检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Songge Cheng, Guoliang Huang, Xinyu Li, Zuguang Wu, Wen Song, Lingyang Shen, Xuemin School of Electronic and Computer Engineering Peking University Shenzhen518000 China Frontier Research Center Pengcheng Laboratory Shenzhen518055 China State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Beijing100871 China School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen518055 China Department of Electrical and Computer Engineering University of Waterloo WaterlooN2L 3G1 Canada

Fine-tuning is the process of adapting the pre-trained large language models (LLMs) for downstream tasks. Due to substantial parameters, fine-tuning LLMs on mobile devices demands considerable memory resources, and suffers from high communication overhead and long fine-tuning delay. In this paper, we propose an efficient LLM fine-tuning scheme in wireless networks, named Split Fine-Tuning (SFT), which can accommodate LLM fine-tuning on mobile devices. Specifically, an LLM is split into a server-side part on the edge server and a device-side part on the mobile device to satisfy the device-side memory constraint. All devices share a server-side model and perform parallel fine-tuning to reduce fine-tuning delay. In addition, to reduce significant communication overhead incurred by data exchange between devices and the edge server, we propose a data compression scheme by jointly leveraging sparsification, stochastic quantization, and lossless encoding methods. Furthermore, we formulate a fine-tuning delay minimization problem under accuracy and memory constraints, taking device heterogeneity and channel dynamics into account. To solve the problem, the nonlinear mixed-integer problem is decoupled into two subproblems in different timescales. The two-timescale resource management algorithm is proposed to jointly optimize the compression rate and transformer block allocation in the large timescale using the augmented Lagrangian method, and determine spectrum resource allocation in the small timescale via sequential quadratic programming. Extensive simulation results demonstrate that the proposed scheme can reduce the fine-tuning delay by up to 80.2% and communication overhead by 93.6% compared to state-of-the-art benchmarks, while satisfying device-side memory and model accuracy constraints. Copyright © 2025, The Authors. All rights reserved.

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

Determination of an implementation order for IS projects

引用

INFORMATION & management 1996年第2期31卷 67-74页

作者： Shoval, P Giladi, R Information Systems Program Department of Industrial Engineering and Management Faculty of Engineering Sciences Ben-Gurion University of the Negev Beer-Sheva 84105 Israel

The process of information systems (IS) planning in an organization occurs when there is a set of IS projects that require implementation, generally within certain time frames and budgetary constraints. We propose a method for determining an optimal order of project implementation. The proposed method utilizes the cost-benefit graph, which considers the expected cost and benefit of each of the projects comprising the set, as well as the weight (importance) of the cost and benefit factors to the decision-makers. The method allows us to analyze the sensitivity of a preferred implementation order to changes in cost and benefits, and the importance of these factors.

关键词： cost-benefit analysis cost-benefit graph decision-making process information systems planning and selection project management

来源：评论

学校读者我要写书评

暂无评论

systems methodology and framework for problem definition in Mobile ad hoc networks

Systems methodology and framework for problem definition in ...

引用

2008 IEEE International systems Conference Proceedings, SysCon 2008

作者： Anguswamy, Reghu Thiagarajan, Maheswaran Dagli, Cihan H. Systems Engineering Program Department of Engineering Management and Systems Engineering Missouri University of Science and Technology Rolla MO 65401 United States Systems Engineering Graduate Program Department of Engineering Management and Systems Engineering Missouri University of Science and Technology Rolla MO 65401 United States

ISBN: (纸本)9781424421503

Mobile Ad Hoc Networks are communication networks built up of a collection of mobile devices which can communicate through wireless connections. Mobile Ad Hoc Networks have many challenges such as routing, which is the task of directing data packets from a source node to a given destination. This task is particularly hard in Mobile Ad Hoc Networks: due to the mobility of the network elements and the lack of central control, robustness and adaptability in routing algorithms and work in a decentralized and self organizing way. Through the principles of systems architecting and engineering, the problem statement in Mobile Ad Hoc Networks could be defined more specifically and accurately. The uncertainties and techniques for mitigating and even taking positive advantages of them can be achieved through a framework of uncertainties as in [1]. The systems methodology framework called Total systems Intervention (TSI) described by Flood and Jackson [2] select a systems methodology for Mobile Ad Hoc Networks. The purpose of this paper is to show how TSl when integrated with a framework created to understand the risks and opportunities can help develop strategies to minimize the risks and to take advantage of the opportunities for facing challenges in Mobile Ad Hoc Networks. ©2008 IEEE.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Contextual Caching for Mobile Edge Large Language Model Service

arXiv

引用

arXiv 2025年

作者： Liu, Guangyuan Liu, Yinqiu Wang, Jiacheng Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui College of Computing and Data Science The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Electronic Engineering University of Hong Kong Hong Kong School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore

Mobile edge Large Language Model (LLM) deployments face inherent constraints, such as limited computational resources and network bandwidth. Although Retrieval-Augmented Generation (RAG) mitigates some challenges by integrating external knowledge bases, inefficient cache management can still result in high retrieval latency and frequent cache updates. To address these issues, we propose an Adaptive Contextual Caching (ACC) framework that anticipates user needs by proactively caching semantically relevant data for mobile-edge LLMs. ACC utilizes a deep reinforcement learning (DRL) module to refine cache replacement policies, balancing user context, document similarity, and the overhead associated with cache misses. Experimental results demonstrate that ACC increases cache hit rates to over 80% after only 11 training episodes, outperforming FIFO, LRU, and semantic-only caching while reducing retrieval latency by up to 40%. In particular, ACC also reduces local caching overhead (i.e., the cost of updating the cache when a miss occurs) by as much as 55%, enabling scalable, low-latency LLM services in resource-constrained edge environments. © 2025, CC BY.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Cascaded evolutionary multiobjective identification based on correlation function statistical tests for improving velocity analyzes in swimming

Cascaded evolutionary multiobjective identification based on...

引用

2014 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making, MCDM 2014

作者： Ayala, Helon Vicente Hultmann Da Cruz, Luciano Ferreira Freire, Roberto Zanetti Coelho, Leandro Dos Santos Industrial and Systems Engineering Graduate Program PUCPR Curitiba Brazil Industrial and Systems Engineering Graduate Program Department of Electrical Engineering UFPR Curitiba Brazil

ISBN: (纸本)9781479944682

By using biomechanical analyses applied to sports many researchers are providing important information to coaches and athletes in order to reach better performance in a shorter time. In swimming, these kinds of analyses are being used to evaluate, to detect and to improve the skills of high level athletes. Recently, evolutionary computing theories have been adopted to support swim velocity profile identification. Based on velocity profiles recognition, it is possible to identify distinct characteristics and classify swimmers according to their abilities. In this way, this work presents an application of Radial Basis Function Neural Network (RBF-NN) associated to a proposed cascaded evolutionary procedure composed by a genetic and Multiobjective Differential Evolution (MODE) algorithms as optimization method for searching the best fitness within a set of parameters to configure the RBF-NN. The main goal and novelty of the proposed approach is to enable, through the adoption of cascaded multiobjective optimization, the use of correlation based tests in order to select both the model lagged inputs and the associated parameters in a supervised fashion. Finally, the real data of a Brazilian elite female swimmer in crawl and breaststroke styles obtained into a 25 meters swimming pool have been identified by the proposed method. The soundness of the approach is illustrated with the adherence to the model validity tests and the values of the multiple correlation coefficients between 0.95 and 0.93 for two tests for both breaststroke and crawl strokes, respectively. © 2014 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Entity-relationship and object-oriented data modeling - An experimental comparison of design quality

引用

DATA & KNOWLEDGE engineering 1997年第3期21卷 297-315页

作者： Shoval, P Shiran, S Information Systems Program Department of Industrial Engineering and Management Ben-Gurion University of the Negev Beer-Sheva 84105 Israel

We compare EER and OO data models from the point of view of design quality. Quality is measured in terms of (a) correctness of the conceptual schemas being designed, (b) time to complete the design task, and (c) designers' preferences of the models. Result of an experimental comparison of the two models reveal that the EER model surpasses the OO model for designing unary and ternary relationships, it takes less time to design EER schemas, and the EER model is preferred by designers. We conclude that even if the objective is to implement an OO database schema, the recommended procedure is to: (1) create an EER conceptual scheme, (2) map it to an OO schema, and augment the target schema with behavioral constructs that are unique to the 00 approach.

关键词： data modeling entity relationship model object oriented model database design conceptual schema experimentation schema transformation quality of design

来源：评论

学校读者我要写书评

暂无评论

STRUCTURED METHOD FOR DESIGNING SUBsystems

引用

INFORMATION AND SOFTWARE TECHNOLOGY 1995年第2期37卷 79-85页

作者： SHOVAL, P Information Systems Program Department of Industrial Engineering and Management Ben-Gurion University of the Negev Beer-Sheva 84105 Israel

This paper describes a structured method for designing subsystems from a whole system, which extends ADISSA methodology for systems analysis, design and prototyping, The design of a subsystem includes: (a) definition of the transactions, or processes, that belong to the subsystem, thus determining the boundaries of the subsystem;(b) design of the subsystem user-interface, a sub-menu-tree, derivable from the menu-tree interface of the global system;and (c) design of the database sub-schema, derivable from the global database schema. The method is supported by a CASE tool, enabling automatic and interactive design and prototyping of the subsystems.

关键词： SUBSYSTEM ANALYSIS AND DESIGN METHODOLOGY CASE PROTOTYPING TRANSACTIONS MAN-MACHINE INTERFACE MENU-TREE DATABASE SCHEMA SUB-SCHEMA

来源：评论

学校读者我要写书评

暂无评论

Role of the Ionomer in Supporting Electrolyte-Fed Anion Exchange Membrane Water Electrolyzers

ACS electrochemistry

引用

ACS electrochemistry 2025年第2期1卷 239-248页

作者： Emily K Volk Arielle L Clauser Melissa E Kreider Diego D Soetrisno Sunilkumar Khandavalli Joshua D Sugar Stephanie Kwon Shaun M Alia Advanced Energy Systems Graduate Program Colorado School of Mines Golden Colorado 80401 United States. Sandia National Laboratories Livermore California 94550 United States. Chemistry and Nanoscience Center National Renewable Energy Laboratory Golden Colorado 80401 United States. Materials Science Center National Renewable Energy Laboratory Golden Colorado 80401 United States. Department of Chemical and Biological Engineering Colorado School of Mines Golden Colorado 80401 United States.

While anion exchange membrane water electrolyzers (AEMWEs) have achieved significant performance advances in recent decades, overpotentials remain high relative to their proton exchange membrane water electrolyzer (PEMWE) counterparts, requiring AEMWE-specific catalyst layer design strategies to further advance this technology. In this work, the role of the ionomer in catalyst layer structure and quality, catalyst layer stability, and ion conduction for supporting electrolyte-fed AEMWEs is assessed for catalyst layers composed of NiFeO and PiperION TP85 from Versogen at variable ionomer contents (0-30 wt %) for tests up to 200 h. The results reveal that, for supporting electrolyte-fed AEM devices, the ionomer is not required for ion conduction through the catalyst layer. Instead, the ionomer is found to play a critical role in catalyst layer structure and stability, where intermediate ionomer contents lead to the lowest overpotentials, highest effective surface areas, and lowest catalyst layer resistances. Catalyst layer stability is found to be a function of both catalyst adhesion and ionomer loss. These results show that an ionomer may be selected which is not of the same chemistry as the anion exchange membrane, mitigating ionomer stability concerns throughout the catalyst layer and offering a pathway towards highly active and stable AEMWEs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time anomaly detection for very short-term load forecasting

引用

Journal of Modern Power systems and Clean Energy 2018年第2期6卷 235-243页

作者： Jian LUO Tao HONG Meng YUE School of Management Science and Engineering Dongbei University of Finance and Economics Department of Systems Engineering and Engineering Management University of North Carolina at Charlotte Brookhaven National Laboratory

Although the recent load information is critical to very short-term load forecasting(VSTLF), power companies often have difficulties in collecting the most recent load values accurately and timely for VSTLF *** paper tackles the problem of real-time anomaly detection in most recent load information used by *** paper proposes a model-based anomaly detection method that consists of two components, a dynamic regression model and an adaptive anomaly threshold. The case study is developed using the data from ISO New England. This paper demonstrates that the proposed method significantly outperforms three other anomaly detection methods including two methods commonly used in the field and one state-of-the-art method used by a winning team of the Global Energy Forecasting Competition 2014. Finally, a general anomaly detection framework is proposed for the future research.

关键词： Real-time anomaly detection Very short-term load forecasting Multiple linear regression Data cleansing

来源：评论

学校读者我要写书评

暂无评论

A Study on Purchasing Behavior Analysis Method by Comparing Difference in Latent Class Distributions between Membership Stages

引用

Journal of Japan Industrial management Association 2022年第2期73卷 54-69页

作者： Yang, Tianxiang Yamashita, Haruka Goto, Masayuki Major of Industrial and Management Systems Engineering Graduate School of Creative Science and Engineering Waseda University Japan Department of Information and Communication Sciences Faculty of Science and Technology Sophia University Japan Department of Industrial and Management Systems Engineering School of Creative Science and Engineering Waseda University Japan

A marketing policy called the"Membership Stage System" is widely used in retail business. A membership stage provides benefits to customers such as shopping points when a customer's annual cumulative purchase amount exceeds a certain threshold and the customer's stage is raised a level. As a result, the company is not only able to promote the customer's willingness to purchase, but it can also obtain the purchasing history data, thereby enabling high-quality customer analysis. The most fundamental analysis is to infer the difference of purchasing characteristics between member stages and to construct different clustering models for each member stage. However, when the clustering models are learned independently for each membership stage, it is not possible to compare the obtained clusters between membership stages. In this study, we propose a new analytical method and its learning algorithm to analyze differences in cluster distribution between membership stages. Through demonstrating the proposed model applied to an actual data set of purchasing history data on a membership stage system, the effectiveness of our proposal is clarified. © 2022 Japan Industrial management Association. All rights reserved.

关键词： Sales

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：