检索结果-内蒙古大学图书馆

2024 Winter simulation Conference, WSC 2024

作者： Martínez, Joseph Llinas, Brian Botello, Jhon G. Padilla, Jose J. Frydenlund, Erika Virginia Modeling Analysis and Simulation Center Old Dominion University SuffolkVA United States

ISBN: (纸本)9798331534202

Recognizing the limited research on Large Language Models (LLMs) capabilities with low-resource languages, this study evaluates and increases the proficiency of the LLM GPT-3.5 in generating interface and procedural code elements for NetLogo, a multi-agent programming language and modeling environment. To achieve this, we employed "few-shot" prompting and Retrieval-Augmented Generation (RAG) methodologies using two manually created datasets, NetLogoEvalCode and NetLogoEvalInterface. The results demonstrate that GPT-3.5 can generate NetLogo elements and code procedures more effectively when provided with additional examples to learn from, highlighting the potential of LLMs in aiding the development of agent-based models (ABMs). On the other hand, the RAG model obtained a poor performance. We listed possible reasons for this result, which were aligned with RAG’s common challenges identified by the state-of-the-art. We propose future research directions for leveraging LLMs for simulation development and instructional purposes in the context of ABMs. © 2024 IEEE.

关键词： modeling languages

来源：评论

学校读者我要写书评

暂无评论

U-Net Based Disaster Damage Detection Through Semantic Segmentation

U-Net Based Disaster Damage Detection Through Semantic Segme...

引用

2023 International Symposium on Networks, Computers and Communications, ISNCC 2023

作者： Nipa, Nishat Ara Lu, Yan Shetty, Sachin Virginia Modeling Analysis & Simulation Center Old Dominion University NorfolkVA United States

ISBN: (纸本)9798350335590

Satellite image analysis of natural disasters is critical for effective emergency response, relief planning, and disaster prevention. They can provide a comprehensive view of the affected area allowing for quick and accurate assessments of the extent of damage by providing critical information on the disaster's development. Semantic segmentation is believed to be one of the best techniques to capture pixel-wise information in computer vision. In this work, we will be using U-Net-based architectures to address the building localization and damage detection of the complex Xview2 dataset. We propose a generic algorithm that is not constrained by the nature of the disaster and can be deployed to various classes of disaster types with slight modifications. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

ACCELERATING HYBRID AGENT-BASED MODELS AND FUZZY COGNITIVE MAPS: HOW TO COMBINE AGENTS WHO THINK ALIKE?

ACCELERATING HYBRID AGENT-BASED MODELS AND FUZZY COGNITIVE M...

引用

2024 Winter simulation Conference, WSC 2024

作者： Giabbanelli, Philippe J. Beerman, Jack T. Virginia Modeling Analysis and Simulation Center Old Dominion University NorfolkVA United States School of Data Science University of Virginia CharlottesvilleVA United States

ISBN: (纸本)9798331534202

While Agent-Based Models can create detailed artificial societies based on individual differences and local context, they can be computationally intensive. Modelers may offset these costs through a parsimonious use of the model, for example by using smaller population sizes (which limits analyses in sub-populations), running fewer what-if scenarios, or accepting more uncertainty by performing fewer simulations. Alternatively, researchers may accelerate simulations via hardware solutions (e.g., GPU parallelism) or approximation approaches that operate a tradeoff between accuracy and compute time. In this paper, we present an approximation that combines agents who ‘think alike’, thus reducing the population size and the compute time. Our innovation relies on representing agent behaviors as networks of rules (Fuzzy Cognitive Maps) and empirically evaluating different measures of distance between these networks. Then, we form groups of think-alike agents via community detection and simplify them to a representative agent. Case studies show that our simplifications remain accuracy. © 2024 IEEE.

关键词： Fuzzy inference

来源：评论

学校读者我要写书评

暂无评论

Transmission Power Control for Interference Reduction in Cellular D2D Networks

Transmission Power Control for Interference Reduction in Cel...

引用

2023 International Symposium on Networks, Computers and Communications, ISNCC 2023

作者： Sadehvand, Mehrdad Moghim, Neda Ghahfarokhi, Behrouz Shahgholi Shetty, Sachin University of Isfahan Department of Computer Engineering Isfahan Iran Virginia Modeling Analysis and Simulation Center Old Dominion University Suffolk United States

ISBN: (纸本)9798350335590

Interference is one of the most critical issues in the cellular Device-to-Device (D2D) networks. The sharing of radio resources in cellular and D2D communications offers spectrum efficiency advantages for the cellular network. However, resource sharing also introduces interference, leading to a reduction in the quality of service experienced by users. In this paper, we propose an adversarial Multi-Armed Bandit learning-based transmission Power Control method called MAB-PC for both cellular and D2D transmitters. The objective of this method is to ensure the minimum service quality for users, considering the minimum spectral efficiency and maximum block error rate. Additionally, to address the conflicting objectives of D2D and cellular communications, MAB-PC is modeled as a Pareto optimization problem for D2D transmitters. MAB-PC is a distributed method that minimizes signaling overhead and relies solely on local Channel State Information (CSI). The effectiveness of the proposed method is evaluated based on reliability, total data rate, spectral efficiency, block error rate, and outage probability, demonstrating superior performance compared to its counterpart. © 2023 IEEE.

关键词： Spectrum efficiency

来源：评论

学校读者我要写书评

暂无评论

BROADENING ACCESS TO simulationS FOR END-USERS VIA LARGE LANGUAGE MODELS: CHALLENGES AND OPPORTUNITIES

BROADENING ACCESS TO SIMULATIONS FOR END-USERS VIA LARGE LAN...

引用

2024 Winter simulation Conference, WSC 2024

作者： Giabbanelli, Philippe J. Padilla, Jose J. Agrawal, Ameeta Virginia Modeling Analysis and Simulation Center Old Dominion University NorfolkVA United States Dept. of Computer Science Portland State University PortlandOR United States

ISBN: (纸本)9798331534202

Large Language Models (LLMs) are becoming ubiquitous to create intelligent virtual assistants that assist users in interacting with a system, as exemplified in marketing. Although LLMs have been discussed in modeling & simulation (M&S), the community has focused on generating code or explaining results. We examine the possibility of using LLMs to broaden access to simulations, by enabling non-simulation end-users to ask what-if questions in everyday language. Specifically, we discuss the opportunities and challenges in designing such an end-to-end system, divided into three broad phases. First, assuming the general case in which several simulation models are available, textual queries are mapped to the most relevant model. Second, if a mapping cannot be found, the query can be automatically reformulated and clarifying questions can be generated. Finally, simulation results are produced and contextualized for decision-making. Our vision for such system articulates long-term research opportunities spanning M&S, LLMs, information retrieval, and ethics. © 2024 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Exploring Large Language Models for Analyzing Changes in Web Archive Content: A Retrieval-Augmented Generation Approach

Exploring Large Language Models for Analyzing Changes in Web...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Botello, Jhon G. Frew, Lesley Padilla, Jose J. Weigle, Michele C. Old Dominion University Department of Computer Science NorfolkVA United States Virginia Modeling Analysis and Simulation Center Old Dominion University NorfolkVA United States

ISBN: (纸本)9798350362480

Websites typically display only their most recent content. However, the dynamic nature of the web leads to frequent updates and deletions. Web archives preserve snapshots of earlier versions for those interested in tracking changes over time. Analyzing these changes often requires a manual process that relies on traditional methods focused on terms or phrase-level differences. This study explores the capability of Large Language Models (LLMs), specifically GPT-4o, through a Retrieval-Augmented Generation (RAG) approach for detecting changes in archived web pages. Using WARC-GPT, a RAG pipeline to interact with Web ARChive (WARC) files, we identify and analyze changes across a small set of U.S. federal environmental web pages that changed between 2016 and 2020. Our findings show that GPT-4o can effectively be used to detect inconsistencies in web archive content, including consideration of the change and the semantic context upon which the changes occurred. Our exploration represents an initial step toward using Artificial Intelligence (AI) for deeper and scalable web change analysis. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Enhancing GPT-3.5's Proficiency in Netlogo through Few-Shot Prompting and Retrieval-Augmented Generation 24

Enhancing GPT-3.5's Proficiency in Netlogo through Few-Shot ...

引用

Proceedings of the Winter simulation Conference

作者： Joseph Martínez Brian Llinas Jhon G. Botello Jose J. Padilla Erika Frydenlund Virginia Modeling Analysis and Simulation Center Old Dominion University Suffolk VA USA

ISBN: (纸本)9798331534202

Recognizing the limited research on Large Language Models (LLMs) capabilities with low-resource languages, this study evaluates and increases the proficiency of the LLM GPT-3.5 in generating interface and procedural code elements for NetLogo, a multi-agent programming language and modeling environment. To achieve this, we employed "few-shot" prompting and Retrieval-Augmented Generation (RAG) methodologies using two manually created datasets, NetLogoEvalCode and NetLogoEvalInterface. The results demonstrate that GPT-3.5 can generate NetLogo elements and code procedures more effectively when provided with additional examples to learn from, highlighting the potential of LLMs in aiding the development of agent-based models (ABMs). On the other hand, the RAG model obtained a poor performance. We listed possible reasons for this result, which were aligned with RAG's common challenges identified by the state-of-the-art. We propose future research directions for leveraging LLMs for simulation development and instructional purposes in the context of ABMs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing GPT-3.5's Proficiency in Netlogo Through Few-Shot Prompting and Retrieval-Augmented Generation

Enhancing GPT-3.5's Proficiency in Netlogo Through Few-Shot ...

引用

simulation Winter Conference

作者： Joseph Martínez Brian Llinas Jhon G. Botello Jose J. Padilla Erika Frydenlund Virginia Modeling Analysis and Simulation Center Old Dominion University Suffolk VA USA

ISBN: (数字)9798331534202

ISBN: (纸本)9798331534219

Recognizing the limited research on Large Language Models (LLMs) capabilities with low-resource languages, this study evaluates and increases the proficiency of the LLM GPT-3.5 in generating interface and procedural code elements for NetLogo, a multi-agent programming language and modeling environment. To achieve this, we employed “few-shot” prompting and Retrieval-Augmented Generation (RAG) methodologies using two manually created datasets, NetLogoEvalCode and NetLogoEvalInterface. The results demonstrate that GPT-3.5 can generate NetLogo elements and code procedures more effectively when provided with additional examples to learn from, highlighting the potential of LLMs in aiding the development of agent-based models (ABMs). On the other hand, the RAG model obtained a poor performance. We listed possible reasons for this result, which were aligned with RAG's common challenges identified by the state-of-the-art. We propose future research directions for leveraging LLMs for simulation development and instructional purposes in the context of ABMs.

关键词： Hands Computer languages Codes Large language models Retrieval augmented generation

来源：评论

学校读者我要写书评

暂无评论

modeling and simulation as a Bridge to Advance Practical and Theoretical Insights About Forced Migration Studies

引用

Journal on Migration and Human Security 2021年第3期9卷 165-181页

作者： Frydenlund, Erika Virginia Modeling Analysis and Simulation Center Old Dominion University United States

modeling and simulation (M&S) is a relatively unused research approach in forced migration studies. In most of its application areas, M&S is applied in several broad thematic policy-oriented topics: predicting human movement, humanitarian logistics, communicable diseases, healthcare, policing, and economics. More recently, there has been increased use of M&S in predicting human movement and health impacts resulting from climate change. Computer modeling has benefits for both policy and theoretical advancements in the field. M&S is often associated as a predictive tool that appeals to policymakers and planners. But M&S has many other significant benefits. For policymakers and planners, M&S provides a simulated environment to explore “what-if” scenarios. These scenarios can be adjusted to reflect different assumptions and conditions in the field. M&S can provide a means for translating interpretivist research findings—themselves rich in descriptions of actors, relationships, and dynamics—into visual artifacts that can communicate results to policymakers. It also can help to test the assumptions of theoretical findings, explore generalizability to other cases and conditions, and inform future data collection efforts. On the other hand, because models can take a long time to construct and test, they cannot provide rapid insights about evolving situations to inform decision-making at the onset of a new emergency. Data dashboards, the staple of modern humanitarian operations, are better for identifying emergent needs and tracking efforts. However, modeling what we know from one situation allows us to use those insights in systematic and strategic ways to improve operations for the future. M&S can also provide researchers with an additional tool that allows improved integration of multiple data types and sources. These data, assumptions, and theoretical constructs can be linked together in a complex, nonlinear, dynamic system that can then be set in motion to see if the si

关键词：

来源：评论

学校读者我要写书评

暂无评论

MIA-BAD: An Approach for Enhancing Membership Inference Attack and its Mitigation with Federated Learning

MIA-BAD: An Approach for Enhancing Membership Inference Atta...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Soumya Banerjee Sandip Roy Sayyed Farid Ahamed Devin Quinn Marc Vucovich Dhruv Nandakumar Kevin Choi Abdul Rahman Edward Bowen Sachin Shetty Virginia Modeling Analysis and Simulation Center Old Dominion University Virginia USA Deloitte & Touche LLP

ISBN: (数字)9798350370997

ISBN: (纸本)9798350371000

The membership inference attack (MIA) is a popular paradigm for compromising the privacy of a machine learning (ML) model. MIA exploits the natural inclination of ML models to overfit upon the training data. MIAs are trained to distinguish between training and testing prediction confidence to infer membership information. Federated Learning (FL) is a privacy-preserving ML paradigm that enables multiple clients to train a unified model without disclosing their private data. In this paper, we propose an enhanced Membership Inference Attack with the Batch-wise generated Attack Dataset (MIA-BAD), a modification to the MIA approach. We investigate that the MIA is more accurate when the attack dataset is generated batch-wise. This quantitatively decreases the attack dataset while qualitatively improving it. We show how training an ML model through FL, has some distinct advantages and investigate how the threat introduced with the proposed MIA-BAD approach can be mitigated with FL approaches. Finally, we demonstrate the qualitative effects of the proposed MIA-BAD methodology by conducting extensive experiments with various target datasets, variable numbers of federated clients, and training batch sizes.

关键词： Training Privacy Accuracy Federated learning Training data Data models Testing

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：