检索结果-内蒙古大学图书馆

39th International Symposium on Lattice Field Theory, LATTICE 2022

作者： Yamazaki, Takeshi Ishikawa, Ken-Ichi Ishizuka, Naruhito Kuramashi, Yoshinobu Namekawa, Yusuke Taniguchi, Yusuke Ukita, Naoya Yoshié, Tomoteru Faculty of Pure and Applied Sciences University of Tsukuba Ibaraki Tsukuba305-8571 Japan Center for Computational Sciences University of Tsukuba Ibaraki Tsukuba305-8577 Japan Core of Research for the Energetic Universe Graduate School of Advanced Science and Engineering Hiroshima University Higashi-Hiroshima739-8526 Japan Education and Research Center for Artificial Intelligence and Data Innovation Hiroshima University Higashi-Hiroshima739-8521 Japan

We calculate the kaon semileptonic form factors using the two sets of the PACS10 configuration, whose physical volumes are more than (10 fm)4 at the physical point. The lattice spacings are 0.063 and 0.085 fm. The configurations were generated using the Iwasaki gauge action and Nf = 2 + 1 stout-smeared nonperturbatively O(a)-improved Wilson quark action. From the momentum transfer dependence of the form factors, we evaluate the slope and curvature for the form factors at the zero momentum transfer. Furthermore, we calculate the phase space factor, which is used to obtain |Vus| through the kaon semileptonic decay. These results are compared with previous lattice results and experimental values. © Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0).

关键词： Momentum transfer

来源：评论

学校读者我要写书评

暂无评论

Adversarial Examples for Captcha Generation Adversarial Machine Learning for Social Good

SSRN

引用

SSRN 2023年

作者： Hajaj, Chen Litman, Meir Department of Industrial Engineering and Management Ariel University 40700 Israel Data Science and Artificial Intelligence Research Center Ariel University 40700 Israel Ariel Cyber Innovation Center Ariel University 40700 Israel

The increasing computational power and sophistication of Machine Learning (ML) methods pose significant challenges to traditional CAPTCHA mechanisms designed to differentiate between humans and ML-based bots. To counteract these evolving threats, this research proposes a novel real-time noise generation method with an intelligent spread mechanism to produce cleaner adversarial examples. Unlike conventional CAPTCHA methods that randomly select the target deceiving class, our approach leverages the statistical properties of image classifiers or datasets used in the generation process. We evaluate our methodology on state-of-the-art network architectures, emphasizing real-time efficiency and judicious control of added noise. Our findings demonstrate the effectiveness and efficiency of our approach, enabling the generation of high-quality adversarial examples in real time while minimizing the added noise. These advancements contribute to enhancing the practicality and security of CAPTCHA systems in differentiating between humans and automated bots, signifying a marked improvement in the broader domain of computer security. © 2023, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Efficient Named Entity Recognition Based on Broad Learning System and BERT 4

Efficient Named Entity Recognition Based on Broad Learning S...

引用

4th International Conference on data-Driven Optimization of Complex Systems, DOCS 2022

作者： Wang, Yudi Zuo, Yi Li, Tieshan Philip Chen, C.L. Dalian Maritime University Navigation College Dalian China Dalian Maritime University Collaborative Innovation Center of Maritime Big Data & Artificial General Intelligence Navigation College Dalian China University of Electronic Science and Technology of China School of Automatic Engineering Chengdu China

ISBN: (数字)9781665459822

ISBN: (纸本)9781665459822

In this paper, we propose an efficient approach for named entity recognition (NER). This paper applies the broad learning system (BLS) to NER task, which includes the feature learning and incremental learning processes. In the feature learning of BLS, the calculation of each new feature node involves only matrix multiplication, and can effectively reduce the amount of calculation to improve efficiency in obtaining rich features. In the incremental learning of BLS, the feature nodes are calculated by active function and ridge regression in order to obtain incremental nodes. In this paper, we combine the BLS with bidirectional encoder representations from transformers (BERT) and conditional random fields (CRF) algorithms to conduct NER of English corpus. Firstly, we extract features through BERT. Secondly, we use BLS to calculate the extracted features. Finally, we apply CRF to decoding features. In numerical experiments, NER of English corpus based on BIO schema is used as benchmark, And the proposed method shows higher accuracy and faster training than other baseline methods. © 2022 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

P2TC: A Lightweight Pyramid Pooling Transformer-CNN Network for Accurate 3D Whole Heart Segmentation

引用

IEEE Journal of Biomedical and Health Informatics 2025年第6期29卷 4279-4289页

作者： Hengfei Cui Yifan Wang Fan Zheng Yan Li Yanning Zhang Yong Xia National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Polytechnical University Xi'an China Research and Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen China Chongqing Innovation Center Northwestern Polytechnical University Chongqing China

Cardiovascular disease is a leading global cause of death, requiring accurate heart segmentation for diagnosis and surgical planning. Deep learning methods have been demonstrated to achieve superior performances in cardiac structures segmentation. However, there are still limitations in 3D whole heart segmentation, such as inadequate spatial context modeling, difficulty in capturing long-distance dependencies, high computational complexity, and limited representation of local high-level semantic information. To tackle the above problems, we propose a lightweight Pyramid Pooling Transformer-CNN (P2TC) network for accurate 3D whole heart segmentation. The proposed architecture comprises a dual encoder-decoder structure with a 3D pyramid pooling Transformer for multi-scale information fusion and a lightweight large-kernel Convolutional Neural Network (CNN) for local feature extraction. The decoder has two branches for precise segmentation and contextual residual handling. The first branch is used to generate segmentation masks for pixel-level classification based on the features extracted by the encoder to achieve accurate segmentation of cardiac structures. The second branch highlights contextual residuals across slices, enabling the network to better handle variations and boundaries. Extensive experimental results on the Multi-Modality Whole Heart Segmentation (MM-WHS) 2017 challenge dataset demonstrate that P2TC outperforms the most advanced methods, achieving the Dice scores of 92.6% and 88.1% in Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) modalities respectively, which surpasses the baseline model by 1.5% and 1.7%, and achieves state-of-the-art segmentation results.

关键词： Transformers Image segmentation Three-dimensional displays Heart Accuracy Feature extraction Convolutional neural networks Context modeling Computational modeling Solid modeling

来源：评论

学校读者我要写书评

暂无评论

Microstructure and Localized Corrosion Properties of 2219 Aluminum Alloy Manufactured by Additive Friction Stir Deposition

SSRN

引用

SSRN 2024年

作者： Wang, Zikang Qian, Hongchang Chang, Weiwei Yu, Zhihao Qiao, Qian Zhou, Min Guo, Dawei Zhang, Dawei Kwok, Chi Tat Tam, Lap Mou Beijing Advanced Innovation Center for Materials Genome Engineering Institute for Advanced Materials and Technology University of Science and Technology Beijing Beijing100083 China National Materials Corrosion and Protection Data Center University of Science and Technology Beijing Beijing100083 China Shunde Innovation School of University of Science and Technology Beijing Foshan528399 China Co. Ltd. Guangdong China Department of Electromechanical Engineering University of Macau Macao China

Multi-layer 2219 aluminum alloy samples were successfully fabricated using additive friction stir deposition (AFSD). AFSD deposition reduced grain size and the size of intermetallic Al2Cu particles, but greatly increased the amount of Al2Cu particles. More Al2Cu particles increased the number of galvanic microcells on alloy surface and at the grain boundaries, which promoted the localized corrosion and improved the intergranular corrosion sensitivity of AFSD alloy. Subsequent T6 heat treatment had little effect on grain size but enhanced the corrosion resistance of AFSD alloy, primarily attributed to the reduction in Al2Cu particles and the elimination of dislocations within grains. © 2024, The Authors. All rights reserved.

关键词： Aluminum alloys

来源：评论

学校读者我要写书评

暂无评论

Multi-scale attention semi-supervised network based on confidence iteration and pseudo-label optimization for COVID-19 CT segmentation

Multi-scale attention semi-supervised network based on confi...

引用

第42届中国控制会议

作者： Kun Liu Mei Chen JunfeiXie JingKun Mao WeiPeng Liu School of Artificial Intelligence and Data Science Hebei University of Technology Control Engineering Technology Innovation Center of Hebei Province Hebei University of Technology Department of Automation Tianjin University of Technology

Computed tomography(CT) image segmentation for COVID-19 lung infection has made great ***,accurate segmentation remains a major challenge due to the varying shape and size of COVID-19 infected areas,the more similar tissue of infected lung images to normal lung images,and the additional problem of a limited number of medical images annotated at the pixel *** this paper,we propose a semi-supervised segmentation network based on confidence iteration and pseudo-label optimization for COVID-19 CT *** addition,we develop a multi-scale attention module which can achieve attentional feature fusion at different *** experiment evaluated on the COVID-19 CT Segmentation dataset,demonstrate our method achieves higher segmentation accuracy than the state-of-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A review of travel behavioural pattern using GPS dataset: A systematic literature review

引用

Measurement: Sensors 2024年 32卷

作者： Sivalingam, Prahaladhan Asirvatham, David Marjani, Mohsen Syed Masood, Jafar Ali Ibrahim Chakravarthy, N.S. Kalyan Veerisetty, Gopinath Lestari, Martha Tri Faculty of Innovation & Technology Taylor's University Subang Jaya Malaysia Department of Internet of Things School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Vellore632 014 India Center for Data Science School of Computer Science and Engineering QIS College of Engineering and Technology Andhra Pradesh Ongole523272 India Department of Mechanical Engineering QIS College of Engineering and Technology Andhra Pradesh Ongole523272 India Department of Business Communication Telkom University Indonesia

In the last few years, the Global positioning system (GPS) has been used to study travel patterns with the advancement of data collection techniques. A GPS device precisely records the time and the location data of an individual travel. The accuracy of travel studies is usually improved by integrating travel surveys or travel activity diaries with GPS data. GPS surveys are implemented to replace paper-based techniques and reduce human error on trip-misreporting issues. Several reviews have been performed previously on GPS travel studies. Still, a detailed systematic review on the comparison of different modes and methods on the entire procedure of GPS data processing has not been thoroughly studied. This review identified 116 peer-reviewed studies and journal papers from 2013 to 2020, and 53 papers were studied. The review focused on travel behavior pattern (TBP) analysis using GPS studies only and a combination of travel surveys. Our review reveals that 53 only 40 have quality assessment scores of >50 %, meaning the remaining TBP studies are conventional methods. The study also benefits data analysis and researchers to select the most appropriate data collection techniques for studying TBP and improvise them further for meta-analysis travel behavior studies. © 2024 The Authors

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Domain generalized solar cell defect segmentation based on shape-aware and multi-view meta-learning

Domain generalized solar cell defect segmentation based on s...

引用

第42届中国控制会议

作者： Kun Liu Ying Yang Jingkun Mao Weipeng Liu School of Artificial Intelligence and Data Science Hebei University of Technology Control Engineering Technology Innovation Center of Hebei Province Hebei University of Technology Department of Automation Tianjin University of Technology

Various defects are inevitably generated in the manufacturing process of solar *** learning-based methods for defect segmentation under closed situation have achieved remarkable *** to the difference of imaging condition and camera parameter under different production line,there are large differences in brightness distribution of solar cell *** model trained under closed situation cannot achieve good performance in opened situation such as multi-production *** this paper,a new shape-aware and multi-view meta-learning scheme is proposed to improve the model generalization performance for single-domain solar cell defect *** scheme roots in gradient-based *** view information is yielded from the generated augmented images,and explicitly simulating domain shift with virtual meta-train and meta-test during training to mitigate overfitting in single-source domain train and unstable ***,considering tiny and faint solar cell defects are not easily identified under different image brightness conditions,shape edge constraint loss is proposed to encourage shape compactness and shape smoothness of *** results show that the proposed method has high segmentation accuracy,which outperforms the state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Epidemiology,pathogenesis,and management of coronavirus disease 2019-associated stroke

引用

Frontiers of Medicine 2023年第6期17卷 1047-1067页

作者： Lu Liu Chenxia Zhou Huimin Jiang Huimin Wei Yifan Zhou Chen Zhou Xunming Ji Department of Neurology Xuanwu HospitalCapital Medical UniversityBeijing 100032China Neurology and Intracranial Hypertension and Cerebral Venous Disease Center National Health Commission of ChinaXuanwu HospitalCapital Medical UniversityBeijing 100032China Beijing Institute of Brain Disorders Capital Medical UniversityBeijing 100069China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine School of Biological Science and Medical EngineeringBeihang UniversityBeijing 100191China Department of Neurology Beijing Shjitan HospitalCapital Medical UniversityBeijing 100038China Department of Neurosurgery Xuanwu HospitalCapital Medical UniversityBeijing 100032China

The coronavirus disease 2019(COVID-19)epidemic has triggered a huge impact on healthcare,socioeconomics,and other aspects of the world over the past three *** increasing number of studies have identified a complex relationship between COVID-19 and stroke,although active measures are being implemented to prevent disease *** COVID-19 may be associated with an increased risk of stroke and increase the rates of disability and mortality,posing a serious challenge to acute stroke diagnosis,treatment,and *** review aims to provide an update on the influence of COVID-19 itself or vaccines on stroke,including arterial stroke(ischemic stroke and hemorrhagic stroke)and venous stroke(cerebral venous thrombosis).Additionally,the neurovascular mechanisms involved in SARS-CoV-2 infection and the clinical characteristics of stroke in the COVID-19 setting are *** on vaccinations,potential therapeutic approaches,and effective strategies for stroke management has been highlighted.

关键词： SARS-CoV-2 ischemic stroke stroke hemorrhagic stroke cerebral venous thrombosis vaccination

来源：评论

学校读者我要写书评

暂无评论

Do You Think You Can Hold Me? The Real Challenge of Problem-Space Evasion Attacks

arXiv

引用

arXiv 2022年

作者： Berger, Harel Dvir, Amit Hajaj, Chen Ronen, Rony Ariel Cyber Innovation Center Computer Science Department Ariel University Ariel Israel Ariel Cyber Innovation Center Data Science and Artificial Intelligence Research Center Industrial Engineering and Management Department Ariel University Ariel Israel

Android malware is a spreading disease in the virtual world. Anti-virus and detection systems continuously undergo patches and updates to defend against these threats. Most of the latest approaches in malware detection use Machine Learning (ML). Against the robustifying effort of detection systems, raise the evasion attacks, where an adversary changes its targeted samples so that they are misclassified as benign. This paper considers two kinds of evasion attacks: feature-space and problem-space. Feature-space attacks consider an adversary who manipulates ML features to evade the correct classification while minimizing or constraining the total manipulations. Problem-space attacks refer to evasion attacks that change the actual sample. Specifically, this paper analyzes the gap between these two types in the Android malware domain. The gap between the two types of evasion attacks is examined via the retraining process of classifiers using each one of the evasion attack types. The experiments show that the gap between these two types of retrained classifiers is dramatic and may increase to 96%. Retrained classifiers of feature-space evasion attacks have been found to be either less effective or completely ineffective against problem-space evasion attacks. Additionally, exploration of different problem-space evasion attacks shows that retraining of one problem-space evasion attack may be effective against other problem-space evasion attacks. © 2022, CC BY.

关键词： Virtual reality

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：