检索结果-内蒙古大学图书馆

4th International Conference on Machine Learning, Big Data and Business Intelligence, MLBDBI 2022

作者： Lu, Lianwen Cui, Yuhan Lu, Xinghua Qiu, Jitao Ye, Zongyuan Institute of Computer Control Technology Guangzhou Huali College Guangzhou China Guangzhou Huali College School of Computer and Information Engineering Guangzhou China

ISBN: (纸本)9798350333947

This paper proposes a data federation multiobjective tracking (MOT) method based on a graph neural network framework, where a graph-based approach merges the optimisation data between multiple objects in the same frame and between objects in the preceding and following frames into the feature learning task. This approach uses the data logic and topological properties of graphs, combined with detectors to encapsulate the neighbourhood information of each node, in order to construct an association graph between multi-objective multi-features with the inference logic of optimised occlusion data, which is then learned by linear filtering to constrain feature score similarity. Finally, this paper conducts comparative experiments on the MOT dataset. By comparing the experimental index data of MOT15/17/20, the outstanding performance of this paper's method can be effectively demonstrated. © 2022 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Evaluating Different Fault Injection Abstractions on the Assessment of DNN SW Hardening Strategies

Evaluating Different Fault Injection Abstractions on the Ass...

引用

Asian Test Symposium (ATS)

作者： Giuseppe Esposito Juan-David Guerrero-Balaguera Josie E. Rodriguez Condia Matteo Sonza Reorda Department of Control and Computer Engineering (DAUIN) Politecnico di Torino Turin Italy

ISBN: (数字)9798331529161

ISBN: (纸本)9798331529178

1 The reliability of Neural Networks has gained significant attention, prompting efforts to develop SW-based hardening techniques for safety-critical scenarios. However, evaluating hardening techniques using application-level fault injection (FI) strategies, which are commonly hardware-agnostic, may yield misleading results. This study for the first time compares two FI approaches (at the application level (APP) and instruction level (ISA)) to evaluate deep neural network SW hardening strategies. Results show that injecting permanent faults at ISA (a more detailed abstraction level than APP) changes completely the ranking of SW hardening techniques, in terms of both reliability and accuracy. These results highlight the relevance of using an adequate analysis abstraction for evaluating such techniques.

关键词： Degradation Fault tolerance Accuracy Simulation Fault tolerant systems Artificial neural networks Color Reliability engineering Safety Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

MINOS: A Tool To Analyze HTTP Requests for compliance to GDPR

MINOS: A Tool To Analyze HTTP Requests for compliance to GDP...

引用

International Conference on Application of Information and Communication Technologies (AICT)

作者： Lorenzo Laudadio Riccardo Coppola Antonio Vetrò Marco Torchiano Juan Carlos De Martin Dept. of Control and Computer Engineering Politecnico di Torino Turin Italy

ISBN: (数字)9798350387537

ISBN: (纸本)9798350387544

Many of the currently available services and commodities extensively share personal data and digital identities, raising privacy, security and ethical *** this paper, we present a novel software, MINOS, designed to enhance users’ privacy awareness while browsing the web. Our approach combines a user-friendly browser with a backend tailored to record and analyze HTTP requests directed to countries outside the European Economic Area (EEA).As opposed to other available tools, our solution uniquely addresses the issue of data transfers to third *** simulations have yielded promising results and clear directions for further research and development of the tool.

关键词： Economics Data privacy Ethics Europe Data transfer HTTP Software Information and communication technology Security Research and development

来源：评论

学校读者我要写书评

暂无评论

Hunger games search optimization with deep learning model for sustainable supply chain management

引用

Discover Internet of Things 2023年第1期3卷 1-17页

作者： Xu, Zheng Jain, Deepak Kumar Neelakandan, S. Abawajy, Jemal School of Computer and Information Engineering Institute for Artificial Intelligence Shanghai Polytechnic University Shanghai201209 China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian116024 China School of Artificial Intelligence Dalian China Symbiosis Institute of Technology Symbiosis International University Pune India Department of Computer Science and Engineering R.M.K Engineering College Taluk India Deakin University Geelong Australia

The supply chain network is one of the most important areas of focus in the majority of business circumstances. Blockchain technology is a feasible choice for secure information sharing in a supply chain network. Despite the fact that maintaining security at all levels of the blockchain is difficult, cryptographic methods are commonly used in existing works. Effective supply chain management (SCM) offers various benefits to organizations, such as enhanced customer satisfaction, increased operational efficiency, competitive advantage, and cost reduction. Potential SCM for agricultural and food supply chains needs distributors, coordination and collaboration among farmers, retailers, and stakeholders. The use of technology like Block Chain (BC), sensors, and data analytics, can boost traceability and visibility, decrease waste, and ensure safety and quality throughout the supply chain. Therefore, this study develops a Hunger Games Search Optimization with Deep Learning Model for Sustainable agricultural and food Supply Chain Management (HGSODL-ASCM) technique. The fundamental goal of the HGSODL-ASCM technique is to improve decision-making processes for agricultural and food commodity production and storage in order to optimise revenue. In the provided HGSODL-ASCM technique, a bidirectional long short-term memory (Bi-LSTM) model is built to determine the amount of productivity and storage required to maximise profit. In order to boost the performance of the Bi-LSTM classification process, the HGSO algorithm has been utilized in this work. The presented HGSODL-ASCM technique can independently achieve the SCM policies via interaction with complicated and adaptive environments. A brief set of simulations were performed to ensure the improved performance of the HGSODL-ASCM technique. The simulation results demonstrated how superior the HGSODL-ASCM method is to other methods already in use. © The Author(s) 2023.

关键词： Food supply

来源：评论

学校读者我要写书评

暂无评论

Path Planning Method for Large-Area Stamp-Based DLP Printing

Path Planning Method for Large-Area Stamp-Based DLP Printing

引用

Electronic Information engineering and computer Science (EIECS), 2021 International Conference on

作者： Xiaokuo Gao Yanling Guo Jian Li Yangwei Wang College of Computer and Control Engineering Northeast Forestry University Harbin Heilongjiang China

ISBN: (数字)9798331531409

ISBN: (纸本)9798331531416

To address the issues of low efficiency and difficulty in interval printing splicing in large-area stamping-based stereolithography, a print path planning method based on an improved ant colony algorithm is proposed. The approach involves adjusting the distribution of ant parameters, updating the pheromone mechanism, and incorporating a time evaluation function to specifically solve the optimal print path problem. Experimental results show that this method achieves shorter print path lengths compared to the Zigzag algorithm and more effectively reduces the number of interval prints and the difficulty of splicing compared to the original ant colony algorithm, thereby improving print efficiency and quality.

关键词： Printing computer science Cross layer design Splicing Optimization methods Path planning Stereolithography Synchronization

来源：评论

学校读者我要写书评

暂无评论

Research on Hybrid Mechanistic and Data-Driven Modeling of Wind Turbines Based on Particle Swarm Optimization

Research on Hybrid Mechanistic and Data-Driven Modeling of W...

引用

IEEE International Conference on Energy Internet (ICEI)

作者： Zhanyang Ji Xiyang Wang Shuai Wang School of Control and Computer Engineering North China Electric Power University China

ISBN: (数字)9798331523558

ISBN: (纸本)9798331523565

In response to the complex nonlinear operational characteristics of large wind turbines, a hybrid semi-mechanistic modeling method for multi-condition operations is proposed, based on a refined 5MW wind turbine model and co-simulation using FAST and Simulink. First, a complex nonlinear mechanistic model is constructed through mechanistic analysis, identifying the input and output variables, and completing data collection. Then, the aerodynamic system is linearized using a Taylor expansion, and an incremental model is built for key nonlinear components at steady-state operating points. Finally, guided by mechanistic insights, the particle swarm optimization (PSO) algorithm is applied to refine the aerodynamic partial derivatives, optimizing the results of the model linearization. The conclusions show that the proposed modeling method retains advantages of speed and precision under various operating conditions, while preserving the physical meaning of model parameters. This method effectively captures the complex nonlinear response characteristics of wind turbines across different operating conditions, laying the foundation for wind turbine condition monitoring and controller research.

关键词： Parameter estimation Software packages Wind speed Aerodynamics Taylor series Mathematical models Wind turbines Steady-state Particle swarm optimization MATLAB

来源：评论

学校读者我要写书评

暂无评论

ForPKG-1.0: A Framework for Constructing Forestry Policy Knowledge Graph and Application Analysis

arXiv

引用

arXiv 2024年

作者： Sun, Jingyun Luo, Zhongze College of Computer and Control Engineering Northeast Forestry University Harbin150040 China

A policy knowledge graph can provide decision support for tasks such as project compliance, policy analysis, and intelligent question answering, and can also serve as an external knowledge base to assist the reasoning process of related large language models. Although there have been many related works on knowledge graphs, there is currently a lack of research on the construction methods of policy knowledge graphs. This paper, focusing on the forestry field, designs a complete policy knowledge graph construction framework, including: firstly, proposing a fine-grained forestry policy domain ontology;then, proposing an unsupervised policy information extraction method, and finally, constructing a complete forestry policy knowledge graph. The experimental results show that the proposed ontology has good expressiveness and extensibility, and the policy information extraction method proposed in this paper achieves better results than other unsupervised methods. Furthermore, by analyzing the application of the knowledge graph in the retrieval-augmented-generation task of the large language models, the practical application value of the knowledge graph in the era of large language models is confirmed. The knowledge graph resource will be released on an open-source platform and can serve as the basic knowledge base for forestry policy-related intelligent systems. It can also be used for academic research. In addition, this study can provide reference and guidance for the construction of policy knowledge graphs in other fields. © 2024, CC BY.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

MPAT: Building Robust Deep Neural Networks against Textual Adversarial Attacks

arXiv

引用

arXiv 2024年

作者： Zhang, Fangyuan Zhou, Huichi Li, Shuangjiao Wang, Hongtao School of Control and Computer Engineering North China Electric Power University China

Deep neural networks have been proven to be vulnerable to adversarial examples and various methods have been proposed to defend against adversarial attacks for natural language processing tasks. However, previous defense methods have limitations in maintaining effective defense while ensuring the performance of the original task. In this paper, we propose a malicious perturbation based adversarial training method (MPAT) for building robust deep neural networks against textual adversarial attacks. Specifically, we construct a multi-level malicious example generation strategy to generate adversarial examples with malicious perturbations, which are used instead of original inputs for model training. Additionally, we employ a novel training objective function to ensure achieving the defense goal without compromising the performance on the original task. We conduct comprehensive experiments to evaluate our defense method by attacking five victim models on three benchmark datasets. The result demonstrates that our method is more effective against malicious adversarial attacks compared with previous defense methods while maintaining or further improving the performance on the original task. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Decentralized Task Allocation for Redundant Multi-Robot Systems: An Iterative Consensus Approach

Decentralized Task Allocation for Redundant Multi-Robot Syst...

引用

International Conference on control and Automation (ICCA)

作者： Lorenzo Govoni Andrea Cristofaro Department of Computer Control and Management Engineering Sapienza University of Rome Rome Italy

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

An overactuated heterogeneous multi-robot system is considered, this being characterized by both a redundancy of the number of agents with respect to the tasks to be performed and input redundancy for each individual agent. We propose an algorithm that, based on local information only, can simultaneously assign the tasks, consistently with the different nature of each robot, and allocate the control efforts while satisfying the constraints on the actuators. The performances of the proposed method have been analysed by means of a simulation study, considering different scenarios and illustrating also the resilience of the approach with respect to faults.

关键词： Actuators Scalability Redundancy Robustness Multi-robot systems Resource management Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Kolmogorov–Arnold Graph Neural Networks

arXiv

引用

arXiv 2024年

作者： De Carlo, Gianluca Mastropietro, Andrea Anagnostopoulos, Aris Department of Computer Control and Management Engineering Sapienza University of Rome Rome Italy

Graph neural networks (GNNs) excel in learning from network-like data but often lack interpretability, making their application challenging in domains requiring transparent decision-making. We propose the Graph Kolmogorov–Arnold Network (GKAN), a novel GNN model leveraging spline-based activation functions on edges to enhance both accuracy and interpretability. Our experiments on five benchmark datasets demonstrate that GKAN outperforms state-of-the-art GNN models in node classification, link prediction, and graph classification tasks. In addition to the improved accuracy, GKAN’s design inherently provides clear insights into the model’s decision-making process, eliminating the need for post-hoc explainability techniques. This paper discusses the methodology, performance, and interpretability of GKAN, highlighting its potential for applications in domains where interpretability is crucial. © 2024, CC BY-NC-SA.

关键词： Classification (of information)

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：