检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Lu, Feng Li, Wei Sun, Yifei Song, Cheng Ren, Yufei Zomaya, Albert Y. School of Computer Science and Technology Huazhong University of Science and Technology China The Australia-China Joint Research Centre for Energy Informatics and Demand Response Technologies Centre for Distributed and High Performance Computing School of Computer Science The University of Sydney Australia Tongji Hospital Tongji Medical College Huazhong University of Science and Technology China

Artificial intelligence (AI) has immense potential in time series prediction, but most explainable tools have limited capabilities in providing a systematic understanding of important features over time. These tools typically rely on evaluating a single time point, overlook the time ordering of inputs, and neglect the time-sensitive nature of time series applications. These factors make it difficult for users, particularly those without domain knowledge, to comprehend AI model decisions and obtain meaningful explanations. We propose CGS-Mask, a post-hoc and model-agnostic cellular genetic strip mask-based saliency approach to address these challenges. CGS-Mask uses consecutive time steps as a cohesive entity to evaluate the impact of features on the final prediction, providing binary and sustained feature importance scores over time. Our algorithm optimizes the mask population iteratively to obtain the optimal mask in a reasonable time. We evaluated CGS-Mask on synthetic and real-world datasets, and it outperformed state-of-the-art methods in elucidating the importance of features over time. According to our pilot user study via a questionnaire survey, CGS-Mask is the most effective approach in presenting easily understandable time series prediction results, enabling users to comprehend the decision-making process of AI models with ease. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Generalizing knowledge graph embedding with universal orthogonal parameterization 24

Generalizing knowledge graph embedding with universal orthog...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Rui Li Chaozhuo Li Yanming Shen Zeyu Zhang Xu Chen Gaoling School of Artificial Intelligence Renmin University of China Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (MOE) Beijing University of Posts and Telecommunications China School of Computer Science and Technology Dalian University of Technology China

Recent advances in knowledge graph embedding (KGE) rely on Euclidean/hyperbolic orthogonal relation transformations to model intrinsic logical patterns and topological structures. However, existing approaches are confined to rigid relational orthogonalization with restricted dimension and homogeneous geometry, leading to deficient modeling capability. In this work, we move beyond these approaches in terms of both dimension and geometry by introducing a powerful framework named GoldE, which features a universal orthogonal parameterization based on a generalized form of Householder reflection. Such parameterization can naturally achieve dimensional extension and geometric unification with theoretical guarantees, enabling our framework to simultaneously capture crucial logical patterns and inherent topological heterogeneity of knowledge graphs. Empirically, GoldE achieves state-of-the-art performance on three standard benchmarks. Codes are available at https://***/xxrep/GoldE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time action feature extraction via fast PCA-Flow

Real-time action feature extraction via fast PCA-Flow

引用

作者： Chen, Huafeng Li, Hongyang Xu, Zengmin Zhao, Yunhong He, Tigang School of Computer Engineering Jingchu University of Technology Jingmen China College of Computer and Information Technology China Three Gorges University Yichang China School of Mathematics and Computing Science Guilin University of Electronic Technology Guilin China

Action recognition is a research hotspot in the field of Internet of Things (IoT). Currently, local pixel-domain spatiotemporal feature extraction methods have reached the state-of-the-art action recognition performance on many challenging datasets. However, the poor computational complexity of these approaches prevents them from scaling up to real-time applications. For solving this problem, we present a novel real-time video feature extraction technique by exploiting the fast PCA-Flow algorithm. Firstly, we down-sample video images in form of grid. Based on the down-sampling images, PCA-Flow algorithm is used to calculate optical flow among adjacent images. The PCA-Flow matrices are then expanded to the original video image size by using efficient gCLSR super-resolution method to keep the inherent geometric structure of the optical flow. Finally, we compute action descriptors based on original pixel frames and the enlarged PCA-Flow images. The proposed approach is validated on three challenging datasets: UCF50, Hollywood2, and HMDB51. Experimental results indicate that the proposed method is more efficient in computation and can achieve competitive quality than the state-of-the-art methods. © 2019 John Wiley & Sons, Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Research on Optimization of Nuclear Power Security DCS Gateway Encryption Communication Based on OPC UA Protocol 9th

Research on Optimization of Nuclear Power Security DCS Gatew...

引用

9th International Conference on Energy Engineering and Environmental Engineering, ICEEEE 2022

作者： Zhou, Pengjun Chen, Zhi Jiang, Wei Liu, Jie Zhang, Yan Zhong, Ke Wu, Zhiqiang School of Computer Science University of South China Hengyang421200 China Nuclear Power Institute of China Chengdu610000 China Intelligent Equipment Software Evaluation Engineering Technology Research Center of Hunan Hengyang China CNNC Key Laboratory on High Trusted Computing Hunan Hengyang China

ISBN: (纸本)9783031302329

Nuclear power safety grade DCS gateway is an important hub for information transmission between safety grade equipment and non-safety grade equipment, and its security is very important in the transmission process. At present, the communication protocol used by the Chinese nuclear power security grade DCS gateway does not use data encryption in the data transmission process. However, the signature certificate, user authentication, access control and data encryption transmission of OPC UA protocol have more advantages in ensuring the data security of nuclear power security grade DCS gateway, which helps to meet the technical requirements for nuclear power security grade DCS information security. Based on the cryptography theory, this paper analyzes the security and efficiency of the original RSA encryption algorithm of the OPC UA protocol, and concludes that the encryption efficiency of the RSA algorithm is poor, which leads to the application of the OPC UA protocol to the nuclear power security grade DCS gateway communication process can not meet the time requirements of data transmission, so it is necessary to optimize and improve the communication process of the OPC UA protocol applied to the nuclear power security grade DCS gateway. This paper optimizes and improves the encryption transmission in the communication process of the nuclear power security grade DCS gateway of OPC UA protocol, and proposes a hybrid encryption algorithm of SM2 and AES to replace the original encryption method in OPC UA protocol. Through experiments, it proves that the communication optimization method improves the communication efficiency of the original protocol, and achieves the efficiency index of nuclear power security grade DCS gateway for data transmission. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Nuclear energy

来源：评论

学校读者我要写书评

暂无评论

Improved divergence-free smoothed particle hydrodynamics via priority of divergence-free solver and SOR

Improved divergence-free smoothed particle hydrodynamics via...

引用

作者： Wu, Maolin Liu, Shiguang Xu, Qing School of Computer Science and Technology College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin University Tianjin China

Fluid simulation plays an important role in movie special effects, computer games, etc. In recent years, the Smoothed Particle Hydrodynamics (SPH) has become a popular fluid simulation method due to its simpler implementation and better processing capabilities for various complex scenes. Although the computational efficiency of the current SPH method has been significantly improved, there is still much room for improvement in pressure solving. This paper proposes an improved pressure solution method based on DFSPH. Firstly, we eliminate the velocity divergence of the fluid by changing the solution order of the nonpressure force and divergence solvers, thereby reducing the number of iterations required by the density solver. Secondly, the SOR method is applied to the pressure solver, furthering reducing the number of iterations of the density solver. Various experiments demonstrated that our method improves the efficiency of the solver with little decrease in stability compared to state-of-the-art methods. The speedup factor reaches between 1.35 and 1.4 at a time step of 5ms, and the more the number of particles, the faster the performance increases. © 2021 John Wiley & Sons, Ltd.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices

arXiv

引用

arXiv 2024年

作者： Jia, Yongzhe Zhang, Xuyun Hu, Hongsheng Choo, Kim-Kwang Raymond Qi, Lianyong Xu, Xiaolong Beheshti, Amin Dou, Wanchun State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University China School of Computing Macquarie University Australia School of Information and Physical Sciences University of Newcastle Australia Department of Information Systems and Cyber Security University of Texas San Antonio United States China School of Computer and Software Nanjing University of Information Science and Technology China

Federated learning (FL) has emerged as a prominent machine learning paradigm in edge computing environments, enabling edge devices to collaboratively optimize a global model without sharing their private data. However, existing FL frameworks suffer from efficacy deterioration due to the system heterogeneity inherent in edge computing, especially in the presence of domain shifts across local data. In this paper, we propose a heterogeneous FL framework DapperFL, to enhance model performance across multiple domains. In DapperFL, we introduce a dedicated Model Fusion Pruning (MFP) module to produce personalized compact local models for clients to address the system heterogeneity challenges. The MFP module prunes local models with fused knowledge obtained from both local and remaining domains, ensuring robustness to domain shifts. Additionally, we design a Domain Adaptive Regularization (DAR) module to further improve the overall performance of DapperFL. The DAR module employs regularization generated by the pruned model, aiming to learn robust representations across domains. Furthermore, we introduce a specific aggregation algorithm for aggregating heterogeneous local models with tailored architectures and weights. We implement DapperFL on a real-world FL platform with heterogeneous clients. Experimental results on benchmark datasets with multiple domains demonstrate that DapperFL outperforms several state-of-the-art FL frameworks by up to 2.28%, while significantly achieving model volume reductions ranging from 20% to 80%. Our code is available at: https://***/jyzgh/DapperFL. © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Mixed Graph Convolutional Network with Cross-Distance Syntactic Aware for Aspect-Based Sentiment Analysis

A Mixed Graph Convolutional Network with Cross-Distance Synt...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Ruhan Deng Qinghua Zhang Man Gao Meiling Fu Ye Wang Guoyin Wang School of computer science and technology chongqing university of posts and telecommunications Chongqing China Chongqing key laboratory of computational intelligence computing Chongqing university of posts and telecommunications Chongqing China

ISBN: (数字)9798350377613

ISBN: (纸本)9798350377620

Aspect-based sentiment analysis(ABSA) is one of the text classification tasks, aiming to classify sentiment of aspect words in the given text. Since syntactic information of text can be effectively modeled by dependency tree. Meanwhile, local and global information of sentences can be well learned by graph convolutional network(GCN), so dependency tree-based GCN is widely used in ABSA, where the relationships between sentence words can be effectively captured. However, deep GCN suffers from the problem of over-smoothing, which simply means that nodes of different orders are indistinguishable, especially on small scale datasets. And syntactic information is enhanced early in model training in previous studies. In order to address these problems from other perspectives, first, a mix graph convolutional network with cross-distance syntactic aware for ABSA is proposed, to alleviate nodes over-smoothing of GCN problem. Second, Mixhop is combined with GCN, to help the aspectual node to acquire feature information of multi-layer neighbors. The proposed model, not only allows aspect words to fuse the information learned from the shallow-layer neighbors, but also fuses the information from deep-layer neighbors. Third, attention mechanism is used to focus on syntactic information of nodes that are distant from the aspect words. Finally, experiments conducted on widely used public datasets that the proposed model achieves superior results.

关键词： Training Analytical models Sentiment analysis Attention mechanisms Graph convolutional networks Fuses Text categorization Syntactics Transformers Data models

来源：评论

学校读者我要写书评

暂无评论

ProxiCycle: Passively Mapping Cyclist Safety Using Smart Handlebars for Near-Miss Detection 25

ProxiCycle: Passively Mapping Cyclist Safety Using Smart Han...

引用

Proceedings of the 2025 CHI Conference on Human Factors in computing Systems

作者： Joseph Breda Keyu Chen Thomas Plötz Shwetak Patel Paul G. Allen School of Computer Science & Engineering University of Washington Seattle Washington USA Gridware San Fancisco California USA School of Interactive Computing Georgia Institute of Technology Atlanta Georgia USA

来源：评论

学校读者我要写书评

暂无评论

An Entity Alignment Algorithm Based on Ontology Enhancement and Multi-Feature Fusion

An Entity Alignment Algorithm Based on Ontology Enhancement ...

引用

Frontiers technology of Information and computer (ICFTIC), IEEE International Conference on

作者： Hao Song Yuxia Lei Kangli Zi Fuyuan Quan Tianhang Zhang Qi Li School of Computer Science Qufu Normal University Rizhao Shandong China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

Entity alignment plays a crucial role in the integration of knowledge graphs. However, current knowledge graphs often suffer from inconsistent construction standards, structural heterogeneity, and imprecise semantic representation of entities, which can lead to suboptimal embedding of structural information. Moreover, most existing entity alignment methods rely heavily on structural information, which limits alignment efficiency. To address these challenges, this paper presents Onto-IMF, an ontology-enhanced entity alignment method based on multi-feature fusion. This approach aims to enhance the semantic representation of entities by incorporating ontology information, thereby reducing structural discrepancies among heterogeneous graphs and improving the embedding of structural information. The multi-feature fusion entity alignment leverages diverse semantic features, including relations, attributes, and entity names, to achieve more accurate alignment. Experimental results on various DBP15K subsets indicate that the proposed method achieves Hits@l scores of 86.6%, 93.0%, and 97.7%, respectively, representing an average improvement of 7.9 % over the best-performing baseline models.

关键词： Accuracy Semantics Knowledge graphs Contrastive learning Ontologies Data models Standards

来源：评论

学校读者我要写书评

暂无评论

CoPEFT: Fast Adaptation Framework for Multi-Agent Collaborative Perception with Parameter-Efficient Fine-Tuning

arXiv

引用

arXiv 2025年

作者： Wei, Quanmin Dai, Penglin Li, Wei Liu, Bingyi Wu, Xiao School of Computing and Artificial Intelligence Southwest Jiaotong University China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education China School of Computer Science and Artificial Intelligence Wuhan University of Technology China

Multi-agent collaborative perception is expected to significantly improve perception performance by overcoming the limitations of single-agent perception through exchanging complementary information. However, training a robust collaborative perception model requires collecting sufficient training data that covers all possible collaboration scenarios, which is impractical due to intolerable deployment costs. Hence, the trained model is not robust against new traffic scenarios with inconsistent data distribution and fundamentally restricts its real-world applicability. Further, existing methods, such as domain adaptation, have mitigated this issue by exposing the deployment data during the training stage but incur a high training cost, which is infeasible for resource-constrained agents. In this paper, we propose a Parameter-Efficient Fine-Tuning-based lightweight framework, CoPEFT, for fast adapting a trained collaborative perception model to new deployment environments under low-cost conditions. CoPEFT develops a Collaboration Adapter and Agent Prompt to perform macro-level and micro-level adaptations separately. Specifically, the Collaboration Adapter utilizes the inherent knowledge from training data and limited deployment data to adapt the feature map to new data distribution. The Agent Prompt further enhances the Collaboration Adapter by inserting fine-grained contextual information about the environment. Extensive experiments demonstrate that our CoPEFT surpasses existing methods with less than 1% trainable parameters, proving the effectiveness and efficiency of our proposed method. Copyright © 2025, The Authors. All rights reserved.

关键词： Multi agent systems

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：