检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Huijie Zhang Yifu Lu Ismail Alkhouri Saiprasad Ravishankar Dogyoon Song Qing Qu Department of Electrical Engineering & Computer Science University of Michigan Department of Computational Mathematics Science & Engineering Michigan State University Department of Biomedical Engineering Michigan State University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Diffusion models, emerging as powerful deep generative tools, excel in various applications. They operate through a two-steps process: introducing noise into training samples and then employing a model to convert random noise into new samples (e.g., images). However, their remarkable generative performance is hindered by slow training and sampling. This is due to the necessity of tracking extensive forward and reverse diffusion trajectories, and employing a large model with numerous parameters across multiple timesteps (i.e., noise levels). To tackle these challenges, we present a multi-stage framework inspired by our empirical findings. These observations indicate the advantages of employing distinct parameters tailored to each timestep while retaining universal parameters shared across all time steps. Our approach involves segmenting the time interval into multiple stages where we employ custom multi-decoder U-net architecture that blends time-dependent models with a universally shared encoder. Our framework enables the efficient distribution of computational resources and mitigates inter-stage interference, which substantially improves training efficiency. Extensive numerical experiments affirm the effectiveness of our framework, showcasing significant training and sampling efficiency enhancements on three state-of-the-art diffusion models, including large-scale latent diffusion models. Furthermore, our ablation studies illustrate the impact of two important components in our framework: (i) a novel timestep clustering algorithm for stage division, and (ii) an innovative multi-decoder U-net architecture, seamlessly integrating universal and customized hyperparameters.

关键词： Training computer vision Noise computer architecture Interference Diffusion models Trajectory

来源：评论

学校读者我要写书评

暂无评论

Improved Metaheuristics with Deep Autoencoders for COVID-19 Detection and Classification 2

Improved Metaheuristics with Deep Autoencoders for COVID-19 ...

引用

2nd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2023

作者： Assudani, Manish K Nirmala, B. Kanimozhi, N. Chandre, Shanker Sunalini, K.K. Gopatoti, Anandbabu G H Raisoni University Department of Computer Science and Engineering Maharashtra Amravati India Sri Ramachandra Institute of Higher Education and Research Sri Ramachandra Faculty of Engineering and Technology Department of Computer Science and Engineering Chennai India School of Computing SRM Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Chennai India SR University Department of Computer Science & Artificial Intelligence Telangana Warangal India Koneru Lakshmaiah Education Foundation Department of English Andhrapradesh Guntur India Hindusthan College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9798350397635

A healthcare monitoring system requires the support of current technologies like big data, artificial intelligence (AI), and machine learning (ML), particularly during the outbreak of COVID19. This pandemic caused millions of death worldwide. ML and AI are used to detect and combat COVID19 in the initial phase. Deep learning refers to a subdivision of ML that utilizes NN for making predictions and learning from data. In the context of COVID19 detection, deep learning (DL) methods can be trained for examining medical images like CT scans and chest X-rays and identify the presence of virus. This study presents an improved whale optimization algorithm with deep autoencoder (IWOA-DAE) algorithm for COVID-19 detection and classification. The presented IWOA-DAE technique makes use of DL model with metaheuristic hyperparameter optimizer for COVID-19 classification. To accomplish this, the IWOA-DAE technique employs bilateral filtering (BF) process to eliminate noisy data. Next, the IWOA-DAE technique uses NASNetLarge model for feature vector generation purposes. For COVID-19 detection, the IWOA-DAE technique uses deep autoencoder (DAE) model with IWOA based optimal hyperparameter adjustment process. To highlight the improved performance of the IWOA-DAE algorithm, a wide-ranging simulation analysis takes place. The simulation outcomes highlighted the enhanced performance of the IWOA-DAE technique over other methods. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Multiobjective adaptive car-following control of an intelligent vehicle based on receding horizon optimization

引用

science China(Information sciences) 2023年第4期66卷 301-302页

作者： Hongbo GAO Juping ZHU Fei ZHANG Ruidong YAN Junjie ZHOU Lei JIANG Jianqiang WANG Keqiang LI Department of Automation University of Science and Technology of China Institute of Advanced Technology University of Science and Technology of China Department of Computational Mathematics School of Mathematical Sciences Anhui University School of Traffic and Transportation Beijing Jiaotong University Autonomous Driving Business Unit Chery Automobile School of College of Computer Science and Technology Zhejiang University China North Vehicle Research Institute School of Automotive Engineering Tsinghua University

Dear editor, Vehicle control is one of the key steps of intelligent driving [1]. Algorithms based on receding horizon optimization(RHO) can predict future trajectories and handle multiobjective constraint conditions; therefore, RHO-based methods have attracted considerable attention in the field of vehicle control. Although existing methods use RHO to design controllers, they do not simultaneously meet the multiobjective optimal control performance requirements on tracking, fuel economy, and ride comfort.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Enhancing Digital Twin Security Systems with Explainable AI Techniques

A Comprehensive Survey on Enhancing Digital Twin Security Sy...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： B. Lalithadevi S. Krishnaveni Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

Digital Twin (DT) technology has emerged as a cornerstone in modern engineering, enabling real-time digital replication of physical assets for monitoring, diagnostics, and optimization. However, as DTs become increasingly integrated into critical infrastructure, their security has become a paramount concern. This paper presents a comprehensive survey on the integration of Explainable Artificial Intelligence (XAI) into Digital Twin security, highlighting the potential of XAI in enhancing the transparency, interpretability, and trustworthiness of AI - driven security mechanisms in DTs. We explore various XAI techniques, including model- agnostic approaches, interpretable neural networks, and rule-based systems, detailing their potential applications in bolstering the security of Digital Twins. Furthermore, we identify several key challenges in implementing XAI for DT security, such as the need for standardized metrics for interpretability, the trade-offs between model complexity and explainability, and the potential for adversarial attacks on explainable models. Through our analysis, we highlight the critical research gaps, including the security of Digital Twin (DT) systems and explores the integration of Explainable AI (XAI) to enhance transparency, interpretability, and trustworthiness. Outcomes include detailed XAI applications for DT security, identification of limitations, and a roadmap for future research. We discuss various XAI techniques, their applications, and the current challenges in implementing XAI for DT security. Our survey identifies key research gaps and offers a roadmap for future research in this emerging field.

关键词： Surveys Measurement Explainable AI Neural networks Real-time systems Digital twins Security Internet of Things Optimization Monitoring

来源：评论

学校读者我要写书评

暂无评论

Bayes-Q-Learning Algorithm in Edge Computing for Waste Tracking

引用

Intelligent Automation & Soft Computing 2023年第5期36卷 2425-2440页

作者： D.Palanikkumar R.Ramesh Kumar Mehedi Masud Mrim M.Alnfiai Mohamed Abouhawwash Department of Computer Science and Engineering Dr.NGP Institute of TechnologyCoimbatore641048India Department of Information Technology Sri Krishna College of TechnologyCoimbatore641042India Department of Computer Science College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif P.O.Box 11099Taif21944Saudi Arabia Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of Computational Mathematics Scienceand Engineering(CMSE)Michigan State UniversityEast LansingMI48824USA

The major environmental hazard in this pandemic is the unhygienic dis-posal of medical *** wastage is not properly managed it will become a hazard to the environment and *** medical wastage is a major issue in the city,municipalities in the aspects of the environment,and *** efﬁcient supply chain with edge computing technology is used in managing medical *** supply chain operations include processing of waste collec-tion,transportation,and disposal of *** research works have been applied to improve the management of *** main issues in the existing techniques are ineffective and expensive and centralized edge computing which leads to failure in providing security,trustworthiness,and *** over-come these issues,in this paper we implement an efﬁcient Naive Bayes classiﬁer algorithm and Q-Learning algorithm in decentralized edge computing technology with a binary bat optimization algorithm(NBQ-BBOA).This proposed work is used to track,detect,and manage medical *** minimize the transferring cost of medical wastage from various nodes,the Q-Learning algorithm is *** accuracy obtained for the Naïve Bayes algorithm is 88%,the Q-Learning algo-rithm is 82%and NBQ-BBOA is 98%.The error rate of Root Mean Square Error(RMSE)and Mean Error(MAE)for the proposed work NBQ-BBOA are 0.012 and 0.045.

关键词： Binary bat algorithm naïve bayes supply chain edge medical wastage

来源：评论

学校读者我要写书评

暂无评论

Learning Dynamics of Deep Linear Networks Beyond the Edge of Stability

arXiv

引用

arXiv 2025年

作者： Ghosh, Avrajit Kwon, Soo Min Wang, Rongrong Ravishankar, Saiprasad Qu, Qing Computational Mathematics Science and Engineering Michigan State University United States Department of Electrical Engineering & Computer Science University of Michigan United States

Deep neural networks trained using gradient descent with a fixed learning rate η often operate in the regime of "edge of stability" (EOS), where the largest eigenvalue of the Hessian equilibrates about the stability threshold 2/η. In this work, we present a fine-grained analysis of the learning dynamics of (deep) linear networks (DLNs) within the deep matrix factorization loss beyond EOS. For DLNs, loss oscillations beyond EOS follow a period-doubling route to chaos. We theoretically analyze the regime of the 2-period orbit and show that the loss oscillations occur within a small subspace, with the dimension of the subspace precisely characterized by the learning rate. The crux of our analysis lies in showing that the symmetry-induced conservation law for gradient flow, defined as the balancing gap among the singular values across layers, breaks at EOS and decays monotonically to zero. Overall, our results contribute to explaining two key phenomena in deep networks: (i) shallow models and simple tasks do not always exhibit EOS (Cohen et al., 2021);and (ii) oscillations occur within top features (Zhu et al., 2023a). We present experiments to support our theory, along with examples demonstrating how these phenomena occur in nonlinear networks and how they differ from those which have benign landscape such as in DLNs. Copyright © 2025, The Authors. All rights reserved.

关键词： Matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Optimizing Generative AI Applications: A Comparative Study of Effective Prompting Techniques

Optimizing Generative AI Applications: A Comparative Study o...

引用

Pervasive Computing and Social Networking (ICPCSN), International Conference on

作者： Shivya Jyoti Moulik Tejpal Jothi K R Department of Software Systems School of Computer Science & Engineering Vellore Institute of Technology Vellore India Department of Computational Intelligence School of Computer Science & Engineering Vellore Institute of Technology Vellore India

ISBN: (数字)9798331535193

ISBN: (纸本)9798331535209

Generative Artificial Intelligence (GenAI) has emerged as a pivotal technology across various industries, driving advancements in automation, decision-making, and content generation. This paper investigates the efficacy of the prompt engineering methods such as zero-shot, one-shot, and few-shot prompting—in optimizing GenAI systems for diverse applications. Through a comprehensive literature review and an empirical survey involving 13 use cases such as chatbots, content creation, and medical decision support, we evaluate the performance of these prompting methods. The findings reveal that few-shot prompting excels in complex tasks, while zero-shot and one-shot prompting are more effective for simpler tasks. These insights provide practical guidance for leveraging GenAI across different domains, contributing to the advancement of AI-driven solutions.

关键词： Surveys Pervasive computing Industries Decision support systems Social networking (online) Large language models Chatbots Prompt engineering Human resource management Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Dynamic Signal Switching: A Promising Solution to Traffic Congestion

Machine Learning-Based Dynamic Signal Switching: A Promising...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Kanchana, M. Gopirajan, P.V. Mahalakshmi, B. Vijaya Nirmala, B. SRM Institute of Science and Technology School of Computing Department of Computing Technologies Katankulathur Tamil Nadu Chennai603203 India SRM Institute of Science and Technology School of Computing Department of Computational Intelligence Katankulathurx Tamil Nadu Chennai603203 India AMC Engineering College Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350319200

Today's growing urban population means increased revenue for individuals, translating into growing vehicles on the road. Nowadays, people use their private vehicles instead of public transportation, which results in a considerable number of personal vehicles that lead totraffic congestion everywhere. The ever-increasing number of vehicles and complex congestion leads to frequent traffic jams in major cities. In today's scenario, traditional traffic management methods have become redundant as the traffic volume has grown exponentially. The primary goal of this proposed work is to develop an algorithm that uses machine learning to control traffic effectively and ensure efficient traffic flow in the event of unforeseen events like accidents. The existing algorithm focuses on predicting shortterm traffic flow but ignores that traffic congestion may also occur due to accidents and emergencies. Our proposed model will consider all the above factors and use dynamic signal switching among lanes to predict the best and most efficient solution to reducing waiting time for vehicles and congestion on the road. To create an effective traffic flow management model with the least amount of road mayhem, our suggested model needs traffic data as input, which was then trained using various Machine Learning (ML) models. © 2023 IEEE.

关键词： IDD Image processing Machine Learning Neural Network RCNN Traffic Management YOLO

来源：评论

学校读者我要写书评

暂无评论

A GPU Algorithm for Detecting Strongly Connected Components 23

A GPU Algorithm for Detecting Strongly Connected Components

引用

2023 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2023

作者： Alabandi, Ghadeer Sands, William Biros, George Burtscher, Martin Department of Computer Science Texas State University San MarcosTX United States Oden Institute for Computational Engineering and Sciences The University of Texas at Austin AustinTX United States

ISBN: (纸本)9798400701092

Detecting strongly connected components (SCCs) is an important step in various graph computations. The fastest GPU and CPU implementations from the literature work well on graphs where most of the vertices belong to a single SCC and the vertex degrees follow a power-law distribution. However, these algorithms can be slow on the mesh graphs used in certain radiative transfer simulations, which have a nearly constant vertex degree and can have significant variability in the number and size of SCCs. We introduce ECL-SCC, an SCC detection algorithm that addresses these shortcomings. Our approach is GPU friendly and employs innovative techniques such as maximum ID propagation and edge removal. On an A100 GPU, ECL-SCC performs on par with the fastest prior GPU code on power-law graphs and outperforms it by 7.8× on mesh graphs. Moreover, ECL-SCC running on the GPU outperforms fast parallel CPU code by three orders of magnitude on meshes. © 2023 ACM.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Automated Hematocyte Classification using Hybrid Deep Learning Model

Automated Hematocyte Classification using Hybrid Deep Learni...

引用

Pervasive Computing and Social Networking (ICPCSN), International Conference on

作者： Bhavani M Prithi Samuel Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Chennai

ISBN: (数字)9798331535193

ISBN: (纸本)9798331535209

Numerous applications of deep learning have already shown their efficacy, and more and more people are beginning to accept that deep learning is better than older machine learning methods. Deep learning algorithms, in particular, have enormous benefits in the medical profession, where a huge quantity of pictures must be analysed and assessed. The categorisation of blood cells, one of the most difficult problems in blood diagnostics, intends to create a deep-learning model. The nucleus of cells provides important data to specialists for disease classification, as the massive diseases can be differentiated by observing the classification of hematocytes. This addresses two primary goals: giving a stained image of a WBC and classifying it as either polynuclear or mononuclear. Second, using a stained picture, identify the eosinophils, neutrophils, lymphocytes, and monocytes to determine the kind of hematocytes. The classification of hematocytes is resource-intensive; hence, this work, intend to present a novel framework to improve the detection and classification of hematocytes.

关键词： Deep learning Pervasive computing Machine learning algorithms Social networking (online) Lymphocytes Cells (biology) Feature extraction Medical diagnostic imaging Eosinophils Diseases

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：