simple MLP. It achieves the mIoU of 73.7%, 81.4%, and 69.1% on the S3DIS Area5, NuScenes, and SemanticKITTI validation benchmarks, respectively, while speeding up almost 10x times over PointNeXt. Our work further reveals both the efficacy and efficiency potential of the vanilla point-based models in large-scale representation learning. Our code will be available at https://***/DengH293/LinNet. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Platelet membrane-camouflaged bioactive glass nano-formulations for enhanced drug delivery in the treatment of acute arterial thrombosis

引用

Acta Biomaterialia 2025年 199卷 324-336页

作者： Ji, Minglin Tang, Qinying Olatunji, Olanrewaju Yaasir Ge, Rufei Ying, Yue Pan, Jianwei Yunusov, Khaydar E. Jiang, Guohua School of Materials Science and Engineering Zhejiang Sci-Tech University Hangzhou310018 China International Scientific and Technological Cooperation Base of Intelligent Biomaterials and Functional Fibers of Zhejiang Province Hangzhou China The First Affiliated Hospital of School of Medicine Zhejiang University Hangzhou310058 China Institute of Polymer Chemistry and Physics Uzbekistan Academy of Sciences Tashkent100128 Uzbekistan State Key Laboratory of Bio-based Fiber Materials Zhejiang Sci-Tech University Hangzhou310018 China

Thrombus treatment remains a significant challenge, primarily due to factors such as the short half-life of thrombolytic agents, suboptimal drug utilization, and limited therapeutic efficacy. In this study, we developed a platelet membrane-camouflaged bioactive glass nanoparticles (BGs) as drug carriers to load thrombolytic agent urokinase (UK) and anticoagulant drug tirofiban (TF). UK and TF were firstly incorporated onto BGs, and followed by a camouflage of polydopamine (PDA) and platelet membrane (PM) to form composite nano-formulation (TUBGs@PP). This composite nano-formulation leverages the PM camouflage to enhance its biocompatibility, prolong circulation time in vivo, and extend the half-life of drugs. Additionally, as-fabricated TUBGs@PP composite nano-formulation can circumvent immune system-mediated clearance, thereby facilitating targeted drug delivery to the thrombus sites and enhancing the thrombolytic efficacy. In vivo results demonstrated that the TUBGs@PP composite nano-formulations not only prolonged circulation time but also effectively unclogged blood vessels at the site of thrombosis, while reducing recurrence of thrombosis and drug side effects. statement of significance: The platelet membrane-camouflaged bioactive glass nanoparticles as drug carriers for the synergistic co-delivery of urokinase and tirofiban have been developed (TUBGs@PP) for the treatment of acute arterial thrombosis. This cutting-edge therapeutic strategy addresses several critical limitations inherent in current thrombolytic treatments, including the transient half-life of thrombolytic agents, suboptimal drug bioavailability, and limited therapeutic efficacy. In vivo studies demonstrate that TUBGs@PP not only achieves sustained circulation but also effectively restores vascular patency at thrombotic loci, concurrently reducing the risk of thrombotic recurrence and minimizing adverse drug effects. This study highlights the paradigm-shifting potential of TUBGs@PP in thrombolyt

关键词： Bioactive glass

来源：评论

学校读者我要写书评

暂无评论

8-channel CWDM filter on the lithium-niobate-on-insulator platform using cascaded multimode waveguide gratings

8-channel CWDM filter on the lithium-niobate-on-insulator pl...

引用

2024 Asia Communications and Photonics Conference, ACP 2024 and International Conference on Information Photonics and Optical Communications, IPOC 2024

作者： He, Jianghao Dai, Daoxin Liu, Dajian Zhang, Ming College of Optical Science and Engineering Zhejiang University Hangzhou China Hangzhou Global Scientific and Technological Innovation Center Zhejiang University Hangzhou China State Key Laboratory of Extreme Photonics and Instrumentation College of Optical Science and Engineering International Research Center for Advanced Photonics Ningbo Innovation Center Zhejiang University Hangzhou310058 China Zhejiang University Hangzhou China

An 8-channel coarse-wavelength-division multiplexing device is realized on lithium-niobate-on-insulator platform. The experiment result exhibits box-like spectral responses with ~20 nm channel spacing, 1-dB bandwidth ... 详细信息

ISBN: (纸本)9798350379266

关键词： Wavelength division multiplexing

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：