检索结果-内蒙古大学图书馆

A Nonconformal SETI-DP Method for Transient Thermal Simulation

IEEE Transactions on Components, Packaging and Manufacturing Technology 2025年

作者： Feng, Naixing Li, Hongyang Huang, Zhixiang Liu, Qi Qiang Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education The Information Materials and Intelligent Sensing Laboratory of Anhui Province The Key Laboratory of Electromagnetic Environmental Sensing of Anhui Higher Education Institutes Hefei China Hangzhou Dianzi University School of Electronics and Information Engineering Hangzhou310018 China

This paper proposes a novel nonconformal meshbased dual-primal spectral element tearing and interconnecting (SETI-DP) method designed for the efficient transient simulation of complex large-scale heat conduction problems utilizing a domain decomposition method (DDM). This method allows for the division of complex, large-scale problems into smaller subdomain problems. By applying Robin-type transmission conditions at the subdomain interfaces, rapid convergence of the global interface iterative solution is achieved for arbitrary non-conformal subdomain problems. This non-conformal DDM approach supports independent meshing of subdomains, eliminating the need to generate a globally continuous mesh for large-scale problems, thereby significantly enhancing meshing efficiency. In addition, this non-conformal meshing strategy enables high-contrast spatial discretization and mixed-order spectral interpolation between different subdomains. This significantly increases meshing flexibility, minimizes the number of degrees of freedom (DoF) in multi-scale problems, and reduces computational costs. In addition, by developing a subdomain-coupled time iteration scheme, the global corner problem of residual transfer is explicitly given, which greatly improves the versatility and flexibility of the algorithm. Finally, to demonstrate the accuracy, efficiency, and robustness of our algorithm, we conduct benchmark tests on several representative examples. © 2011-2012 IEEE.

关键词： Domain decomposition methods

来源：评论

学校读者我要写书评

暂无评论

V-GnNet: Voxel and Graph Node Based Network for Continuously Consistent Artery and Vein Classification in Non-contrast CT Images 13th

V-GnNet: Voxel and Graph Node Based Network for Continuously...

引用

13th International Conference on Health Information Science, HIS 2024

作者： Li, Qingya Yuan, Ye Liu, Lu Zhang, Ziming Tan, Wenjun College of Computer Science and Engineering Northeastern University Shenyang110189 China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang110189 China

ISBN: (纸本)9789819655960

In medical imaging, especially CT scanning, accurate classification of arteries and veins is crucial for diagnosis and treatment. Existing deep learning methods, although capable of capturing arterial and venous features, often process voxel points independently and lack a holistic understanding of vascular branch structures. This limitation results in misclassifications at branch points, especially in distal branches, necessitating post-processing for correction. Traditional post-processing algorithms, such as arterial and venous density calculations or graph cut methods, can correct short intrusions but are limited in addressing long intrusions or mixed intrusions, hindering the application in complex vascular networks. To address this issue, this paper proposes V-GnNet, a fusion learning method combining voxel-based predictions and graph structure node predictions. Firstly, V-GnNet employs an iterative 3D neural network based on the UNet architecture, IterUNet3D, for preliminary classification of vascular data. IterUNet3D enhances the classification performance of arteries and veins by enriching the network's multi-level feature inputs through iterative mini-UNet3D modules. Subsequently, a special graph structure is established by extracting the vascular skeleton, integrating priori knowledge into a feature matrix, and utilizing a Graph Attention Network (GAT) for node classification of the IterUNet3D results. Finally, a voting algorithm fuses the voxel prediction results and node prediction results, ensuring consistent branch classification in artery and vein separation, therefore addressing the challenges of branch misclassification. Experimental results demonstrate that V-GnNet significantly improves the accuracy and consistency of pulmonary artery and vein classification, effectively reducing branch misjudgments and mutual intrusions, which showcases its great potential in medical image processing. © The Author(s), under exclusive license to Springer Nature S

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

ISGAN: Unsupervised Domain Adaptation With Improved Symmetric GAN for Cross-Modality Multi-Organ Segmentation

引用

IEEE Journal of Biomedical and Health Informatics 2024年第6期29卷 3874-3885页

作者： Jiapeng Li Yifan Zhang Lisheng Xu Yudong Yao Lin Qi College of Medicine and Biological Information Engineering Northeastern University Shenyang China Engineering Research Center of Medical Imaging and Intelligent Analysis Ministry of Education Shenyang China Key Laboratory of Medical Image Computing Ministry of Education Northeastern University Shenyang China Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken NJ USA

The differences between cross-modality medical images are significant, so several studies are working on unsupervised domain adaptation (UDA) segmentation, which aims to adapt a segmentation model trained on a labeled source domain to an unlabeled target domain. The conventional UDA segmentation strategy aims to integrate image generation and segmentation. However, conventional image generation modules only consider information from a single domain (source or target), resulting in visual inconsistencies. The image generation module may also lack anatomical constraints, leading to incorrect pseudo-label generation. To address these issues, we propose an improved symmetric generative adversarial network (ISGAN). Unlike conventional approaches that perform domain adaptation only in the source or target domain, ISGAN adopts a symmetric architecture using two-path domain adaptation to reduce the visual difference. In addition, ISGAN adopts a bidirectional training strategy to optimize the image generation and segmentation modules. The bidirectional training strategy introduces the anatomical constraints into the image generation module, thereby reducing the generation of incorrect pseudo labels. Finally, we validate ISGAN on two cross-modality datasets (the MMWHS cardiac dataset and Abdomen dataset). ISGAN delivers promising segmentation and generalization performance compared with state-of-the-art UDA methods.

关键词： Image segmentation Training Biomedical imaging Image synthesis Magnetic resonance imaging Computed tomography Feature extraction Generative adversarial networks Generators Diffusion models

来源：评论

学校读者我要写书评

暂无评论

Reduced-search guessing random additive noise decoding of polar codes

引用

Science China(Information Sciences) 2023年第2期66卷 283-284页

作者： Kefan WANG Yuejun WEI Zhenyuan CHEN Huarui YIN Liping LI Wenyi ZHANG Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education of China Anhui University Huawei Technologies Department of Electronic Engineering and Information Science University of Science and Technology of China

Guessing random additive noise decoding(GRAND) has attracted researchers since its introduction in [1]. For an additive noise channel with hard decision output, the algorithm checks all error patterns, and it schedules its search in descending likelihood order. Ordered reliability bit GRAND(ORBGRAND) [2] is a variant of *** soft channel output is available,

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories 25

Adaptive Activation Steering: A Tuning-Free LLM Truthfulness...

引用

34th ACM Web Conference, WWW 2025

作者： Wang, Tianlong Jiao, Xianfeng Zhu, Yinghao Chen, Zhongzhi He, Yifan Chu, Xu Gao, Junyi Wang, Yasha Ma, Liantao School of Software and Microelectronics Peking University Beijing China Key Laboratory of High Confidence Software Technologies Ministry of Education Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China Beihang University Beijing China Center on Frontiers of Computing Studies Peking University Beijing China Centre for Medical Informatics University of Edinburgh Edinburgh United Kingdom Health Data Research UK London United Kingdom Key Laboratory of High Confidence Software Technologies Ministry of Education National Engineering Research Center for Software Engineering Peking University Beijing China

ISBN: (纸本)9798400712746

Recent studies have indicated that Large Language Models (LLMs) harbor an inherent understanding of truthfulness, yet often fail to consistently express it and generate false statements. This gap between "knowing" and "telling" poses a challenge for ensuring the truthfulness of generated content. Inspired by recent work on the practice of encoding human-interpretable concepts linearly within large language models, we treat truthfulness as a specially linearly encoded concept within LLMs, and introduce Adaptive Activation Steering (ACT), a tuning-free method that adaptively shifts LLM’s activations in the "truthful" direction during inference. ACT addresses diverse categories of hallucinations by utilizing diverse truthfulness-related steering vectors and adjusting the steering intensity adaptively. Applied as an add-on across various models, ACT significantly improves truthfulness in LLaMA (↑ 142%), LLaMA2 (↑ 24%), Alpaca (↑ 36%), Vicuna (↑ 28%), LLaMA2-Chat (↑ 19%), and LLaMA3(↑ 34%). Furthermore, we verify ACT’s scalability across larger models (13B, 33B, 65B), underscoring the adaptability of ACT to large-scale language models. © 2025 Copyright held by the owner/author(s).

关键词： hallucination

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Speech Noise Reduction Method Based on Noise Classification

An Adaptive Speech Noise Reduction Method Based on Noise Cla...

引用

IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems

作者： Ben Niu Yangjie Wei Key Laboratory of Intelligent Computing in Medical Image Ministry of Education College of Computer Science and Engineering Northeastern University Shenyang

To improve the accuracy and robustness of existing speech denoising methods, this study proposes an adaptive speech noise reduction method based on noise classification. First, to adapt to different time-varying characteristics of various noises in complex environments, a new acoustic feature matrix is constructed by combining the LogFbank features and the perceptual linear prediction coefficients, and a noise classifier based on the support vector machine is designed to classify the experimental noise. Then, to address the problem of “music noise” in traditional speech denoising methods, the voice activity detection threshold is adaptively updated according to the judgment result of background noise types, and the optimal parameters for the improved minima controlled recursive averaging noise estimation algorithm are obtained to accurately estimate current noise and reduce it. Finally, the performance of the proposed method is evaluated using a serial of experiments on different situations, and the experimental results prove the effectiveness and feasibility of our proposed method in this study.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High Order Conditional Random Field Based Cervical Cancer Histopathological Image Classification

High Order Conditional Random Field Based Cervical Cancer Hi...

引用

International Conference on Image, Vision and Intelligent Systems, ICIVIS 2023

作者： Zhou, Shangqi Li, Xintong Fu, Yanyu Ouyang, Xinyu Yang, Jinzhu Grzegorzek, Marcin Li, Chen Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China Institute of Medical Informatics University of Luebeck Luebeck Germany Department of Knowledge Engineering University of Economics in Katowice Katowice Poland

ISBN: (纸本)9789819708543

Cervical cancer ranks as the fourth most frequently diagnosed cancer. This disease has an extended precancerous stage and can be completely cured and prevented through early detection. Currently, the analysis of histopathological images of cervical cancer relies on manual assessment by pathologists, a subjective and time-consuming process. Moreover, there is limited research on differentiating the severity of cervical cancer in histopathological images. To address these challenges, this study proposes a classification algorithm based on high-order conditional random field for cervical cancer histopathologic images. The algorithm effectively categorizes images into high differentiation, medium differentiation, and low differentiation stages. Three deep learning models, namely VGG-16, Inception-V3, and ResNet-50, are utilized for pre-classification at the image block level. For image-level classification, the Visual Transformer model is employed. Finally, the block-level and image-level classification components are integrated using the conditional random field model, resulting in the high-order conditional random field model. Following training and testing using the dataset, the model achieves an overall accuracy of 75.4%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Neural Network Based Sperm Detection in Microscopic Videos

Deep Convolutional Neural Network Based Sperm Detection in M...

引用

International Conference on Image, Vision and Intelligent Systems, ICIVIS 2023

作者： Ma, Shiyi Li, Jindong Zhang, Wenbo Yang, Jinzhu Grzegorzek, Marcin Li, Chen Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China Institute of Medical Informatics University of Luebeck Luebeck Germany Department of Knowledge Engineering University of Economics in Katowice Katowice Poland

ISBN: (纸本)9789819708543

In recent years, with the increasingly serious quality problems of human sperm, the performance of traditional sperm analysis methods has been unable to meet the growing demand for diagnosis and treatment. The purpose of this study was to explore the application of deep convolutional neural network microvideo in computer assisted sperm analysis (CASA). For the sperm detection task, the model structure, loss function and non-maximum suppression algorithm were optimized to improve the performance of the model, reflecting the advantages of deep learning. To avoid the impact of data differences, cross-validation test was adopted in this study, and multiple indexes such as F1-score and AP were compared with the original model after training. These improvements significantly improved the average accuracy and F1 scores of the models. The performance of the model not only has an important impact on the indicators of the target detection model, but also has an important impact on the visualization results of the model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Tumor State-Space Network for High and Low Grade Glioma Classification 17

Tumor State-Space Network for High and Low Grade Glioma Clas...

引用

17th IEEE International Conference on Signal Processing, ICSP 2024

作者： Chen, Qijian Wang, Lihui Deng, Zeyu Wang, Li Ye, Chen Zhu, YueMin Guizhou University Engineering Research Center of Text Computing Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang China University Lyon Insa Lyon Cnrs Inserm Irp Metislab Creatis UMR5220 U1206 Lyon69621 France

ISBN: (纸本)9798350387384

Accurately predicting the grade of gliomas is crucial for choosing right treatment plans. While current methods using radiomics and deep learning can predict glioma grades effectively using magnetic resonance imaging (MRI), they overlook dynamic changes in the tumor and its neighboring areas. To address this issue, we propose a tumor state-space network (TSSNet), which fully exploits changes in the tumor region and its surroundings through dynamical updating strategy. The experimental results demonstrated that TSSNet achieves 90.32% accuracy and 93.55% area under the curve (AUC) for the prediction of high-grade and low-grade gliomas, respectively, which are 2.4% and 2.5% higher than the best state-of-the-art deep learning models. Moreover, the proposed state-space module can effectively enhance prediction performance, which is advantageous for personalized glioma treatment. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Distributed estimation on semi-supervised generalized linear model

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 3735-3775页

作者： Jiyuan Tu Weidong Liu Xiaojun Mao School of Mathematics Shanghai University of Finance and Economics Shanghai China School of Mathematical Sciences MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University Shanghai China School of Mathematical Sciences Ministry of Education Key Laboratory of Scientific and Engineering Computing Shanghai Jiao Tong University Shanghai China

Semi-supervised learning is devoted to using unlabeled data to improve the performance of machine learning algorithms. In this paper, we study the semi-supervised generalized linear model (GLM) in the distributed setup. In the cases of single or multiple machines containing unlabeled data, we propose two distributed semi-supervised algorithms based on the distributed approximate Newton method. When the labeled local sample size is small, our algorithms still give a consistent estimation, while fully supervised methods fail to converge. Moreover, we theoretically prove that the convergence rate is greatly improved when sufficient unlabeled data exists. Therefore, the proposed method requires much fewer rounds of communications to achieve the optimal rate than its fully-supervised counterpart. In the case of the linear model, we prove the rate lower bound after one round of communication, which shows that rate improvement is essential. Finally, several simulation analyses and real data studies are provided to demonstrate the effectiveness of our method.

关键词： distributed learning semi-supervised learning generalized linear model

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：