检索结果-内蒙古大学图书馆

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Konti, Xenia Riess, Hans Giannopoulos, Manos Shen, Yi Pencina, Michael J. Economou-Zavlanos, Nicoleta J Zavlanos, Michael M. Duke University School of Medicine United States Duke University Dept. of Computer Science United States Duke University Dept. of Electrical and Computer Engineering United States Duke University Dept. of Mechanical Engineering & Materials Science United States

ISBN: (纸本)9798350316339

In this paper, we address the challenge of heterogeneous data distributions in cross-silo federated learning by introducing a novel algorithm, which we term Cross-silo Robust Clustered Federated Learning (CS-RCFL). Our approach leverages the Wasserstein distance to construct ambiguity sets around each client's empirical distribution that capture possible distribution shifts in the local data, enabling evaluation of worst-case model performance. We then propose a model-agnostic integer fractional program to determine the optimal distributionally robust clustering of clients into coalitions so that possible biases in the local models caused by statistically heterogeneous client datasets are avoided, and analyze our method for linear and logistic regression models. Finally, we discuss a federated learning protocol that ensures the privacy of client distributions, a critical consideration, for instance, when clients are healthcare institutions. We evaluate our algorithm on synthetic and real-world healthcare data. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Developing local rubber mixture for seismic base isolation system type high damping rubber bearing

Developing local rubber mixture for seismic base isolation s...

引用

作者： Ghrewati, Bahaa Eddin Tarsha Kurdi, Kheir Eddine Jena, Trilochan Siksha ‘O’ Anusandhan University Odisha Bhubaneswar India Dept. of Engineering Materials Science Faculty of Mechanical Engineering Aleppo University Syria

The research objective is to develop a rubber mixture for the High Damping Rubber Bearing HDRB type of seismic base isolation system to resist seismic loads, and compare it with international companies’ brochures. Experiments were conducted on three HDRB models of 150 mm in diameter and 12 cm in height. These models were manufactured locally from natural rubber with other chemical additives and steel sheets. Load and unload tests (quasi-static) were conducted on the models simulating earthquake loads, first loaded with a vertical load of 110 kN, and then the base cyclic horizontally with an increasing amplitude of 25 % until 125 % of the shear strain. The vertical stiffness was 44,027 kN/m, the effective horizontal stiffness was 334 kN/m, and the damping ratio was 20.1 % experimentally. The results were within satisfactory ranges of the parametric values in the manufacturing design brochure, indicating the developed rubber mixture is convenient, giving a great motivation to manufacture seismic isolators locally at suitable prices. © 2022

关键词： Rubber

来源：评论

学校读者我要写书评

暂无评论

SHELL-BASED COMPUTATIONAL HOMOGENISATION WITH IMMERSED METHODS FOR MESO-SCALE MODELLING OF FIBRE REINFORCED COMPOSITES 23

SHELL-BASED COMPUTATIONAL HOMOGENISATION WITH IMMERSED METHO...

引用

23rd International Conference on Composite materials, ICCM 2023

作者： Börjesson, Elias Verhoosel, Clemens Remmers, Joris J.C. Fagerström, Martin Dept. Industrial and Materials Science Chalmers University of Technology Gothenburg Sweden Dept. Mechanical Engineering Eindhoven University of Technology Eindhoven Netherlands

来源：评论

学校读者我要写书评

暂无评论

Predicting CO and NOx Emissions from a Gas Turbine Using Machine Learning Techniques

Predicting CO and NOx Emissions from a Gas Turbine Using Mac...

引用

AIAA SciTech Forum and Exposition, 2023

作者： Shahadat, Muhammad Rubayat Bin Murillo, Michael S. Jaberi, Farhad A. Michigan State University Dept. of Computational Mathematics Science and Engineering Dept. of Chemical Engineering and Materials Science East LansingMI48824 United States Michigan State University Dept. of Mechanical Engineering East LansingMI48824 United States

ISBN: (纸本)9781624106996

CO and NOx are emitted from various sources among which gas turbine power plants play a significant role. CO and NOx emissions from a gas turbine are dependent on various factors such as ambient temperature, pressure, humidity, turbine inlet temperature, exhaust temperature, compressor pressure, turbine energy yield, etc. The dataset we are using in this study contains these features which are connected to CO and NOx emissions from a gas turbine power plant. This dataset is used here to predict CO and NOx emissions with several machine learning algorithms. Six different machine learning algorithms (deep neural network, random forest, decision tree, support vector regression, lasso regression, and linear regression) have been used to predict these emissions separately. All the machine learning algorithms were optimized and the best algorithm for this dataset has been found based on four performance metrics: testing scores, R2 value, mean square error (MSE), mean absolute error (MAE), and computational efficiency. The deep neural network and support vector regression have the highest scores, whereas linear regression has the lowest testing score and R2 value for CO prediction. However, for NOx prediction, in terms of testing score and R2 value, support vector regression works better than all other algorithms considered in this study. From MSE and MAE analysis, support vector regression is found to be the algorithm with the least error and linear regression has the highest error for both CO and NOx predictions. On the other hand, linear regression is computationally very efficient because of its simplicity and the deep neural network is computationally costly because of its higher number of hyperparameters. Considering all the performance parameters and computational efficiency, support vector regression is found to be the best machine learning algorithm for predicting CO and NOx emissions. © 2023, American Institute of Aeronautics and Astronautics Inc, AIAA. All right

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

EVALUATING DESIGN RATIONALE

EVALUATING DESIGN RATIONALE

引用

ASME 2024 International Design engineering Technical Conferences and Computers and Information in engineering Conference, IDETC-CIE 2024

作者： Mirabito, Yakira Liu, Xiaowen Goucher-Lambert, Kosa Dept. of Mechanical Engineering University of California Berkeley BerkeleyCA United States Cognitive Science Program University of California Berkeley BerkeleyCA United States

ISBN: (纸本)9780791888407

Design rationale captures the justification behind a design decision. Often, rationales vary in the content and dept. of information, making the study and comparison of rationales challenging. This project aims to characterize design rationale and develop a computational approach to evaluate design rationale quality at scale. In total, 2250 rationales were machine-generated using GPT across two different representations, and a portion of the rationales (n = 512) were evaluated by two raters across five dimensions of quality. Rationales were then characterized using natural language processing techniques, resulting in 108 linguistic features for each rationale. The evaluations and linguistic features were used to build eight predictive models for each quality dimension. The main results show that structured rationales were rated higher than unstructured rationales across the five dimensions. Thus, the tested feature, specification, and evidence (FSE) framework was shown to be a worthwhile approach to represent the justification behind a design decision. Moreover, key linguistic features that correlate with higher quality ratings were identified. Future work will explore how design rationale quality and characteristics impact design decisions, particularly in a human-AI teaming context where generative design recommendations could benefit from including generative design rationales. Copyright © 2024 by ASME.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

CAVITATIONAL EROSION RESISTANCE CONSIDERATIONS FOR ALLOY 6082 STATE T651

引用

UPB Scientific Bulletin, Series B: Chemistry and materials science 2023年第1期85卷 213-224页

作者： Bordeasu, Ilare Ghiban, Brandusa Nagy, Vasile Paraianu, Vlad Ghera, Cristian Istrate, Dionisie Demian, Alin Mihai Odagiu, Petrisor-Ovidiu Romanian Academy of Scientists Timisoara branch Timisoara Romania Hydraulics Hydraulic Machinery and Environmental Engineering University POLITEHNICA of Bucharest Romania Dept. of Metallic Materials Science University POLITEHNICA of Bucharest Romania Dept. of Mechanical Machinery Equipment and Transport University POLITEHNICA of Timisoara Romania Dept. of Hydraulics Hydraulic Machinery and Environmental Engineering University POLITEHNICA of Bucharest Romania

The study presents the results of experimental research on the behaviour and resistance to vibratory cavitation erosion of the structure of aluminum alloy 6082 state 651. The analysis performed on macro and microscopic images shows the degradation mode of the microstructure, and the comparison with alloy 5083 state H111, using the specific parameters of cavitational erosion resistance recommended by ASTM G32-2016 standards, suggests an insignificant difference. Discussions of the plots containing experimental values of the cumulative eroded mass created by cavitational erosion and the related velocities using averaging curves show a behaviour strongly dependent on the nature of the blank, structural homogeneity, mass of intermetallic compounds and mechanical property values. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Microstructure

来源：评论

学校读者我要写书评

暂无评论

The Diagnosis of Cardiovascular Disease Using Simple Blood Biomarkers Through AI and Big Data 46

The Diagnosis of Cardiovascular Disease Using Simple Blood B...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Pezoulas, Vasileios Ehret, Georg Dobretz, Kevin Fotiadis, Dimitrios I. Sakellarios, Antonis I. Biomedical Resarch Institute FORTH-IMBB Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering IoanninaGR 45110 Greece Universitaires de Genève Department of Internal Medicine Hôpitaux Geneva Switzerland University of Patras Dept. of Mechanical and Aeronautics Engineering Patras Greece University of Ioannina Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering Ioannina Greece

ISBN: (纸本)9798350371499

Cardiovascular disease (CVD) is the leading cause of global mortality, diagnosed primarily through costly imaging modalities which are often overused in asymptomatic patients. Our project aims to develop an AI-based solution for CVD risk stratification using routine blood biomarkers, serving as a pre-imaging test. We used anonymized data from over 500,000 UK Biobank (UKB) patients with CVD assessments. Initially, 701 features including demographics, blood tests, medical conditions, and clinical assessments were selected. The UKB dataset was refined using an automated data curation pipeline to deal with outliers, duplicated fields, and missing values. Then, a hybrid XGBoost classifier was employed, with a scalable loss function, to address overfitting effects during the training process, yielding 0.83 accuracy, 0.82 sensitivity, and 0.84 specificity in diagnosing CVD comorbidities. Key biomarkers identified included blood pressure, BMI, and age. To our knowledge, this is the first case study which utilizes the UKB data towards the identification of cost-effective CVD (non-imaging) risk factors, thus reducing the reliance on imaging modalities. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Effect of Pb on microstructure and mechanical properties of Tin Babbitt alloy 3

Effect of Pb on microstructure and mechanical properties of ...

引用

3rd International Conference on Defence Technology, ICDT 2022

作者： Ren, Xiaoyan Chen, Ningning Zhang, Guowei Xu, Hong Zhang, Yougui Shi, Zhenhua Zhaojie, Wang Yijun, Liu Dept. of Mechanical Engineering Taiyuan Institute of Technology Shanxi Taiyuan030051 China School of Materials Science and Engineering North University of China Shanxi Taiyuan030051 China

This paper mainly studies the microstructure and properties of babbitt alloys, and analyzed the influence of lead on the microstructure and properties of the alloys by adding alloying element Pb, The results show as follows:with the increase of Pb content, the hardness of ZSnSb11Cu6 alloy first increases and then decreases. The maximum at 0.75% is 26.96HB. The tensile strength and elongation showed a trend of rising, then falling and then rising, and the mechanical properties were relatively high at 0.35%.The addition of Pb changes the morphology of Cu6Sn5 phase. With the increase of lead content, the β phase decreases and then grows, and the needle-like • phase dendrite grows. © Published under licence by IOP Publishing Ltd.

关键词： Tin alloys

来源：评论

学校读者我要写书评

暂无评论

Microstructures in Heat Treated LPBF Ti-6Al-4V Alloys after α′phase Decomposition and their mechanical Properties

引用

Funtai Oyobi Fummatsu Yakin/Journal of the Japan Society of Powder and Powder Metallurgy 2025年第4期72卷 79-84页

作者： Anan, Reita Kariya, Shota Li, Shufeng Yang, Yafeng Umeda, Junko Kondoh, Katsuyoshi Dept. of Mechanical Engineering Graduate School of Engineering Osaka University 2-1 Yamadaoka Suita565-0871 Japan Joining and Welding Research Institute Osaka University 11-1 Mihogaoka Ibaraki567-0047 Japan School of Materials Science and Engineering Xi’an University of Technology NO.5 South Jinhua Road Xi’an710048 China University of Chinese Academy of Sciences Beijing100049 China

Alloys formed by laser power bed fusion (LPBF) contain high residual stress and strain due to the cyclic heating process, which decreases ductility. Therefore, many researchers have investigated heat treatments to improve ductility by removing residual stress and forming α + β phase structures. However, in this study the ductility of some heat-treated samples was found to decrease below that of as-built samples. This study investigated the heat treatment of LPBF at different temperatures to decompose α′ grains to α grains and understand the resulting microstructure and mechanical properties. Specifically, the influence of microstructural factors on ductility was examined. In the samples heat treated at 500°C, α′ was found to decompose into α with elevated strain and finer β grains, which increased yield strength at the cost of ductility. Meanwhile, in the samples heat treated at 700°C, coarser β phase was precipitated, and greater ductility was supported by the transfer of the slip deformation between α phase grains. ©2025 Japan Society of Powder and Powder Metallurgy.

关键词： Ductility

来源：评论

学校读者我要写书评

暂无评论

Breaking Barriers and Building Confidence: Unleashing the Power of Digital Tools and Gender-Balanced Teams in engineering Education 54

Breaking Barriers and Building Confidence: Unleashing the Po...

引用

54th IEEE Frontiers in Education Conference, FIE 2024

作者： Barry, Matthew M. Deangelo, Linda Rossetti, Cara R. Wielgosz, Sarah E. Pabst, David M. Mezini, Lorena Dosse, Lee A. University of Pittsburgh Dept. of Mechanical Engineering and Materials Science PittsburghPA United States University of Pittsburgh Dept. of Educational Foundations Organizations and Policy PittsburghPA United States University of Maryland Dept. of Aerospace Engineering College ParkMD United States University of Pittsburgh Dept. of Physics and Astronomy PittsburghPA United States

ISBN: (纸本)9798350351507

This research-based full paper focuses on building confidence and inclusion for women engineering students by implementing various modes of learning (e.g., an interactive online textbook, Pre-recorded Lecture Videos (PLVs), and equally gendered-ratio teams for in-class team worksheets and course project) into a sophomore-level engineering course. It has been recognized that lack of inclusion has been linked to negative outcomes in student performance, specifically for women. As men dominate most engineering majors, it has been seen that women students find it hard to participate in group work settings. When working in groups, women students have experienced gender biases that were demeaning and often have their ideas or designs second-guessed. These feelings of self-doubt and lack of involvement, repeated over time, led many women students to leave engineering. It is hypothesized that by providing many learning opportunities outside the classroom that positively reinforce their knowledge and understanding and by balancing the gender ratio of teams, women will be more confident in their abilities and feel more included, respectively. Confidence plays a deciding factor in the retention rates of women within science, technology, engineering, and mathematics (STEM) fields of study. Anecdotally, it was discovered that during the development and implementation of an interactive online textbook and using PLVs, many women within the introductory Statics and Mechanics of materials 1 course felt something unfamiliar compared to other STEM courses: confidence. Confidence is a prime indicator of successful completion of a program. To further explore this finding, a study involving focus groups was conducted with three assemblages of women within the course. Two focus groups discussed using the interactive online textbook (n=8 and n = 9), while one discussed using PLVs (n=8). These focus groups were moderated by two women, a Ph.D. student in Physics and a current mechanical Engi

关键词： Students

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：