检索结果-内蒙古大学图书馆

5th International Conference on big data and Artificial intelligence and Software Engineering, ICBASE 2024

作者： Lian, Xiaoqin Liu, Chunquan Gao, Chao Ma, Guochun Gong, Yonggang Li, Jin Beijing Technology and Business University School of Computer and Artificial Intelligence Beijing100048 China China National Light Industry Beijing Technology and Business University Key Laboratory of Industrial Internet and Big Data Beijing100048 China

ISBN: (纸本)9798331506612

In recent years, facial recognition technology has seen rapid advancements and is now extensively utilized in security surveillance and financial transactions. The face recognition process usually includes image preprocessing, feature extraction, and classification. However, it is often difficult for a single feature to fully capture the complex features of a human face, thus affecting the accuracy of recognition. To address this issue, this study presented an AdaBoost-SVM face recognition algorithm that fuses local binary pattern and Gabor features, which can enable comprehensive extraction of facial features from images and enhance recognition accuracy. This method first performs bilateral filtering on the face image to reduce noise and retain edge information. Then, it extracts the local binary pattern and Gabor features and weights the fusion. Finally, it uses the AdaBoost-SVM classifier for identification. Moreover, the algorithm performance was comprehensively evaluated using the ten-fold cross-validation method. The experimental results demonstrated that this method achieves recognition accuracy of 98.75% and 96.25% on ORL and Yale A face databases respectively, and still performs well in complex lighting and expression-changing environments, significantly improving the accuracy of face recognition and its robustness. © 2024 IEEE.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Research on EEG Emotion Recognition Based on Multi-scale Residual Convolutional Neural Network 5

Research on EEG Emotion Recognition Based on Multi-scale Res...

引用

5th International Conference on big data and Artificial intelligence and Software Engineering, ICBASE 2024

作者： Lian, Xiaoqin Shi, Ziqi Gao, Chao Ma, Guochun Wu, Yelan Guan, Wenyang Beijing Technology and Business University School of Computer and Artificial Intelligence Beijing100048 China China National Light Industry Beijing Technology and Business University Key Laboratory of Industrial Internet and Big Data Beijing100048 China

ISBN: (纸本)9798331506612

Emotion recognition based on EEG signals has become an essential method in fields such as human-computer interaction and disease assessment. To further improve the recognition effect of human emotions, this paper fused the spatial and frequency information in EEG signals. It proposed a multi-scale residual convolutional neural network (ECA-Resnet-CNN) with an ECA attention mechanism to perform multi-scale information fusion on the constructed original features. The method first divides the EEG signals into six frequency bands;then, the differential entropy features are extracted from each frequency band and converted into a spatial-band three-dimensional feature matrix;then, the deep information of the three-dimensional feature matrix is extracted through a multi-scale residual convolutional neural network;finally, the weights of different channels of the feature map are adjusted by introducing the ECA attention mechanism, and the emotion classification is completed. The results show that on the Deap dataset, the arousal dimension and valence dimension binary classification accuracy of this method can reach 97.16% and 96.30% respectively, which is a significant improvement compared with the existing mainstream emotion recognition models, proving the effectiveness of this method. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving multi-view document clustering: leveraging multi-structure processor and hybrid ensemble clustering module 30

Improving multi-view document clustering: leveraging multi-s...

引用

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 Extended-Isomap for high-dimensional data accuracy and efficiency: a comprehensive survey

引用

Multimedia Tools and Applications 2024年第38期83卷 85523-85574页

作者： Yousaf, Mahwish Shakoor Khan, Muhammad Saadat Ullah, Shamsher Institute of Intelligence Machine Hefei Institutes of Physical Science Chinese Academy of Sciences Anhui Hefei230027 China Key Laboratory of Materials Physics Institute of Solid-State Physics Chinese Academy of Sciences Anhui Hefei230027 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen518060 China

Manifold learning is a widely adopted nonlinear dimensionality reduction technique employed to discover low-dimensional representations from high-dimensional data and to explore the intrinsic data structure. It encompasses a range of nonlinear techniques, including Isomap, Local Linear Embedding (LLE), Local Tangent Space Alignment (LTSA), and Multidimensional Scaling (MDS), among others. Isomap, as a popular method in manifold learning, has exhibited promising results. However, it encounters several challenges, such as the Topological Stability Problem, Shortest Path Distance, and noise sensitivity, which compromise its accuracy and elevate its computational demands. This survey paper presents three novel existing approaches to address these challenges and enhance the performance of Isomap. Firstly, the FastIsomap method, an existing approach that combines state-of-the-art algorithms like the KD tree and NN-descent to increase graph accuracy while reducing computational cost. Secondly, the FastIsomapVis method, also an existing technique, employs a hierarchical divide-and-conquer strategy employing the KD tree and Dijkstra Buckets Double, which enhances accuracy and reduces computational time in Isomap. Lastly, the NR-Isomap method, another existing approach, used the Local Tangent Space Alignment algorithm to remove noise sensitivity and short-circuit edge problems. The existing methods improve the accuracy of Isomap but also streamline its computational requirements. Furthermore, this survey paper discusses the open issues and future research directions for Isomap and manifold learning methods. It can be a valuable resource for researchers seeking insights across diverse domains. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models 31

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal L...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Li Xiao, Zhiding Huang, Wenxin Zhong, Xian Hubei Key Laboratory of Big Data Intelligent Analysis and Application School of Computer Science and Information Engineering Hubei University China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798891761964

The rapid development of multi-modal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences and frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language and Vision Assistant (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a Topic-Driven Narrative Optimizer (TDNO) that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model are available at https://***/XxxZzD/StoryLLaVA. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Global-Local Representations Network for Speech Steganalysis 5

A Novel Global-Local Representations Network for Speech Steg...

引用

5th International Conference on Artificial intelligence and Pattern Recognition, AIPR 2022

作者： Xu, Shulong Tian, Hui Quan, Hanyu Lu, Jing College of Computer Science and Technology Xiamen Key Laboratory of Data Security and Blockchain Technology Fujian Key Laboratory of Big Data Intelligence and Security National Huaqiao University China

ISBN: (纸本)9781450396899

With the popularity of the internet and the development of network services, Steganography based on speech stream has become a research hotspot in information hiding. To improve the detection performance of steganalysis of multiple steganography methods, in this paper, we proposed the Global-Local Representations Network (GLRN), which consists of a Global Correlation Extraction (GCE) module and a Local Correlation Enhancement (LCE) module. Firstly, considering the inter-class differences of different coding elements, the GCE module is used to capture the global correlation of different coding elements by using multi-channel modeling. Then, we realize that the process of global correlation extraction suffers from the loss of detailed information, so the LCE module is used to capture local correlations to complement the global features. The experiments show that the GLRN achieves the start-of-art detection performance. © 2022 ACM.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

An Improved Algorithm for Elliptic Curve Digital Signature 42

An Improved Algorithm for Elliptic Curve Digital Signature

引用

42nd Chinese Control Conference, CCC 2023

作者： Cui, Wenjun Li, Yidong School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education Beijing China

ISBN: (纸本)9789887581543

The Elliptic Curve Digital Signature Algorithm (ECDSA) is an elliptic curve variant based on the Digital Signature Algorithm (DSA). Based on the classical ECDSA scheme, a large number of improved algorithms have been proposed, but most of them use only one private key. Once the unique private key is leaked, security is not guaranteed. In this paper, we propose a new enhancement of the ECDSA scheme by introducing two private keys for the sender. We eliminate the inversion operation in both signature and verification processes. And in our signature equation, the number of model multiplications reaches the minimum number of zeros. Mainly relying on the mathematical problem Elliptic Curve Discrete Logarithm Problem (ECDLP), our scheme is resistant to private key attacks and provides unforgeability. Meanwhile, our scheme partly counteracts the risk of private key leakage. In this way, our scheme provides higher security compared with existing schemes. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

The Caching and Pricing Strategy for Information-Centric Networking with Advertisers’Participation

引用

China Communications 2024年第3期21卷 283-295页

作者： Zheng Quan Yan Wenliang Wu Rong Tan Xiaobin Yang Jian Yuan Liu Xu Zhenghuan Laboratory for Future Networks Department of AutomationUniversity of Science and Technology of ChinaHefei 230026China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Institute of Advanced Technology University of Science and Technology of ChinaHefei 230088China Suzhou Nuclear Power Research Institute Suzhou 215004China National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data(NEL-PSRPC) China Academy of Electronics and Information Technology of CETCBeijing 100041China

As users’access to the network has evolved into the acquisition of mass contents instead of IP addresses,the IP network architecture based on end-to-end communication cannot meet users’***,the Information-Centric Networking(ICN)came into *** a technical point of view,ICN is a promising future network *** and customizing a reasonable pricing mechanism plays a positive role in promoting the deployment of *** current research on ICN pricing mechanism is focused on paid ***,we study an ICN pricing model for free content,which uses game theory based on Nash equilibrium to *** this work,advertisers are considered,and an advertiser model is established to describe the economic interaction between advertisers and ICN *** solution can formulate the best pricing strategy for all ICN entities and maximize the benefits of each *** extensive analysis and numerical results show that the proposed pricing framework is significantly better than existing solutions when it comes to free content.

关键词： advertisers cache free content Information-Centric Networking pricing strategy

来源：评论

学校读者我要写书评

暂无评论

DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment 38

DFA-GNN: Forward Learning of Graph Neural Networks by Direct...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhao, Gongpei Wang, Tao Lang, Congyan Jin, Yi Li, Yidong Ling, Haibin Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education China School of Computer Science & Technology Beijing Jiaotong University China Department of Computer Science Stony Brook University United States

Graph neural networks (GNNs) are recognized for their strong performance across various applications, with the backpropagation (BP) algorithm playing a central role in the development of most GNN models. However, despite its effectiveness, BP has limitations that challenge its biological plausibility and affect the efficiency, scalability and parallelism of training neural networks for graph-based tasks. While several non-backpropagation (non-BP) training algorithms, such as the direct feedback alignment (DFA), have been successfully applied to fully-connected and convolutional network components for handling Euclidean data, directly adapting these non-BP frameworks to manage non-Euclidean graph data in GNN models presents significant challenges. These challenges primarily arise from the violation of the independent and identically distributed (i.i.d.) assumption in graph data and the difficulty in accessing prediction errors for all samples (nodes) within the graph. To overcome these obstacles, in this paper we propose DFA-GNN, a novel forward learning framework tailored for GNNs with a case study of semi-supervised learning. The proposed method breaks the limitations of BP by using a dedicated forward training mechanism. Specifically, DFA-GNN extends the principles of DFA to adapt to graph data and unique architecture of GNNs, which incorporates the information of graph topology into the feedback links to accommodate the non-Euclidean characteristics of graph data. Additionally, for semi-supervised graph learning tasks, we developed a pseudo error generator that spreads residual errors from training data to create a pseudo error for each unlabeled node. These pseudo errors are then utilized to train GNNs using DFA. Extensive experiments on 10 public benchmarks reveal that our learning framework outperforms not only previous non-BP methods but also the standard BP methods, and it exhibits excellent robustness against various types of noise and attacks. © 2024 Neura

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning Network Optimization Based on Weight Adaptive 11

Multi-Task Learning Network Optimization Based on Weight Ada...

引用

11th IEEE International Conference on Behavioural and Social Computing, BESC 2024

作者： Cao, Zizhuo Li, Yidong Ding, Chuntao Zhang, Zhuxi School of Computer Science and Technology Beijing Jiaotong University Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education Beijing100044 China General Logistics Information Center Beijing100036 China

ISBN: (纸本)9798331531904

Multi-task learning has emerged as a significant topic in artificial intelligence research, where a singular network model performs numerous tasks. This approach simultaneously processes multiple related tasks and shared knowledge, enhancing model generalization while increasing efficiency. This methodology provides innovative solutions to complex real-world problems. However, the single-model-based approach for multi-task learning suffers from inter-task interference in practice. Therefore, the exploration of more efficient multi-task learning strategies, aimed at balancing the synergy and conflict among tasks and minimizing the dependence on computational resources, is pivotal for the field's future progress. We propose a strategy that autonomously adjusts both the parameters and structures of the model to alleviate gradient interference in multi-task learning. This method includes integrating a lightweight, weight-adaptive module that enhances the network's ability to process tasks by optimally balancing parameter sharing and isolation. This adaptation enables the model to share common features across tasks while allocating distinct spaces for each task, thereby reducing interference. Our extensive experimental validation indicates that our framework surpasses other multi-task learning approaches, achieving joint optimization of tasks more effectively. This enhancement not only bolsters performance but also maintains an equilibrium between accuracy and inference speed. © 2024 IEEE.

关键词： Multi-task learning

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：