检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wan, Zhijing Wang, Zhixiang Wang, Yuran Wang, Zheng Zhu, Hongyuan Satoh, Shinichi National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Wuhan University China Hubei Key Laboratory of Multimedia and Network Communication Engineering China The University of Tokyo Japan National Institute of Informatics Japan A*STAR Singapore

Coreset selection seeks to choose a subset of crucial training samples for efficient learning. It has gained traction in deep learning, particularly with the surge in training dataset sizes. Sample selection hinges on two main aspects: a sample's representation in enhancing performance and the role of sample diversity in averting overfitting. Existing methods typically measure both the representation and diversity of data based on similarity metrics, such as L2-norm. They have capably tackled representation via distribution matching guided by the similarities of features, gradients, or other information between data. However, the results of effectively diverse sample selection are mired in sub-optimality. This is because the similarity metrics usually simply aggregate dimension similarities without acknowledging disparities among the dimensions that significantly contribute to the final similarity. As a result, they fall short of adequately capturing diversity. To address this, we propose a feature-based diversity constraint, compelling the chosen subset to exhibit maximum diversity. Our key lies in the introduction of a novel Contributing Dimension Structure (CDS) metric. Different from similarity metrics that measure the overall similarity of high-dimensional features, our CDS metric considers not only the reduction of redundancy in feature dimensions, but also the difference between dimensions that contribute significantly to the final similarity. We reveal that existing methods tend to favor samples with similar CDS, leading to a reduced variety of CDS types within the coreset and subsequently hindering model performance. In response, we enhance the performance of five classical selection methods by integrating the CDS constraint. Our experiments on three datasets demonstrate the general effectiveness of the proposed method in boosting existing methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Evolving Long-Short Term Memory Networks with Attention for Network Intrusion Detection

SSRN

引用

SSRN 2022年

作者： Wei, Wenhong Chen, Yi Lin, Qiuzhen Ji, Junkai Wong, Ka-Chun Li, Jianqiang School of Computer Science and Technology Dongguan University of Technology Dongguan China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong

Cyber security has received more and more attention, as people use more Internet applications in their life and are concerned about the security of their personal data. Intrusion Detection System (IDS) is an important security tool that can detect abnormal Internet network activities. Deep Learning (DL) techniques have been widely applied in the field of IDS and achieved promising performance in terms of detection accuracy. However, the design of DL architectures usually requires professional knowledge and dramatically impacts the performance of the DL model. Moreover, due to the existence of a small ratio of abnormal traffic in a large number of network traffic, this serious imbalance data problem leads to poor performance of the DL model in detecting minority attack classes. To alleviate these problems, this paper proposes a hybrid evolutionary DL model (called EvoBMF) to detect intrusion behaviors in the network, which uses bidirectional Long-short Term Memory (BiLSTM) for preliminary feature extraction, Multi-Head Attention (MHA) for further capturing features and global information of the network traffic, and full-connected layer module to do final classification. To deal with the problem of parameter tuning manually in the DL model when tackling different tasks, the EvoBMF model is first encoded as the chromosome of Multi-objective Evolutionary Algorithm (MOEA) and then its two conflicting objectives (the complexity and classification ability of the model) will be optimized. Later, a state-of-the-art MOEA (MOEA/D-DRA) is modified to optimize the above two objectives, which can obtain the optimal architecture for EvoBMF. The proposed EvoBMF model can be easily deployed in Cloud computing scenarios to resist network intrusion. Moreover, in order to alleviate the severe imbalance in routine network traffic, the synthetic minority over-sampling technique is introduced to generate representative samples of minority classes in order to improve the overall performanc

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Long-Term Preservation of Electronic Record Based on Digital Continuity in Smart Cities

引用

computers, Materials & Continua 2021年第3期66卷 3271-3287页

作者： Yongjun Ren Kui Zhu Yuqiu Gao Jinyue Xia Shi Zhou Ruiguo Hu Xiujuan Feng School of Computer and Software Engineering Research Center of Digital ForensicsMinistry of EducationNanjing University of Information Science&TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China Changwang School of Honors Nanjing University of Information Science&TechnologyNanjing210044China International Business Machines Corporation(IBM) USA School of Architectural and Surveying&Mapping Engineering Jiangxi University of Science and TechnologyGan Zhou341000China

Under the co-promotion of the wave of urbanization and the rise of data science,smart cities have become the new concept and new practice of urban *** cities are the combination of information technology represented by the Internet of Things,cloud computing,mobile networks and big data,and *** to effectively achieve the long-term preservation of massive,heterogeneous,and multi-source digital electronic records in smart cities is a key issue thatmust be *** continuity can ensure the accessibility,integrity and availability of *** quality management of electronic record,like the quality management of product,will run through every phase of the urban *** on data quality management,this paper constructs digital continuity of smart city electronic ***,thework in this paper ensures the authenticity,integrity,availability and timeliness of electronic documents by quality management of electronic *** paper elaborates on the overall technical architecture of electronic record,as well as the various technical means needed to protect its four characteristics.

关键词： Smart city electronic record long term preservation digital continuity

来源：评论

学校读者我要写书评

暂无评论

When Digital Economy Meets Web3.0: Applications and Challenges

arXiv

引用

arXiv 2022年

作者： Chen, Chuan Zhang, Lei Li, Yihao Liao, Tianchi Zhao, Siran Zheng, Zibin Huang, Huawei Wu, Jiajing School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510275 China School of Software Engineering Sun Yat-Sen University Zhuhai519000 China

With the continuous development of web technology, Web3.0 has attracted a considerable amount of attention due to its unique decentralized characteristics. The digital economy is an important driver of high-quality economic development and is currently in a rapid development stage. In the digital economy scenario, the centralized nature of the Internet and other characteristics usually bring about security issues such as infringement and privacy leakage. Therefore, it is necessary to investigate how to use Web3.0 technologies to solve the pain points encountered in the development of the digital economy by fully exploring the critical technologies of digital economy and Web3.0. In this paper, we discuss the aspects of Web3.0 that should be integrated with the digital economy to better find the entry point to solve the problems by examining the latest advances of Web3.0 in machine learning, finance, and data management. We hope this research will inspire those who are involved in both academia and industry, and finally help to build a favourable ecology for the digital economy. Copyright © 2022, The Authors. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Mining High Utility Itemset with Multiple Minimum Utility Thresholds Based on Utility Deviation

Mining High Utility Itemset with Multiple Minimum Utility Th...

引用

IEEE International Conference on Data Mining Workshops (ICDM Workshops)

作者： Naji Alhusaini Jing Li Philippe Fournier-Viger Ammar Hawbani Guilin Chen School of Computer and Information Engineering. Chuzhou University Chuzhou China School of Computer Since and Technology University of Since and Technology of China Hefei China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

High Utility Itemset Mining (HUIM) is the task of extracting actionable patterns considering the utility of items such as profits and quantities. An important issue with traditional HUIM methods is that they evaluate all items using a single threshold, which is inconsistent with reality due to differences in the nature and importance of items. Recently, algorithms were proposed to address this problem by assigning a minimum item utility threshold to each item. However, since the minimum item utility (MIU) is expressed as a percentage of the external utility, these methods still face two problems, called “itemset missing” and “itemset explosion”. To solve these problems, this paper introduces a novel notion of Utility Deviation (UD), which is calculated based on the standard deviation. The U D and actual utility are jointly used to calculate the MIU of items. By doing so, the problems of “itemset missing” and “itemset explosion” are alleviated. To implement and evaluate the U D notion, a novel algorithm is proposed, called HUI-MMU-UD. Experimental results demonstrate the effectiveness of the proposed notion for solving the problems of “itemset missing” and “itemset explosion”. Results also show that the proposed algorithm outperforms the previous HUI-MMU algorithm in many cases, in terms of runtime and memory usage.

关键词： Runtime Itemsets Conferences Explosions Data mining Task analysis Standards

来源：评论

学校读者我要写书评

暂无评论

Reasoning3D - Grounding and Reasoning in 3D: Fine-Grained Zero-Shot Open-Vocabulary 3D Reasoning Part Segmentation via Large Vision-Language Models

arXiv

引用

arXiv 2024年

作者： Chen, Tianrun Yu, Chunan Li, Jing Zhang, Jianqi Zhu, Lanyun Ji, Deyi Zhang, Yong Zang, Ying Li, Zejian Sun, Lingyun Tech. Co. Ltd China College of Computer Science and Technology Zhejiang University China School of Information Engineering Huzhou University China Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore School of Software Technology Zhejiang University China School of Information Science and Technology University of Science and Technology of China China

In this paper, we introduce a new task: Zero-Shot 3D Reasoning Segmentation for parts searching and localization for objects, which is a new paradigm to 3D segmentation that transcends limitations for previous category-specific 3D semantic segmentation, 3D instance segmentation, and open-vocabulary 3D segmentation. We design a simple baseline method, Reasoning3D, with the capability to understand and execute complex commands for (fine-grained) segmenting specific parts for 3D meshes with contextual awareness and reasoned answers for interactive segmentation. Specifically, Reasoning3D leverages an off-the-shelf pre-trained 2D segmentation network, powered by Large Language Models (LLMs), to interpret user input queries in a zero-shot manner. Previous research have shown that extensive pre-training endows foundation models with prior world knowledge, enabling them to comprehend complex commands, a capability we can harness to "segment anything" in 3D with limited 3D datasets (source efficient). Experimentation reveals that our approach is generalizable and can effectively localize and highlight parts of 3D objects (in 3D mesh) based on implicit textual queries, including these articulated 3d objects and real-world scanned data. Our method can also generate natural language explanations corresponding to these 3D models and the decomposition. Moreover, our training-free approach allows rapid deployment and serves as a viable universal baseline for future research of part-level 3d (semantic) object understanding in various fields including robotics, object manipulation, part assembly, autonomous driving applications, augment reality and virtual reality (AR/VR), and medical applications. The code, the model weight, the deployment guide, and the evaluation protocol are: http://***/Reason3D/. © 2024, CC BY-NC-ND.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Dual Branch CNN and Transformer for Cardiac Atherosclerotic Plaque Classification

Dual Branch CNN and Transformer for Cardiac Atherosclerotic ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Haijun Lei Jia Zhao Guanjie Tong Longjiang Zhang Huaqiang Su Baiying Lei College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Radiology Jinling Hospital Medical School of Nanjing University Shenzhen University Nanjing China School of Biomedical Engineering& Shenzhen University Medical School Shenzhen University Shenzhen China

Accurate classification of coronary artery plaques can provide effective assistance for the diagnosis of coronary artery disease(CAD). The task of coronary artery plaque classification remains extremely challenging due to the complex anatomical structure and background of coronary arteries. 3D convolution still has limitations in feature modeling, so this study builds a dual branch bridge network based on convolution neural network (CNN) and Transformer framework, and fused the local feature extraction ability of convolution and the global modeling ability of Transformer through the bridge communication module. By using a shift attention (SA) module at the intersection of dual branch information to utilizes minimal computational complexity to fuse feature maps from both branches. The ghost plus (GP) module was aimed at balancing the enormous computational power issues of building rich semantic information and training difficulties in 3D Transformers. The proposed method have demonstrated the effectiveness through a large number of comparative and ablation experiment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Attention-based Explainable Deep Learning Framework Towards Medical Image Classification

A Novel Attention-based Explainable Deep Learning Framework ...

引用

Innovative Approaches in Smart Technologies (ISAS), International Symposium on

作者： Gladys W. Muoka Ding Yi Chiagoziem Chima Ukwuoma Moindi Duke Martin Ahmet Arif Aydin Mugahed A. Al-Antari School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu China Department of Computer Science Unicaf University Lilongwe Lilongwe Malawi Department of Computer Engineering Faculty of Engineering İnönü University Turkey Department of Artificial Intelligence College of Software & Convergence Technology Daeyang AI Center Sejong University Seoul Korea

Deep learning applications for medical image classification have shown remarkable promise, particularly incorporating attention-based neural networks. This is particularly relevant in medical imaging, where the integration of Artificial Intelligence assists with various imaging tasks, including classification, segmentation, and detection. Deep learning is revolutionizing medical research and playing a significant role in advancing personalized clinical treatment. However, the lack of interpretability in these models presents a significant obstacle to their adoption in clinical practice. Therefore, there is a growing need for a comprehensive understanding of artificial intelligence systems and their internal mechanisms, capabilities, and limitations, which is the focus of the field of explainable AI. This study proposes a novel attention-based explainable deep learning framework for medical image classification tasks, including Covid-19, breast cancer (BreakHis), lung cancer (LC2500), and Retinal optical coherence tomography (OCT). The proposed framework recorded overall accuracies of 98% (Covid-19 Radiography), 95% (BreakHis), 99.8% (LC2500), and 95%(OCT). For visual analysis of the outcomes, we employ and use the LIME, SHAP, and ELI-5 to analyze the achieved results. The study’s primary goal is to bridge the gap between the high performance achieved by attention-based models and the necessity for transparency and interpretability in medical image diagnostics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LALISA: Adaptive Bitrate Ladder Optimization in HTTP-based Adaptive Live Streaming

LALISA: Adaptive Bitrate Ladder Optimization in HTTP-based A...

引用

IEEE Symposium on Network Operations and Management

作者： Farzad Tashtarian Abdelhak Bentaleb Hadi Amirpour Babak Taraghi Christian Timmerer Hermann Hellwagner Roger Zimmermann Christian Doppler Laboratory ATHENA Alpen-Adria-Universitat Klagenfurt Austria Department of Computer Science and Software Engineering Concordia University Canada School of Computing National University of Singapore Singapore

Video content in Live HTTP Adaptive Streaming (HAS) is typically encoded using a pre-defined, fixed set of bitrate-resolution pairs (termed Bitrate Ladder), allowing play-back devices to adapt to changing network conditions using an adaptive bitrate (ABR) algorithm. However, using a fixed one-size-fits-all solution when faced with various content complexities, heterogeneous network conditions, viewer device resolutions and locations, does not result in an overall maximal viewer quality of experience (QoE). Here, we consider these factors and design LALISA, an efficient framework for dynamic bitrate ladder optimization in live HAS. LALISA dynamically changes a live video session’s bitrate ladder, allowing improvements in viewer QoE and savings in encoding, storage, and bandwidth costs. LALISA is independent of ABR algorithms and codecs, and is deployed along the path between viewers and the origin server. In particular, it leverages the latest developments in video analytics to collect statistics from video players, content delivery networks and video encoders, to perform bitrate ladder tuning. We evaluate the performance of LALISA against existing solutions in various video streaming scenarios using a trace-driven testbed. Evaluation results demonstrate significant improvements in encoding computation (24.4%) and bandwidth (18.2%) costs with an acceptable QoE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge-Guided Multilevel Feature Fusion Network for Lightweight Camouflaged Object Detection

Edge-Guided Multilevel Feature Fusion Network for Lightweigh...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xingpeng Zhang Meilin Gao Guohai Gao Xin Wang Qiuli Wang School of Computer Science and Software Engineering Southwest Petroleum University Chengdu China Engineering Research Center for Intelligent Oil & Gas Exploration and Development of Sichuan Province Chengdu China Department of Radiology The First Affiliated Hospital of Army Medical University Chongging China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Camouflaged object detection (COD) aims to accurately recognize targets in intricate environments that blend into the background. Although numerous camouflage object identification techniques have demonstrated effectiveness, they often possess a substantial number of parameters. Therefore, we propose a new lightweight edge-guided multilevel feature fusion camouflaged object detection network, codenamed as LEMFNet. Initially, we adopt a lightweight CNN network model for feature extraction to reduce model complexity. Subsequently, we introduced a neighborhood feature association module (NFAM) to integrate feature information from different stages to obtain complementary feature representations and enhance the overall model performance. Furthermore, to obtain a more complete object structure, we introduce a boundary aggregation module (BAM) to delve into the edge semantics associated with the target and integrate the edge features into the proposed edge-guided aggregation module (EGAM). Experiments on three challenging benchmarks demonstrate our approach, with fewer parameters, achieves comparable or superior performance, effectively balancing resource utilization and accuracy.

关键词： Accuracy Target recognition Image edge detection Semantics Neural networks Object detection Benchmark testing

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：