检索结果-内蒙古大学图书馆

Proceedings of the Winter Simulation Conference

作者： Hannah Danielle Ladera Villaplana Jaeyoung Kwak Michael H. Lees Hongying Li Wentong Cai College of Computing and Data Science Nanyang Technological University Singapore Singapore Informatics Institute University of Amsterdam Amsterdam The Netherlands Department of Fluid Dynamics Institute of High Performance Computing Singapore Singapore

ISBN: (纸本)9798331534202

Epidemic models have become increasingly useful, especially in the wake of the recent COVID-19 pandemic, emphasizing the crucial role of human behavior in the spread of disease. There has been a recent rise in the usage and popularity of generative artificial intelligence (GenAI), such as ChatGPT especially with its ability to mimic human behavior. In this study, we demonstrate a novel application of GenAI for epidemic modeling. We employed GenAI for creating agents living in a hypothetical town in simulations and simulating their behavior within the context of an ongoing pandemic. We performed a series of simulations to quantify the impact of agent traits and the availability of information for health condition, virus, and government guidelines on the disease spread patterns in terms of peak time and epidemic duration. We also characterized the most influential factors in agents' decision-making using random forest model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant LOBPCG for Nuclear CI Calculations 23

Fault-Tolerant LOBPCG for Nuclear CI Calculations

引用

6th International Conference on High Performance computing in Asia-Pacific Region, HPC Asia 2023

作者： Shao, Meiyue Oryspayev, Dossay Yang, Chao Maris, Pieter Cook, Brandon School of Data Science Fudan University China Computational Science Initiative Brookhaven National Laboratory United States Department of Physics and Astronomy Iowa State University United States National Energy Research Scientific Computing Center Lawrence Berkeley National Laboratory United States

ISBN: (纸本)9781450398060

Exascale computing platforms with millions of compute units and with thousands of nodes are predicted to experience frequent faults which interrupt applications' execution. In this context resilience against faults becomes important. We examine user and software level fault mitigation strategies in a distributed LOBPCG algorithm targeting nuclear CI calculations. In particular, we present and evaluate one strategy that keeps the total number of fault-Tolerant LOBPCG iterations close to that of the standard LOBPCG algorithm ran on a fault-free machine. © 2023 ACM.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

SKETCH2MANGA: Shaded Manga Screening from Sketch with Diffusion Models

SKETCH2MANGA: Shaded Manga Screening from Sketch with Diffus...

引用

IEEE International Conference on Image Processing

作者： Jian Lin Xueting Liu Chengze Li Minshan Xie Tien-Tsin Wong School of Computing and Information Sciences Saint Francis University Department of Computer Science and Engineering The Chinese University of Hong Kong Department of Data Science and Artificial Intelligence Monash University

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

While manga is a popular entertainment form, creating manga is tedious, especially adding screentones to the created sketch, namely manga screening. Unfortunately, there is no existing method that tailors for automatic manga screening, probably due to the difficulty in generating shaded high-frequency screentones of high-quality. Classic manga screening approaches generally require user input to provide screentone exemplars or a reference manga image. Recent deep learning models enable automatic generation by learning from a large-scale dataset. However, the state-of-the-art models still fail to generate high-quality shaded screentones due to the lack of a tailored model and high-quality manga training data. In this paper, we propose a novel sketch-to-manga framework that first generates a color illustration from the sketch and then generates a screentoned manga based on the intensity guidance. Our method significantly outperforms existing methods in generating high-quality manga with shaded high-frequency screentones.

关键词： Deep learning Image color analysis Training data Entertainment industry Diffusion models Animation data models

来源：评论

学校读者我要写书评

暂无评论

Contract-Inspired Contest Theory for Controllable Image Generation in Mobile Edge Metaverse

arXiv

引用

arXiv 2025年

作者： Liu, Guangyuan Du, Hongyang Wang, Jiacheng Niyato, Dusit Kim, Dong In College of Computing and Data Science The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore Department of Electrical and Electronic Engineering University of Hong Kong Hong Kong College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

The rapid advancement of immersive technologies has propelled the development of the Metaverse, where the convergence of virtual and physical realities necessitates the generation of high-quality, photorealistic images to enhance user experience. However, generating these images, especially through Generative Diffusion Models (GDMs), in mobile edge computing environments presents significant challenges due to the limited computing resources of edge devices and the dynamic nature of wireless networks. This paper proposes a novel framework that integrates contract-inspired contest theory, Deep Reinforcement Learning (DRL), and GDMs to optimize image generation in these resource-constrained environments. The framework addresses the critical challenges of resource allocation and semantic data transmission quality by incentivizing edge devices to efficiently transmit high-quality semantic data, which is essential for creating realistic and immersive images. The use of contest and contract theory ensures that edge devices are motivated to allocate resources effectively, while DRL dynamically adjusts to network conditions, optimizing the overall image generation process. Experimental results demonstrate that the proposed approach not only improves the quality of generated images but also achieves superior convergence speed and stability compared to traditional methods. This makes the framework particularly effective for optimizing complex resource allocation tasks in mobile edge Metaverse applications, offering enhanced performance and efficiency in creating immersive virtual environments. © 2025, CC BY.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Efficient acne classification based on Resnet18 3

Efficient acne classification based on Resnet18

引用

3rd International Conference on Algorithms, Network, and Communication Technology, ICANCT 2024

作者： Cheng, Shi Sun, Mingze Huang, Zhongyi Wang, Yushan Fu, Jiaxuan School of Engineering University of Manchester ManchesterM13 9PL United Kingdom School of Computing Science University of Glasgow GlasgowG12 8RZ United Kingdom School of Data Science and Big Data Nanjing Institute of Technology Nanjing210000 China The Affiliated High School Renmin University of China Beijing100083 China International Department Nanjing Jinling High School Nanjing21000 China

ISBN: (数字)9781510688902

ISBN: (纸本)9781510688896

In this study, we investigated the mechanical performance of lightweight composite slabs, specifically focusing on the application of an integrated face recognition and acne classification pipeline. We propose a comprehensive approach that commences with facial detection, proceeds to the acne region localization, and concludes with acne classification utilizing ResNet18 architecture. The aim is to develop a highly accurate and efficient system for acne classification, particularly beneficial for remote patients or those seeking a convenient self-assessment tool. Our dataset, though limited in size and diversity, is iteratively refined and augmented to mitigate data scarcity issues. Through experimental evaluations, we demonstrate that the combination of ResNet18 and Support Vector Machine (SVM) achieves an accuracy rate of 96%, significantly outperforming traditional manual feature extraction methods. Additionally, visualization techniques such as Principal Component Analysis (PCA) and t-Distributed Stochastic Neighbor Embedding (t-SNE) are employed to gain insights into the data distribution and the effectiveness of automatically extracted features. This study highlights the potential of deep learning for acne detection and underscores the importance of dataset refinement for enhancing model performance. © 2025 SPIE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Automated Defect Detection in Electronic Components using Convolutional Neural Networks 9

Automated Defect Detection in Electronic Components using Co...

引用

9th International Conference on science, Technology, Engineering and Mathematics, ICONSTEM 2024

作者： Shobanadevi, A. Kottu, Sreekanth Kumar, K. R. Senthil Amudha, K. Praveena, K. Venkatesh, R. School of Computing Srm Institute of Science And Technology Department of Data Science And Business Systems Tamil Nadu Chennai600026 India Mallareddy University Department of Computer Science & Engineering Telangana Hyderabad500043 India R.M.K. Engineering College Department of Mechanical Engineering Tamil Nadu Kavaraipettai601206 India Department of Science And Humanities-Physics Tamil Nadu Kavaraipettai601206 India Mohan Babu University Erstwhile SreeVidyanikethan Engineering College Department of Electronics And Communication Engineering Andhra Pradesh 517102 India Department of Physics Tamil Nadu Dindigul624622 India

ISBN: (纸本)9798350365092

This exploration paper explores the operation of convolutional neural networks(CNNs) in automating the discovery of blights in electronic factors. With the rapid-fire advancement of technology, the demand for high- quality electronic factors has surged, emphasizing the need for effective disfigurement discovery styles. using the capabilities of CNNs, this study aims to develop a robust and accurate automated system able to relate colorful types of blights to electronic factors. By training the CNN model on a different dataset of disfigurement images, the system learns to fete subtle variations and anomalies reflective of faults, thereby enhancing examination delicacy and effectiveness. The proposed approach offers promising results in streamlining disfigurement discovery processes, reducing homemade intervention, and ameliorating overall quality control in electronics manufacturing. Results indicate the effectiveness and trustability of CNNs in automating disfigurement discovery, paving the way for enhanced productivity and product trustability in electronic diligence. © 2024 IEEE.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

FROM LAYERS TO STATES: A STATE SPACE MODEL PERSPECTIVE TO DEEP NEURAL NETWORK LAYER DYNAMICS

arXiv

引用

arXiv 2025年

作者： Liu, Qinshuo Zhao, Weiqin Huang, Wei Fang, Yanwen Yu, Lequan Li, Guodong School of Computing and Data Science The University of Hong Kong Hong Kong Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong

The depth of neural networks is a critical factor for their capability, with deeper models often demonstrating superior performance. Motivated by this, significant efforts have been made to enhance layer aggregation - reusing information from previous layers to better extract features at the current layer, to improve the representational power of deep neural networks. However, previous works have primarily addressed this problem from a discrete-state perspective which is not suitable as the number of network layers grows. This paper novelly treats the outputs from layers as states of a continuous process and considers leveraging the state space model (SSM) to design the aggregation of layers in very deep neural networks. Moreover, inspired by its advancements in modeling long sequences, the Selective State Space Models (S6) is employed to design a new module called Selective State Space Model Layer Aggregation (S6LA). This module aims to combine traditional CNN or transformer architectures within a sequential framework, enhancing the representational capabilities of state-of-the-art vision networks. Extensive experiments show that S6LA delivers substantial improvements in both image classification and detection tasks, highlighting the potential of integrating SSMs with contemporary deep learning techniques. Copyright © 2025, The Authors. All rights reserved.

关键词： State space methods

来源：评论

学校读者我要写书评

暂无评论

In-Depth Sleep Disorder Assessment using REMcraft Navigator IoT and Random Forest Algorithms 2

In-Depth Sleep Disorder Assessment using REMcraft Navigator ...

引用

2nd International Conference on Computer, Communication and Control, IC4 2024

作者： Praveen, More Srinivasan, V. Prasanna Sivakumar, V.G. Vijayan, P. Tharun, R. Thamizhamuthu, R. Sreenidhi Institute of Science and Technology Department of Computer Science and Engineering Telangana Hyderabad India R.M.D. Engineering College Department of Information Technology Tamil Nadu Chennai India Vidya Jyothi Institute of Technology Department of Electronics and Communication Engineering Telangana Hyderabad India Saveetha Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Mother Theresa Institute of Engineering and Technology Department of Civil Engineering Andhra Pradesh Palamaner India Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Tamil Nadu Chennai India

ISBN: (纸本)9798350387933

To accurately diagnose and treat sleep problems, which are major challenges to public health, more sophisticated evaluation methods are needed. Using Rapid Eye Movement (REM) craft Navigator's Internet of Things (IoT) capabilities in conjunction with Random Forest algorithms, this research presents a novel method for comprehensive assessments of sleep disorders. The REMcraft Navigator IoT system incorporates a wide range of physiological and environmental factors into its comprehensive real-time data collection on sleep patterns. The research uses Random Forest algorithms' ability to handle complicated, multi-dimensional datasets by using them to examine the gathered data. In detecting and categorizing sleep problems, the algorithm model outperforms the conventional diagnosis techniques. The comprehensive evaluation is provided by taking contextual elements like the surrounding surroundings and the sleep environment. The suggested method has promising use as a powerful tool for sleep problem diagnosis, and results from a large-scale clinical investigation confirm its efficacy. The system can improve assessment accuracy and personalized treatment plans. This paper provides a high-tech and realistic solution for doctors dealing with sleep disorders, which helps move the field forward in its diagnostic capabilities. The suggested system is an excellent option for home-based monitoring and extensive use in sleep clinics due to its scalability and flexibility, improving the treatment of sleep-related health problems in the long term. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Target networks and over-parameterization stabilize off-policy bootstrapping with function approximation 24

Target networks and over-parameterization stabilize off-poli...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Fengdi Che Chenjun Xiao Jincheng Mei Bo Dai Ramki Gummadi Oscar A Ramirez Christopher K Harris A. Rupam Mahmood Dale Schuurmans Department of Computing Science University of Alberta School of Data Science The Chinese University of Hong Kong Shenzhen Google DeepMind Google DeepMind and School of Computational Science and Engineering Georgia Tech Figure and Google Google and Uber Department of Computing Science University of Alberta and CIFAR AI Chair Amii Department of Computing Science University of Alberta and Google DeepMind and CIFAR AI Chair Amii

We prove that the combination of a target network and over-parameterized linear function approximation establishes a weaker convergence condition for bootstrapped value estimation in certain cases, even with off-policy data. Our condition is naturally satisfied for expected updates over the entire state-action space or learning with a batch of complete trajectories from episodic Markov decision processes. Notably, using only a target network or an over-parameterized model does not provide such a convergence guarantee. Additionally, we extend our results to learning with truncated trajectories, showing that convergence is achievable for all tasks with minor modifications, akin to value truncation for the final states in trajectories. Our primary result focuses on temporal difference estimation for prediction, providing high-probability value estimation error bounds and empirical analysis on Baird's counterexample and a Four-room task. Furthermore, we explore the control setting, demonstrating that similar convergence conditions apply to Q-learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SP-DSTS-MIMO Scheme-Aided H.266 for Reliable High data Rate Mobile Video Communication

引用

Computers, Materials & Continua 2023年第1期74卷 995-1010页

作者： Khadem Ullah Nasru Minallah Durre Nayab Ishtiaque Ahmed Jaroslav Frnda Jan Nedoma Department of Computer Systems Engineering University of Engineering and Technology PeshawarPeshawar25000Pakistan National Centre in Big Data and Cloud Computing University of Engineering and Technology Peshawar(NCBC-UETP)Peshawar25000Pakistan Department of Quantitative Methods and Economic Informatics Faculty of Operation and Economics of Transport and CommunicationsUniversity of Zilina01026ZilinaSlovakia Department of Telecommunications Faculty of Electrical Engineering and Computer ScienceVSB-Technical University of OstravaOstrava-PorubaCzech Republic

With the ever growth of Internet users,video applications,and massive data traffic across the network,there is a higher need for reliable bandwidth-efficient multimedia *** Video Coding(VVC/H.266)is finalized in September 2020 providing significantly greater compression efficiency compared to Highest Efficient Video Coding(HEVC)while providing versatile effective use for Ultra-High Definition(HD)*** article analyzes the quality performance of convolutional codes,turbo codes and self-concatenated convolutional(SCC)codes based on performance metrics for reliable future video *** advent of turbo codes was a significant achievement ever in the era of wireless communication approaching nearly the Shannon *** codes are operated by the deployment of an interleaver between two Recursive Systematic Convolutional(RSC)encoders in a parallel *** RSC encoders may be operating on the same or different architectures and code *** proposed work utilizes the latest source compression standards H.266 and H.265 encoded standards and Sphere Packing modulation aided differential Space Time Spreading(SP-DSTS)for video transmission in order to provide bandwidth-efficient wireless video ***,simulation results show that turbo codes defeat convolutional codes with an averaged E_(b)/N_(0) gain of 1.5 dB while convolutional codes outperformcompared to SCC codes with an E_(b)/N_(0) gain of 3.5 dBatBit ErrorRate(BER)of 10−*** Peak Signal to Noise Ratio(PSNR)results of convolutional codes with the latest source coding standard of H.266 is plotted against convolutional codes with H.265 and it was concluded H.266 outperform with about 6 dB PSNR gain at E_(b)/N_(0) value of 4.5 dB.

关键词： H.265 RSC turbo codes SCC SP-DSTS BP-CNN BER PSNR

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：