检索结果-内蒙古大学图书馆

2nd International Conference for Advancement in technology, ICONAT 2023

作者： Liu, Hongkang Deng, Feifei Wuhan University of Technology School of Computer Science and Artificial Intelligence Hubei Wuhan China

ISBN: (纸本)9781665475174

Convolutional neural networks are widely used in deep learning, and convolutional computation accounts for the largest proportion of time in convolutional neural networks, which basically determines the performance of the whole network, so it is important to perform acceleration optimization for the convolutional layer, which can improve the operation speed of the whole neural network to a certain extent and thus accelerate the forward inference of the model. In this paper, we propose an effective convolutional acceleration method that combines traditional compilation techniques and deep learning compilation techniques, starting from the data layout and computational order of the input matrix for convolutional operations. First, we combine the data layout of the input matrix in the MEC algorithm with the loop unrolling, which enhances the parallelism of data transformation. Next, we integrate the intermediate state matrix multiplication operation with the traditional compilation optimization technique and the Ansor [22] in deep learning compiler TVM, which effectively improves the speed of the matrix multiplication operation. In addition, our experiments show that our method effectively speeds up the convolution operation and reduces the running time. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Image Tampering Detection With Frequency-Aware Attention and Multiview Fusion

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial intelligence 2025年第3期6卷 614-625页

作者： Xu, Xu Chen, Junxin Lv, Wenrui Wang, Wei Zhang, Yushu Dalian University of Technology School of Software Dalian116621 China Northeastern University School of Computer Science and Engineering Shenyang110004 China Shenzhen MSU-BIT University Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen518172 China Jiangxi University of Finance and Economics School of Computing and Artificial Intelligence Nanchang330013 China

Manipulated images are flooding our daily lives, which poses a threat to social security. Recently, many studies have focused on image tampering detection. However, they have poor performance on independent validation due to differences in image scenes and tampering methods. The key question is how to design a network that is able to adaptively enhance the tampering information and suppress the generalization features during training. To this end, we propose a dual-branch network with a frequency adaptation paradigm and a feature fusion module for robust tampering image detection. First, this paradigm is designed to adaptively highlight tampering features through frequency conversion and learnable weight. Second, a feature fusion module is developed to filter redundant features and dynamically fuse two-branch features. Experiments on eight typical datasets demonstrate that our model has advantages over state-of-the-art algorithms, and our paradigm can well empower semantic segmentation networks for tampering detection. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Joint computation offloading and parallel scheduling to maximize delay-guarantee in cooperative MEC systems

引用

Digital Communications and Networks 2024年第3期10卷 693-705页

作者： Mian Guo Mithun Mukherjee Jaime Lloret Lei Li Quansheng Guan Fei Ji School of Electronics and Information Guangdong Polytechnic Normal UniversityGuangzhouChina School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjingChina Universitat Politecnica de Valencia 46022ValenciaSpain South China University of Technology China

The growing development of the Internet of Things(IoT)is accelerating the emergence and growth of new IoT services and applications,which will result in massive amounts of data being generated,transmitted and pro-cessed in wireless communication *** Edge Computing(MEC)is a desired paradigm to timely process the data from IoT for value *** MEC,a number of computing-capable devices are deployed at the network edge near data sources to support edge computing,such that the long network transmission delay in cloud computing paradigm could be *** an edge device might not always have sufficient resources to process the massive amount of data,computation offloading is significantly important considering the coop-eration among edge ***,the dynamic traffic characteristics and heterogeneous computing capa-bilities of edge devices challenge the *** addition,different scheduling schemes might provide different computation delays to the offloaded ***,offloading in mobile nodes and scheduling in the MEC server are coupled to determine service *** paper seeks to guarantee low delay for computation intensive applica-tions by jointly optimizing the offloading and scheduling in such an MEC *** propose a Delay-Greedy Computation Offloading(DGCO)algorithm to make offloading decisions for new tasks in distributed computing-enabled mobile devices.A Reinforcement Learning-based Parallel Scheduling(RLPS)algorithm is further designed to schedule offloaded tasks in the multi-core MEC *** an offloading delay broadcast mechanism,the DGCO and RLPS cooperate to achieve the goal of delay-guarantee-ratio ***,the simulation results show that our proposal can bound the end-to-end delay of various *** under slightly heavy task load,the delay-guarantee-ratio given by DGCO-RLPS can still approximate 95%,while that given by benchmarked algorithms is reduced to intolerable *** simulation resul

关键词： Edge computing Computation offloading Parallel scheduling Mobile-edge cooperation Delay guarantee

来源：评论

学校读者我要写书评

暂无评论

Product Quality Enhancement in Social Media using Emotion-Enhanced Bert (EE-BERT) Model 2

Product Quality Enhancement in Social Media using Emotion-En...

引用

2nd International Conference on Self Sustainable artificial intelligence Systems, ICSSAS 2024

作者： Raj Kumar, V.S. Kumaresan, T. Mythily, V. Raghavendran, N. Bannari Amman Institute of Technology Department of Artificial Intelligence and Data science Sathyamangalam India Bannari Amman Institute of Technology Department of Computer Science and Engineering Sathyamangalam India Nandha Engineering College Department of Computer Science and Engineering Erode India Rmk college of Engineering and Technology Department of Artificial Intelligence and Data science Chennai India

ISBN: (纸本)9798350368413

Twitter plays an important role in understanding the consumer sentiment about the products. The advanced analytics and Natural Language Processing (NLP) are used to extract actionable insights from this data and useful for a business to improve features and address issues on time for better customer satisfaction and brand loyalty. Most of the current models suffer from a lack of effective ways to handle subtle sentiment analysis because of a lack of contextual understanding and proper feature extraction. Most traditional models cannot combine and optimize features that lead to obtaining sentiments. This leads to overfitting and problems caused by local minima. The proposed Emotion-Enhanced BERT (EE-BERT) model is an extension of the standard BERT to learn contextual embeddings in user sentiment. In this work, data preprocessing includes text cleaning, tokenization, dealing with emojis and emoticons, and lemmatization with the best quality data. The proposed work is basically a dual-stream architecture extended with butterfly optimizer. First, the advanced tokenization and semantic understanding techniques is used for extracting textual features. Second, the emotion-enhanced features extracted through emotion-hash vectorization to enhance the model's contextual awareness in social media data. This provides a unified framework that combines the feature extraction methods to enhance the accuracy in sentiment analysis. It demonstrated with an impressive accuracy of 98.2% on sentiment in posts and comments with 0.15 losses. The proposed work is free from overfitting and local minima in product quality enhancement. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Deep Wyner-Ziv Decoding Using Auxiliary Hierarchical Features 3

Deep Wyner-Ziv Decoding Using Auxiliary Hierarchical Feature...

引用

2023 3rd International Conference on Electrical, Electronics, and Computing technology, EECT 2023

作者： Zhou, Junwei Yi, Xiangbo School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan430070 China

Wyner-Ziv (WZ) video coding shifts the burden of complex calculations from the encoder to the decoder, making it suitable for video coding scenarios with limited resources. Motivated by deep learning has shown superior performance over traditional methods, this paper proposes deep WZ video coding with the help of auxiliary hierarchical features in the decoder. It uses an autoencoder to encode WZ frames. In the decoder side, an inter-frame correlation model called SI-Net is employed to enhance WZ frame quality with Key frames. The auxiliary hierarchical features are extracted from Key frames through multi-level downsampling and employed in autoencoder to optimize feature extraction, avoiding gradient disappearance caused by deep networks. Since the auxiliary hierarchical features of Key frames describe spatial information and expand the network's perception of video frame features, a high-quality WZ frame reconstructed can be obtained. Compared with previous work, our method shows obvious superiority on four video datasets with different degrees of motion. © Published under licence by IOP Publishing Ltd.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Cyclical Training Framework with Graph Feature Optimization for Knowledge Graph Reasoning

引用

computers, Materials & Continua 2025年第5期83卷 1951-1971页

作者： Xiaotong Han Yunqi Jiang Haitao Wang Yuan Tian School of Artificial Intelligence Jilin UniversityChangchun130012China Engineering Research Center of Knowledge-Driven Human-Machine Intelligence MOEChangchun130012China College of Computer Science and Technology Jilin UniversityChangchun130012China

Knowledge graphs(KGs),which organize real-world knowledge in triples,often suffer from issues of *** address this,multi-hop knowledge graph reasoning(KGR)methods have been proposed for interpretable knowledge graph *** primary approaches to KGR can be broadly classified into two categories:reinforcement learning(RL)-based methods and sequence-to-sequence(seq2seq)-based *** each method has its own distinct advantages,they also come with inherent *** leverage the strengths of each method while addressing their weaknesses,we propose a cyclical training method that alternates for several loops between the seq2seq training phase and the policy-based RL training phase using a transformer ***,a multimodal data encoding(MDE)module is introduced to improve the representation of entities and relations in *** module treats entities and relations as distinct modalities,processing each with a dedicated network specialized for its respective *** then combines the representations of entities and relations in a dynamic and fine-grained manner using a gating *** experimental results from the knowledge graph completion task highlight the effectiveness of the proposed *** five benchmark datasets,our framework achieves an average improvement of 1.7%in the Hits@1 metric and a 0.8%average increase in the Mean Reciprocal Rank(MRR)compared to other strong baseline ***,the maximum improvement in Hits@1 exceeds 4%,further demonstrating the effectiveness of the proposed approach.

关键词： Knowledge graph reinforcement learning transformer

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

Can Large Language Models Analyze Graphs like Professionals? A Benchmark, datasets and Models 38

Can Large Language Models Analyze Graphs like Professionals?...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Xin Chen, Weize Chu, Qizhi Li, Haopeng Sun, Zhaojun Li, Ran Qian, Chen Wei, Yiwei Liu, Zhiyuan Shi, Chuan Sun, Maosong Yang, Cheng School of Computer Science Beijing University of Posts and Telecommunications China Department of Computer Science and Technology Tsinghua University China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Karamay China Institute for Artificial Intelligence Tsinghua University China

The need to analyze graphs is ubiquitous across various fields, from social networks to biological research and recommendation systems. Therefore, enabling the ability of large language models (LLMs) to process graphs is an important step toward more advanced general intelligence. However, current LLM benchmarks on graph analysis require models to directly reason over the prompts describing graph topology, and are thus limited to small graphs with only a few dozens of nodes. In contrast, human experts typically write programs based on popular libraries for task solving, and can thus handle graphs with different scales. To this end, a question naturally arises: can LLMs analyze graphs like professionals? In this paper, we introduce ProGraph, a manually crafted benchmark containing 3 categories of graph tasks. The benchmark expects solutions based on programming instead of directly reasoning over raw inputs. Our findings reveal that the performance of current LLMs is unsatisfactory, with the best model achieving only 36% accuracy. To bridge this gap, we propose LLM4Graph datasets, which include crawled documents and auto-generated codes based on 6 widely used graph libraries. By augmenting closed-source LLMs with document retrieval and fine-tuning open-source ones on the codes, we show 11-32% absolute improvements in their accuracies. Our results underscore that the capabilities of LLMs in handling structured data are still under-explored, and show the effectiveness of LLM4Graph in enhancing LLMs' proficiency of graph analysis. The benchmark, datasets and enhanced open-source models are available at https://***/BUPT-GAMMA/ProGraph. © 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

Collaborative Edge Server Placement for Maximizing QoS With Distributed data Cleaning

引用

IEEE Transactions on Services Computing 2025年第3期18卷 1321-1335页

作者： Liang, Yuzhu Yin, Mujun Wang, Wenhua Liu, Qin Wang, Liang Zheng, Xi Wang, Tian Beijing Normal University Institute of Artificial Intelligence and Future Networks Zhuhai519000 China Huaqiao University College of Computer Science and Technology Xiamen361021 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Northwestern Polytechnical University School of Computer Science Xi’an710072 China Macquarie University School of Computing SydneyNSW2109 Australia

The proliferation of contaminated data on Internet of Things (IoT) devices has the potential to undermine the accuracy of data-driven decision-making by altering the distribution of original data. Existing data cleaning methods primarily depend on cloud center or cloud-edge cooperation, leading to prolonged data transmission delays and reduced cleaning accuracy. In this study, we identify edge server placement as a crucial step aligned with data cleaning and view the collaborative edge server placement with distributed data cleaning (SPDC) as a holistic problem. We comprehensively quantify the complexity of our issue through the analysis of numerous scenarios. To address this problem, we introduce a novel distributed collaborative edge framework comprising two key stages: server placement and data cleaning. We propose an optimized clustering algorithm for the former, considering the data distribution on the IoT layer and the constraints of the edge layer. For the latter, we introduce a gossip-based data cleaning algorithm that fully utilizes edge collaboration to enhance data cleaning accuracy. The algorithm exhibits an approximate performance complexity of O(ln m), where m represents the number of users’ tasks. Both theoretical analysis and experimental results reveal that our algorithm an average improvement in data cleaning accuracy of 9.02% and a reduction in delay of 36.61%, surpassing the performance of state-of-the-art works in various scenarios. © 2008-2012 IEEE.

关键词： data accuracy

来源：评论

学校读者我要写书评

暂无评论

Research on Tensor Multi-Clustering Distributed Incremental Updating Method for Big data

引用

computers, Materials & Continua 2024年第10期81卷 1409-1432页

作者： Hongjun Zhang Zeyu Zhang Yilong Ruan Hao Ye Peng Li Desheng Shi School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing210023China Ministry of Science and Technology Innovation China Communications Services Corporation LimitedBeijing100071China School of Artificial Intelligence The University of ManchesterManchesterM139PLUK Ministry of Technology Innovation China Telecom Artificial Intelligence Technology(Beijing)Corporation LimitedBeijing100032China Ministry of Science and Technology Innovation Zhongbo Information Technology Research Institute Corporation LimitedNanjing210012China Jiangsu Postal Big Data Technology and Application Engineering Research Center Nanjing University of Posts and TelecommunicationsNanjing210003China

The scale and complexity of big data are growing continuously,posing severe challenges to traditional data processing methods,especially in the field of clustering *** address this issue,this paper introduces a new method named Big data Tensor Multi-Cluster Distributed Incremental Update(BDTMCDIncreUpdate),which combines distributed computing,storage technology,and incremental update techniques to provide an efficient and effective means for clustering ***,the original dataset is divided into multiple subblocks,and distributed computing resources are utilized to process the sub-blocks in parallel,enhancing ***,initial clustering is performed on each sub-block using tensor-based multi-clustering techniques to obtain preliminary *** new data arrives,incremental update technology is employed to update the core tensor and factor matrix,ensuring that the clustering model can adapt to changes in ***,by combining the updated core tensor and factor matrix with historical computational results,refined clustering results are obtained,achieving real-time adaptation to dynamic *** experimental simulation on the Aminer dataset,the BDTMCDIncreUpdate method has demonstrated outstanding performance in terms of accuracy(ACC)and normalized mutual information(NMI)metrics,achieving an accuracy rate of 90%and an NMI score of 0.85,which outperforms existing methods such as TClusInitUpdate and TKLClusUpdate in most ***,the BDTMCDIncreUpdate method offers an innovative solution to the field of big data analysis,integrating distributed computing,incremental updates,and tensor-based multi-clustering *** not only improves the efficiency and scalability in processing large-scale high-dimensional datasets but also has been validated for its effectiveness and accuracy through *** method shows great potential in real-world applications where dynamic data growth is common,and it is of significant imp

关键词： Tensor incremental update distributed clustering processing big data

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：