检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Kaya, Cem Kilimci, Zeynep Hilal Uysal, Mitat Kaya, Murat Dogus University Turkey Department of Information Systems Engineering Kocaeli University Turkey Department of Software Engineering Dogus University Turkey Department of Computer Programming Acibadem University Turkey

This research introduces a novel approach, MBO-NB, that leverages Migrating Birds Optimization (MBO) coupled with Naive Bayes as an internal classifier to address feature selection challenges in text classification having large number of features. Focusing on computational efficiency, we preprocess raw data using the information Gain algorithm, strategically reducing the feature count from an average of 62221 to 2089. Our experiments demonstrate MBO-NB's superior effectiveness in feature reduction compared to other existing techniques, emphasizing an increased classification accuracy. The successful integration of Naive Bayes within MBO presents a well-rounded solution. In individual comparisons with Particle Swarm Optimization (PSO), MBO-NB consistently outperforms by an average of 6.9% across four setups. This research offers valuable insights into enhancing feature selection methods, providing a scalable and effective solution for text classification. © 2024, CC BY-NC-ND.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Automated Recipe Creation & Verification of Single Wafer Wet Etching: Ensemble Learning with Backcasting & Forecasting AIs using Scarce Data

Automated Recipe Creation & Verification of Single Wafer Wet...

引用

IEEE Silicon Nanoelectronics Workshop (SNW)

作者： Koki Shibata Hiroshi Horiguchi Chihiro Matsui Ken Takeuchi Dept. of Electrical Engineering and Information Systems The University of Tokyo Tokyo Japan Application Software Engineering Operations SCREEN Semiconductor Solutions Co. Ltd. Japan

ISBN: (数字)9798350391633

ISBN: (纸本)9798350391640

Towards smart semiconductor fabrication, the automated process recipe determination with AI is required under scarce data (NOT big data) conditions. This paper proposes precise recipe determination by ensemble learning combining backcasting & forecasting AIs. Proposed backcasting AI predicts etching recipe to optimize the equipment arm motion, traditionally set manually, to achieve the desired etching amount. Automatically estimated etching recipe is optimized in real time and both throughput and yield improve. By means of incorporating additional features such as the differential and variance of etching results and employing ensemble learning with multiple neural networks, RMSE (Root Mean Squared Error) of the objective variable representing the periodic motion of the arm reduces by more than 40%. In addition, forecasting AI that predicts etching results from a recipe made by backcasting AI automatically validates the recipe.

关键词： Wet etching Neural networks Throughput Silicon Real-time systems Ensemble learning Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Interference-Limits Aware Power and Receiver Optimization for 5G NR-U and Wi-Fi in the 6 GHz Shared-Spectrum

Interference-Limits Aware Power and Receiver Optimization fo...

引用

IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)

作者： Rasika Nilaweera Kalahe-Wattege Fernando Beltran Jairo Gutierrez Information Systems The University of Auckland Auckland New Zealand Computer Science and Software Engineering Auckland University of Technology Auckland New Zealand

ISBN: (数字)9798331540906

ISBN: (纸本)9798331540913

Adjacent Channel Interference (ACI) presents a significant concern for densely deployed Wi-Fi networks in the $\mathbf{6 G H z}$ spectrum. Coexisting Wi-Fi and 5G may be exposed to ACI due to the limitations in the devices’ receiver filtering capabilities or nearby user devices’ high transmit power. Since users of 5G and Wi-Fi networks operate in close proximity in frequency, space, and time, harmful ACI between 5 G and $\mathrm{Wi}-\mathrm{Fi}$ is unavoidable. This study investigates interference-limits aware approaches for enhancing throughput in distributed 5G NR-U-enabled femtocells and interference mitigation in Wi-Fi6E/7 network. Users act rationally and non-cooperatively to optimize their own utility. We have developed a non-cooperative Stackelberg game model to maximize throughput for 5G and mitigate ACI in $\mathrm{Wi-Fi}$ user devices. Our analysis explores the conditions necessary for the existence of a Stackelberg equilibrium within this context. The effectiveness of the proposed model is further demonstrated through simulation results.

关键词： Performance evaluation 5G mobile communication Radio transmitters Receivers Games Throughput Resource management Femtocells Wireless fidelity Optimization

来源：评论

学校读者我要写书评

暂无评论

Characterizing The Impact of Culture on Agile Methods: The MoCA Model

arXiv

引用

arXiv 2023年

作者： Neumann, Michael Schmid, Klaus Baumann, Lars Hochschule Hannover Dpt. of Business Information Systems Hannover Germany University of Hildesheim Software Systems Engineering Hildesheim Germany

Agile methods are well-known approaches in software development and used in various settings, which may vary wrt. organizational size, culture, or industrial sector. One important facet for the successful use of agile methods is the strong focus on social aspects. We know, that cultural values influence the behaviour of humans. Thus, an in-depth understanding of the influence of cultural aspects on agile methods is necessary to be able to adapt agile methods to various cultural contexts. In this paper we focus on an enabler to this problem. We want to better understand the influence of cultural factors on agile practices. The core contribution of this paper is MoCA: A model describing the impact of cultural values on agile elements. Copyright © 2023, The Authors. All rights reserved.

关键词： Social aspects

来源：评论

学校读者我要写书评

暂无评论

Navigating Fairness: Practitioners’ Understanding, Challenges, and Strategies in AI/ML Development

arXiv

引用

arXiv 2024年

作者： Pant, Aastha Hoda, Rashina Tantithamthavorn, Chakkrit Turhan, Burak Department of Software Systems and Cybersecurity Monash University Melbourne Australia Faculty of Information Technology and Electrical Engineering University of Oulu Oulu Finland

The rise in the use of AI/ML applications across industries has sparked more discussions about the fairness of AI/ML in recent times. While prior research on the fairness of AI/ML exists, there is a lack of empirical studies focused on understanding the perspectives and experiences of AI practitioners in developing a fair AI/ML system. Understanding AI practitioners’ perspectives and experiences on the fairness of AI/ML systems is important because they are directly involved in its development and deployment and their insights can offer valuable real-world perspectives on the challenges associated with ensuring fairness in AI/ML systems. We conducted semi-structured interviews with 22 AI practitioners to investigate their understanding of what a ‘fair AI/ML’ is, the challenges they face in developing a fair AI/ML system, the consequences of developing an unfair AI/ML system, and the strategies they employ to ensure AI/ML system fairness. We developed a framework showcasing the relationship between AI practitioners’ understanding of ‘fair AI/ML’ system and (i) their challenges in its development, (ii) the consequences of developing an unfair AI/ML system, and (iii) strategies used to ensure AI/ML system fairness. By exploring AI practitioners’ perspectives and experiences, this study provides actionable insights to enhance AI/ML fairness, which may promote fairer systems, reduce bias, and foster public trust in AI technologies. Additionally, we also identify areas for further investigation and offer recommendations to aid AI practitioners and AI companies in navigating fairness. © 2024, CC BY-NC-ND.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Characterizing The Impact of Culture on Agile Methods: The MoCA Model

Characterizing The Impact of Culture on Agile Methods: The M...

引用

International Conference on software and System Process (ICSSP)

作者： Michael Neumann Klaus Schmid Lars Baumann Dpt. of Business Information Systems Hochschule Hannover Hannover Germany Software Systems Engineering University of Hildesheim Hildesheim Germany

关键词：

来源：评论

学校读者我要写书评

暂无评论

On deployment of Eclipse Kuksa as a framework for an intelligent moving test platform for research of autonomous vehicles 2

On deployment of Eclipse Kuksa as a framework for an intelli...

引用

2nd Eclipse Research International Conference on Security, Artificial Intelligence, Architecture and Modelling for Next Generation Mobility, SAAM Mobility 2021

作者： Hirvonsalo, Harri Seppänen, Pertti Faculty of Information Technology and Electrical Engineering Empirical Software Engineering in Software Systems and Services M3S Group University of Oulu Oulu Finland

After an era of huge propagation within the field of mobile communications, digitalization has been spreading during the latest years at an accelerating speed to automotive technology and business. Following the developments experienced earlier in the mobile communications branch, open solutions and platforms are emerging in the automotive industries, challenging the traditional proprietary systems. Like in mobile communications, open platforms enable development of a wide variety of novel applications and systems that speed up the digitalization of the automotive and traffic ecosystems and offer the developers new attractive business opportunities. One of such open approaches is the Eclipse Kuksa framework developed in a consortium of European research institutions and automotive industries. In this study, we explored how the Kuksa framework could be used as a technology basis for an automotive data system combining in-vehicle functionality to cloud-based services. The study was carried out as a part of the SMAD research project of the University of Oulu aiming at an intelligent moving test platform for research of autonomous vehicles built on top of a Toyota Rav4 hybrid car. Our study covered subsystems of the Kuksa framework, the in-vehicle subsystem, cloud subsystems and the data communications between them. Our results indicate that the Kuksa framework is a feasible basis for the development of open, intelligent automotive data systems, though with a considerable learning needs. The results and experiences of our study provide besides additional knowledge for our continuing research on automotive software, also new, valuable contribution to the Eclipse Kuksa community and the practitioners planning to deploy open approaches in their automotive software development. Copyright © 2021 for this paper by its authors.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

MRUIE: Multi-Reference Mapping for Underwater Image Enhancement

MRUIE: Multi-Reference Mapping for Underwater Image Enhancem...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Tonglin Cheng Juan Li Jintao Luo Zhihui Li Faculty of Information Technology Beijing University of Technology Beijing China Beijing Engineering Research Center for loT Software and Systems Beijing China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

In complex underwater environments, the image quality will be damaged due to light absorption, water quality and other factors, which brings certain challenges to the underwater object detection task. In order to improve the quality of under-water images, as well as the effectiveness of underwater detection tasks, we proposed a multi-reference mapping based image enhancement network (MRUIE). Previous image enhancement methods set only one reference image for the original image to be learned, ignoring the diversity of real underwater images. We optimized for the salient problems of underwater images by allowing the network to learn multiple reference images to capture the uncertainty of real underwater images. First, for the prominent problems of color distortion, contrast imbalance, and low brightness and darkness in underwater images, we designed three optimization paths to generate three reference images respectively. Then, the three reference images are fed into the feature extraction network to construct the statistical distribution of features and generate a series of potential enhancement distributions. Finally, based on the enhancement distributions, Monte Carlo likelihood estimation is used to determine the final enhancement results. Experiments conducted on two datasets demonstrate that our proposed image enhancement algorithm can effectively enhance the restoration of the original underwater images and provide significant performance improvement in underwater vision tasks.

关键词： Image quality Monte Carlo methods Image color analysis Statistical distributions Water quality Feature extraction Image restoration

来源：评论

学校读者我要写书评

暂无评论

FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuning

arXiv

引用

arXiv 2024年

作者： Qi, Jiaxing Luan, Zhongzhi Huang, Shaohan Fung, Carol Yang, Hailong Qian, Depei Sino-German Joint Software Institute Beihang University Beijing China Concordia Institute for Information Systems Engineering Concordia University Canada

Large language models (LLMs) have emerged as important components across various fields, yet their training requires substantial computation resources and abundant labeled data. It poses a challenge to robustly training LLMs for individual users (clients). To tackle this challenge, the intuitive idea is to introduce federated learning (FL), which can collaboratively train models on distributed private data. However, existing methods suffer from the challenges of data heterogeneity, system heterogeneity, and model size, resulting in suboptimal performance and high costs. In this work, we proposed a variant of personalized federated learning (PFL) framework, namely FDLoRA, which allows the client to be a single device or a cluster and adopts low-rank adaptation (LoRA) tuning. FDLoRA sets dual LoRA modules on each client to capture personalized and global knowledge, respectively, and only the global LoRA module uploads parameters to the central server to aggregate cross-client knowledge. Finally, an adaptive fusion approach is employed to combine the of the dual LoRAs. This enables FDLoRA to make effective use of private data distributed across different clients, thereby improving performance on the client without incurring high communication and computing costs. We conducted extensive experiments in two practice scenarios. The results demonstrate that FDLoRA outperforms six baselines in terms of performance, stability, robustness, computation cost, and communication cost. © 2024, CC BY.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

SFedXSL: Semi-Synchronous Federated Cross-Sharpness Learning for UAV Swarm 24

SFedXSL: Semi-Synchronous Federated Cross-Sharpness Learning...

引用

24th IEEE International Conference on Communication Technology, ICCT 2024

作者： Zhao, Mingxiong Zhao, Shihao Feng, Chenyuan Yang, Howard H. Quek, Tony Q. S. Yunnan University Engineering Research Center of Cyberspace National Pilot School of Software China Eurecom Department of Communication France Zhejiang University/University of Illinois Urbana-Champaign Institute Zhejiang University China Singapore University of Technology and Design Information Systems Technology and Design Pillar Singapore

ISBN: (纸本)9798350363760

Federated learning (FL) emerges as an innovative approach to manage a collection of client UAVs in order to co-train machine-learning models that are readily integrated into an Unmanned Aerial Vehicle (UAV) swarm. However, due to more erratic communication conditions than in terrestrial wireless networks, synchronous aggregation - which is utilized in traditional FL - is no longer feasible in UAV swarm. Additionally, because of the various deployment zones or specifications of UAVs, the data gathered by them are frequently heterogeneous. A significant amount of unlabeled data will be collected by the UAV swarm in light of its new flight trajectory and unseen scenarios. To address these issues, we propose a unique Semi-synchronous Federated Cross-Sharpness Learning (SFedXSL) framework to tackle the problems of semisynchronous devices and unlabeled data. This framework incorporates unsupervised pre-training and client UAV clustering scheduling. These proposed techniques aim to unlock the full potential of unlabeled and labeled user data, expediting the training process. Simulation results demonstrate that our proposed algorithm surpasses state-of-the-art FL techniques in terms of objection recognition accuracy and service latency. © 2024 IEEE.

关键词： Federated learning

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：