检索结果-内蒙古大学图书馆

SAFARI: Sparsity enabled Federated Learning with Limited and Unreliable Communications

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mao, Yuzhu Zhao, Zihao Yang, Meilin Liang, Le Liu, Yang Ding, Wenbo Lan, Tian Zhang, Xiao-Ping Tsinghua-Berkeley Shenzhen Institute Tsinghua Shenzhen International Graduate School Tsinghua University China RISC-V International Open Source Laboratory Shenzhen518055 China National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The Purple Mountain Laboratories Nanjing211111 China Tsinghua University China Department of Electrical and Computer Engineering George Washington University DC United States Department of Electrical Computer and Biomedical Engineering Ryerson University TorontoONM5B 2K3 Canada

Federated learning (FL) enables edge devices to collaboratively learn a model in a distributed fashion. Many existing researches have focused on improving communication efficiency of high-dimensional models and addressing bias caused by local updates. However, most of FL algorithms are either based on reliable communications or assume fixed and known unreliability characteristics. In practice, networks could suffer from dynamic channel conditions and non-deterministic disruptions, with time-varying and unknown characteristics. To this end, in this paper we propose a sparsity enabled FL framework with both communication efficiency and bias reduction, termed as SAFARI. It makes novel use of a similarity among client models to rectify and compensate for bias that is resulted from unreliable communications. More precisely, sparse learning is implemented on local clients to mitigate communication overhead, while to cope with unreliable communications, a similarity-based compensation method is proposed to provide surrogates for missing model updates. We analyze SAFARI under bounded dissimilarity and with respect to sparse models. It is demonstrated that SAFARI under unreliable communications is guaranteed to converge at the same rate as the standard FedAvg with perfect communications. Implementations and evaluations on CIFAR-10 dataset validate the effectiveness of SAFARI by showing that it can achieve the same convergence speed and accuracy as FedAvg with perfect communications, with up to 80% of the model weights being pruned and a high percentage of client updates missing in each round. Copyright © 2022, The Authors. All rights reserved.

关键词： Efficiency

Nucleus subtype classification using inter-modality learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Remedios, Lucas W. Bao, Shunxing Remedios, Samuel W. Lee, Ho Hin Cai, Leon Y. Li, Thomas Deng, Ruining Cui, Can Li, Jia Liu, Qi Lau, Ken S. Roland, Joseph T. Washington, Mary K. Coburn, Lori A. Wilson, Keith T. Huo, Yuankai Landman, Bennett A. Vanderbilt University Department of Computer Science Nashville United States Vanderbilt University Department of Electrical and Computer Engineering Nashville United States Johns Hopkins University Department of Computer Science Baltimore United States National Institutes of Health Department of Radiology and Imaging Sciences Bethesda United States Vanderbilt University Department of Biomedical Engineering Nashville United States Vanderbilt University Medical Center Department of Biostatistics Nashville United States Vanderbilt University Medical Center Center for Quantitative Sciences Nashville United States Vanderbilt University Medical Center Epithelial Biology Center Nashville United States Vanderbilt University School of Medicine Department of Cell and Developmental Biology Nashville United States Vanderbilt University Medical Center Division of Gastroenterology Hepatology and Nutrition Department of Medicine Nashville United States Vanderbilt University Medical Center Vanderbilt Center for Mucosal Inflammation and Cancer Nashville United States Vanderbilt University School of Medicine Program in Cancer Biology Nashville United States Veterans Affairs Tennessee Valley Healthcare System NashvilleTN United States Vanderbilt University Medical Center Department of Pathology Microbiology and Immunology NashvilleTN United States

Understanding the way cells communicate, co-locate, and interrelate is essential to understanding human physiology. Hematoxylin and eosin (H&E) staining is ubiquitously available both for clinical studies and research. The Colon Nucleus Identification and Classification (CoNIC) Challenge has recently innovated on robust artificial intelligence labeling of six cell types on H&E stains of the colon. However, this is a very small fraction of the number of potential cell classification types. Specifically, the CoNIC Challenge is unable to classify epithelial subtypes (progenitor, endocrine, goblet), lymphocyte subtypes (B, helper T, cytotoxic T), or connective subtypes (fibroblasts, stromal). In this paper, we propose to use inter-modality learning to label previously un-labelable cell types on virtual H&E. We leveraged multiplexed immunofluorescence (MxIF) histology imaging to identify 14 subclasses of cell types. We performed style transfer to synthesize virtual H&E from MxIF and transferred the higher density labels from MxIF to these virtual H&E images. We then evaluated the efficacy of learning in this approach. We identified helper T and progenitor nuclei with positive predictive values of 0.34 ± 0.15 (prevalence 0.03 ± 0.01) and 0.47 ± 0.1 (prevalence 0.07 ± 0.02) respectively on virtual H&E. This approach represents a promising step towards automating annotation in digital pathology. © 2024, CC BY.

关键词： Cell culture

Predicting value of alternativea fistula risk score and first postoperative day drain fluid amylase levels for pancreatic fistula following pancreatoduodenectomy

学校读者我要写书评

暂无评论

Pancreatology 2024年 24卷 e184-e184页

作者： Skreka, Androniki-Maria Chardalias, Leonidas Vezakis, Ioannis Politis, Dimitrios Iliakopoulos, Konstantinos Memos, Nikolaos Vezakis, Antonios Konstantoulakis, Manousos 2nd Department of Surgery Aretaieion Hospital National and Kapodistrian University of Athens Athens Attiki Greece Biomedical Engineering Laboratory School of Electrical and Computer Engineering National and Technical University of Athens Athens Attiki - Greece

Semiconductor quantum well magnetic memory using confinement from proximity exchange fields for high magnetoresistances in a field-effect transistor

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Rogers, William S. Incorvia, Jean Anne C. Graduate Program in Applied Physics Northwestern University EvanstonIL United States Chandra Department of Electrical and Computer Engineering The University of Texas at Austin AustinTX United States

There is a growing demand for highly-performant memories and memristive technologies for use in in-memory computing. Magnetic tunnel junctions (MTJs) have thus far addressed this need in the field of spintronics. Despite their low write power and high speeds, MTJs are limited by their modest on/off ratio at room temperature, which motivates a search for beyond-MTJ spintronic devices. In this work, we propose a device that uses two layers of ferromagnetic insulator (FMI) cladding a semiconductor QW, which is able to modulate the QW bandgap via electronic confinement resulting from proximity magnetization at the interfaces of the quantum well depending on the relative magnetization of the FMI layers. We predict that this device has the potential for very high magnetoresistances (MRs) possibly exceeding 10,000% at room temperature. We also predict that this device will operate with maximal MR in charge neutrality, and that electrostatic gating may promote the device to act as a magnetic memtransistor. This motivates the search for candidate materials and ultimately experimental demonstration of magnetic QW memories or memtransistors, which may have the potential to advance the state of the art in logic, memory, or neuromorphic circuits. © 2025, CC BY.

关键词： Magnetic core storage

Dedicated low-cost spectrophotometer to assist in cystic fibrosis diagnosis

学校读者我要写书评

暂无评论

Research on biomedical engineering 2021年第2期37卷 329-337页

作者： Spozito, Daniel Saverio Vieira Junior, Francisco Ubaldo Costa, Eduardo Tavares Federal Institute of Education Science and Technology of São Paulo – IFSP Campinas Campus Rua Heitor Lacerda Guedes 1000 Cidade Satélite Íris CEP.: 13.059-581 CampinasSP Brazil Biomedical Engineering Center – CEB Campinas State University – UNICAMP Cidade Universitária Zeferino Vaz Caixa Postal 6040. CEP.: 13083-970 CampinasSP Brazil Semiconductor Instrumentation and Photonics Department Faculty of Electrical and Computer Engineering Campinas State University – UNICAMP Cidade Universitária Zeferino Vaz Caixa Postal 6040. CEP.: 13083-970 CampinasSP Brazil

Introduction: The sweat test (ST) is essential in the diagnosis of cystic fibrosis (CF) whose protocol provides for the measurement of chloride in sweat. One of the techniques used to measure sweat is colorimetry. In this technique, a visible light spectrophotometer measures the absorbance of sweat samples added to a specific reagent. The amount of light absorbed is directly related to the concentration of chlorides in the sweat. This article proposes the development and testing of a low-cost sensor for the quantification of chlorides in sweat. Methods: A sensor was developed using the rapid prototyping (3D) technique dedicated to absorbance measurement for colorimetric technique. An experimental work was carried out using two groups of solutions, the first group being prepared with dyes and the second group prepared with a sweat-like solution added to a commercial reagent widely used for the purposes of dosing chlorides in sweat in order to verify the applicability of the sensor. Results: The sensor responded appropriately and presented linearity (R2 = 0.9954) with statistical equality (p > 0.05) in six tests. The comparison between the prototype and the reference equipment showed statistical equality (p > 0.05). Results: Based on the results, we believe that the sensor can be used to measure chloride in sweat. © 2021, Sociedade Brasileira de Engenharia Biomedica.

关键词： Colorimetry

Characterization of Fluorinated Polyimide Films

学校读者我要写书评

暂无评论

MRS Online Proceedings Library 2020年第1期264卷 263-268页

作者： Pradnya V. Nagarkar Jiong Ping Lu David Volfson Klavs F. Jensen Stephen D. Senturia Electronics Packaging Program and Department of Materials Science & Engineering Massachusetts Institute of Technology Cambridge Electronics Packaging Program and Department of Chemical Engineering Massachusetts Institute of Technology Cambridge Electronics Packaging Program and Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge

X-ray photoelectron spectroscopy (XPS) and Fourier transform infrared spectroscopy (FTIR) have been used to characterize the polyimide film based on 4,4′ hexafluoro-isopropylidene -bis pthalic anhydride (HFDA) and 4,4′ -bis (4-aminophenoxy) biphenyl (APBP). Films of varying thicknesses made from diluted precursors were studied by IR and XPS. An elemental analysis and a tentative peak assignment for C 1s in XPS is presented. The HFDA-APBP thick films are stoichiometric in composition and binding energies are in good agreement with data on hexafluorodianhydride-oxydianiline (HFDA-ODA). For thinner films, certain chemical modifications were observed at high cure temperatures.

关键词：

Increasing a microscope's effective field of view via overlapped imaging and machine learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yao, Xing Pathak, Vinayak Xi, Haoran Chaware, Amey Cooke, Colin Kim, Kanghyun Xu, Shiqi Li, Yuting Dunn, Timothy Konda, Pavan Chandra Zhou, Kevin C. Horstmeyer, Roarke Department of Biomedical Engineering Duke University DurhamNC27708 United States Department of Computer Science Duke University DurhamNC27708 United States Department of Electrical and Computer Engineering Duke University DurhamNC27708 United States Department of Neurosurgery Duke University DurhamNC27708 United States

This work demonstrates a multi-lens microscopic imaging system that overlaps multiple independent fields of view on a single sensor for high-efficiency automated specimen analysis. Automatic detection, classification and counting of various morphological features of interest is now a crucial component of both biomedical research and disease diagnosis. While convolutional neural networks (CNNs) have dramatically improved the accuracy of counting cells and sub-cellular features from acquired digital image data, the overall throughput is still typically hindered by the limited space-bandwidth product (SBP) of conventional microscopes. Here, we show both in simulation and experiment that overlapped imaging and co-designed analysis software can achieve accurate detection of diagnostically-relevant features for several applications, including counting of white blood cells and the malaria parasite, leading to multi-fold increase in detection and processing throughput with minimal reduction in accuracy. © 2021, CC BY.

关键词： Image enhancement

Improving STEM education for lower-division college students at HSI by utilizing relevant sociocultural and academic experiences: First year results from ASSURE-US project

学校读者我要写书评

暂无评论

Improving STEM education for lower-division college students...

2020 ASEE Virtual Annual Conference, ASEE 2020

作者： Huang, Jidong Kurwadkar, Sudarshan Bein, Doina Bai, Yu Mayoral, Salvador Department of Electrical Engineering California State University Fullerton FullertonCA United States Department of Civil and Environmental Engineering California State University Fullerton FullertonCA United States Department of Computer Science California State University Fullerton FullertonCA United States Computer Engineering Program California State University Fullerton FullertonCA United States Department of Mechanical Engineering California State University Fullerton FullertonCA United States

Despite national efforts in increasing representation of minority students in STEM disciplines, disparities prevail. Hispanics account for 17.4% of the U.S. population, and nearly 20% of the youth population (21 years and below) in the U.S. is Hispanic, yet they account for just 7% of the STEM workforce. To tackle these challenges, the National Science Foundation (NSF) has granted a 5-year project - ASSURE-US, that seeks to improve undergraduate education in engineering and computer Science (ECS) at California State University, Fullerton. The project seeks to advance student success during the first two years of college for ECS students. Towards that goal, the project incorporates a very diverse set of approaches, such as socio-cultural and academic interventions. Multiple strategies including developing early intervention strategies in gateway STEM courses, creating a nurturing faculty-student interaction and collaborative learning environment, providing relevant, contextual-based learning experiences, integrating project-based learning with engineering design in lower-division courses, exposing lower-division students to research to sustain student interests, and helping students develop career-readiness skills. The project also seeks to develop an understanding of the personal, social, cognitive, and contextual factors contributing to student persistence in STEM learning that can be used by STEM faculty to improve their pedagogical and student-interaction approaches. This paper summarizes the major approaches the ASSURE-US project plans to implement to reduce the achievement gap and motivate ECS students to remain in the program. Preliminary findings from the first-year implementation of the project including pre- and post- data were collected and analyzed from about one hundred freshmen and sophomore ECS students regarding their academic experience in lower-division classes and their feedback for various social support events held by the ASSURE-US project during

关键词： Students

Control of a Dual Fed Open End Winding SPMSM with a Floating Capacitor 12

学校读者我要写书评

暂无评论

Control of a Dual Fed Open End Winding SPMSM with a Floating...

12th Annual IEEE Energy Conversion Congress and Exposition, ECCE 2020

作者： Minaglia, Davide Rovere, Luca Formentini, Andrea Leuzzi, Riccardo Pipolo, Sabino Marchesoni, Mario Zanchetta, Pericle Danieli Automation S.P.A. Genoa Italy University of Nottingham Pemc Nottingham United Kingdom University of Pavia Department of Electrical Computer and Biomedical Engineering Italy University of Genoa Diten Genoa Italy

ISBN: (纸本)9781728158266

Surface Permanent Magnet Synchronous Motor (SPMSM) are not the first choice when a motor drive is required to operate over a wide speed range with an extended Constant Power Speed Range (CPSR). Nevertheless, SPMSMs offer high torque density, high efficiency simple manufacturing process and robustness which makes them an attractive alternative to Interior PMSMs. The Open End Winding (OEW) dual inverter topology, with one of the two Voltage Source Inverters (VSI) connected to a floating capacitor (FC), has shown to be capable of significantly increasing the operating speed range and CPSR of the SPMSM at the price of an increased controller complexity. In this paper, the analytical state space model of the OEW-FC SPMSM is derived, a state feedback controller is proposed and a possible tuning strategy is given to allow for high dynamics over the whole operating range and simplified controller design and tuning. © 2020 IEEE.

关键词： Controllers