检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Cao, Yuan Chen, Xiangru Liu, Zifan Jia, Wenzhe Meng, Fanlei Gui, Jie School of Computer Science and Technology Ocean University of China Qingdao China School of Cyber Science and Engineering Southeast University Nanjing China Engineering Research Center of Blockchain Application Supervision and Management (Southeast University) Ministry of Education Nanjing China Purple Mountain Laboratories Nanjing China

ISBN: (纸本)157735897X

Online hashing has attracted much research attention for large-scale image retrieval in a streaming way. The main challenge lies in keeping balance between high retrieval accuracy and low training time. Existing online hashing methods almost rely on shallow models rather than deep networks due to high training costs, because it is unacceptable to update hash functions on an order of hours. In addition, the multi-label supervision information is not fully utilized to guide the hash learning process and the affinity matrix is always fixed once constructed. In this paper, we propose a novel Deep Graph Online Hashing (DGOH) method, which for the first time introduces inductive graph neural networks (GNNs) to realize deep online hashing with acceptable training costs on an order of seconds. Furthermore, we mine the multi-label information of the images by constructing a label network and learn label-wise weights dynamically to help to update the affinity matrix. In addition, we provide a strategy to obtain examples from the old data to solve the catastrophic forgetting problem. An integrated objective function is designed to train the entire architecture. Extensive experiments on two common benchmarks demonstrate that the proposed method achieves up to 13.3% accuracy gains over state-of-the-art baselines and shows competitive performance on training time. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning 38

HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder fo...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Bai, Lu Xu, Zhuo Cui, Lixin Li, Ming Wang, Yue Hancock, Edwin R. School of Artificial Intelligence Beijing Normal University Beijing100875 China Engineering Research Center of Intelligent Technology and Educational Application Ministry of Education Beijing Normal University Beijing100875 China School of Information Central University of Finance and Economics Beijing100081 China Zhejiang Institute of Optoelectronicss Jinhua321004 China Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University Jinhua321004 China Department of Computer Science University of York YorkYO10 5GH United Kingdom

Graph Auto-Encoders (GAEs) are powerful tools for graph representation learning. In this paper, we develop a novel Hierarchical Cluster-based GAE (HC-GAE), that can learn effective structural characteristics for graph data analysis. To this end, during the encoding process, we commence by utilizing the hard node assignment to decompose a sample graph into a family of separated subgraphs. We compress each subgraph into a coarsened node, transforming the original graph into a coarsened graph. On the other hand, during the decoding process, we adopt the soft node assignment to reconstruct the original graph structure by expanding the coarsened nodes. By hierarchically performing the above compressing procedure during the decoding process as well as the expanding procedure during the decoding process, the proposed HC-GAE can effectively extract bidirectionally hierarchical structural features of the original sample graph. Furthermore, we re-design the loss function that can integrate the information from either the encoder or the decoder. Since the associated graph convolution operation of the proposed HC-GAE is restricted in each individual separated subgraph and cannot propagate the node information between different subgraphs, the proposed HC-GAE can significantly reduce the over-smoothing problem arising in the classical convolution-based GAEs. The proposed HC-GAE can generate effective representations for either node classification or graph classification, and the experiments demonstrate the effectiveness on real-world datasets. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Traffic Prediction Analysis (TPA) Using Machine Learning Methodologies

Traffic Prediction Analysis (TPA) Using Machine Learning Met...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Mohit Solanki Vandana Rawat Monika Pandey Neelam Singh Shobha Aswal Department Of Computer Application Graphic Era Deemed To Be University Dehradun India Department Of Computer Science and Engineering Graphic Era Deemed To Be University Dehradun India School of Computing Graphic Era University Dehradun India

A traffic prediction system might help drivers in making better travel choices. Minimizing carbon emissions, reducing traffic congestion, and improving the effectiveness of traffic management to deliver such traffic flow data is the main aim of traffic flow prediction. Prediction of traffic is essential in a system of intelligent transportation. Effective traffic forecasting can help with route design, vehicle dispatching, and reducing traffic congestion. Due to its incredible capacity to predict traffic patterns, a branch of machine learning which is also called “deep learning,” has recently attracted a lot of attention. In this study, a comparative evaluation has been done to predict traffic flow based on deep learning. To prepare the stacked auto encoder model, basic traffic flow features are included. The goal of this study is to conduct a thorough screening for deep earning -based traffic forecast algorithms from multiple angles. This study recommends a deep learning method to predict urban traffic that combines data from twitter messages with traffic and weather data. The predictive model uses a deep Bi-directional long- short-term memory (LSTM) Stacked Auto Encoder (SAE) architecture for multi-step traffic flow prediction that was trained from tweets, traffic, and weather datasets. To support study in this area, it also gathers and arranges frequently available public datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis Scheme for Image-Text Comments Based on Multimodal Deep Learning and Spatiotemporal Attention

Sentiment Analysis Scheme for Image-Text Comments Based on M...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Fanchang TangYa Ling Amit Yadav Abhishek Pratap Sah Asif Khan Department of Software Engineering Chengdu Neusoft University Chengdu China College of Engineering IT and Environment Charles Darwin University NT Australia School of Management Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Application Integral University Lucknow India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

A sentiment analysis scheme for image and text comments based on multimodal deep learning and spatiotemporal attention is proposed to address the issues of incomplete spatiotemporal considerations, incomplete implementation details, and cutting-edge theoretical algorithms in graphic and textual sentiment analysis schemes. The proposed model has clear layering including data preprocessing layer, modal encoding layer, modal fusion layer, sentiment classification layer, loss function and optimizer, evaluation and feedback. The implementation details of each layer are introduced. The entire scheme model incorporates Multimodal Fusion Neural Network (MFNN) deep learning and spatiotemporal attention mechanism, which makes the scheme perform well in terms of security, robustness and performance, making up for the shortcomings of existing research schemes.

关键词： Deep learning Sentiment analysis Neural networks Data preprocessing Encoding Robustness Spatiotemporal phenomena Security Informatics Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Industrial IoT Smart Manufacturing Systems based on Cloud Computing Energy Efficiency Analysis using Machine Learning Algorithms

Industrial IoT Smart Manufacturing Systems based on Cloud Co...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： P. Chinnasamy Patan Feridoz Khan C Sasikala Mavalluru Swathi M Prema Kumar Ajay Kumar Yadav Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Tamilnadu India Department of Computer Science and Engineering School of Computing Mohan Babu University Tirupati Andhra Pradesh India Dept of CSE Srinivasa Ramanujan Institute of Technology (Autonomous) Ananthapuramu Andhra Pradesh India Audisankara College of Engineering and Technology Andhra Pradesh India Dept. of ECE Shri Vishnu Engineering College for Women (A) Bhimavaram Andhra Pradesh India Department of Computer Application United Institute of Management Prayagraj India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

With open connectivity and emergent computing, the Industrial Internet of Things (IIoT) combined with cloud computing resources provides significant breakthroughs in the field of industrial automation. These developments lead to the evolution of supplemental services, which improve automation in the production and industrial sectors. This research proposes novel technique in smart manufacturing system based on cloud computing with IIoT in energy efficiency using machine learning. Here the smart manufacturing process has been analysed based on IIoT with cloud computing network, where the energy efficiency is analysed using virtual machine-based reinforcement markov chain based linear regression. Experimental analysis has been carried out in terms of latency, energy efficiency, task response time, accuracy. proposed technique obtained 97% of Latency, 95% of Energy efficiency, 98% of Accuracy, 94% of Task response time.

关键词： Cloud computing Machine learning algorithms Automation Accuracy Linear regression Energy efficiency Virtual machines Time factors Industrial Internet of Things Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Approach for Threat Detection in Cyber Security using AI algorithm

A Novel Hybrid Approach for Threat Detection in Cyber Securi...

引用

Computing, sciences and Communications (ICCSC), International Conference on

作者： Abhishek Kumar Gupta Neetu Dixit Sujeet Kumar Priyanka Rawat Madhumita Department of Information Technology Jagannath International Management School New Delhi Department of Computer Application RBMI Greater Noida India GL Bajaj Institute of Management Greater Noida India Department of Computer Science & Engineering Lingaya's Vidyapeeth Faridabad India

ISBN: (数字)9798350353648

ISBN: (纸本)9798350353655

The dynamic cyber-attack landscape might require more traditional ways of detecting and preventing threats. It has also paved the way for new hybrid approaches that merge attributes of two or more different methods, enabling a better and more efficient cyber defence. Such an approach would be to apply artificial intelligence (AI) algorithms to detect threats. In this way, organizations can apply various capabilities to automatically scan network traffic round-the-clock for indicators of suspicious activities, notifying security teams immediately. Despite this, a system that relies entirely on AI algorithms gets many false positives, increasing the time and effort required by security personnel. Our hybrid approach includes human expertise and input to help detect potential risks. This comes as a human-in-the-loop solution, where AI algorithms identify suspicious signals, and humans then corroborate those leads before making an arrest. Combining human and AI intelligence results in a far more accurate and efficient threat detection system. Our strategy incorporates big data analytics and anomaly detection methods to highlight unusual behaviours that suggest a risk is forming. This allows our system to discover and eliminate these cyber attacks in real-time instead of merely reacting after a breach. By leveraging our novel hybrid approach, you can have better coverage and a more robust cyber security plan in the face of threats, giving you a higher level of protection and peace of mind about future attacks.

关键词： Training Telecommunication traffic Feature extraction Threat assessment Real-time systems Classification algorithms Security Artificial intelligence Faces Cyberattack

来源：评论

学校读者我要写书评

暂无评论

Disentangling Heterogeneous Knowledge Concept Embedding for Cognitive Diagnosis on Untested Knowledge

arXiv

引用

arXiv 2024年

作者： Zhang, Miao Wang, Ziming Xing, Runtian Xiao, Kui Li, Zhifei Zhang, Yan Tang, Chang School of Computer Science and Information Engineering Hubei University China Key Laboratory of Intelligent Sensing System and Security China Hubei Key Laboratory of Big Data Intelligent Analysis and Application China

Cognitive diagnosis is a fundamental and critical task in learning assessment, which aims to infer students’ proficiency on knowledge concepts from their response logs. Current works assume each knowledge concept will certainly be tested and covered by multiple exercises. However, whether online or offline courses, it’s hardly feasible to completely cover all knowledge concepts in several exercises. Restricted tests lead to undiscovered knowledge deficits, especially untested knowledge concepts(UKCs). In this paper, we propose a novel framework for Cognitive Diagnosis called Disentangling Heterogeneous Knowledge Cognitive Diagnosis(DisKCD) on untested knowledge. Specifically, we leverage course grades, exercise questions, and learning resources to learn the potential representations of students, exercises, and knowledge concepts. In particular, knowledge concepts are disentangled into tested and untested based on the limiting actual exercises. We construct a heterogeneous relation graph network via students, exercises, tested knowledge concepts(TKCs), and UKCs. Then, through a hierarchical heterogeneous message-passing mechanism, the fine-grained relations are incorporated into the embeddings of the entities. Finally, the embeddings will be applied to multiple existing cognitive diagnosis models to infer students’ proficiency on UKCs. Experimental results on real-world datasets show that the proposed model can effectively improve the performance of the task of diagnosing students’ proficiency on UKCs. Our code is available at https://***/Hubuers/DisKCD. © 2024, CC BY.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Hierarchical multi-granularity classification based on bidirectional knowledge transfer

引用

Multimedia Systems 2024年第4期30卷 207-207页

作者： Jiang, Juan Yang, Jingmin Zhang, Wenjie Zhang, Hongbin School of Computer Science Minnan Normal University Fujian Zhangzhou363000 China Key Laboratory of Data Science and Intelligence Application Fujian Province University Fujian Zhangzhou363000 China Department of Electronic Engineering National Taipei University of Technology Taipei China

Hierarchical multi-granularity classification is the task of classifying objects according to multiple levels or granularities. The class hierarchy is vital side information for hierarchical multi-granularity classification. The existing hierarchical multi-granularity classification research utilizes class hierarchy to classify from coarse to fine or fine to coarse. Although these methods are effective in many cases, there are still two issues: (1) multi-task learning for hierarchical multi-granularity classification leads to decreased classification performance;(2) class hierarchy transfer learning is prone to error propagation. In this paper, we propose a bidirectional knowledge transfer model framework to address these issues. Firstly, we improve classification performance through data augmentation. Specifically, by learning the similarity between the original image and the enhanced image, better learn discriminative features, which is beneficial for subsequent classification. Secondly, using class hierarchy trees, we propose reverse hierarchical knowledge transfer to correct some errors in forward hierarchical propagation and improve hierarchical consistency. In addition, we also construct a hierarchical network that adds features from coarse-grained levels to fine-grained levels. The experimental results on six datasets with different class hierarchies demonstrate the effectiveness and superiority of the proposed model. Especially on the CUB-200-2011 and Cifar-100 datasets, our model improved classification accuracy by 3.61% and 4.17% compared to the suboptimal model. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Modality Decoupling is All You Need: A Simple Solution for Unsupervised Hyperspectral Image Fusion

arXiv

引用

arXiv 2024年

作者： Du, Songcheng Zou, Yang Wang, Zixu Li, Xingyuan Li, Ying Shen, Qiang School of Computer Science Northwestern Polytechnical University China School of Software Technology Dalian University of Technology China Institute of Mathematics Physics and Computer Science Aberystwyth University United Kingdom The National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University China

Hyperspectral Image Fusion (HIF) aims to fuse low-resolution hyperspectral images (LR-HSIs) and high-resolution multispectral images (HR-MSIs) to reconstruct high spatial and high spectral resolution images. Current methods typically apply direct fusion from the two modalities without valid supervision, failing to fully perceive the deep modality-complementary information and hence, resulting in a superficial understanding of inter-modality connections. To bridge this gap, we propose a simple and effective solution for unsupervised HIF with an assumption that modality decoupling is essential for HIF. We introduce the modality clustering loss that ensures clear guidance of the modality, decoupling towards modality-shared features while steering clear of modality-complementary ones. Also, we propose an end-to-end Modality-Decoupled Spatial-Spectral Fusion (MossFuse) framework that decouples shared and complementary information across modalities and aggregates a concise representation of the LR-HSI and HR-MSI to reduce the modality redundancy. Systematic experiments over multiple datasets demonstrate that our simple and effective approach consistently outperforms the existing HIF methods while requiring considerably fewer parameters with reduced inference time. Copyright © 2024, The Authors. All rights reserved.

关键词： Spectral resolution

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical and Ensemble Surrogate-Assisted Evolutionary Algorithm With Model Reduction for Expensive Many-Objective Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Yang, Qi-Te Li, Jian-Yu Zhan, Zhi-Hui Jiang, Yunliang Jin, Yaochu Zhang, Jun School of Computer Science and Engineering South China University of Technology Guangzhou China College of Artificial Intelligence Nankai University Tianjin China Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University Jinhua China School of Engineering Westlake University Hangzhou China

The Kriging model has been widely used in regression-based surrogate-assisted evolutionary algorithms (SAEAs) for expensive multiobjective optimization by using one model to approximate one objective, and the fusion of all the models forms the fitness surrogate. However, when tackling expensive many-objective optimization problems, too many models are required to construct such a fitness surrogate, which incurs cumulative prediction uncertainty and higher computational cost. Considering that the fitness surrogate works to predict different objective values to help select promising solutions with good convergence and diversity, this article proposes a novel model reduction idea to change the many-models-based fitness surrogate to a two-models-based indicator surrogate (TIS) that directly approximates convergence and diversity indicators. Based on TIS, a hierarchical and ensemble surrogate-assisted evolutionary algorithm (HES-EA) is proposed with three stages. Firstly, the HES-EA transforms the many objectives of the real-evaluated solutions into two indicators (i.e., the convergence and diversity indicators) and divides these solutions into different clusters. Secondly, a HES consisting of a cluster surrogate and different TISs is trained through these clustered solutions and their indicators. Thirdly, during the optimization process, the HES can predict the candidate solutions’ cluster information via the cluster surrogate and indicator information via the TISs. Promising solutions can thus be selected based on the predicted information via a clustering-based sequential selection strategy without real fitness evaluation consumption. Compared with state-of-the-art SAEAs on three widely used benchmark suites up to 184 instances and one real-world application, HES-EA shows its superiority in both optimization performance and computational cost. IEEE

关键词： Kriging

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：