检索结果-内蒙古大学图书馆

10th International Conference on e-Society, e-Learning and e-Technologies, ICSLT 2024

作者： Chen, Xi Wan, Yu Tang, Jun Zhao, Zipeng Laboratory for Big Data and Decision National University of Defense Technology China

ISBN: (纸本)9798400716799

Unmanned Aerial Vehicle (UAV) carries relief materials to perform cooperative delivery mission, which has a high guarantee in both flexibility and security, and can avoid the personal safety threat of pilots in the original delivery mode in the post-disaster scenario. In this paper, we study the problem of collaborative path planning before start of the multi-UAV cooperative delivery mission. Based on the knowledge of graph theory and the generalized multiple traveling salesman problem, the model of multi-UAV mission path planning problem is established. Real and reasonable constraints are added and formulated, including UAV cooperation constraints and task order constraints. According to the characteristics of the problem model, this paper innovatively proposes a Hybrid Grouping Particle Swarm Optimization (HGPSO) algorithm. The particle population is divided into subgroups of the same size to represent the feasible solution. Then, based on the crossover and mutation idea of genetic algorithm, this paper improves the velocity update rule of particle swarm, and proposes four crossover and mutation methods. Finally, simulation experiments verify the effectiveness of the algorithm, and the convergence data show that the algorithm can meet the needs of rapid decision-making and response in post-disaster rescue. © 2024 Copyright held by the owner/author(s).

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Driven Cooperative Hole Crossing by Multiple UAVs 24

Deep Learning-Driven Cooperative Hole Crossing by Multiple U...

引用

10th International Conference on e-Society, e-Learning and e-Technologies, ICSLT 2024

作者： Wan, Yu Tang, Jun Zhao, Zipeng Chen, Xi Laboratory for Big Data and Decision National University of Defense Technology China

ISBN: (纸本)9798400716799

This research presents a novel deep learning framework designed to enable autonomous navigation of unmanned aerial vehicle (UAV) swarms through confined spaces, specifically focusing on the challenge of hole crossing. Leveraging the Gazebo simulation environment, we develop and test a vision-based swarm control strategy that employs onboard cameras and a TensorFlow-based end-to-end controller for decentralized, onboard decision-making. Our approach eliminates the reliance on inter-UAV Wireless communication, instead utilizing deep learning algorithms to process visual inputs and guide UAVs through narrow openings autonomously. Experimental results demonstrate the proposed system’s robustness in formation control and obstacle avoidance, achieving successful navigation without the need for external positional data sharing. The study compares the performance of our deep learning-driven model against traditional control systems, revealing comparable efficiency and highlighting the potential for practical applications. This research advances the field of autonomous UAV operations, offering a scalable and effective solution for UAV swarm navigation in complex environments, thereby opening new avenues for the application of UAV swarms in areas such as search and rescue, surveillance, and environmental monitoring. © 2024 Copyright held by the owner/author(s).

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Boosting Adversarial Robustness through Channel Adversarial Distillation 6

Boosting Adversarial Robustness through Channel Adversarial ...

引用

6th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2024

作者： Li, Xiaolong Guo, Yanming Du, Chengsi Li, Dengjin Jiang, Jie Lao, Mingrui Laboratory of Big Data and Decision National University of Defense Technology Changsha China

ISBN: (纸本)9798331541699

Adversarial attacks have become a significant challenge for deep learning models, especially in resource-constrained environments. While adversarial training (AT) has proven effective for improving robustness, it often suffers from limited applicability to smaller models due to their computational constraints. Recently, adversarial distillation has emerged as a promising approach to transfer robustness from large teacher models to smaller student models. However, existing adversarial distillation methods often focus on logits-level distillation and overlook the importance of intermediate layer features. In this paper, we propose a novel method called Channel Adversarial Robustness Distillation (CARD) which attempts to identify the vital knowledge against adversarial threats through channel distillation. CARD leverages feature alignment at the channel level between the teacher and student models, utilizing 1x1 convolutions to ensure compatibility in feature map dimensions. We introduce Channel Distillation Loss (CD), which computes the divergence between aligned feature maps, and incorporate adaptive KL divergence for the upper bound of prediction discrepancy. The experimental results demonstrate that CARD effectively enhances adversarial robustness while maintaining high accuracy, offering a balanced approach to model distillation. Our method provides a promising direction for improving the robustness of student models in adversarial settings. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Graph-CoRe: Graph Representation Learning with Contrastive Subgraph Replacement 17

Graph-CoRe: Graph Representation Learning with Contrastive S...

引用

IEEE Congress on Cybermatics: 17th IEEE International Conference on Internet of Things, iThings 2024, 20th IEEE International Conference on Green Computing and Communications, GreenCom 2024, 17th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th IEEE International Conference on Smart data, Smartdata 2024

作者： Kang, Jie Liu, Shixuan Huang, Kuihua Fan, Changjun He, Hua Chen, Chao National University of Defense Technology Laboratory for Big Data and Decision Changsha China

ISBN: (纸本)9798350351637

The interpretability of Graph Neural Networks (GNNs) is crucial for enhancing trustworthiness and practical utility in various domains like finance, healthcare, and transportation. Given the unique challenges posed by graph data, traditional interpretability methods fall short in deciphering the intricate workings of GNNs. In this study, we propose a subgraph replacement strategy combined with supervised contrastive learning to improve the interpretability and predictive capabilities of GNNs when processing graph data. By introducing perturbations during training and addressing data biases, our approach enhances model robustness, stability, and key feature identification. Moreover, by mitigating label imbalance issues through tailored data augmentation techniques, we ensure a more balanced and accurate prediction model. Experimental results demonstrate the effectiveness of our proposed method in outperforming other subgraph representation techniques across diverse datasets, showcasing its utility in enhancing model interpretability and performance. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

LLM4HIN: Discovering Meta-path with Large Language Model for Reasoning on Complex Heterogeneous Information Networks 17

LLM4HIN: Discovering Meta-path with Large Language Model for...

引用

作者： Cheng, Haoxiang Liu, Shixuan Fan, Changjun Huang, Kuihua He, Hua Wang, Xianghan Liu, Zhong National University of Defense Technology Laboratory for Big Data and Decision Changsha China

ISBN: (纸本)9798350351637

Heterogeneous Information Networks (HINs) are complex structures hosting various types of entity nodes and diverse relationships. Meta-paths are crucial in HINs for relaying detailed information and enhancing knowledge transfer. However, their discovery is challenged by the expansive meta-path space inherent in complex HINs. To address this, we introduce LLM4HIN, an innovative meta-path discovery framework that utilizes Large Language Models (LLMs) for efficient meta-path discovery. Through the use of LLMs, LLM4HIN bypasses challenges including computational limitations, semantic inconsistency, and path selection optimization traditionally associated with meta-path reasoning. LLM4HIN could efficiently discovers meta-paths by utilizing LLMs to generate these paths from a minimal subset of HIN samples. Experimental evaluation on large-scale HINs attests to the enhanced performance of the meta-paths generated by LLM4HIN in link prediction tasks compared to state-of-the-art methods. © 2024 IEEE.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Enhanced Reinforcement Learning for TSP: Proximal Policy Optimization with Graph Attention and Entropy Regularization 5

Enhanced Reinforcement Learning for TSP: Proximal Policy Opt...

引用

5th International Conference on Computer, big data and Artificial Intelligence, ICCBD+AI 2024

作者： Yao, Chendie Liang, Xingxing Zhang, Longfei Huang, Jincai National University of Defense Technology Laboratory for Big Data and Decision Changsha China

ISBN: (纸本)9798331533991

The application of reinforcement learning (RL) to combinatorial optimization problems has gained significant attention due to its strong capability, high efficiency, and fast solving speed. However, the Travelling Salesman Problem (TSP) poses considerable challenges for existing RL methods, primarily due to the exponential growth of potential routes as the number of cities increases, complicating the search for optimal solutions. To address these challenges, this paper proposes a novel solution based on an approximate policy optimization algorithm for TSP. The TSP is modeled as an RL problem, with its environment, states, rewards, and actions defined. We then introduce an approximate state value estimation method that leverages the true cost and probabilities of TSP sampling tours, offering improved accuracy as a baseline for policy guidance. Our network model employs a graph attention mechanism and introduces first-visit city policy entropy loss to update the network using the Proximal Policy Optimization (PPO) method. Experiments demonstrate that our approach outperforms heuristic algorithms and can approximate the exact solution quickly. It achieves results comparable to or better than popular RL algorithms such as EAN and GAT among instances of various sizes while converging faster with the same amount of data. © 2024 IEEE.

关键词： Graph Attention Mechanism PPO Reinforcement Learning TSP

来源：评论

学校读者我要写书评

暂无评论

Feature Balance Method for Multi-modal Entity Alignment 27th

Feature Balance Method for Multi-modal Entity Alignment

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Chen, Wei Li, Xiaofei Long, Sheng Lei, Jun Li, Shuohao Zhang, Jun Laboratory for Big Data and Decision National University of Defense Technology Hunan Changsha410073 China

ISBN: (纸本)9783031781858

Multi-modal Entity Alignment (MMEA) aims to establish correlations between modalities such as images and texts to align equivalent entities across different multi-modal knowledge graphs, thereby enhancing knowledge graph coverage and addressing issues of information loss and low coverage in multi-modal knowledge graphs. Existing MMEA techniques mainly focus on heuristic merging paradigms of single-modal embedding. However, due to modality heterogeneity and the absence of visual imagery, current MMEA approaches encounter challenges such as imbalance and ambiguity in multi-modal data fusion, leading to semantic inconsistencies. To address this issue, this paper proposes a feature-balanced Multi-modal Entity Alignment method (FBMEA) and designs a corresponding fusion framework. Different modalities’ information is independently encoded, and through adaptive feature fusion and multi-head attention mechanisms, the training effects of weak modalities like visual information are dynamically adjusted to enhance the utilization of long-tail entities. Experimental results on three public bilingual datasets and two cross-graph datasets demonstrate that the model’s alignment capability surpasses that of current mainstream models, validating the feasibility and effectiveness of FBMEA. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Typical News Event Argument Extraction Method Based on BERT-Bi-LSTM-CRF 5

Typical News Event Argument Extraction Method Based on BERT-...

引用

5th International Conference on Artificial Intelligence and Electromechanical Automation, AIEA 2024

作者： Yang, Jiwei Zhang, Chong Tang, Wen Ge, Bin He, Chunhui National University of Defense Technology Laboratory for Big Data and Decision Hunan 410073 China

ISBN: (纸本)9798350366174

News serves as a crucial foundation for decisionmaking. However, its vast and unstructured text format poses challenges for storage, retrieval, and comprehension. To address this issue, this paper establishes an event description model for the typical news event 'Ship Voyage' based on the general ' 4 W 1 H ' event description framework. The arguments of this typical news event are then categorized accordingly. We introduce the BERT-Bi-LSTM-CRF model to extract these arguments from the collected corpus data. The model achieves a precision of 95.33%, a recall of 95.64%, and an F1 score of 95.43%, surpassing the current mainstream HanLP platform. These experimental results demonstrate that the BERT-Bi-LSTM-CRF model excels in extracting arguments from typical news events. © 2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Hypernetwork-Based Multi-Objective Optimization with NSGA-II

Hypernetwork-Based Multi-Objective Optimization with NSGA-II

引用

2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion

作者： He, Jie Zhang, Yaohong Wang, Ji Li, Xiaoqing Bao, Weidong National University of Defense Technology Laboratory for Big Data and Decision Hunan Changsha China

ISBN: (纸本)9798400704956

Multi-objective optimization algorithms have a wide range of applications in various fields. NSGA-II (Non-dominated Sorting Genetic Algorithm II) is a well-known multi-objective optimization algorithm. However, when solving high-dimensional problems using NSGA-II, the algorithm complexity increases linearly with the problem dimension. To address this issue, this paper proposes the HNSGA-II (Hypernetwork Non-dominated Sorting Genetic Algorithm II) algorithm based on hypernetwork modeling. The HNSGA-II algorithm introduces a binary tree data structure and uses hypernetworks to model candidate solutions. A new crowding calculation is designed to improve the algorithm's convergence. Horizontal and vertical comparative experiments were conducted on standard test sets ZDT and BT using the newly proposed algorithm, NSGA-II, MOEAD, and other algorithms. The results demonstrate that the HNSGA-II algorithm achieves a maximum improvement of about 10% in time efficiency when solving high-dimensional problems and exhibits better algorithmic convergence than the original NSGA-II algorithm. © 2024 held by the owner/author(s).

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Uncertain knowledge graph embedding:an effective method combining multi-relation and multi-path

引用

Frontiers of Computer Science 2024年第3期18卷 73-89页

作者： Qi LIU Qinghua ZHANG Fan ZHAO Guoyin WANG Key Laboratory of Tourism Multisource Data Perception and Decision Ministry of Culture and TourismChongqing University of Posts and TelecommunicationsChongqing 400065China Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing 400065China Chongqing Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and TelecommunicationsChongqing 400065China

Uncertain Knowledge Graphs(UKGs)are used to characterize the inherent uncertainty of knowledge and have a richer semantic structure than deterministic knowledge *** research on the embedding of UKG has only recently begun,Uncertain Knowledge Graph Embedding(UKGE)model has a certain effect on solving this ***,there are still unresolved *** the one hand,when reasoning the confidence of unseen relation facts,the introduced probabilistic soft logic cannot be used to combine multi-path and multi-step global information,leading to information *** the other hand,the existing UKG embedding model can only model symmetric relation facts,but the embedding problem of asymmetric relation facts has not be *** address the above issues,a Multiplex Uncertain Knowledge Graph Embedding(MUKGE)model is proposed in this ***,to combine multiple information and achieve more accurate results in confidence reasoning,the Uncertain ResourceRank(URR)reasoning algorithm is ***,the asymmetry in the UKG is *** embed asymmetric relation facts of UKG,a multi-relation embedding model is ***,experiments are carried out on different datasets via 4 tasks to verify the effectiveness of *** results of experiments demonstrate that MUKGE can obtain better overall performance than the baselines,and it helps advance the research on UKG embedding.

关键词： knowledge representation uncertain knowledge graph multi-relation embedding uncertain reasoning

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：