检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Jiang, Hao Jin, Cheng Lin, Huangjing Zhou, Yanning Wang, Xi Ma, Jiabo Ding, Li Hou, Jun Liu, Runsheng Chai, Zhizhong Luo, Luyang Shi, Huijuan Qian, Yinling Wang, Qiong Li, Changzhong Han, Anjia Chan, Ronald Cheong Kin Chen, Hao Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Tencent AI Lab Shenzhen China Department of Pathology The First Affiliated Hospital Sun Yat-sen University Guangzhou China Center of Obstetrics and Gynecology Peking University Shenzhen Hospital Shenzhen China Institute of Obstetrics and Gynecology Shenzhen PKU-HKUST Medical Center Shenzhen China Shenzhen Key Laboratory on Technology for Early Diagnosis of Major Gynecologic Diseases Shenzhen China Department of Biomedical Informatics Harvard University United States Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Department of Anatomical and Cellular Pathology The Chinese University of Hong Kong Hong Kong Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen China Division of Life Science The Hong Kong University of Science and Technology Hong Kong State Key Laboratory of Molecular Neuroscience The Hong Kong University of Science and Technology Hong Kong

Cervical cancer is a leading malignancy in female reproductive system. While AI-assisted cytology offers a cost-effective and non-invasive screening solution, current systems struggle with generalizability in complex clinical scenarios. To address this issue, we introduced Smart-CCS, a generalizable Cervical Cancer Screening paradigm based on pretraining and adaptation to create robust and generalizable screening systems. To develop and validate Smart-CCS, we first curated a large-scale, multi-center dataset named CCS-127K, which comprises a total of 127,471 cervical cytology whole-slide images collected from 48 medical centers. By leveraging large-scale self-supervised pretraining, our CCS models are equipped with strong generalization capability, potentially generalizing across diverse scenarios. Then, we incorporated test-time adaptation to specifically optimize the trained CCS model for complex clinical settings, which adapts and refines predictions, improving real-world applicability. We conducted large-scale system evaluation among various cohorts. In retrospective cohorts, Smart-CCS achieved an overall area under the curve (AUC) value of 0.965 and sensitivity of 0.913 for cancer screening on 11 internal test datasets. In external testing, system performance maintained high at 0.950 AUC across 6 independent test datasets. In prospective cohorts, our Smart-CCS achieved AUCs of 0.947, 0.924, and 0.986 in three prospective centers, respectively. Moreover, the system demonstrated superior sensitivity in diagnosing cervical cancer, confirming the accuracy of our cancer screening results by using histology findings for validation. Interpretability analysis with cell and slide predictions further indicated that the system’s decision-making aligns with clinical practice. Smart-CCS represents a significant advancement in cervical cancer screening and highlights the potential for generalizable screening in real-word practice across diverse clinical contexts. Copyright ©

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Dimming the Lights: 2D Simulations of Deflagrations of Hybrid C/O/Ne White Dwarfs using FLASH

arXiv

引用

arXiv 2023年

作者： Feldman, Catherine Gutierrez, Nathanael Eisenberg, Ellis Willcox, Donald E. Townsley, Dean M. Calder, Alan C. Department of Physics and Astronomy Stony Brook University Stony BrookNY11794-3800 United States Institute for Advanced Computational Science Stony Brook University Stony BrookNY11794-3800 United States School of Computer Science Georgia Institute of Technology AtlantaGA30332 United States Yale University New HavenCT06520 United States Center for Computational Sciences and Engineering Lawrence Berkeley National Lab BerkeleyCA94720 United States Department of Physics and Astronomy The University of Alabama TuscaloosaAL35487-0324 United States

The dimmest and most numerous outlier of the Type Ia supernova population, Type Iax events, is increasingly being found in the results of observational campaigns. There is currently no single accepted model to describe these events. This 2D study explores the viability of modeling Type Iax events as a hybrid C/O/Ne white dwarf progenitor undergoing a deflagration using the multi-physics software FLASH. This hybrid was created using the stellar evolution code MESA, and its C-depleted core and mixed structure have demonstrated lower yields than traditional C/O progenitors in previous deflagration-to-detonation studies. To generate a sample, 30 "realizations" of this simulation were performed, the only difference being the shape of the initial matchhead used to start the deflagration. As consistent with earlier work, these realizations produce the familiar hot dense bound remnant surrounded by sparse ejecta. Our results indicate the majority of the star remains unburned (∼ 70%) and bound (> 90%). Our realizations produce total ejecta yields on the order of 10−2 - 10−1 M☉, ejected 56Ni yields on the order of 10−4 - 10−2 M☉, and ejecta kinetic energies on the order of 1048 - 1049 ergs. Compared to yields inferred from recent observations of the dimmest Type Iax events - SN 2007qd, SN 2008ha, SN 2010ae, SN 2019gsc, SN 2019muj, SN 2020kyg, and SN 2021fcg - our simulation produces comparable 56Ni yields, but too-small total yields and kinetic energies. Reignition of the remnant is also seen in some realizations. © 2023, CC BY.

关键词： Supernovae

来源：评论

学校读者我要写书评

暂无评论

PointAtrousGraph: Deep Hierarchical Encoder-Decoder with Point Atrous Convolution for Unorganized 3D Points

PointAtrousGraph: Deep Hierarchical Encoder-Decoder with Poi...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Liang Pan Chee-Meng Chew Gim Hee Lee Advanced Robotics Centre National University of Singapore Department of Mechanical Engineering National University of Singapore Computer Vision and Robotic Perception (CVRP) Lab National University of Singapore

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

Motivated by the success of encoding multi-scale contextual information for image analysis, we propose our PointAtrousGraph (PAG) - a deep permutation-invariant hierarchical encoder-decoder for efficiently exploiting multi-scale edge features in point clouds. Our PAG is constructed by several novel modules, such as Point Atrous Convolution (PAC), Edgepreserved Pooling (EP) and Edge-preserved Unpooling (EU). Similar with atrous convolution, our PAC can effectively enlarge receptive fields of filters and thus densely learn multi-scale point features. Following the idea of non-overlapping maxpooling operations, we propose our EP to preserve critical edge features during subsampling. Correspondingly, our EU modules gradually recover spatial information for edge features. In addition, we introduce chained skip subsampling/upsampling modules that directly propagate edge features to the final stage. Particularly, our proposed auxiliary loss functions can further improve our performance. Experimental results show that our PAG outperform previous state-of-the-art methods on various 3D semantic perception applications.

关键词： Three-dimensional displays Picture archiving and communication systems Convolution Semantics Image edge detection Task analysis Decoding

来源：评论

学校读者我要写书评

暂无评论

SqueezeNet with Attention for Remote Sensing Scene Classification

SqueezeNet with Attention for Remote Sensing Scene Classific...

引用

International Conference on computer Applications & Information Security (ICCAIS)

作者： Asmaa S. Alswayed Haikel S. Alhichri Yakoub Bazi Department of Computer Engineering King Saud University Riyadh Saudi Arabia Advanced Lab for Intelligent Systems Research (ALISR) King Saud University Riyadh Saudi Arabia

ISBN: (数字)9781728142135

ISBN: (纸本)9781728142142

Scene classification is an important problem in remote sensing (RS) since it is a prerequisite to other more intelligent analysis operations. Given an RS scene, not all of its parts are important for classification. Thus, using an attention mechanism that directs the classification system to focus on the parts that are important and ignore the irrelevant background should enhance the system's accuracy. In this work we propose a deep CNN architecture based on the pre-trained SqueezeNet CNN. This CNN is composed of nine fire modules (fire 1 to fire 9) each consisting of Squeeze followed by expansion convolution layers. First, we improve the SqueezeNet CNN by introducing several modifications to the architecture. Then we introduce a separate branch to the network that implements an attention mechanism. Each neuron in this activation map of the fire 9 module covers a different receptive field in the original scene. An attention mechanism is applied to these neurons to learn the appropriate weighing scheme for merging the feature vectors corresponding to each neuron. Feature vectors that are assigned a higher weight indicate that the network has given more attention to the receptive field in the scene corresponding to that feature vector. Preliminary results are presenting on five popular scene datasets, namely UC Merced, KSA, AID, Whurs19, and Optimal31 datasets.

关键词： Fires Feature extraction Remote sensing Image analysis Spatial resolution Machine learning Meters

来源：评论

学校读者我要写书评

暂无评论

Fusion of CNN ensemble for Remote Sensing Scene Classification

Fusion of CNN ensemble for Remote Sensing Scene Classificati...

引用

International Conference on computer Applications & Information Security (ICCAIS)

作者： Najd Alosaimi Haikel Alhichri Department of Computer Engineering King Saud University Riyadh Saudi Arabia Advanced Lab for Intelligent Systems Research (ALISR) King Saud University Riyadh Saudi Arabia

ISBN: (数字)9781728142135

ISBN: (纸本)9781728142142

Scene classification problem in remote sensing (RS) images has attracted many researchers recently. Different fusion methods have been widely used by the machine learning community to fuse classifiers. In this paper, a decision-level fusion method has been proposed to fuse a set of stat-of-the-art CNN classifiers, namely VGG-16, SqueezeNet, and DenseNet. First, the experiment proves that these classifiers do not make the same classification mistakes, i.e. most of the time at least one of them provides correct classification. Thus these three classifiers are diverse and hence complement each other. To exploit this discovery, a novel decision-level fusion method that combines the classification decisions using voting and confidence fusion techniques has been developed. To show the effectiveness of the proposed fusion method, the results demonstrate how the accuracy of the classification can be enhanced using fusion versus training individual networks. The preliminary results for the UC Merced dataset, the KSA multisensor dataset, Aerial Image Datasets (AID), Optimal31 dataset and Whurs19 dataset have been presented. Preliminary comparison to state-of-the-art methods show the promising capabilities of this solution and encourages to investigate this method further.

关键词： Computational modeling Training Predictive models Feature extraction Remote sensing Testing Load modeling

来源：评论

学校读者我要写书评

暂无评论

Space self-adaption global variance Reduction(SsGVR) method for large-scale radiation shielding calculation

引用

Annals of Nuclear Energy 2025年 223卷

作者： Jichong Lei Zhenping Chen Zhiqiang Peng Zining Ni Jun Hong Hong Hu Xiaoyong Fang Cannan Yi Changan Ren Muhammad Abdul Wasaye Tao Yu School of Safe and Management Engineering Hunan Institute of Technology Hengyang 421002 China School of Nuclear Science and Technology University of South China Hengyang 421001 China Key Lab of Advanced Nuclear Energy Design and Safety Ministry of Education Hengyang 421001 China School of Electrical and Information Engineering Hunan Institute of Technology Hengyang 421002 China School of Computer Science and Engineering Hunan Institute of Technology Hengyang 421002 China

The absence of a universal and effective Global Variance Reduction (GVR) methodology poses significant challenges for accurate and efficient radiation field calculations in large-scale nuclear facilities using Monte Carlo methods. This study introduces a novel Space self-adaption Global Variance Reduction(SsGVR) method for large-scale radiation field simulations. The method dynamically adjusts the lower limit of the window weight during the iteration process by statistically considering the empty mesh rate and the average relative error. Using the NUREG-CR-6115 1/4 core benchmark problem, it was found that the computational efficiency of the SsGVR method was improved by more than three orders of magnitude compared to standard Monte Carlo simulation. Beyond its computational advantages, the SsGVR method exhibits high versatility and robustness, leveraging a straightforward approach to construct global information that circumvents intricate mathematical derivations or geometric modeling. These attributes highlight its substantial potential for advanced applications in large-scale radiation analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Co2-Induced Switching between Mof-Based Bio-Mimic Slow Anion Channel and Proton Pump for Medical Exhalation Detection

SSRN

引用

SSRN 2024年

作者： Chen, Honghao Yue, Xiaorui Fan, Yifei Zheng, Bin Lv, Sitao Wang, Fengnan Gao, Yixun Li, Hao Lee, Yi-Kuen French, Patrick J. Umar Siddiqui, Ahmad M. Wang, Yao Zhou, Guofu Guangdong Provincial Key Laboratory of Optical Information Materials and Technology Institute of Electronic Paper Displays South China Academy of Advanced Optoelectronics South China Normal University Guangzhou510006 China National Center for International Research on Green Optoelectronics South China Normal University Guangzhou510006 China Department of Thoracic Oncology State Key Laboratory of Respiratory Diseases The First Affiliated Hospital of Guangzhou Medical University Guangzhou510006 China Department of Mechanical & Aerospace Engineering Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong Department of Electronic & Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong BE Lab Faculty EWI Delft University of Technology Delft2628CD Netherlands Najran University Najran11001 Saudi Arabia

Inspired by the activation mechanism of slow anion channels (SLAC1) in plants that proton pump reversibly induces plant stomata open for CO2 adsorption, a CO2-switching H+ conduction/HCO3– diffusion dual ion channel ( PCBD ion channel) was constructed by assembling γ-cyclodextrin-MOF (γ-CD-MOF) and 3,4,9,10-perylenetetracarboxylic acid (PTCA) for CO2 chemiresistive sensing. The obtained CO2 sensor exhibited high response (Rg/R0 = 1.33, 50 ppm) and selectivity, low practical limit of detection (1 ppm) and excellent consistency (94.5%) with a commercial infrared CO2 meter at room temperature. It is indicated that hydrogen bond networks in PCBD ion channel will be enlarged with the increasing of carboxylic group’s content on perylene skeleton, thereby modulating proton conductivity at molecular level and furthermore CO2 sensing performance of the composite. The PCBD ion channel-based sensor has been utilized to distinguish the exhaled CO2 concentration between lung cancer patients and healthy individuals, illustrating its promising application prospect in non-invasive diagnose. © 2024, The Authors. All rights reserved.

关键词： Carbon dioxide

来源：评论

学校读者我要写书评

暂无评论

Multi-Stage Speaker Extraction with Utterance and Frame-Level Reference Signals

Multi-Stage Speaker Extraction with Utterance and Frame-Leve...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Meng Ge Chenglin Xu Longbiao Wang Eng Siong Chng Jianwu Dang Haizhou Li Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China School of Computer Science and Engineering Nanyang Technological University Singapore National University of Singapore Singapore Japan Advanced Institute of Science and Technology Ishikawa Japan Machine Listening Lab University of Bremen Germany

ISBN: (纸本)9781728176055;9781728176062

Speaker extraction requires a sample speech from the target speaker as the reference. However, enrolling a speaker with a long speech is not practical. We propose a speaker extraction technique, that performs in multiple stages to take full advantage of short reference speech sample. The extracted speech in early stages is used as the reference speech for late stages. For the first time, we use frame-level sequential speech embedding as the reference for target speaker. This is a departure from the traditional utterance-based speaker embedding reference. In addition, a signal fusion scheme is proposed to combine the decoded signals in multiple scales with automatically learned weights. Experiments on WSJ0-2mix and its noisy versions (WHAM! and WHAMR!) show that SpEx++ consistently outperforms other state-of-the-art baselines.

关键词： Conferences Signal processing Acoustics Noise measurement Time-domain analysis Speech processing

来源：评论

学校读者我要写书评

暂无评论

Rebar Detection and Localization for Non-destructive Infrastructure Evaluation of Bridges Using Deep Residual Networks 14th

Rebar Detection and Localization for Non-destructive Infrast...

引用

14th International Symposium on Visual Computing, ISVC 2019

作者： Ahmed, Habib La, Hung Manh Pekcan, Gokhan Advanced Robotics and Automation Lab Department of Computer Science and Engineering University of Nevada RenoNV89557 United States Department of Civil and Environmental Engineering University of Nevada RenoNV89557 United States

ISBN: (纸本)9783030337193

Nondestructive Evaluation (NDE) of civil infrastructure has been an active area of research for the past few decades. Traditional inspection of civil infrastructure, mostly relying on visual inspection is time-consuming, labor-intensive and often provides subjective and erroneous results. To facilitate this process, different sensors for data collection and techniques for data analyses have been used to effectively carry out this task in an automated manner. The purpose of this research is to provide a novel Deep Learning-based method for detection of steel rebars in reinforced concrete bridge elements using data from Ground Penetrating Radar (GPR). At the same time, a novel technique is proposed for the localization of rebar in B-scan images. In order to examine the performance of the rebar detection and localization system, results are outlined to demonstrate the feasibility of the proposed system within relevant practical applications. © 2019, Springer Nature Switzerland AG.

关键词： Structural health monitoring

来源：评论

学校读者我要写书评

暂无评论

The formation of cancer stem cells in EMT6/Ro tumor: Hybrid modeling within its micro-environment

引用

Informatics in Medicine Unlocked 2020年 18卷

作者： Pirastehzad, Armin Taghizadeh, Amirheckmat Jamshidi, Arta A. School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Advanced Systems Biology and Cancer Research Lab School of Mathematics Statistics and Computer Science College of Science University of Tehran Tehran Iran

We investigate the formation of cancer stem cells and their role in maintaining avascular solid tumors. For this purpose, we provide a mathematical framework to study the major biological interpretations on the stemness of cancerous cells (stochastic scheme) and the self-renewal ability of particular progenitor cells (hierarchical scheme). These interpretations are related to the genetic characteristics of cancer, which could be described by a set of mechanisms shared by all types of cancer, i.e., hallmarks of cancer. Hallmarks of cancer relate cellular genetics, differentiation and heterogeneity, and tumor micro-environment (TME). To reach our goal, based on hallmarks of cancer, we propose a hybrid discrete-continuous model that combines continual interactions of cellular genetics and tumor micro-environment. Using this model, we conduct computational experiments on EMT6/Ro tumor to study the possibility of stochastic and hierarchical schemes. Our experiments suggest that even in well-suited genomic and micro-environmental conditions, a tumor survives only when the majority of tumor cells are in the stemness state (stochastic approach), or progenitor to CSC transition exists (hierarchical approach). In the lack of progenitor to CSC transition, in the hierarchical scheme, the tumor fades away due to the CSCs malnutrition. These results are supported by a sensitivity analysis of the model parameters. Although our computational experiments are carried out for the EMT6/Ro tumor, due to the generic nature of this approach, we believe, this work could provide insights regarding similar behaviors in other tumors. © 2019

关键词： Agent-based modeling Avascular solid tumor Cancer stem cell Discrete-continuous model EMT6/Ro tumor Hallmarks of cancer Partial differential equation modeling Tumor micro-environment

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：