检索结果-内蒙古大学图书馆

Conference on Data science and Machine Learning Applications (CDMA)

作者： Raed Alharbi Truc Nguyen Nooshin Yousefzadeh Ahmed Aljohani College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia Computatioual Science Center National Renewable Energy Laboratory Golden CO USA Computer and Information Science and Engineering Department University of Florida Gainesville FL USA Computer Science and Engineering University of North Texas Denton USA

ISBN: (数字)9798331539696

ISBN: (纸本)9798331539702

Federated learning (FL) has emerged as a powerful framework for training deep learning models across numerous distributed clients, where a central server distributes and aggregates model updates without accessing clients' raw data, ensuring privacy. However, this decentralized approach introduces significant challenges regarding fairness. Existing research shows that non-i.i.d. data distributions among clients can lead to biased global models, particularly affecting decisions based on sensitive attributes. This paper aims to investigate these fairness issues rigorously by analyzing how disparities in client data distribution impact model fairness. We conduct experiments using various models and datasets to evaluate and mitigate biases. We also propose novel data partitioning strategies to reflect real-world client data distributions accurately. Our finding shows that FL is highly vulnerable to the fairness problem due to the Non-IID property. The experiment's code can be found here: https://***/raed19/Questionable-Fairness-in-Federated-Learning.

关键词： Training Deep learning Data privacy Federated learning Prevention and mitigation Distributed databases Data science Data models Servers Multiaccess communication

来源：评论

学校读者我要写书评

暂无评论

School re-opening simulations with covid-19 agent-based model for quezon city, philippines

School re-opening simulations with covid-19 agent-based mode...

引用

2021 Philippine Geomatics Symposium 2021

作者： Celeste, J.J. Bongolan, V.P. System Modeling and Simulation Laboratory Department of Computer Science University of the Philippines Diliman Quezon City Philippines

The COVID-19 pandemic prompted schools to close in 2020, and with its negative impact on the quality of learning, the conversation shifts to the re-opening scenarios. In this study, we coupled a COVID-19 agent-based model (ABM) with social contact probabilities from pre-pandemic estimates. We then simulated school re-opening and vaccination scenarios in Quezon City, Philippines using our ABM. Our toy simulations suggest that the city could already re-open schools with 50% vaccination coverage. However, we suggest that students shall be vaccinated first, mask-wearing and physical distance shall be strictly observed, and schools shall only be re-opened by 25% as a precaution. Policymakers may take insights from the study. © International Archives of the Photogrammetry, Remote Sensing and Spatial Information sciences - ISPRS Archives

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Integrated Multi-Omics and Whole Slide Images for Survival Prediction in Glioblastoma Using Multiple Instance Learning and Co-Attention 46

Integrated Multi-Omics and Whole Slide Images for Survival P...

引用

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

作者： Hao, Jie Liu, Yangrui Mo, Zhiqiang Liu, Xing Sun, Haixia Li, Jiao University of Science and Technology of China Department of Computer Science Hefei China Capital Medical University Beijing Neurosurgical Institute Department of Neuropathology Beijing China Chinese Academy of Medical Sciences Peking Union Medical College Institute of Medical Information Beijing China Chinese Academy of Medical Sciences Peking Union Medical College Key Laboratory of Medical Information Intelligence Technology Beijing China

ISBN: (纸本)9798350371499

Glioblastoma multiforme (GBM) is the most aggressive adult brain tumor and presents significant treatment challenges due to its poor prognosis and heterogeneity. Despite the rapid development of deep learning, integrating multi-omics with whole slide images (WSIs) for survival prediction remains difficult. This study aims to improve GBM prognosis by integrating WSIs with multi-omic data through the incorporation of biological pathway knowledge. Utilizing multiple instance learning and co-attention mechanisms, we initiated the integration of multi-omic data informed by biological pathways, leveraging existing knowledge of molecular interactions. The proposed model was evaluated using data from 214 GBM patients from The Cancer Genome Atlas. This dataset included 447 WSIs and multi-omic features such as 927 RNA sequencing gene expressions, 1,168 copy number alterations, and 1,489 DNA methylation patterns. These multi-omic features were organized into nine biological pathways, each selected based on their relevance to GBM, ensuring a targeted and biologically informed strategy for survival prediction. Our results show that the proposed model outperforms existing benchmarks by at least 4.5%, highlighting the potential of incorporating additional biological knowledge into the integration of multimodal data to improve GBM survival prediction. © 2024 IEEE.

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

Lumbar spine localisation method based on feature fusion

引用

CAAI Transactions on Intelligence Technology 2023年第3期8卷 931-945页

作者： Yonghong Zhang Ning Hu Zhuofu Li Xuquan Ji Shanshan Liu Youyang Sha Xiongkang Song Jian Zhang Lei Hu Weishi Li Robotics Institute School of Mechanical Engineering and AutomationBeihang UniversityBeijingChina Beijing Zhuzheng Robot Co. LTDBeijingChina Department of Mechanical Aerospace and Biomedical EngineeringUniversity of TennesseeKnoxvilleTennesseeUSA Department of Orthopaedics Peking University Third HospitalBeijingChina Engineering Research Center of Bone and Joint Precision Medicine Ministry of EducationBeijingChina Beijing Key Laboratory of Spinal Disease Research BeijingChina School of Biological Science and Medical Engineering Beihang UniversityBeijingChina Department of Computer Science University of WarwickCoventryUK

To eliminate unnecessary background information,such as soft tissues in original CT images and the adverse impact of the similarity of adjacent spines on lumbar image segmentation and surgical path planning,a two‐stage approach for localising lumbar segments is ***,based on the multi‐scale feature fusion technology,a non‐linear regression method is used to achieve accurate localisation of the overall spatial region of the lumbar spine,effectively eliminating useless background information,such as soft *** the second stage,we directly realised the precise positioning of each segment in the lumbar spine space region based on the non‐linear regression method,thus effectively eliminating the interference caused by the adjacent *** 3D Intersection over Union(3D_IOU)is used as the main evaluation indicator for the positioning *** an open dataset,3D_IOU values of 0.8339�0.0990 and 0.8559�0.0332 in the first and second stages,respectively is *** addition,the average time required for the proposed method in the two stages is 0.3274 and 0.2105 s ***,the proposed method performs very well in terms of both pre-cision and speed and can effectively improve the accuracy of lumbar image segmentation and the effect of surgical path planning.

关键词： CT image lumbar spatial orientation multi‐scale information fusion

来源：评论

学校读者我要写书评

暂无评论

Active twistoptics: on-chip multidimensional dynamic control for data hypercube reconstruction

Active twistoptics: on-chip multidimensional dynamic control...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Tang, Haoning Lou, Beicheng Du, Fan Gao, Guangqi Zhang, Mingjie Ni, Xueqi Yacoby, Amir Cao, Yuan Fan, Shanhui Mazur, Eric School of Engineering and Applied Sciences Harvard University CambridgeMA02138 United States Department of Electrical Engineering and Computer Science University of California at Berkeley BerkeleyCA94720 United States National Institute for Materials Science Namiki 1-1 Ibaraki Tsukuba305-0044 Japan Department of Applied Physics Ginzton Laboratory Stanford University StanfordCA94305 United States

Our MEMS-integrated twistoptics device enables precise control of interlayer gaps and twist angles in photonic crystals, achieving high-accuracy, multidimensional light manipulation with significant potential in recon... 详细信息

ISBN: (纸本)9781957171395

关键词： Nanophotonics

来源：评论

学校读者我要写书评

暂无评论

Dietary carbohydrate intake and risk of type 2 diabetes:a 16-year prospective cohort study

引用

science China(Life sciences) 2025年第4期68卷 1149-1157页

作者： Lu Gan Yi Yang Bin Zhao Kai Yu Kehua Guo Fang Fang Zhiguang Zhou Demetrius Albanes Jiaqi Huang National Clinical Research Center for Metabolic Diseases Metabolic Syndrome Research CenterKey Laboratory of Diabetes ImmunologyMinistry of Educationand Department of Metabolism and EndocrinologyThe Second Xiangya Hospital of Central South UniversityCSU-Sinocare Research Center for Nutrition and Metabolic HealthXiangya School of Public HealthCentral South UniversityFurong LaboratoryChangsha410011China Division of Cancer Epidemiology and Genetics National Cancer InstituteNIHDepartment of Health and Human ServicesBethesdaMD20892USA School of Computer Science and Engineering Central South UniversityChangsha410083China Institute of Environmental Medicine Karolinska InstituteStockholm17177Sweden National Clinical Research Center for Metabolic Diseases Key Laboratory of Diabetes ImmunologyMinistry of Educationand Department of Metabolism and EndocrinologyThe Second Xiangya Hospital of Central South UniversityChangsha410011China

Despite considerable research underscoring the importance of carbohydrate intake in relation to the risk of type 2 diabetes(T2D),a comprehensive assessment of this relationship is currently *** aimed to examine the associations of various types and food sources of dietary carbohydrate intake with the risk of T2D,to evaluate potential effect modification by other factors,including genetic susceptibility,and to explore the potential mediators for such *** present study included 161,872 participants of the UK Biobank who were free of prevalent cancer,cardiovascular disease,or diabetes,and had at least one validated 24-h dietary recall *** age-stratified Cox proportional hazard regression models were applied to estimate hazard ratios(HRs)and 95%confidence intervals(CI)for the associations of various types and food sources of dietary carbohydrate intake with risk of *** a median follow-up of 13.6 years,4,176 incident cases of T2D were *** the multivariable-adjusted models,a greater intake of fiber,carbohydrates from whole grains,and carbohydrates from non-starchy vegetables was significantly associated with a lower risk of T2D(highest *** quantile,HR[95%CI]=0.70[0.62–0.79],0.74[0.67–0.82],and 0.83[0.75–0.92],respectively,all P for trend<0.005).In contrast,a higher intake of starch and carbohydrate from starchy vegetables was associated with an increased risk of T2D(highest *** quantile,HR[95%CI]=1.31[1.16–1.48]and 1.19[1.09–1.31],respectively,both P for trend<0.005).Replacing one serving of refined grains or starchy vegetables with an equal amount of whole grains or non-starchy vegetables was associated with 4%to 10%lower risk of T2D(all P values<0.001).The observed associations were generally similar across population subgroups,including individuals with different genetic susceptibility to *** analyses of the inverse association between T2D risk and isocaloric substitution of carbohy

关键词： dietary carbohydrate type 2 diabetes prospective cohort study UK Biobank

来源：评论

学校读者我要写书评

暂无评论

Synthetic Data for Face Recognition: Current State and Future Prospects

arXiv

引用

arXiv 2023年

作者： Boutros, Fadi Struc, Vitomir Fierrez, Julian Damer, Naser Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Faculty of Electrical Engineering University of Ljubljana Ljubljana Slovenia School of Engineering Universidad Autonoma de Madrid Madrid Spain Department of Computer Science TU Darmstadt Darmstadt Germany

Over the past years, deep learning capabilities and the availability of large-scale training datasets advanced rapidly, leading to breakthroughs in face recognition accuracy. However, these technologies are foreseen to face a major challenge in the next years due to the legal and ethical concerns about using authentic biometric data in AI model training and evaluation along with increasingly utilizing data-hungry state-of-the-art deep learning models. With the recent advances in deep generative models and their success in generating realistic and high-resolution synthetic image data, privacy-friendly synthetic data has been recently proposed as an alternative to privacy-sensitive authentic data to overcome the challenges of using authentic data in face recognition development. This work aims at providing a clear and structured picture of the use-cases taxonomy of synthetic face data in face recognition along with the recent emerging advances of face recognition models developed on the bases of synthetic data. We also discuss the challenges facing the use of synthetic data in face recognition development and several future prospects of synthetic data in the domain of face recognition. Copyright © 2023, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Quantum Hybrid Support Vector Machines for Stress Detection in Older Adults

Quantum Hybrid Support Vector Machines for Stress Detection ...

引用

2025 IEEE International Conference on Consumer Electronics, ICCE 2025

作者： Saif Hassan Onim, Md. Humble, Travis S. Thapliyal, Himanshu Department of Electrical Engineering and Computer Science University of Tennessee KnoxvilleTN United States Quantum Science Center Oak Ridge National Laboratory Oak RidgeTN United States

ISBN: (纸本)9798331521165

Stress can increase the possibility of cognitive impairment and decrease the quality of life in older adults. Smart healthcare can deploy quantum machine learning to enable preventive and diagnostic support. This work introduces a unique technique to address stress detection as an anomaly detection problem that uses quantum hybrid support vector machines. With the help of a wearable smartwatch, we mapped baseline sensor reading as normal data and stressed sensor reading as anomaly data using cortisol concentration as the ground truth. We have used quantum computing techniques to explore the complex feature spaces with kernel-based preprocessing. We illustrate the usefulness of our method by doing experimental validation on 40 older adults with the help of the TSST protocol. Our findings highlight that using a limited number of features, quantum machine learning provides improved accuracy compared to classical methods. We also observed that the recall value using quantum machine learning is higher compared to the classical method. The higher recall value illustrates the potential of quantum machine learning in healthcare, as missing anomalies could result in delayed diagnostics or treatment. © 2025 IEEE.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Event-based Shape from Polarization with Spiking Neural Networks

arXiv

引用

arXiv 2023年

作者： Kang, Peng Banerjee, Srutarshi Chopp, Henry Katsaggelos, Aggelos Cossairt, Oliver Department of Computer Science Northwestern EvanstonIL United States Argonne National Laboratory LemontIL United States Department of Electrical and Computer Engineering Northwestern EvanstonIL United States

Recent advances in event-based shape determination from polarization offer a transformative approach that tackles the trade-off between speed and accuracy in capturing surface geometries. In this paper, we investigate event-based shape from polarization using Spiking Neural Networks (SNNs), introducing the Single-Timestep and Multi-Timestep Spiking UNets for effective and efficient surface normal estimation. Specificially, the Single-Timestep model processes event-based shape as a non-temporal task, updating the membrane potential of each spiking neuron only once, thereby reducing computational and energy demands. In contrast, the Multi-Timestep model exploits temporal dynamics for enhanced data extraction. Extensive evaluations on synthetic and real-world datasets demonstrate that our models match the performance of state-of-the-art Artifical Neural Networks (ANNs) in estimating surface normals, with the added advantage of superior energy efficiency. Our work not only contributes to the advancement of SNNs in event-based sensing but also sets the stage for future explorations in optimizing SNN architectures, integrating multi-modal data, and scaling for applications on neuromorphic hardware. © 2023, CC BY.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Testing GPU Numerics: Finding Numerical Differences Between NVIDIA and AMD GPUs

Testing GPU Numerics: Finding Numerical Differences Between ...

引用

High Performance Computing, Networking, Storage and Analysis, SC-W: Workshops of the International Conference for

作者： Anwar Hossain Zahid Ignacio Laguna Wei Le Department of Computer Science Iowa State University Ames IA Center for Applied Scientific Computing Lawrence Livermore National Laboratory Livermore CA

ISBN: (数字)9798350355543

ISBN: (纸本)9798350355550

As scientific codes are ported between GPU platforms, continuous testing is required to ensure numerical robustness and identify potential numerical differences between platforms. Compiler-induced numerical differences can occur when a program is compiled and run on different GPUs and compilers, and the numerical outcomes are different for the same input. We present a study of compiler-induced numerical differences between NVIDIA and AMD GPUs, two widely used GPUs in HPC clusters. Our approach uses a random program generator (Varity) to generate thousands of short numerical tests in CUDA and HIP, and their inputs; then, we use differential testing to check if the program produced a numerical inconsistency when run on NVIDIA and AMD GPUs, using the same compiler optimization level. We also use the AMD’s HIPIFY tool to convert CUDA tests into HIP tests and test if there are numerical inconsistencies induced by HIPIFY. In our study, we generated more than 600,000 tests and found subtle numerical differences occurring between the two classes of GPUs. We found that some of the differences come from (1) math library calls, (2) differences in floating-point precision (FP64 versus FP32), and (3) converting code to HIP with HIPIFY.

关键词： Codes High performance computing graphics processing units Production Numerical simulation Robustness Libraries Hip Optimization Testing

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：