检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Chen, Huiyuan Chen, Weiting Zhang, Yiqing Li, Na East China Normal University Moe Research Center of Software/Hardware Co-Design Engineering Shanghai Key Laboratory of Trustworthy Computing Shanghai China Shanghai Jiao Tong University School of Medicine Children's Hospital Shanghai China

ISBN: (纸本)9798350337488

Automatic video seizure detection can assist in the diagnosis of seizures. Existing works usually rely on the information of single granularity for learning seizure patterns and the performance of these works is often constrained by the limited annotated data. To overcome these problems, we introduce a multi-granularity information flow method to enhance skeleton-based infant seizure detection from different perspectives. A forward-backward consistency constraint is proposed to use the reverse temporal sequences as augmented data, helping make better predictions. Besides, an importance-aware module is proposed to adaptively pay more attention to important frames. Experimental results indicate that our method can improve the performance of seizure detection and achieve high performance with a relatively low amount of parameters. © 2023 IEEE.

关键词： forward-backward consistency multi-granularity information seizure detection skeleton-based action recognition

来源：评论

学校读者我要写书评

暂无评论

Precise Analysis of Covariance Identifiability for Activity Detection in Grant-Free Random Access

arXiv

引用

arXiv 2024年

作者： Luo, Shengsong Ma, Junjie Xu, Chongbin Wang, Xin the Department of Communication Science and Engineering Fudan University Shanghai200433 China The State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

We consider the identifiability issue of maximum-likelihood based activity detection in massive MIMO-based grant-free random access. An intriguing observation by Chen et al. [1] indicates that the identifiability undergoes a phase transition for commonly-used random user signatures as L2, N and K tend to infinity with fixed ratios, where L, N and K denote the user signature length, the total number of users, and the number of active users, respectively. In this letter, we provide a precise analytical characterization of the phase transition based on a spectral universality conjecture. Numerical results demonstrate excellent agreement between our theoretical predictions and the empirical phase transitions. Copyright © 2024, The Authors. All rights reserved.

关键词： Maximum likelihood

来源：评论

学校读者我要写书评

暂无评论

Adaptive energy-preserving algorithms for guiding center system

引用

Plasma Science and Technology 2023年第4期25卷 11-22页

作者：朱贝贝刘健张嘉炜祝爱卿唐贻发 Department of Applied Mathematics School of Mathematics and PhysicsUniversity of Science and Technology BeijingBeijing 100083Peopleʼs Republic of China School of Nuclear Science and Technology University of Science and Technology of ChinaHefei 230026Peopleʼs Republic of China Advanced algorithm Joint Lab Shandong Computer Science CenterQilu University of TechnologyJinan 250014Peopleʼs Republic of China The State Key Laboratory of Scientific and Engineering Computing The Institute of Computational Mathematics and Scientific/Engineering ComputingAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190Peopleʼs Republic of China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049Peopleʼs Republic of China

We develop two types of adaptive energy preserving algorithms based on the averaged vector field for the guiding center dynamics,which plays a key role in magnetized *** adaptive scheme is applied to the Gauss Legendre’s quadrature rules and time stepsize respectively to overcome the energy drift problem in traditional energy-preserving *** new adaptive algorithms are second order,and their algebraic order is carefully *** results show that the global energy errors are bounded to the machine precision over long time using these adaptive algorithms without massive extra computation cost.

关键词： guiding center system energy-preserving methods adaptive energy conservation

来源：评论

学校读者我要写书评

暂无评论

PassAugment: Pass Nodes Importance in Graph Data Augmentation for Graph Classification

PassAugment: Pass Nodes Importance in Graph Data Augmentatio...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Li, Xiaohu Li, Yan Liu, Shasha Cao, Guitao Cao, Wenming East China Normal University MoE Engineering Research Center of SW/HW Co-design Technology and Application Shanghai Key Laboratory of Trustworthy Computing Shanghai200062 China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Data augmentation has been widely introduced into graph-based tasks to improve the generalizability of models. Based on empirical hypothesis, we show that the node in a graph has different importance, the important one is critical for classification task while the unimportant one hurts the performance. However, there are few works in data augmentation addressing the information propagation of nodes with different importance. In this work, we propose a novel graph data augmentation algorithm for graph classification task, called PassAugment, aiming to pass these importance in graph data augmentation. After distinguishing the importance of all nodes in each graph using the saliency map, we design a data augmentation approach including two strategies: (i) randomly adding edges between the important nodes and the other nodes to globally improve the effective information passing, and (ii) randomly removing edges between the unimportant nodes and their neighbors to locally reduce the ineffective information passing. More importantly, our proposed approach as a standalone module can be combined with many GNNs architectures. Experimental results on graph classification task show that our approach consistently improves the accuracy and achieves or closely matches the state-of-the-art performance. © 2022 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

CBPGM: A Cache Based Piecewise Geometric Model Index

CBPGM: A Cache Based Piecewise Geometric Model Index

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Xu, Xiaopei Cao, Guitao Li, Yan MoE Engineering Research Center of SW/HW Co-design Technology and Application Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai200062 China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Recent works on learned indexes have changed the way we look at the decades-old field of Database Management System indexing. However, they are limited to too many hyperparameters, long model construction time, and not taking full advantage of CPU cache and hardware acceleration. In this paper, we propose a Cache Based Piecewise Geometric Model (CBPGM) Index to address these issues with only one hyperparameter and effectively combines a sampling approach to reduce training dataset size that accelerates the construction procedure and aligns models and data to the CPU cache line to improve search performance. Experimental results show that the CBPGM index can improve the construction speed up to 8× and the query speed by 30% compared with the PGM index. © 2022 IEEE.

关键词： Query processing

来源：评论

学校读者我要写书评

暂无评论

Adaptively feature matching via joint transformational-spatial clustering

Adaptively feature matching via joint transformational-spati...

引用

作者： Wang, Linbo Tan, Li Fang, Xianyong Guo, Yanwen Wan, Shaohua MOE Key Laboratory of Intelligent Computing and Signal Processing School of Computer Science and Technology Anhui University Hefei China National Key Lab for Novel Software Technology Nanjing University Nanjing China School of Information and Safety Engineering Zhongnan University of Economics and Law Wuhan China

The transformational and spatial proximities are important cues for identifying inliers from an appearance based match set because correct matches generally stay close in input images and share similar local transformations. However, most existing approaches only check one type of them or both types consecutively with manually set thresholds, and thus their matching accuracy and flexibility in handling large-scale images are limited. In this paper, we present an efficient clustering based approach to identify match inliers with both proximities simultaneously. It first projects the putative matches into a joint transformational-spatial space, where mismatches tend to scatter all around while correct matches gather together. A mode-seeking process based on joint kernel density estimation is then proposed to obtain significant clusters in the joint space, where each cluster contains matches mapping the same object across images with high accuracy. Moreover, kernel bandwidths for measuring match proximities are adaptively set during density estimation, which enhances its applicability for matching different images. Experiments on three standard datasets show that the proposed approach delivers superior performance on a variety of feature matching tasks, including multi-object matching, duplicate object matching and object retrieval. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Clustering Density estimation Feature matching Mode-seeking

来源：评论

学校读者我要写书评

暂无评论

3D visualization and detection of glomeruli in whole mouse kidney 16

3D visualization and detection of glomeruli in whole mouse k...

引用

16th International Conference on Photonics and Imaging in Biology and Medicine, PIBM 2023

作者： Li, Yuxin Cao, Jia Li, Anan Li, Xiangning Feng, Zhao Shaanxi Key Laboratory for Network Computing and Security Technology School of Computer Science and Engineering Xi an University of Technology Xi an710048 China Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for Optoelectronics MoE Key Laboratory for Biomedical Photonics Huazhong University of Science and Technology Wuhan430074 China HUST-Suzhou Institute for Brainsmatics Suzhou215123 China

ISBN: (纸本)9781510667341

The kidney is an important organ in the body to excrete metabolic waste, and the glomerulus is an essential structure for the kidney to play a role in blood filtration. Abnormal glomerular numbers are associated with nephropathy or circulatory disease. With the development of imaging technology, mesoscopic optical imaging can obtain whole kidney images at single cell resolution. The detection of glomeruli from images is very crucial for understanding the renal function and studying nephropathy. Existing detection methods cannot balance both accuracy and efficiency, so we proposed a deep learning-based glomeruli detection method. First, we imaged an entire mouse kidney with High-Definition fluorescent Micro-Optical Sectioning Tomography (HD-fMOST) and obtained a three-dimensional (3D) kidney image at cellular resolution. Then, we designed an end-To-end 3D convolutional neural network based on the morphological features of glomeruli in the kidney image, which can directly read 3D images and predict the precise coordinates of glomeruli. We used the acquired kidney dataset to train the network and validated the effect of glomeruli detection. Finally, we applied our approach to detect glomeruli in large-scale mouse kidney. The results showed that the proposed method reached the state-of-The-Art level, which is more efficient and accurate compared to similar methods. The proposed method will provide a powerful tool for kidney-related research. © 2023 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

STk: A Scalable Module for Solving Top-k Problems 38

STk: A Scalable Module for Solving Top-k Problems

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Xia, Hanchen Liu, Weidong Mao, Xiaojun School of Mathematical Sciences Shanghai Jiao Tong University Shanghai China Ministry of Education Key Lab of Artificial Intelligence Shanghai Jiao Tong University Shanghai China Ministry of Education Key Laboratory of Scientific and Engineering Computing Shanghai Jiao Tong University Shanghai China RoyalFlush AI Research Institute Hangzhou China

The cost of ranking becomes significant in the new stage of deep learning. We propose STk, a fully differentiable module with a single trainable parameter, designed to solve the Top-k problem without requiring additional time or GPU memory. Due to its fully differentiable nature, STk can be embedded end-to-end into neural networks and optimize the Top-k problems within a unified computational graph. We apply STk to the Average Top-k Loss (ATk), which inherently faces a Top-k problem. The proposed STk Loss outperforms ATk Loss and achieves the best average performance on multiple benchmarks, with the lowest standard deviation. With the assistance of STk Loss, we surpass the state-of-the-art (SOTA) on both CIFAR-100-LT and Places-LT leaderboards. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FedPerturb: Covert Poisoning Attack on Federated Learning via Partial Perturbation 26

FedPerturb: Covert Poisoning Attack on Federated Learning vi...

引用

26th European Conference on Artificial Intelligence, ECAI 2023

作者： Jin, Tongsai Fu, Zhihui Meng, Dan Wang, Jun Qi, Yue Cao, Guitao MoE Engineering Research Center of SW/HW Co-design Technology and Application East China Normal University Shanghai China Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China Oppo Research Institute China

ISBN: (纸本)9781643684369

Federated learning breaks through the barrier of data owners by allowing them to collaboratively train a federated machine learning model without compromising the privacy of their own data. However, Federation Learning also faces the threat of poisoning attacks, especially from the client model updates, which may impair the accuracy of the global model. To defend against the poisoning attacks, previous work aims to identify the malicious updates in high dimensional spaces. However, we find that the distances in high dimensional spaces cannot identify the changes in a small subset of dimensions, and the small changes may affect the global models severely. Based on this finding, we propose an untargeted poisoning attack under the federated learning setting via the partial perturbations on a small subset of the carefully selected model parameters, and present two attack object selection strategies. We experimentally demonstrate that the proposed attack scheme achieves high attack success rate on five state-of-the-art defense schemes. Furthermore, the proposed attack scheme remains effective at low malicious client ratios and still circumvents three defense schemes with a malicious client ratio as low as 2%. © 2023 The Authors.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

MODERATE DEVIATION PRINCIPLES FOR A REACTION DIFFUSION MODEL IN NON-EQUILIBRIUM

arXiv

引用

arXiv 2024年

作者： Zhao, Linjie School of Mathematics and Statistics Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and Technology Wuhan430074 China

We study moderate deviations from hydrodynamic limits of a reaction diffusion model. The process is defined as the superposition of the symmetric exclusion process with a Glauber dynamics. When the process starts from a product measure with a constant density, which is a non-equilibrium measure for the process, we prove that the re-scaled density fluctuation field satisfies the moderate deviation principle. Our proof relies on the so-called main lemma developed by Jara and Menezes [5, 6]. © 2024, CC BY.

关键词： Equilibrium constants

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：