检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Peng, Xin Wang, Shangwen Qin, Yihao Lin, Bo Chen, Liqian Mao, Xiaoguang Cheng, Jieren The Key Laboratory of Software Engineering for Complex Systems College of Computer Science and Technology National University of Defense Technology Changsha China The Hainan University Haikou China

Software vulnerability detection is crucial for high-quality software development. Recently, some studies utilizing Graph Neural Networks (GNNs) to learn the graph representation of code in vulnerability detection tasks have achieved remarkable success. However, existing graph-based approaches mainly face two limitations that prevent them from generalizing well to large code graphs: (1) the interference of noise information in the code graph;(2) the difficulty in capturing long-distance dependencies within the graph. To mitigate these problems, we propose a novel vulnerability detection method, ANGEL, whose novelty mainly embodies the hierarchical graph refinement and context-aware graph representation learning. The former hierarchically filters redundant information in the code graph, thereby reducing the size of the graph, while the latter collaboratively employs the Graph Transformer and GNN to learn code graph representations from both the global and local perspectives, thus capturing long-distance dependencies. Extensive experiments demonstrate promising results on three widely used benchmark datasets: our method significantly outperforms several other baselines in terms of the accuracy and F1 score. Particularly, in large code graphs, ANGEL achieves an improvement in accuracy of 34.27%-161.93% compared to the state-of-the-art method, AMPLE. Such results demonstrate the effectiveness of ANGEL in vulnerability detection tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

In-situ growth of heterophase Ni nanocrystals on graphene for enhanced catalytic reduction of 4-nitrophenol

引用

Nano Research 2022年第2期15卷 1230-1237页

作者： Jiahao Zhuang Feng He Xianglin Liu Pengchao Si Fangna Gu Jing Xu Yu Wang Guangwen Xu Ziyi Zhong Fabing Su School of Chemical Engineering University of Chinese Academy of SciencesBeijing 100049China State Key Laboratory of Multiphase Complex Systems Institute of Process EngineeringChinese Academy of SciencesBeijing 100190China Key Laboratory on Resources Chemicals and Materials of Ministry of Education Shenyang University of Chemical TechnologyShenyang 110142China State Key Laboratory of Chemical Engineering School of Chemical EngineeringEast China University of Science and TechnologyShanghai 200237China Department of Chemical Engineering Guangdong Technion-Israel Institute of Technology(GTIIT)Shantou 515063China Technion-Israel Institute of Technology(IIT) Haifa 32000Israel

Generating heterophase structures in nanomaterials,e.g.,heterophase metal nanocrystals,is an effective way to tune their physicochemical properties because of their high-energy nature and unique electronic environment of the generated ***,the direct synthesis of heterophase metal nanocrystals remains a great challenge due to their unstable ***,we report the in situar direct synthesis of heterophase Ni nanocrystals on *** heterostructure of face-centered cubic(fee)and hexagonal close-packed(hep)phase was generated via the epitaxial growth of hep Ni and the partial transformation of fee Ni and stabilized by the anchoring effect of graphene toward fee Ni nanocrystal and the preferential adsorption of surfactant polyethylenimine(PEI)toward epitaxial hep *** with the fee Ni nanocrystals grown on graphene,the heterophase(fcc/hcp)Ni nanocrystals in situ grown on graphene showed a greatly improved catalytic activity and reusability in 4-nitrophenol(4-NP)reduction to 4-aminophenol(4-AP).The measured apparent rate constant and the activity parameter were 2.958 min^(-1) and 102 min^(-1)·mg^(-1),respectively,higher than that of the best reported non-noble metal catalysts and most noble metal *** control experiments and density functional theory calculations reveal that the interface of the fee and hep phases enhances the adsorption of substrate 4-NP and thus facilitates the reaction *** work proves the novel idea for the rational design of heterophase metal nanocrystals by employing the synergistic effect of surfactant and support,and also the potential of creating the heterostructure for enhancing their catalytic reactivity.

关键词： heterophase structure Ni nanocrystals graphene 4-nitrophenol(4-NP)reduction catalysts

来源：评论

学校读者我要写书评

暂无评论

Numerical Study and Flight Control of Active Flow Control Based on Plasma Synthetic Jet

Numerical Study and Flight Control of Active Flow Control Ba...

引用

第43届中国控制会议

作者： Chunzhi Li Sheng Zhai Jianying Yang LandSpace Technology Co. Ltd. State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering Science College of Engineering Peking University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Rapid response control technology has become a key aspect in the development of hypersonic aircraft. Plasma synthetic jet technology, characterized by its extremely fast response and zero-mass properties, has shown promising control capabilities in hypersonic flow control. It holds significant potential for application in the rapid response control of hypersonic aircraft. Leveraging the rapid response characteristics of plasma synthetic jets, this paper proposes a plasma synthetic jet rapid response control technology for hypersonic aircraft. By establishing a simplified model for controlling the flow field of hypersonic aircraft, numerical studies are conducted to investigate the control of hypersonic aircraft using plasma synthetic jets. Several controllers were designed to achieve the attitude control of the aircraft.

关键词： plasma synthetic jet hypersonic aircraft numerical simulation ESO

来源：评论

学校读者我要写书评

暂无评论

State Bounding of Memristive Cohen-Grossberg Neural Networks with Mixed Delays

State Bounding of Memristive Cohen-Grossberg Neural Networks...

引用

第35届中国控制与决策会议

作者： Meng Su Yu Xue Xian Zhang School of Mathematical Science Heilongjiang University Heilongjiang Provincial Key Laboratory of the Theory and Computation of Complex Systems Heilongjiang University IEEE

This paper concerns the state bounding problem for a class of memristive Cohen-Grossberg neural networks with mixed delays and bounded disturbances.A delay-dependent sufficient condition,which is presented in terms of system parameters and contains several simple inequalities,is first given to guarantee that the state trajectories remain inside or converge exponentially into a ***,based on the state bounding results,reachable set estimation and global exponential stability criterion are ***,a numerical simulation illustrates the effectiveness of the obtained theoretical results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Full-State Planning of Nonholonomic Mobile Robots via Dynamic Velocity Vector Fields

Full-State Planning of Nonholonomic Mobile Robots via Dynami...

引用

Chinese Control and Decision Conference, CCDC

作者： Xiaodong He Zhongkui Li Department of Mechanics and Engineering Science State Key Laboratory for Turbulence and Complex Systems College of Engineering Peking University Beijing China

As a rigid body, the nonholonomic mobile robot contains both states of position and orientation. In order to plan these states simultaneously, this paper investigates the full-state planning problem of nonholonomic mobile robots, in the sense that the robots should reach the specified positions and meanwhile point to the desired orientations at the terminal time. To this end, we propose a velocity vector field which guides the mobile robots to the goal points. Particularly, the dynamics of the robot orientation is brought into the vector field, so that the attitude angle of the robot can converge to the specified value following the orientation dynamics. Furthermore, we study the obstacle avoidance and mutual-robot-collision avoidance by proposing another velocity vector field, which guides the robots moving along the tangential direction of the dangerous areas. Finally, several numerical simulation examples are provided to support the theoretical results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

data-Driven Multi-Objective Optimization of Power Consumption and Quality for Finishing Rolling Process

Data-Driven Multi-Objective Optimization of Power Consumptio...

引用

data Driven Control and Learning systems (DDCLS)

作者： Xiaolu Chen Ying Yang Department of Mechanics and Engineering Science State Key Laboratory for Turbulence & Complex Systems College of Engineering Peking University Beijing P. R. China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

This paper investigates the operational optimization in the context of the steel hot rolling production and finishing facilities. Optimizing the operational variables of the finishing rolling process can improve the rolling quality and reduce the unit power consumption. However, there are too many operational variables in the process and their interactions are strongly coupled, making it difficult to develop an effective model for in-depth study. Therefore, this paper adopts a data-driven approach, using neural network algorithms to construct the data prediction models between performance and set values respectively. Multi-objective optimization of the set values is performed by combining the actual mechanism and equipment constraints. In the obtained Pareto optimal solutions, the conflicting choices are further balanced among multiple objectives to obtain the most suitable operating parameters. Experimentally verified using production line production data, the method proposed in this paper significantly improves the performance indexes.

关键词： Power demand Process control Production Predictive models Prediction algorithms data models Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Coordination Under Temporal Logic Tasks and Team-Wise Intermittent Communication

arXiv

引用

arXiv 2023年

作者： Wang, Junjie Guo, Meng Li, Zhongkui State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering Science College of Engineering Peking University Beijing China

Multi-agent systems outperform single agent in complex collaborative tasks. However, in large-scale scenarios, ensuring timely information exchange during decentralized task execution remains a challenge. This work presents an online decentralized coordination scheme for multi-agent systems under complex local tasks and intermittent communication constraints. Unlike existing strategies that enforce all-time or intermittent connectivity, our approach allows agents to join or leave communication networks at aperiodic intervals, as deemed optimal by their online task execution. This scheme concurrently determines local plans and refines the communication strategy, i.e., where and when to communicate as a team. A decentralized potential game is modeled among agents, for which a Nash equilibrium is generated iteratively through online local search. It guarantees local task completion and intermittent communication constraints. Extensive numerical simulations are conducted against several strong baselines. © 2023, CC BY-NC-ND.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Applications of Machine Learning in Biopharmaceutical Process Development and Manufacturing: Current Trends, Challenges, and Opportunities

arXiv

引用

arXiv 2023年

作者： Khuat, Thanh Tung Bassett, Robert Otte, Ellen Grevis-James, Alistair Gabrys, Bogdan Complex Adaptive Systems Laboratory The Data Science Institute University of Technology SydneyNSW2007 Australia CSL Innovation MelbourneVIC3000 Australia

While machine learning (ML) has made significant contributions to the biopharmaceutical field, its applications are still in the early stages in terms of providing direct support for quality-by-design based development and manufacturing of biopharmaceuticals, hindering the enormous potential for bioprocesses automation from their development to manufacturing. However, the adoption of ML-based models instead of conventional multivariate data analysis methods is significantly increasing due to the accumulation of large-scale production data. This trend is primarily driven by the real-time monitoring of process variables and quality attributes of biopharmaceutical products through the implementation of advanced process analytical technologies. Given the complexity and multidimensionality of a bioproduct design, bioprocess development, and product manufacturing data, ML-based approaches are increasingly being employed to achieve accurate, flexible, and high-performing predictive models to address the problems of analytics, monitoring, and control within the biopharma field. This paper aims to provide a comprehensive review of the current applications of ML solutions in a bioproduct design, monitoring, control, and optimisation of upstream, downstream, and product formulation processes. Finally, this paper thoroughly discusses the main challenges related to the bioprocesses themselves, process data, and the use of machine learning models in biopharmaceutical process development and manufacturing. Moreover, it offers further insights into the adoption of innovative machine learning methods and novel trends in the development of new digital biopharma solutions. © 2023, CC BY.

关键词： Product design

来源：评论

学校读者我要写书评

暂无评论

A Physics-Informed Gaussian Process Regression Algorithm for the Dynamics of the Planar Pendulum

A Physics-Informed Gaussian Process Regression Algorithm for...

引用

Chinese Control Conference (CCC)

作者： Tianzhi Li Jinzhi Wang Department of Mechanics and Engineering Science State Key Laboratory for Turbulence and Complex Systems College of Engineering Peking University Beijing China

Gaussian process regression has received considerable attention due to its performance in solving the problem of learning and predicting the dynamics of certain systems in the machine learning area. However, this data-driven method ignores the prior physical information. A feasible method to tackle this problem is to embed prior dynamics into the Gaussian process regression. This naturally relies on numerical discretizations of continuous-time differential equations that describe the dynamics. However, conventional discretization schemes do not respect the intrinsic geometric structure of the system, which plays an important role when analyzing the properties of the mechanical system. In this work, we develop a physic-informed Gaussian process regression algorithm based on Hamel's formalism and its variational integrator. Computational properties are illustrated by the numerical experiment of learning and predicting the dynamics of a planar pendulum.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Coordination Under Temporal Logic Tasks and Team-Wise Intermittent Communication

Multi-agent Coordination Under Temporal Logic Tasks and Team...

引用

IEEE Conference on Decision and Control

作者： Junjie Wang Meng Guo Zhongkui Li Department of Mechanics and Engineering Science State Key Laboratory for Turbulence and Complex Systems College of Engineering Peking University Beijing China

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：