检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Chipilski, Hristo G. Department of Scientific Computing Florida State University Tallahassee Florida Advanced Study Program National Center for Atmospheric Research BoulderCO United States

The majority of data assimilation (DA) methods in the geosciences are based on Gaussian assumptions. While these assumptions facilitate efficient algorithms, they cause analysis biases and subsequent forecast degradations. Non-parametric, particle-based DA algorithms have superior accuracy, but their application to high-dimensional models still poses operational challenges. Drawing inspiration from recent advances in the field of generative artificial intelligence (AI), this article introduces a new nonlinear estimation theory which attempts to bridge the existing gap in DA methodology. Specifically, a Conjugate Transform Filter (CTF) is derived and shown to generalize the celebrated Kalman filter to arbitrarily non-Gaussian distributions. The new filter has several desirable properties, such as its ability to preserve statistical relationships in the prior state and convergence to highly accurate observations. An ensemble approximation of the new theory (ECTF) is also presented and validated using idealized statistical experiments that feature bounded quantities with non-Gaussian distributions, a prevalent challenge in Earth system models. Results from these experiments indicate that the greatest benefits from ECTF occur when observation errors are small relative to the forecast uncertainty and when state variables exhibit strong nonlinear dependencies. Ultimately, the new filtering theory offers exciting avenues for improving conventional DA algorithms through their principled integration with AI techniques. Copyright © 2023, The Authors. All rights reserved.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Model Prediction Using Random Forest Algorithm and Time Series Analysis Parts Distribution with in Indonesia Automotive Industry

Model Prediction Using Random Forest Algorithm and Time Seri...

引用

International Conference on Informatics and computing (ICIC)

作者： H Andy Achmad Arief Ramadhan H Warnars Harco Leslie Widodo Budiharto Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia School of Computing Telkom University Bandung Indonesia

Car spare parts are parts of a car that consist of components that form a certain unity and function, there are some parts that are damaged more often and therefore must be replaced more often. In this research, to predict the availability of spare parts using the times series moving average prediction method with random forest. The dataset used in this research is 19,068 consisting of location, transaction number, transaction date, part number, quantity and odo-km. Distribution of spare parts classified based on recapitulation of spare part distribution is RAE=54.5541% and RSE=63.8888%, distribution of spare parts based on location is RAE=55.5541% and RSE=65.2118%, maintenance based on ODO-KM is RAE=33.0949% and RSE=41.2241 % and distribution quantity RAE=33.749% and RSE=36.2317%. The results of spare part distribution analysis using the Confusion Matrix with probability accuracy are TP Rate=0.903, FP Rate=0.067, Precision=0.911, Recall=0.903, F-Measure=0.893, MCC=0.857, ROC Area=0.983 and PRC Area=0.948. The aim of this research is to determine the factors needed to build a machine learning-based spare parts distribution model, implementation, measurement and prediction in the automotive industry in Indonesia.

关键词：

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

Server Cloud Based Security Surveillance Systems: a Design Science Research

Server Cloud Based Security Surveillance Systems: a Design S...

引用

International Conference on Cyber and IT Service Management (CITSM)

作者： Alexander Nurenie Arief Ramadhan Edi Abdurachman Agung Trisetyarso Muhammad Zarlis Computer Science Department BINUS Graduate Program – Computer Science Bina Nusantara University Jakarta Indonesia School of Computing Telkom University Bandung Indonesia

In this research, the author addresses the prevalent issues faced by users of cloud services, especially those using Peer-to-Peer (P2P) technology, such as connection losses, security concerns, and poor video quality. The study does not delve into the complex problems at the data center level but instead proposes a novel Design Science Research approach. This new method, tested with five clients in varied locations, utilizes port forwarding to establish a direct server-client connection, bypassing traditional P2P frameworks. The results show that this approach significantly improves quality over the P2P system. Feedback from clients before and after the experiment indicates a positive response to this new method. This research offers insights into overcoming P2P-related issues in cloud services and contributes to the development of cloud-based server science, presenting a cost-effective, independent alternative to data center-dependent P2P services, with plans for ongoing research in this area.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Role of Social Media Influencer towards Fashion Brand Sales for Indonesia's Young Consumers

The Role of Social Media Influencer towards Fashion Brand Sa...

引用

International Conference on Business and Industrial Research (ICBIR)

作者： Grasheli Kusuma Andhini Ahmad Seiichi Ramadhan Fashion Design Program Product Design Department School of Computing and Creative Arts Bina Nusantara University Jakarta Indonesia Management Department Binus Business School International Business Program Bina Nusantara University Jakarta Indonesia

With the current ongoing pandemic in Indonesia where everything is forced to be online, consumers have started to forget brand names as there are no physical interaction. Social media becomes the main communication tool for Millennials to seek for social interactions that have been missing. This results in the boom of social media influencers (SMI) to represent brands when communicating to consumers, but how it would directly link to local brand sales is still ambiguous in the midst of fashion consumption disruption. The research looks into how Indonesian fashion brand could benefit from the rising SMIs with their contents towards leveraging leads. An exploratory descriptive research was done with multi method approach and non-probability sampling techniques combining online survey on 80 consumers, archival research on influencer, and interview on influencers. Today, SMIs are influential for local businesses to reach a wider market as the intermediary between brands and consumers. SMI indeed helps brands in achieving success but not a hundred percent it will improve brand sales instantly rather it is more about driving awareness. They induce awareness for brands that would eventually help in the creation of brand image and familiarity that lead to purchase intention and customer loyalty.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of Image Classification Models for Ornamental Rock Classification

Comparative Evaluation of Image Classification Models for Or...

引用

Conferencia Latinoamericana En Informatica (CLEI)

作者： Douglas Fiório Dias Karin Satie Komati Kelly Assis de Souza Gazolli Graduate Program in Applied Computing PPComp IFES Campus Serra Serra-ES Brazil PPComp IFES Campus Serra Instituto Federal do Espírito Santo Serra-ES Brazil

ISBN: (数字)9798331540975

ISBN: (纸本)9798331540982

The ornamental rock industry in Brazil is distinguished by its diverse assortment of rock types, presenting a unique challenge in classification due to its inherent subjectivity and reliance on expert judgment. to address this problem, the present study introduces a publicly accessible database encompassing 12 distinct classes of ornamental rocks, including granite, marble, and quartzite. This database comprises 1,798 images sourced directly from entities within the stone sector. We employ and compare the performance of seven neural network models for ornamental rock image classification: VGG16, VGG19, ResNet50, ResNet101, Xception, InceptionV3, and the Vision Transformer (ViT). Our empirical analysis reveals that the ViT model outperforms conventional architectures, achieving an accuracy rate of 98.36%.

关键词： Computer vision Analytical models Accuracy Databases Computational modeling Pancreatic cancer Computer architecture Rocks Transformers Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning Adaptation and Generalization from Human-Inspired Meta-Reinforcement Learning Using Bayesian Knowledge and Analysis 6

Learning Adaptation and Generalization from Human-Inspired M...

引用

6th IEEE International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2023

作者： Ho, Joshua Wang, Chien-Min King, Chung-Ta You, Yi-Hsin Feng, Chi-Wei Chen, Yen-Min Kuo, Bo-Yi Institute of Information Science Academia Sinica Taipei11529 Taiwan Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Taiwan Institute of Information Systems and Applications National Tsing Hua University Hsinchu30013 Taiwan Department of Computer Science National Tsing Hua University Hsinchu30013 Taiwan Department of Computer Science National Taiwan University Taipei10631 Taiwan Center of Intelligent Healthcare National Taiwan University Hospital Taipei10022 Taiwan

ISBN: (纸本)9798350331288

Over the last decades, there has been growing interest in research in multiple and interdisciplinary fields of human-AI computing. In particular, approaches integrating the intersecting design with reinforcement learning (RL) have received more attention. However, the current research on RL may need to consider its enhancement from a humaninspired approach further. In the present work, we focus on enabling a meta-reinforcement learning (meta-RL) agent to achieve adaptation and generalization according to modeling Markov decision processes using Bayesian knowledge and analysis. By introducing a novel framework called human-inspired meta-RL (HMRL), we incorporate the agent performing resilient actions to leverage the dynamic dense reward based on the knowledge and prediction of a Bayesian analysis. The proposed framework can make the agent learn generalization and prevent the agent from failing catastrophically. The experimental results show that our approach helps the agent reduce computational costs with learning adaptation. Finally, we conclude and anticipate that integrating human-inspired meta-RL can enable learning more formulations relating to robustness and scalability, leading to promising directions and more complex AI goals in the future. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

DC/AC/RF Characteristics of Multi-Channel GAA NS FETs with ML and BL MoS2

DC/AC/RF Characteristics of Multi-Channel GAA NS FETs with M...

引用

International Conference on Simulation of Semiconductor Processes and Devices (SISPAD)

作者： Yueh-Ju Chan Sekhar Reddy Kola Yiming Li Institute of Communications Engineering and Parallel and Scientific Computing Laboratory National Yang Ming Chiao Tung Univeristy Hsinchu Taiwan EECS International Graduate Program and Parallel and Scientific Computing Laboratory National Yang Ming Chiao Tung Univeristy Hsinchu Taiwan

For the first time, we examine the performance of gate-all-around nanosheet field effect transistor (GAA NS FET) with both monolayer (ML) and bilayer (BL) molybdenum disulfide (MoS 2 ). As compared to the control sample of silicon (Si), MoS 2 devices exhibit reduced short-channel effects (SCE) owing to its larger band gap and larger effective mass. The GAA NS FET with BL MoS 2 possesses moderate energy bandgap and large channel thickness which exhibits superior on state current and voltage gain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OGrES Welcome! Toward a systematic theory for serious game design 21

OGrES Welcome! Toward a systematic theory for serious game d...

引用

8th ACM SIGCHI Annual Symposium on Computer-Human Interaction in Play, CHI PLAY 2021

作者： Blackburn, Nancy N. Cardona-Rivera, Rogelio E. Laboratory for Quantitative Experience Design School of Computing and the Entertainment Arts and Engineering Program University of Utah Salt Lake CityUT United States

ISBN: (纸本)9781450383561

Despite the vast scholarship around serious games, there is still no consensus methodology for how to best go about designing them. This paper presents work-in-progress toward synthesizing an actionable, systematic serious game design theory. We introduce mIBO as a computational model to aid in thinking about game design processes and rationales, and OGrES as a method for defining the function of a serious game. © 2021 Owner/Author.

关键词： Serious games

来源：评论

学校读者我要写书评

暂无评论

FluxProg 2.0 - Extended Version of a Visual Tool for Teaching programming Logic Using Flowcharts with Real and Simulated Robots

FluxProg 2.0 - Extended Version of a Visual Tool for Teachin...

引用

2024 Brazilian Symposium on Robotics (SBR), and 2024 Workshop on Robotics in Education (WRE)

作者： Matheus Biscaya Gutierrez João Alberto Fabro André Cristiano Cordeiro Academic Department of Informatics (DAINF-CT) Federal University of Technology - Paraná (UTFPR) Curitiba PR Brazil Graduate Program on Applied Computing (PPGCA) DAINF-CT - UTFPR Curitiba PR Brazil

ISBN: (数字)9798350391084

ISBN: (纸本)9798350391091

This paper presents a new teaching tool with the goal of facilitating the learning of basic programming concepts among high school students and university freshmen. The tool incorporates a user-friendly visual interface and robotics, expanding on the existing Fluxprog project. New features were implemented, such as variables, logical and mathematical operations, conditional structures, and loops, to motivate students to engage in challenges that promote logical thinking. This paper presents the design, implementation and evaluation of a programming teaching tool using a visual language based on flowcharts, with subsequent data collection through a questionnaire and analysis of preliminary results to evaluate the user's experience while interacting with the tool.

关键词： Visualization Flowcharts Conferences Education Data collection User experience Logic Robots programming profession

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：