检索结果-内蒙古大学图书馆

Protein Residue Contact Prediction Based on Deep Learning and Massive Statistical Features from Multi-Sequence Alignment

引用

Tsinghua Science and technology 2022年第5期27卷 843-854页

作者： Huiling Zhang Min Hao Hao Wu Hing-Fung Ting Yihong Tang Wenhui Xi Yanjie Wei Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen 518055China University of Chinese Academy of Sciences Beijing 100049China College of Electronic and Information Engineering Southwest UniversityChongqing 400715China School of Software Engineering University of Science and Technology of ChinaHefei 230051China Department of Computer Science The University of Hong KongHong Kong 999077China School of Computer Science Beijing University of Posts and TelecommunicationsBeijing 100876China

Sequence-based protein tertiary structure prediction is of fundamental importance because the function of a protein ultimately depends on its 3 D *** accurate residue-residue contact map is one of the essential elements for current ab initio prediction protocols of 3 D structure ***,with the combination of deep learning and direct coupling techniques,the performance of residue contact prediction has achieved significant ***,a considerable number of current Deep-Learning(DL)-based prediction methods are usually time-consuming,mainly because they rely on different categories of data types and third-party *** this research,we transformed the complex biological problem into a pure computational problem through statistics and artificial *** have accordingly proposed a feature extraction method to obtain various categories of statistical information from only the multi-sequence alignment,followed by training a DL model for residue-residue contact prediction based on the massive statistical *** proposed method is robust in terms of different test sets,showed high reliability on model confidence score,could obtain high computational efficiency and achieve comparable prediction precisions with DL methods that relying on multi-source inputs.

关键词： multi-sequence alignment residue-residue contact prediction feature extraction statistical information Deep Learning(DL) high computational efficiency

来源：评论

学校读者我要写书评

暂无评论

The Power of Age-based Reward in Fresh Information Acquisition 42

The Power of Age-based Reward in Fresh Information Acquisiti...

引用

42nd IEEE International Conference on Computer Communications, INFOCOM 2023

作者： Wang, Zhiyuan Meng, Qingkai Zhang, Shan Luo, Hongbin Beihang University School of Computer Science and Engineering Beijing China Beihang University State Key Laboratory of Virtual Reality Technology and Systems China Beihang University Institute of Artificial Intelligence Beijing China State Key Laboratory of Software Development Environment China

ISBN: (纸本)9798350334142

Many Internet platforms collect fresh information of various points of interest (PoIs) relying on users who happen to be nearby the PoIs. The platform will offer reward to incentivize users and compensate their costs incurred from information acquisition. In practice, the user cost (and its distribution) is hidden to the platform, thus it is challenging to determine the optimal reward. In this paper, we investigate how the platform dynamically rewards the users, aiming to jointly reduce the age of information (AoI) and the operational expenditure (OpEx). Due to the hidden cost distribution, this is an online non-convex learning problem with partial feedback. To overcome the challenge, we first design an age-based rewarding scheme, which decouples the OpEx from the unknown cost distribution and enables the platform to accurately control its OpEx. We then take advantage of the age-based rewarding scheme and propose an exponentially discretizing and learning (EDAL) policy for platform operation. We prove that the EDAL policy performs asymptotically as well as the optimal decision (derived based on the cost distribution). Simulation results show that the age-based rewarding scheme protects the platform's OpEx from the influence of the user characteristics, and verify the asymptotic optimality of the EDAL policy. © 2023 IEEE.

关键词： Simulation platform

来源：评论

学校读者我要写书评

暂无评论

SWT-UNet: Medical Image Segmentation Based on Multi-modality UNet with Sliding Window Transformer Block

SWT-UNet: Medical Image Segmentation Based on Multi-modality...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Zhang, Yangqianhui Han, Dong Gang, Xiaoming Ma, Jiajun Yuan, Xu Zhejiang University School of Mechanical Engineering Hangzhou China Zhejiang University State Key Laboratory of Fluid Power and Mechatronic Systems Hangzhou China Anshan Municipal Central Hospital Anshan China Shenhua Hollysys Information Technology Co. Ltd Beijing China Dalian University of Technology School of Software Technology Dalian China

ISBN: (纸本)9798350337488

Medical images are information carriers that visually reflect and record the anatomical structure of the human body, and play an important role in clinical diagnosis, teaching and research, etc. Modern medicine has become increasingly inseparable from the intelligent processing of medical images. In recent years, there have been more and more attempts to apply deep learning theory to medical image segmentation tasks, and it is imperative to explore a simple and efficient deep learning algorithm for medical image segmentation. In this paper, we conduct research on multi-modal medical image segmentation algorithms with a hybrid architecture of Convolutional Neural Networks and Vision Transformer. This paper proposes a multi-modal medical image segmentation model SWT-UNet based on the CNN-ViT hybrid framework. The self-attention mechanism and sliding window design of the visual Transformer are used to capture the global feature association and break the limitation of the receptive field caused by the inductive bias of the convolution operation. At the same time, a widened self-attentive vector is used to streamline the number of modules and compress the model size, so as to fit the characteristics of a small amount of medical data, which makes the model easy to be overfitted. Experiments on two multi-modal medical image datasets validate that the algorithm can achieve efficient medical image segmentation at a lightweight scale. © 2023 IEEE.

关键词： attention mechanism medical image segmentation multi-modality Vision Transformer

来源：评论

学校读者我要写书评

暂无评论

Research and development of two-factor authentication methods using neural networks 4

Research and development of two-factor authentication method...

引用

4th IEEE International Conference on Smart Information systems and Technologies, SIST 2024

作者： Darbek, Temirkhan Mukasheva, Assel Bissembayev, Alibek Gnatyuk, Sergiy Mukammejanova, Dinargul The Department of Information Systems and Cybersecurity Almaty university of power engineering and telecommunications Almaty Kazakhstan The School of Information Technology and Engineering Kazakh-British Technical University Almaty Kazakhstan The School of Information Technology and Engineering Kazakh British Technical University Almaty Kazakhstan The Faculty of Cybersecurity Computer and Software Engineering at National Aviation University National Aviation University Kyiv Ukraine The Department of Artificial Intelligence and Big Data Kazakh National University named after Al-Farabi Almaty Kazakhstan

ISBN: (纸本)9798350374865

This article is devoted to the research and development of innovative two-factor authentication (2FA) methods using neural networks. 2FA plays a key role in ensuring the security of data and accounts in the modern digital world, and the use of neural networks opens up new prospects in strengthening protection and improving the user experience. The article presents an analysis of existing 2FA methods, identifies their limitations, and discusses the advantages of using neural networks in this area. The main focus is on the development of new authentication algorithms based on deep learning, providing effective anomaly detection and support for a dynamic adaptive approach. In the context of the article, the issues of privacy and data security are also considered, as well as the possibilities of applying the developed methods in various fields, including finance, medicine and the Internet of Things. The results of the study represent a significant contribution to the field of digital. © 2024 IEEE.

关键词： biometric authentication deep learning digital security identification Neural networks

来源：评论

学校读者我要写书评

暂无评论

Harnessing the Power of AI with Deep Learning: Innovations and Implications

Harnessing the Power of AI with Deep Learning: Innovations a...

引用

2025 IEEE International Conference on Computational, Communication and Information technology, ICCCIT 2025

作者： Upender, Talluri Sathiyamoorthy, C. Udayakumar, K. Kirubakaran, D. Purushothaman, V. Raja, Kiruba Thangam CMR College of Engineering and Technology Department of CSE Medchal Telangana Hyderabad India Department of Commerce Tamil Nadu Chennai India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of CSE Tamil Nadu Chennai India R.M.K. Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Chennai Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India VIT University Department of Software and Systems Engineering Tamil Nadu Vellore India

ISBN: (纸本)9798331512965

The rapid advancements in artificial intelligence (AI) and deep learning have revolutionized various sectors, enabling unprecedented levels of innovation and efficiency. This paper delves into the transformative impact of deep learning across multiple domains, highlighting key innovations and their broader implications. By examining cutting-edge applications in healthcare, finance, autonomous systems, and natural language processing, the study elucidates how deep learning models, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), are pushing the boundaries of what's possible. Moreover, the paper explores the integration of deep learning with emerging technologies such as the Internet of Things (IoT), edge computing, and quantum computing, underscoring the synergistic potential of these combinations. The role of deep learning in predictive analytics and personalized solutions is discussed, showcasing its ability to enhance decision-making processes and improve user experiences. Furthermore, the paper discusses the ethical considerations, challenges, and future prospects associated with the widespread adoption of deep learning technologies. The insights provided aim to foster a deeper understanding of how harnessing AI with deep learning can drive progress while addressing critical societal and technological issues. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine learning and deep learning algorithms in detecting COVID-19 utilizing medical images: a comprehensive review

引用

Iran Journal of Computer Science 2024年第3期7卷 699-721页

作者： Nurjahan Mahbub-Or-Rashid, Md. Satu, Md. Shahriare Tammim, Sanjana Ruhani Sunny, Farhana Akter Moni, Mohammad Ali Department of IoT and Robotics Engineering Bangabandhu Sheikh Mujibur Rahman Digital University Kaliakair Bangladesh Department of Computer Science and Engineering Bangladesh University of Business and Technology Mirpur Bangladesh Department of Management Information Systems Noakhali Science and Technology University Noakhali Bangladesh Department of Computer Science and Software Engineering Auburn University Auburn AL United States Department of Computer Science and Engineering Green University of Bangladesh Dhaka Bangladesh Faculty of Health and Behavioural Sciences School of Health and Rehabilitation Sciences The University of Queensland St Lucia Australia

The public’s health is seriously at risk from the coronavirus pandemic. Millions of people have already died as a result of this devastating illness, which affects countless people daily worldwide. Unfortunately, no specific therapeutic drugs or vaccines are available to cure patients completely. Therefore, early identification of infected individuals and their isolation can help reduce community transmission of COVID-19. Despite being commonly used, the reverse transcription polymerase chain reaction (RT-PCR) test is costly, time-consuming, and requires suitable kits, which are not always readily available. An alternative solution for the traditional RT-PCR test is machine learning and deep learning-based COVID-19 detection that utilizes clinical features of chest X-rays and computed tomography (CT) images. In this study, we conducted a detailed review of more than 100 recently published works to detect COVID-19-infected patients. Thus, different data preprocessing, data augmentation, image enhancement, feature extraction, machine learning, deep learning, Explainable Artificial Intelligence (AI) methods, etc. were explored to understand how these techniques were used to process images for identifying COVID-19. Additionally, we identified the current challenges in this field and suggested further research directions. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Chest X-ray Computed tomography COVID-19 Deep learning Machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimal Resource Allocation Method for Device-to-Device Communication in 5G Networks

引用

Computers, Materials & Continua 2022年第4期71卷 1-15页

作者： Fahd N.Al-Wesabi Imran Khan Saleem Latteef Mohammed Huda Farooq Jameel Mohammad Alamgeer Ali M.Al-Sharafi Byung Seo Kim Department of Computer Science King Khalid UniversityMuhayel AseerKSA Faculty of Computer and IT Sana’a UniversityYemen Department of Electrical Engineering University of Engineering and TechnologyPeshawarPakistan Department of Medical Instrumentation Techniques Engineering Electrical Engineering Technical CollegeMiddle Technical UniversityBaghdad10013Iraq Department of Information Systems King Khalid UniversityMayahel AseerKSA Department of Computer Science College of Computers and Information TechnologyUniversity of BishaKSA Department of Software and Communications Engineering Hongik UniversityKorea

With the rapid development of the next-generation mobile network,the number of terminal devices and applications is growing ***,how to obtain a higher data rate,wider network coverage and higher resource utilization in the limited spectrum resources has become the common research goal of ***-to-Device(D2D)communication technology and other frontier communication technologies have ***-to-Device communication technology is the technology that devices in proximity can communicate directly in cellular *** has become one of the key technologies of the fifth-generation mobile communications system(5G).D2D communication technology which is introduced into cellular networks can effectively improve spectrum utilization,enhance network coverage,reduce transmission delay and improve system throughput,but it would also bring complicated and various interferences due to reusing cellular resources at the same *** resource management is one of the most challenging and importing issues to give full play to the advantages of D2D *** resource allocation is an important factor that needs to be addressed in D2D ***,this paper proposes an optimization method based on the game-matching *** main idea is to model the optimization problem of the quality-of-experience based on user fairness and solve it through game-matching *** results show that the proposed algorithm effectively improved the resource allocation and utilization as compared with existing algorithms.

关键词： D2D communication resource allocation optimization networks

来源：评论

学校读者我要写书评

暂无评论

Interactive 3D Medical Image Segmentation with SAM 2

arXiv

引用

arXiv 2024年

作者： Shen, Chuyun Li, Wenhao Shi, Yuhang Wang, Xiangfeng Huang, Yifei School of Computer Science and Technology East China Normal University Shanghai200062 China School of Software Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai200092 China Shanghai United Imaging Healthcare Advanced Technology Research Institute Co. Ltd Shanghai201807 China School of Software Engineering East China Normal University Shanghai200062 China

Interactive medical image segmentation (IMIS) has shown significant potential in enhancing segmentation accuracy by integrating iterative feedback from medical professionals. However, the limited availability of enough 3D medical data restricts the generalization and robustness of most IMIS methods. The Segment Anything Model (SAM), though effective for 2D images, requires expensive semi-auto slice-by-slice annotations for 3D medical images. In this paper, we explore the zero-shot capabilities of SAM 2, the next-generation Meta SAM model trained on videos, for 3D medical image segmentation. By treating sequential 2D slices of 3D images as video frames, SAM 2 can fully automatically propagate annotations from a single frame to the entire 3D volume. We propose a practical pipeline for using SAM 2 in 3D medical image segmentation and present key findings highlighting its efficiency and potential for further optimization. Concretely, numerical experiments on the BraTS2020 and the medical segmentation decathlon datasets demonstrate that SAM 2 still has a gap with supervised methods but can narrow the gap in specific settings and organ types, significantly reducing the annotation burden on medical professionals. Our code will be open-sourced and available at https://***/Chuyun-Shen/SAM_2_Medical_3D. Copyright © 2024, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware Superpoint Graph Transformer for Weakly Supervised 3D Semantic Segmentation

引用

IEEE Transactions on Fuzzy systems 2025年第6期33卷 1899-1912页

作者： Fan, Yan Wang, Yu Zhu, Pengfei Hui, Le Xie, Jin Hu, Qinghua Tianjin University College of Intelligence and Computing Tianjin300350 China Ministry of Education of the People's Republic of China Engineering Research Center of City Intelligence and Digital Governance China Haihe Laboratory of Itai Tianjin China Northwestern Polytechnical University School of Electronics and Information Shaanxi Key Laboratory of Information Acquisition and Processing China Nanjing University of Science and Technology Pca Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

Weakly supervised 3D semantic segmentation has successfully mitigated the labor-intensive and time-consuming task of annotating 3D point clouds. However, reliably utilizing the minimal point-wise annotations for unlabeled data in complex and large-scale scenes is still challenging, such as only 20 points labeled in 2 million points. To tackle this challenge, we propose a new Uncertainty-aware Superpoint Graph Transformer (UaSGT) framework that utilizes minimal annotations for unlabeled data learning through reliable long-range supervision propagation from labeled superpoints to unlabeled superpoints. First, we propose a superpoint graph transformer to achieve long-range supervision propagation along the attention-based fuzzy subsets defined on superpoints. The attention-based fuzzy subset measures the membership of unlabeled superpoints to clusters centered on labeled superpoints. Second, we employ an uncertainty-aware membership rectification technique on the fuzzy subset to ensure reliable propagation among superpoints within the same category. This technique integrates an uncertainty prediction module to mask the influence of unreliable membership and a spatial prior refinement module to reduce uncertainty in intra-class membership degrees. Finally, experimental results on two large-scale benchmarks S3DIS and ScanNet-V2 demonstrate the superiority of our approach compared to the state-of-the-art with at least 90% annotation reduction, and our method also achieves comparable performance to fully supervised methods with less than 0.1% labeled points. Our code is available at https://***/fanyan0411/UaSGT. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

CNsum:Automatic Summarization for Chinese News Text

arXiv

引用

arXiv 2025年

作者： Zhao, Yu Huang, Songping Zhou, Dongsheng Ding, Zhaoyun Wang, Fei Nian, Aixin Science and Technology on Information Systems Engineering Laboratory National University of Defense Technology Changsha410000 China National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian University Dalian116000 China

Obtaining valuable information from massive data efficiently has become our research goal in the era of Big Data. Text summarization technology has been continuously developed to meet this demand. Recent work has also shown that transformer-based pre-trained language models have achieved great success on various tasks in Natural Language Processing (NLP). Aiming at the problem of Chinese news text summary generation and the application of Transformer structure on Chinese, this paper proposes a Chinese news text summarization model (CNsum) based on Transformer structure, and tests it on Chinese datasets such as THUCNews. The results of the conducted experiments show that CNsum achieves better ROUGE score than the baseline models, which verifies the outperformance of the model. © 2025, CC BY.

关键词： Big data

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：