检索结果-内蒙古大学图书馆

Design of a Lightweight Compressed Video Stream-Based Patient Activity Monitoring System

computers, Materials & Continua 2024年第1期78卷 1253-1274页

作者： Sangeeta Yadav Preeti Gulia Nasib Singh Gill Piyush Kumar Shukla Arfat Ahmad Khan Sultan Alharby Ahmed Alhussen Mohd Anul Haq Department of Computer Science&Applications Maharshi Dayanand UniversityRohtak124001India University Institute of Technology Rajiv Gandhi Proudyogiki VishwavidyalayaBhopal462033India Department of Computer Science College of ComputingKhon Kaen UniversityKhon Kaen40002Thailand Department of Computer Science College of Computer and Information SciencesMajmaah UniversityAl Majmaah11952Kingdom of Saudi Arabia Department of Computer Engineering College of Computer and Information SciencesMajmaah UniversityAl Majmaah11952Kingdom of Saudi Arabia

Inpatient falls from beds in hospitals are a common *** falls may result in severe *** problem can be addressed by continuous monitoring of patients using *** advancements in deep learning-based video analytics have made this task of fall detection more effective and *** with fall detection,monitoring of different activities of the patients is also of significant concern to assess the improvement in their *** computation-intensive models are required to monitor every action of the patient *** requirement limits the applicability of such ***,to keep the model lightweight,the already designed fall detection networks can be extended to monitor the general activities of the patients along with the fall *** by the same notion,we propose a novel,lightweight,and efficient patient activity monitoring system that broadly classifies the patients’activities into fall,activity,and rest classes based on their *** whole network comprises three sub-networks,namely a Convolutional Neural Networks(CNN)based video compression network,a Lightweight Pose Network(LPN)and a Residual Network(ResNet)Mixer block-based activity recognition *** compression network compresses the video streams using deep learning networks for efficient storage and retrieval;after that,LPN estimates human ***,the activity recognition network classifies the patients’activities based on their *** proposed system shows an overall accuracy of approx.99.7% over a standard dataset with 99.63% fall detection accuracy and efficiently monitors different events,which may help monitor the falls and improve the inpatients’health.

关键词： Fall detection activity recognition human pose estimation accuracy

来源：评论

学校读者我要写书评

暂无评论

Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling 38

Provably Faster Algorithms for Bilevel Optimization via With...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Junyi Huang, Heng Department of Computer Science Institute of Health Computing University of Maryland College Park College ParkMD20742 United States

Bilevel Optimization has experienced significant advancements recently with the introduction of new efficient algorithms. Mirroring the success in single-level optimization, stochastic gradient-based algorithms are widely used in bilevel optimization. However, a common limitation in these algorithms is the presumption of independent sampling, which can lead to increased computational costs due to the complicated hyper-gradient formulation of bilevel problems. To address this challenge, we study the example-selection strategy for bilevel optimization in this work. More specifically, we introduce a without-replacement sampling based algorithm which achieves a faster convergence rate compared to its counterparts that rely on independent sampling. Beyond the standard bilevel optimization formulation, we extend our discussion to conditional bilevel optimization and also two special cases: minimax and compositional optimization. Finally, we validate our algorithms over both synthetic and real-world applications. Numerical results clearly showcase the superiority of our algorithms. © 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

An AI-Driven Based Cybersecurity System for Network Intrusion Detection System in Hybrid with EPO and CNNet-LAM 5

An AI-Driven Based Cybersecurity System for Network Intrusio...

引用

5th IEEE International Conference on computing, Power, and Communication Technologies, IC2PCT 2024

作者： Anu Disney, D. Yugha, R. Karachi, S.Bangaru Gangadevi, E. Balusamy, Balamurugan Gite, Shilpa Sathyabama Institute of Science and Technology School of Computing Chennai600119 India Sathyabama Institute of Science and Technology Department of Computer Science Chennai600119 India Loyola College Department of Computer Science Chennai600034 India Delhi India Symbiosis Institute of Technology Aiml Department Pune India Pune412115 India

ISBN: (纸本)9798350383522

The proliferation of large data made possible by ubiquitous internet use has led to an uptick in cyberattacks, despite the proliferation of AI-based security keys like intrusion detection systems (IDS). Improved data classification is one benefit of the suggested detection system's foundation in deep learning (DL) and Convolutional Neural Networks (CNNs). With the use of the IDSAI dataset, this research takes a close look at intrusion detection systems. Z-Score Normalisation and Min-Max Normalisation are used for data preparation. Picking out the most relevant characteristics from the preprocessed data is the next step after data preprocessing. As a result, the feature selection method makes use of an optimisation known as the Eagle Perching Optimisation (EPO) Algorithm. Convolutional Neural Networks with Long Short-Term Memory and Attention Mechanism (CNNet-LAM) are used for classification after selection. It is common practice to employ EPO during hyperparameter tweaking due to its efficacy. Classification issues may be effectively resolved by using the CNNet-LAM hybrid model. The suggested model consistently surpasses the competition, according to the testing data, and it can predict varying time delays with an accuracy of 99.31%. © 2024 IEEE.

关键词： Attention mechanism Convolutional layer Eagle perching optimization Intrusion detection system Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Model Sensitivity Aware Continual Learning 38

Model Sensitivity Aware Continual Learning

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Zhenyi Huang, Heng Department of Computer Science Institute of Health Computing University of Maryland College Park College ParkMD20742 United States

Continual learning (CL) aims to adapt to non-stationary data distributions while retaining previously acquired knowledge. However, CL models typically face a trade-off between preserving old task knowledge and excelling in new task performance. Existing approaches often sacrifice one for the other. To overcome this limitation, orthogonal to existing approaches, we propose a novel perspective that views the CL model ability in preserving old knowledge and performing well in new task as a matter of model sensitivity to parameter updates. Excessive parameter sensitivity can lead to two drawbacks: (1) significant forgetting of previous knowledge;and (2) overfitting to new tasks. To reduce parameter sensitivity, we optimize the model's performance based on the parameter distribution, which achieves the worst-case CL performance within a distribution neighborhood. This innovative learning paradigm offers dual benefits: (1) reduced forgetting of old knowledge by mitigating drastic changes in model predictions under small parameter updates;and (2) enhanced new task performance by preventing overfitting to new tasks. Consequently, our method achieves superior ability in retaining old knowledge and achieving excellent new task performance simultaneously. Importantly, our approach is compatible with existing CL methodologies, allowing seamless integration while delivering significant improvements in effectiveness, efficiency, and versatility with both theoretical and empirical supports. © 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

Ruler Wrapping

引用

International Journal of Computational Geometry and Applications 2023年第1-2期33卷 3-12页

作者： Gagie, Travis Saeidi, Mozhgan Sapucaia, Allan Faculty of Computer Science Dalhousie University Halifax NS Canada Institute of Computing University of Campinas SP Campinas Brazil

In 1985 Hopcroft, Joseph and Whitesides showed it is NP-complete to decide whether a carpenter's ruler with segments of given positive lengths can be folded into an interval of at most a given length, such that the folded hinges alternate between 180 degrees clockwise and 180 degrees counter-clockwise. At the open-problem session of 33rd Canadian Conference on Computational Geometry (CCCG '21), O'Rourke proposed a natural variation of this problem called ruler wrapping, in which all folded hinges must be folded the same way. In this paper we show O'Rourke's variation has a linear-time solution. © 2023 World Scientific Publishing Company.

关键词： Carpenter's ruler folding wrapping

来源：评论

学校读者我要写书评

暂无评论

LayerCFL:an efcient federated learning with layer-wised clustering

引用

Cybersecurity 2025年第1期8卷 72-85页

作者： Jie Yuan Rui Qian Tingting Yuan Mingliang Sun Jirui Li Xiaoyong Li School of Cyberspace Security Beijing University of Posts and TelecommunicationsBeijingChina Key Laboratory of Trustworthy Distributed Computing and Service(BUPT) Ministry of EducationBeijingChina Institute of Computer Science Faculty of Mathematics and Computer ScienceUniversity of GoettingenGöettingenGermany School of Information Technology Henan University of Chinese MedicineZhengzhouHenanChina

Federated Learning(FL)sufers from the Non-IID problem in practice,which poses a challenge for efcient and accurate model *** address this challenge,prior research has introduced clustered FL(CFL),which involves clustering clients and training them *** its potential benefts,CFL can be computationally and communicationally expensive when the data distribution is unknown *** is because CFL involves the entire neural networks of involved clients in computing the clusters during training,which can become increasingly timeconsuming with large-sized *** tackle this issue,this paper proposes an efcient CFL approach called LayerCFL that employs a Layer-wised clustering *** LayerCFL,clients are clustered based on a limited number of layers of neural networks that are pre-selected using statistical and experimental *** experimental results demonstrate the efectiveness of LayerCFL in mitigating the impact of Non-IID data,improving the accuracy of clustering,and enhancing computational efciency.

关键词： Federated learning Clustered federated learning Non-IID Layer-wised clustering

来源：评论

学校读者我要写书评

暂无评论

AI computing Systems for Large Language Models Training

引用

计算机科学技术学报（英文版） 2025年第1期40卷 6-41页

作者：张振兴文渊博吕涵祺刘畅张蕊李夏青王超杜子东郭崎李玲周学海陈云霁 School of Computer Science and Technology University of Science and Technology of China Hefei China State Key Laboratory of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing China Cambricon Technologies Beijing China Shanghai Innovation Center for Processor Technologies Shanghai China Intelligent Software Research Center Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

In this paper,we present a comprehensive overview of artificial intelligence(AI)computing systems for large language models(LLMs)*** rapid advancement of LLMs in recent years,coupled with the widespread adoption of algorithms and applications such as BERT,ChatGPT,and DeepSeek,has sparked significant interest in this *** classify LLMs into encoder-only,encoder-decoder,and decoder-only models,and briefly analyze their training and infer-ence processes to emphasize their substantial need for computational *** operations depend heavily on AI-specific accelerators like GPUs(graphics processing units),TPUs(tensor processing units),and MLUs(machine learning units).However,as the gap widens between the increasing complexity of LLMs and the current capabilities of accelerators,it becomes essential to adopt heterogeneous computing systems optimized for distributed environments to manage the growing computational and memory requirements of *** delve into the execution and scheduling of LLM algo-rithms,underlining the critical role of distributed computing strategies,memory management enhancements,and boosting computational *** paper clarifies the complex relationship between algorithm design,hardware infrastructure,and software optimization,and provides an in-depth understanding of both the software and hardware infrastructure sup-porting LLMs training,offering insights into the challenges and potential avenues for future development and deployment.

关键词： artificial intelligence(AI)chip large language model(LLM) AI computing system accelerator

来源：评论

学校读者我要写书评

暂无评论

The Fine-Grained Complexity of Gradient Computation for Training Large Language Models 38

The Fine-Grained Complexity of Gradient Computation for Trai...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Alman, Josh Song, Zhao Department of Computer Science Columbia University United States Simons Institute for the Theory of Computing University of California Berkeley United States

Large language models (LLMs) have made fundamental contributions over the last a few years. To train an LLM, one needs to alternatingly run 'forward' computations and 'backward' computations. The forward computation can be viewed as attention function evaluation, and the backward computation can be viewed as a gradient computation. In previous work by [Alman and Song, NeurIPS 2023], it was proved that the forward step can be performed in almost-linear time in certain parameter regimes, but that there is no truly sub-quadratic time algorithm in the remaining parameter regimes unless the popular hypothesis SETH is false. In this work, we show nearly identical results for the harder-seeming problem of computing the gradient of loss function of one layer attention network, and thus for the entire process of LLM training. This completely characterizes the fine-grained complexity of every step of LLM training. © 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

Efficient distributed algorithms for holistic aggregation functions on random regular graphs

引用

science China(Information sciences) 2022年第5期65卷 32-50页

作者： Lin JIA Qiang-Sheng HUA Haoqiang FAN Qiuping WANG Hai JIN National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and TechnologyHuazhong University of Science and Technology Institute for Interdisciplinary Information Science Tsinghua University

In this paper, we propose efficient distributed algorithms for three holistic aggregation functions on random regular graphs that are good candidates for network topology in next-generation data *** three holistic aggregation functions include SELECTION（select the k-th largest or smallest element）,DISTINCT（query the count of distinct elements）, MODE（query the most frequent element）. We design three basic techniques — Pre-order Network Partition, Pairwise-independent Random Walk, and Random Permutation Delivery, and devise the algorithms based on the techniques. The round complexity of the distributed SELECTION is Θ（log N） which meets the lower bound where N is the number of nodes and each node holds a numeric element. The round complexity of the distributed DISTINCT and MODE algorithms are O（log3N/log log N） and O（log2N log log N） respectively. All of our results break the lower bounds obtained on general graphs and our distributed algorithms are all based on the CON GE S T model, which restricts each node to send only O（log N） bits on each edge in one round under synchronous communications.

关键词： distributed algorithms holistic aggregation function random regular graph $\mathcal{CONGEST}$ model communication complexity round complexity

来源：评论

学校读者我要写书评

暂无评论

Metric Analysis for AOP and OOP Programming Paradigm

引用

Journal of The Institution of Engineers (India): Series B 2023年第1期104卷 215-220页

作者： Patel, Shrikant Katiyar, Sanjay Kumar Sharma, Naveen School of Computing Science and Engineering Galgotias University Uttar Pradesh Greater Noida India Department of Computer Science Bhai Parmanand Institute of Business Studies GGSIPU Shakarpur New Delhi India

Object-oriented programming (OOP) is a programming that is centered around the articles and their conduct's ideas. It has been utilized for a long time by programmers' gathering. Configuration examples are the best act of OOP that has been assembled. OOP centers around taking care of the issues regarding true components. In any case, sooner or later, OOP has restrictions and execution which can be improved. AOP is a programming worldview that can beat the impediment of the OOP and can accomplish the successes decidedly, yet it can likewise cause the incidental effects in the code even with the victories. Special case taking care of is the component which deals with the run time blunders to protect the customary progression of the application Nonetheless, the execution of like these instruments with viewpoint arranged programming (AOP) could prompt mistake containing situations. Utilizing the AOP idea like joint cut, cross cut, perspective and a lot more can forestall such situations. This paper attempts to carry out the code with special case taking care of with AOP ideas and distinguishes the benefits and inconveniences in gathering with the conventional OOP execution. This report gives the examination of AOP OOP through measurements investigation and gives the depicted data about this area of study. © 2022, The Institution of Engineers (India).

关键词： Aspect oriented programming

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：