检索结果-内蒙古大学图书馆

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Wu, Peng Li, Zhi Zhang, Zhicai Yan, Tao Chen, Lu Shanxi University Institute of Big Data Science and Industry Taiyuan030006 China Shanxi University School of Computer and Information Technology Taiyuan030006 China Hainan University School of Computer Science and Technology Haikou570228 China

ISBN: (纸本)9798350330717

When scheduling a set of real-time tasks, researchers can choose between preemptive and non-preemptive algorithms. However, these algorithms each have their own advantages and drawbacks, necessitating specific analysis in different contexts. In contrast to these two extremes, researchers have proposed the concept of limited-preemption algorithms. Such limited-preemption algorithms serve as feasible alternatives to the former two approaches. Currently, research on this algorithm is based on a homogenous computing *** this paper, we investigate the fixed-preemption point method in limited-preemption algorithms. We compare the impact of limited-preemption EDF algorithm on the performance of homogenous multiprocessors under different fixed-preemption strategies. We introduce a preemptive strategy where high-priority tasks can only be preempted at the most suitable fixed-preemption points, and we provide an effective schedulability analysis for this strategy. The EDF scheduling algorithm based on the best-fit fixed preemption strategy is called the Best Preemptive EDF(BP-EDF). We have introduced an effective schedulability analysis for BP-EDF. Experimental results indicate that the strategy with the most suitable fixed-preemption points demonstrates superior schedulability compared to the other two strategies. Furthermore, its performance in terms of task preemption frequency closely approaches that of the strategy employing fixed-preemption at the lowest priority points. © 2023 IEEE.

关键词： EDF scheduling algorithm fixed preemption points homogeneous multiprocessors limited-preemption Scheduling

来源：评论

学校读者我要写书评

暂无评论

The 32nd AIAI Irish Conference on Artificial Intelligence and Cognitive science 32

The 32nd AIAI Irish Conference on Artificial Intelligence an...

引用

32nd Irish Conference on Artificial Intelligence and Cognitive science, AICS 2024

作者： Pakrashi, Arjun Rushe, Ellen Namee, Brian Mac Brennan, Rob Yaman, Bezya School of Computer Science University College Dublin BelfieldDublin 4 Ireland School of Computer Science Dublin City University Collins Ave Ext Whitehall Dublin 9 Ireland The Insight Centre for Data Analytics Ireland SFI Centre for Research Training in Machine Learning Ireland ADAPT Centre Ireland School of Computer Science Trinity College Dublin College Green Dublin 2 Ireland

The 32nd Irish Conference on Artificial Intelligence and Cognitive science (AICS 2024), hosted by University College Dublin (UCD) in collaboration with Dublin City University (DCU), featured high-quality research in AI and cognitive science, with a focus on trustworthy AI, fairness, and bias mitigation. Of 82 submissions, 44 papers were accepted, covering applications in healthcare, smart mobility, financial forecasting, anomaly detection, and sports analytics, alongside fundamental machine learning advancements. Keynote speakers Dr. Susan Leavy (UCD) discussed AI’s societal impact, while Prof. Eamonn Keogh (UC Riverside) critiqued research in time series anomaly detection. AICS 2024 reaffirmed its role as Ireland’s leading AI research forum, fostering discussions on cutting-edge advancements and their societal implications. © 2024 Copyright for this paper by its authors.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Image super-resolution algorithm based on multi-dimensional Swin Transformers 3

Image super-resolution algorithm based on multi-dimensional ...

引用

3rd International Conference on Electronic Information Engineering and computer Communication, EIECC 2023

作者： Zheng, Qinan Xu, Huahu Bian, Minjie School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Data Group Co. Ltd Shanghai China

ISBN: (纸本)9798350359961

Numerous studies have demonstrated the Swin Transformer performs well in image super-resolution tasks. However, Swin Transformer typically divides the input image into fixed size blocks (such as 48x48) and independently processes each block, causing it to overlook a wider area. Furthermore, many deep learning super-resolution technologies face the challenge of computationally intensive operations. To address these issues, we propose a new NSTSR model consisting of four parts: data preprocessing layer, primary feature extraction layer, advanced feature extraction layer, and image generation layer. The advanced feature extraction layer consists of multiple STNBs (Swin Transformer N-segment blocks). We have introduced a technique called N-Segments, which applies the N-Gram contextual method for natural language processing tasks to low-level visual tasks. In our work, N-Segments refers to neighboring local windows in Swin, distinct from the traditional text analysis definition where N-Segments represents a continuous picture segment. Leveraging sliding-WSA, the N-Segments interact with each other, enabling the expansion of the regions seen to restore degraded pixels effectively. The experimental results demonstrate that the NSTSR model exhibits excellent performance compared to existing advanced methods while maintaining the computational efficiency structure. © 2023 IEEE.

关键词： component data Augmentation Image Super-resolution N-Segments Swin Transformer

来源：评论

学校读者我要写书评

暂无评论

One-shot-but-not-degraded Federated Learning 24

One-shot-but-not-degraded Federated Learning

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zeng, Hui Xu, Minrui Zhou, Tongqing Wu, Xinyi Kang, Jiawen Cai, Zhiping Niyato, Dusit School of Computer National University of Defense Technology Changsha China College of Computing and Data Science Nanyang Technological University Singapore Singapore School of Automation Guangdong University of Technology Guangzhou China

ISBN: (纸本)9798400706868

Transforming the multi-round vanilla Federated Learning (FL) into one-shot FL (OFL) significantly reduces the communication burden and makes a big leap toward practical deployment. However, we note that existing OFL methods all build on model lossy reconstruction (i.e., aggregating while partially discarding local knowledge in clients' models), which attains one-shot at the cost of degraded inference performance. By identifying the root cause of stressing too much on finding a one-fit-all model, this work proposes a novel one-shot FL framework by embodying each local model as an independent expert and leveraging a Mixture-of-Experts network to maintain all local knowledge intact. A dedicated self-supervised training process is designed to tune the network, where the sample generation is guided by approximating underlying distributions of local data and making distinct predictions among experts. Notably, the framework also fuels FL with flexible, data-free aggregation and heterogeneity tolerance. Experiments on 4 datasets show that the proposed framework maintains the one-shot efficiency, facilitates superior performance compared with 8 OFL baselines (+5.54% on CIFAR-10), and even attains over ×4 performance gain compared with 3 multi-round FL methods, while only requiring less than 85% trainable parameters. Our code will be available at https://***/zenghui9977/IntactOFL. © 2024 ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

HOLMES: An Efficient and Lightweight Semantic Based Anomalous Email Detector 19

HOLMES: An Efficient and Lightweight Semantic Based Anomalou...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Wu, Peilun Guo, Hui Data Security & Compliance Cdo Data & Cloud PwC Cn China School of Computer Science and Engineering Australia

ISBN: (纸本)9798350346558

Email threat is a serious issue for enterprise security. The threat can be in various malicious forms, such as phishing, fraud, blackmail and malvertisement. The traditional anti-spam gateway often maintains a greylist to filter out unexpected emails based on suspicious vocabularies present in the email's subject and contents. However, this type of signature-based approach cannot effectively discover novel and unknown suspicious emails that utilize various evolving malicious payloads. To address the problem, in this paper, we present HOLMES, an efficient and lightweight semantic based engine for anomalous email detection. HOLMES can convert each email event log into a sentence through word embedding and then identify abnormalities that deviate from a historical baseline based on those translated sentences. We have evaluated the performance of HOLMES in a real-world enterprise environment, where around 5,000 emails are sent/received each day. In our experiments, HOLMES shows a high capability to detect email threats, especially those that cannot be handled by the enterprise anti-spam gateway. It is also demonstrated through our experiment that HOLMES can discover more concealed malicious emails that are immune from several commercial detection tools. © 2022 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Two-Layer Information Granulation:Mapping-Equivalence Neighborhood Rough Set and Its Attribute Reduction

引用

Intelligent Automation & Soft Computing 2023年第8期37卷 2059-2075页

作者： Changshun Liu Yan Liu Jingjing Song Taihua Xu School of Computer Jiangsu University of Science and TechnologyZhenjiang212100China Key Laboratory of Oceanographic Big Data Mining&Application of Zhejiang Province Zhejiang Ocean UniversityZhoushan316022China

Attribute reduction,as one of the essential applications of the rough set,has attracted extensive attention from *** granulation is a key step of attribute reduction,and its efficiency has a significant impact on the overall efficiency of attribute *** information granulation of the existing neighborhood rough set models is usually a single layer,and the construction of each information granule needs to search all the samples in the universe,which is *** fill such gap,a new neighborhood rough set model is proposed,which aims to improve the efficiency of attribute reduction by means of two-layer information *** first layer of information granulation constructs a mapping-equivalence relation that divides the universe into multiple mutually independent mapping-equivalence *** second layer of information granulation views each mapping-equivalence class as a sub-universe and then performs neighborhood informa-tion granulation.A model named mapping-equivalence neighborhood rough set model is derived from the strategy of two-layer information *** results show that compared with other neighborhood rough set models,this model can effectively improve the efficiency of attribute reduction and reduce the uncertainty of the *** strategy provides a new thinking for the exploration of neighborhood rough set models and the study of attribute reduction acceleration problems.

关键词： Attribute reduction information granulation mapping-equiva-lence relation neighborhood rough set

来源：评论

学校读者我要写书评

暂无评论

Vision Mamba Mender 38

Vision Mamba Mender

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Hu, Jiacong Cao, Anda Feng, Zunlei Zhang, Shengxuming Wang, Yi Jia, Lingxiang Song, Mingli College of Computer Science and Technology Zhejiang University China School of Software Technology Zhejiang University China State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China

Mamba, a state-space model with selective mechanisms and hardware-aware architecture, has demonstrated outstanding performance in long sequence modeling tasks, particularly garnering widespread exploration and application in the field of computer vision. While existing works have mixed opinions of its application in visual tasks, the exploration of its internal workings and the optimization of its performance remain urgent and worthy research questions given its status as a novel model. Existing optimizations of the Mamba model, especially when applied in the visual domain, have primarily relied on predefined methods such as improving scanning mechanisms or integrating other architectures, often requiring strong priors and extensive trial and error. In contrast to these approaches, this paper proposes the Vision Mamba Mender, a systematic approach for understanding the workings of Mamba, identifying flaws within, and subsequently optimizing model performance. Specifically, we present methods for predictive correlation analysis of Mamba's hidden states from both internal and external perspectives, along with corresponding definitions of correlation scores, aimed at understanding the workings of Mamba in visual recognition tasks and identifying flaws therein. Additionally, tailored repair methods are proposed for identified external and internal state flaws to eliminate them and optimize model performance. Extensive experiments validate the efficacy of the proposed methods on prevalent Mamba architectures, significantly enhancing Mamba's performance. For more information, please visit https://***/. © 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

Artificial Intelligence Strategies for Accurate Segmentation and Categorization of Unveiling Genetic Disorders in Bioinformatics 2

Artificial Intelligence Strategies for Accurate Segmentation...

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Sarathamani, T. Kavitha, K. Thirumoorthi, C. Vagini, K Jayanthi Manikandaprabhu, P. Sumathi, P. Kolkata India Mohan Babu University School of Computing Department of Ai and Ml Sree Sainath Nagar Tirupati India Psg College of Arts and Science Department of Computer Science Tamilnadu Coimbatore India Kpr College of Arts Science and Research Department of Computer science with Data Analytics Tamilnadu Coimbatore India Amrita Vishwa Vidyapeetham School of Computing Department of Computer Science Karnataka Mysuru India Dr. G R Damodaran College of Science Department of Computer Science Tamilnadu Coimbatore India

ISBN: (纸本)9798350368413

Women all across the world are affected by the potentially fatal condition known as breast cancer. According to clinical experts, early cancer detection helps to save lives. Several machine learning algorithms have been developed to classify cancers in order to diagnose breast cancer, and medical image processing has been found to be a beneficial area for increasing classification accuracy. One of the most crucial signs for detecting breast cancer early is micro classifications. Machine learning methods have been employed in numerous studies to address this problem. Various classification algorithms are used to find the presence of breast cancer whether it is Benign or Malignant. For earlier cancer detection and diagnosis, an image enhancement approach is being developed. A machine learning technique is employed in this work to attempt to categorize breast cancer. The purpose of the present research was to increase the accuracy of machine learning methods for disease diagnosis using ML techniques. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

CIFD: A Distance for Complex Intuitionistic Fuzzy Set 4th

CIFD: A Distance for Complex Intuitionistic Fuzzy Set

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Zhao, Yangyang Xiao, Fuyuan School of Computer and Information Science Southwest University Chongqing400715 China School of Big Data and Software Engineering Chongqing University Chongqing401331 China

ISBN: (纸本)9783031200953

Intuitionistic fuzzy set (IFS) has attracted much attention because it can deal with fuzziness and uncertainty more flexibly than traditional fuzzy set. Complex intuitionistic fuzzy set (CIFS) extends intuitionistic fuzzy to the complex plane, which can better express and process uncertain information. In this paper, a novel distance measure complex intuitionistic fuzzy distance (CIFD) is proposed for CIFSs. Firstly, inspired by Tanimoto coefficient, a new similarity measure between CIFSs is proposed. Then, based on the similarity measure, the CIFD is proposed and its non-negativity, non-degeneracy, and symmetry are analyzed. Moreover, when CIFS degenerates into classical IFS, CIFD is also applicable to measure the differences between IFSs. Finally, to illustrate the effectiveness of CIFD, an example is given at the end. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

Towards cognitive navigation:A biologically inspired calibration mechanism for the head direction cell network

引用

Journal of Automation and Intelligence 2023年第1期2卷 31-41页

作者： Zhenshan Bing Dominik Nitschke Genghang Zhuang Kai Huang Alois Knoll Department of Informatics Technical University of MunichMunich85741Germany School of Data and Computer Science Sun Yat-sen UniversityGuangzhou510006China

To derive meaningful navigation strategies,animals have to estimate their directional headings in the ***,this function is achieved by the head direction cells that were found in mammalian brains,whose neural activities encode one’s heading *** is believed that such head direction information is generated by integrating self-motion cues,which also introduces accumulative errors in the long *** eliminate such errors,this paper presents an efficient calibration model that mimics the animals’behavior by exploiting visual cues in a biologically plausible way,and then implements it in robotic navigation *** proposed calibration model allows the agent to associate its head direction and the perceived egocentric direction of a visual cue with its position and orientation,and therefore to calibrate the head direction when the same cue is viewed *** examine the proposed head direction calibration model in extensive simulations and real-world experiments and demonstrate its excellent performance in terms of quick association of information to proximal or distal cues as well as accuracy of calibrating the integration errors of the head *** can be viewed at https://***/hdc-calibration.

关键词： Head direction cells Error calibration Cognitive navigation Neural SLAM

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：