检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Ranganath, Kiran Suetterlein, Joshua D. Manzano, Joseph B. Song, Shuaiwen Leon Wong, Daniel Department of Electrical and Computer Engineering University of California RiversideCA United States High-Performance Computing Group Pacific Northwest National Lab WA United States Future System Architecture Lab School of Computer Science University of Sydney SydneyNSW Australia

Multi-accelerator servers are increasingly being deployed in shared multi-tenant environments (such as in cloud data centers) in order to meet the demands of large-scale compute-intensive workloads. In addition, these accelerators are increasingly being inter-connected in complex topologies and workloads are exhibiting a wider variety of inter-accelerator communication patterns. However, existing allocation policies are ill-suited for these emerging use-cases. Specifically, this work identifies that multi-accelerator workloads are commonly fragmented leading to reduced bandwidth and increased latency for inter-accelerator communication. We propose Multi-Accelerator Pattern Allocation (MAPA), a graph pattern mining approach towards providing generalized allocation support for allocating multi-accelerator workloads on multi-accelerator servers. We demonstrate that MAPA is able to improve the execution time of multi-accelerator workloads and that MAPA is able to provide generalized benefits across various accelerator topologies. Finally, we demonstrate a speedup of 12.4% for 75th percentile of jobs with the worst case execution time reduced by up to 35% against baseline policy using MAPA. © 2021, CC BY-NC-SA.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Robust CPAP Device for Respiratory Support

Design and Development of a Robust CPAP Device for Respirato...

引用

IEEE International Conference on Biomedical engineering, computer and Information Technology for Health

作者： M. A. H. Akhand Mithun Kumar Das Nazmul Siddique Dept. of Computer Science and Engineering Khulna Univ. of Engineering & Technology Khulna Bangladesh CEO & System Designer M’s Lab Engineering Solution Dhaka Bangladesh School of Comp. Eng. and Int. Systems Ulster University Northern Ireland UK

ISBN: (数字)9781665466219

ISBN: (纸本)9781665466226

The COVID-19 pandemic has been a challenging time that the mankind had experienced since the Spanish flue where there is no available treatment except supportive care. The patients with COVID-19 suffered from mild to severe breathing difficulties and respiratory support was the main reason of hospitalization. Ventilator is generally used for the respiratory support which mixes air under pressure with required oxygen concentrations. Invasive mechanical ventilator (IMV) is a complex computer-driven machine delivering positive pressure to the lungs via an endotracheal or tracheostomy tube to support full ventilation. IMV is very expensive and the operation requires specialist nurses. An alternative to IMV is a non-invasive ventilation (NIV) which was deemed necessary during the pandemic. Continuous positive airway pressure (CPAP) is a NIV applied through a face mask and does not require specialist nurses. Due to low cost and simple operation, CPAP drew attention during COVID-19 pandemic. This paper presents the design and development of a CPAP ventilation device. The designed CPAP is a microcontroller based electro-mechanical device for supportive care of patients with respiratory problem.

关键词： COVID-19 Ventilators Costs Pandemics Microcontrollers Prototypes Lung

来源：评论

学校读者我要写书评

暂无评论

Mitigating Over-Saturated Fluorescence Images Through a Semi-Supervised Generative Adversarial Network

Mitigating Over-Saturated Fluorescence Images Through a Semi...

引用

IEEE International Symposium on Biomedical Imaging

作者： Shunxing Bao Junlin Guo Ho Hin Lee Ruining Deng Can Cui Lucas W. Remedios Quan Liu Qi Yang Kaiwen Xu Xin Yu Jia Li Yike Li Joseph T. Roland Qi Liu Ken S. Lau Keith T. Wilson Lori A. Coburn Bennett A. Landman Yuankai Huo Department of Electrical and Computer Engineering Nashville TN USA Department of Computer Science Nashville TN USA Department of Biostatistics Vanderbilt University Medical Center Nashville TN USA Department of Otolaryngology-Head and Neck Surgery Vanderbilt University Medical Center Nashville TN USA Department of Surgery Vanderbilt University Medical Center Nashville TN USA Department of Cell and Developmental Biology Vanderbilt University School of Medicine Nashville TN USA Department of Medicine Division of Gastroenterology Hepatology and Nutrition Vanderbilt University Medical Center Nashville TN USA Veterans Affairs Tennessee Valley Healthcare System Nashville TN USA

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Multiplex immunofluorescence (MxIF) imaging is a critical tool in biomedical research, offering detailed insights into cell composition and spatial context. As an example, DAPI staining identifies cell nuclei, while CD20 staining helps segment cell membranes in MxIF. However, a persistent challenge in MxIF is saturation artifacts, which hinder single-cell level analysis in areas with over-saturated pixels. Traditional gamma correction methods for fixing saturation are limited, often incorrectly assuming uniform distribution of saturation, which is rarely the case in practice. This paper introduces a novel approach to correct saturation artifacts from a data-driven perspective. We introduce a two-stage, high-resolution hybrid generative adversarial network (HD-mixGAN), which merges unpaired (CycleGAN) and paired (pix2pixHD) network architectures. This approach is designed to capitalize on the available small-scale paired data and the more extensive unpaired data from costly MxIF data. Specifically, we generate pseudo-paired data from large-scale unpaired over-saturated datasets with a CycleGAN, and train a Pix2pixGAN using both small-scale real and large-scale synthetic data derived from multiple DAPI staining rounds in MxIF. This method was validated against various base-lines in a downstream nuclei detection task, improving the F1 score by 6% over the baseline. This is, to our knowledge, the first focused effort to address multi-round saturation in MxIF images, offering a specialized solution for enhancing cell analysis accuracy through improved image quality. The source code and implementation of the proposed method are available at https://***/MASILab/***.

关键词： Multiplexing Microprocessors Source coding computer architecture Network architecture Generative adversarial networks Immunofluorescence

来源：评论

学校读者我要写书评

暂无评论

Enhanced faster-RCNN algorithm for object detection in aerial images 9

Enhanced faster-RCNN algorithm for object detection in aeria...

引用

9th IEEE Joint International Information Technology and Artificial Intelligence Conference, ITAIC 2020

作者： Yin, Xiaoqing Yang, Yazhou Xu, Hao Li, Weili Deng, Jinsheng National University of Defense Technology College of Advanced Interdisciplinary Research Changsha China National University of Defense Technology College of Computer Science Changsha China National University of Defense Technology College of System Engineering Changsha China

In recent years, a lot of research has been conducted in the field of object detection for aerial image, and many effective methods have emerged. This paper enhances the existing Faster RCNN model to achieve better detection accuracy. We improve the feature extraction of Faster RCNN model using multi-scale feature fusion. Compared with the traditional Faster RCNN model, the accuracy on mAP is improved by 1.06% by applying the proposed method. The visual effects and numerical results of object detection verify the improvement of the proposed method. © 2020 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Photonic Emulator of Potential-free Schrödinger Equation

arXiv

引用

arXiv 2025年

作者： Cao, Qian Zhang, Nianjia Chong, Andy Zhan, Qiwen School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China Zhangjiang Laboratory Shanghai China University of Shanghai for Science and Technology Shanghai Key Laboratory of Modern Optical System Shanghai China Pusan National University Department of Physics Busan Korea Republic of Institute for Future Earth Pusan National University Busan46241 Korea Republic of Westlake Institute for Optoelectronics Hangzhou Fuyang311421 China Hiroshima University Hiroshima Higashihiroshima739-8526 Japan

Photonic quantum emulator utilizes photons to emulate the quantum physical behavior of a complex quantum system. Recent study in spatiotemporal optics has enriched the toolbox for designing and manipulating complex spatiotemporal optical wavepackets, bringing new opportunities in building such quantum emulators. In this work, we demonstrate a new type of photonic quantum emulator enabled by spatiotemporal localized wavepackets with spherical harmonic symmetry. The spatiotemporal field distribution of these wavepackets has the same distributions of the wavefunction solutions to the potential-free Schrödinger equation with two controllable quantum numbers. A series of such localized wavepackets are experimentally generated with their localized feature verified. These localized wavepackets can propagate invariantly in space-time like particles, forming a new type of photonic quantum emulator that may provide new insight in studying quantum physics and open up new applications in studying light-matter interactions and quantum optics. © 2025, CC BY.

关键词： Schrodinger equation

来源：评论

学校读者我要写书评

暂无评论

The Fast Fixed-Time Bipartite Synchronization of Coupled Delayed Neural Networks with Signed Graphs

Research Square

引用

Research Square 2021年

作者： Yang, Shiju Li, Chuandong Li, Yu Yang, Ting Li, Bo Chongqing Engineering Laboratory for Detection Control and Integrated System School of Computer Science and Information Engineering Chongqing Technology and Business University Chongqing400067 China College of Electronic and Information Engineering Southwest University Chongqing400715 China Army Logistics Academy of PLA Chongqing401311 China

In this paper, the fixed-time bipartite synchronization problem for coupled delayed neural networks with signed graphs is discussed. Different from traditional neural networks, the interactions between nodes of delayed neural networks can be either collaborative or antagonistic. Furthermore, compared with the initial-condition based finite-time synchronization, the settling time is bounded by a constant within fixed-time regardless of the initial condition. It is worth noting that the fixed-time stable network for bipartite synchronization in this paper achieves more faster convergence than most existing publications. By applying constructing comparison system method, Lyapunov stability theory and inequality techniques, some sufficient criteria for fixed-time bipartite synchronization are obtained. Finally, two numerical examples are granted to display the performance of the obtained results. © 2021, CC BY.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

Mitigating Unfairness via Evolutionary Multi-objective Ensemble Learning

arXiv

引用

arXiv 2022年

作者： Zhang, Qingquan Liu, Jialin Zhang, Zeqi Wen, Junyi Mao, Bifei Yao, Xin The Research Institute of Trustworthy Autonomous System Southern University of Science and Technology Shenzhen518055 China The Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The Trustworthiness Theory Research Center Huawei Technologies Co. Ltd. Shenzhen518129 China The School of Computer Science University of Birmingham United Kingdom

In the literature of mitigating unfairness in machine learning, many fairness measures are designed to evaluate predictions of learning models and also utilised to guide the training of fair models. It has been theoretically and empirically shown that there exist conflicts and inconsistencies among accuracy and multiple fairness measures. Optimising one or several fairness measures may sacrifice or deteriorate other measures. Two key questions should be considered, how to simultaneously optimise accuracy and multiple fairness measures, and how to optimise all the considered fairness measures more effectively. In this paper, we view the mitigating unfairness problem as a multi-objective learning problem considering the conflicts among fairness measures. A multi-objective evolutionary learning framework is used to simultaneously optimise several metrics (including accuracy and multiple fairness measures) of machine learning models. Then, ensembles are constructed based on the learning models in order to automatically balance different metrics. Empirical results on eight well-known datasets demonstrate that compared with the state-of-the-art approaches for mitigating unfairness, our proposed algorithm can provide decision-makers with better tradeoffs among accuracy and multiple fairness metrics. Furthermore, the high-quality models generated by the framework can be used to construct an ensemble to automatically achieve a better tradeoff among all the considered fairness metrics than other ensemble methods. Our code is publicly available at https://***/qingquan63/FairEMOL. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Finding single-source shortest p-disjoint paths: Fast computation and sparse preservers

arXiv

引用

arXiv 2021年

作者： Bilò, Davide D'Angelo, Gianlorenzo Gualà, Luciano Leucci, Stefano Proietti, Guido Rossi, Mirko Department of Humanities and Social Sciences University of Sassari Italy Gran Sasso Science Institute L'Aquila Italy Department of Enterprise Engineering University of Rome Tor Vergata Italy Department of Information Engineering Computer Science and Mathematics University of l'Aquila Italy Institute for System Analysis and Computer Science Antonio Ruberti Italy

Let G be a directed graph with n vertices, m edges, and non-negative edge costs. Given G, a fixed source vertex s, and a positive integer p, we consider the problem of computing, for each vertex t ≠ s, p edge-disjoint paths of minimum total cost from s to t in G. Suurballe and Tarjan [Networks, 1984] solved the above problem for p = 2 by designing a O(m + n log n) time algorithm which also computes a sparse single-source 2-multipath preserver, i.e., a subgraph containing 2 edge-disjoint paths of minimum total cost from s to every other vertex of G. The case p ≥ 3 was left as an open problem. We study the general problem (p ≥ 2) and prove that any graph admits a sparse single-source p-multipath preserver with p(n - 1) edges. This size is optimal since the in-degree of each non-root vertex v must be at least p. Moreover, we design an algorithm that requires O(pn2(p + log n)) time to compute both p edge-disjoint paths of minimum total cost from the source to all other vertices and an optimal-size single-source p-multipath preserver. The running time of our algorithm outperforms that of a natural approach that solves n - 1 single-pair instances using the well-known successive shortest paths algorithm by a factor of θ(m/np) and is asymptotically near optimal if p = O(1) and m = θ(n2). Our results extend naturally to the case of p vertex-disjoint paths. Copyright © 2021, The Authors. All rights reserved.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

GradSA: Gradient Sparsification and Accumulation for Communication-Efficient Distributed Deep Learning 15th

GradSA: Gradient Sparsification and Accumulation for Communi...

引用

15th International Conference on Green, Pervasive, and Cloud Computing, GPC 2020

作者： Liu, Bo Jiang, Wenbin Zhao, Shaofeng Jin, Hai He, Bingsheng National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan China Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Huazhong University of Science and Technology Wuhan China Library Henan University of Economics and Law Zhengzhou China Department of Computer Science School of Computing National University of Singapore Singapore Singapore

ISBN: (纸本)9783030642426

Large-scale distributed deep learning is of great importance in various applications. For distributed training, the inter-node gradient communication often becomes the performance bottleneck. Gradient sparsification has been proposed to reduce the communication overhead. However, the sparsification only arbitrarily selects a small fraction of gradients, while the efficiency of selection dimension has been overlooked. Furthermore, gradient staleness is inevitable after applying the sparsification which will ultimately lead to model divergence. In this paper, we propose a staleness-compensated sparse stochastic gradient descent algorithm, GradSA, to improve the training efficiency. Layer-level gradients are sparsified to reduce the communication overhead, which conform to the characteristics of the network structure, and historical accumulation of the approximated gradients is utilized to speed up convergence. We demonstrate the model convergence acceleration and the efficiency of our layer-level selection over existing state-of-the-art works, such as DGC, TernGrad, and 8-Bit quantization. © 2020, Springer Nature Switzerland AG.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Clinically Interpretable Machine Learning Models for Early Prediction of Mortality in Older Patients with Multiple Organ Dysfunction Syndrome: An International Multicenter Retrospective Study

引用

Journals of Gerontology - Series A Biological Sciences and Medical Sciences 2023年第4期78卷 718-726页

作者： Liu, Xiaoli DuMontier, Clark Hu, Pan Liu, Chao Yeung, Wesley Mao, Zhi Ho, Vanda Thoral, Patrick J. Kuo, Po-Chih Hu, Jie Li, Deyu Cao, Desen Mark, Roger G. Zhou, FeiHu Zhang, Zhengbo Celi, Leo Anthony Key Laboratory for Biomechanics and Mechanobiology of Ministry of Education Beijing Advanced Innovation Center for Biomedical Engineering School of Biological Science and Medical Engineering Beihang University Beijing China Laboratory for Computational Physiology Institute for Medical Engineering and Science Massachusetts Institute of Technology Cambridge MA United States Center for Artificial Intelligence in Medicine General Hospital of PLA Beijing China New England Geriatric Research Education and Clinical Center VA Boston Healthcare System Boston MA United States Division of Aging Brigham and Women's Hospital Boston MA United States Department of Anesthesiology 920 Hospital of Joint Logistic Support Force of Chinese PLA Kunming Yunnan China Department of Critical Care Medicine First Medical Center General Hospital of PLA Beijing China Department of Medicine National University Hospital Singapore Division of Geriatric Medicine Department of Medicine National University Hospital Singapore Department of Intensive Care Medicine Amsterdam Netherlands Department of Computer Science National Tsing Hua University Hsinchu Taiwan Department of Biomedical Engineering General Hospital of PLA Beijing China Elderly Center General Hospital of PLA Beijing China Department of Medicine Beth Israel Deaconess Medical Center Boston MA United States Department of Biostatistics Harvard T.H. Chan School of Public Health Boston MA United States

BACKGROUND: Multiple organ dysfunction syndrome (MODS) is associated with a high risk of mortality among older patients. Current severity scores are limited in their ability to assist clinicians with triage and management decisions. We aim to develop mortality prediction models for older patients with MODS admitted to the ICU. METHODS: The study analyzed older patients from 197 hospitals in the United States and 1 hospital in the Netherlands. The cohort was divided into the young-old (65-80 years) and old-old (≥80 years), which were separately used to develop and evaluate models including internal, external, and temporal validation. Demographic characteristics, comorbidities, vital signs, laboratory measurements, and treatments were used as predictors. We used the XGBoost algorithm to train models, and the SHapley Additive exPlanations (SHAP) method to interpret predictions. RESULTS: Thirty-four thousand four hundred and ninety-seven young-old (11.3% mortality) and 21 330 old-old (15.7% mortality) patients were analyzed. Discrimination AUROC of internal validation models in 9 046 U.S. patients was as follows: 0.87 and 0.82, respectively;discrimination of external validation models in 1 905 EUR patients was as follows: 0.86 and 0.85, respectively;and discrimination of temporal validation models in 8 690 U.S. patients: 0.85 and 0.78, respectively. These models outperformed standard clinical scores like Sequential Organ Failure Assessment and Acute Physiology Score III. The Glasgow Coma Scale, Charlson Comorbidity Index, and Code Status emerged as top predictors of mortality. CONCLUSIONS: Our models integrate data spanning physiologic and geriatric-relevant variables that outperform existing scores used in older adults with MODS, which represents a proof of concept of how machine learning can streamline data analysis for busy ICU clinicians to potentially optimize prognostication and decision making. © The Author(s) 2022. Published by Oxford University Press on behalf

关键词： International multicenter Interpretable models Machine learning Mortality Multiple organ dysfunction syndrome

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：