检索结果-内蒙古大学图书馆

22nd Annual Conference of the European Association for Machine Translation, EAMT 2020

作者： Gupta, Kamal Kumar Haque, Rejwanul Ekbal, Asif Bhattacharyya, Pushpak Way, Andy Department of Computer Science and Engineering Indian Institute of Technology Patna Patna India Adapt Centre School of Computing Dublin City University Dublin Ireland

ISBN: (纸本)9789893305898

In interactive machine translation (MT), human translators correct errors in automatic translations in collaboration with the MT systems, which is seen as an effective way to improve the productivity gain in translation. In this study, we model sourcelanguage syntactic constituency parse and target-language syntactic descriptions in the form of supertags as conditional context for interactive prediction in neural MT (NMT). We found that the supertags significantly improve productivity gain in translation in interactive-predictive NMT (INMT), while syntactic parsing somewhat found to be effective in reducing human efforts in translation. Furthermore, when we model this source- and target-language syntactic information together as the conditional context, both types complement each other and our fully syntax-informed INMT model shows statistically significant reduction in human efforts for a French- to-English translation task in a referencesimulated setting, achieving 4.30 points absolute (corresponding to 9.18% relative) improvement in terms of word prediction accuracy (WPA) and 4.84 points absolute (corresponding to 9.01% relative) reduction in terms of word stroke ratio (WSR) over the baseline. ©2020 The authors.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis and Power Allocation for Massive MIMO ISAC Systems

arXiv

引用

arXiv 2024年

作者： Nguyen, Nhan Thanh Nguyen, Van-Dinh Nguyen, Hieu V. Ngo, Hien Quoc Swindlehurst, A. Lee Juntti, Markku Centre for Wireless Communications University of Oulu P.O.Box 4500 FI-90014 Finland College of Engineering and Computer Science Viet Nam Center for Environmental Intelligence VinUniversity Vinhomes Ocean Park Hanoi100000 Viet Nam Faculty of Electronic and Telecommunication Engineering The University of Danang University of Science and Technology Da Nang50000 Viet Nam School of Electronics Electrical Engineering and Computer Science Queen’s University Belfast BelfastBT7 1NN United Kingdom Center for Pervasive Communications and Computing University of California IrvineCA92697 United States

Integrated sensing and communications (ISAC) is envisioned as a key feature in future wireless communications networks. Its integration with massive multiple-input-multiple-output (MIMO) techniques promises to leverage substantial spatial beamforming gains for both functionalities. In this work, we consider a massive MIMO-ISAC system employing a uniform planar array with zero-forcing and maximum-ratio downlink transmission schemes combined with monostatic radar-type sensing. Our focus lies on deriving closed-form expressions for the achievable communications rate and the Cramér–Rao lower bound (CRLB), which serve as performance metrics for communications and sensing operations, respectively. The expressions enable us to investigate important operational characteristics of massive MIMO-ISAC, including the mutual effects of communications and sensing as well as the advantages stemming from using a very large antenna array for each functionality. Furthermore, we devise a power allocation strategy based on successive convex approximation to maximize the communications rate while guaranteeing the CRLB constraints and transmit power budget. Extensive numerical results are presented to validate our theoretical analyses and demonstrate the efficiency of the proposed power allocation approach. © 2024, CC BY.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Flip Learning: Weakly Supervised Erase to Segment Nodules in Breast Ultrasound

arXiv

引用

arXiv 2025年

作者： Huang, Yuhao Chang, Ao Dou, Haoran Tao, Xing Zhou, Xinrui Cao, Yan Huang, Ruobing Frangi, Alejandro F. Bao, Lingyun Yang, Xin Ni, Dong National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Shenzhen University Medical School Shenzhen University Shenzhen China Lab Shenzhen University Shenzhen China Marshall Laboratory of Biomedical Engineering Shenzhen University Shenzhen China School of Computing University of Leeds Leeds United Kingdom Shenzhen RayShape Medical Technology Co. Ltd Shenzhen China Division of Informatics Imaging and Data Science School of Health Sciences University of Manchester Manchester United Kingdom Department of Computer Science School of Engineering University of Manchester Manchester United Kingdom Department of Electrical Engineering Department of Cardiovascular Sciences KU Leuven Belgium Alan Turing Institute London United Kingdom NIHR Manchester Biomedical Research Centre Manchester Academic Health Science Centre Manchester United Kingdom Department of Ultrasound Affiliated Hangzhou First People’s Hospital School of Medicine Westlake University China School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing China

Accurate segmentation of nodules in both 2D breast ultrasound (BUS) and 3D automated breast ultrasound (ABUS) is crucial for clinical diagnosis and treatment planning. Therefore, developing an automated system for nodule segmentation can enhance user independence and expedite clinical analysis. Unlike fully-supervised learning, weakly-supervised segmentation (WSS) can streamline the laborious and intricate annotation process. However, current WSS methods face challenges in achieving precise nodule segmentation, as many of them depend on inaccurate activation maps or inefficient pseudo-mask generation algorithms. In this study, we introduce a novel multi-agent reinforcement learning-based WSS framework called Flip Learning, which relies solely on 2D/3D boxes for accurate segmentation. Specifically, multiple agents are employed to erase the target from the box to facilitate classification tag flipping, with the erased region serving as the predicted segmentation mask. The key contributions of this research are as follows: 1) Adoption of a superpixel/supervoxel-based approach to encode the standardized environment, capturing boundary priors and expediting the learning process. 2) Introduction of three meticulously designed rewards, comprising a classification score reward and two intensity distribution rewards, to steer the agents’ erasing process precisely, thereby avoiding both under- and over-segmentation. 3) Implementation of a progressive curriculum learning strategy to enable agents to interact with the environment in a progressively challenging manner, thereby enhancing learning efficiency. Extensively validated on the large in-house BUS and ABUS datasets, our Flip Learning method outperforms state-of-the-art WSS methods and foundation models, and achieves comparable performance as fully-supervised learning algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Improving 6G Network Safety, Privacy, and Resource Efficiency via the Application of Machine Learning and Network Data Analytics

Improving 6G Network Safety, Privacy, and Resource Efficienc...

引用

Communications and Information Technologies (GCCIT), Global Conference on

作者： Supriya Rai Manoj Chandra Lohani K. Ranjith Singh Sukhman Ghumman Swati Bula Patil Mythili V School of Management - UG Management JAIN (Deemed to be University) Bangalore Karnataka School of Computing Graphic Era Hill University Haldwani Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Computer Science Karpagam Academy of Higher Education Coimbatore Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India IT Vishwakarma Institute of Technology Pune India Department of Science and Humanities Prince Shri Venkateshwara Padmavathy Engineering College Chennai

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

The 6G era of networks is tightly tied to intelligent network orchestration while administration, but the cloudification of networks using a micro-services-oriented architecture is a well-known element of 5G. It follows that the proposed 6G paradigm heavily relies on AI, ML, and DL. Proactive threat identification, smart mitigation tactics, and assurance that 6G networks would be self-sustaining are essential for future end-to-end network automation. In order to solidify and enhance AI's position in 6G network security, this article delves at potential AI applications in 6G security. To get there, our research reworked an existing 6G network anomaly detection system to make it operate with ensemble learning (EL) to communicate networks. In order to protect 6G user data from unauthorized access, resale, intoxication, and free-riding attacks, we offer a thorough framework for detecting data attacks that is optimized for secure aggregation using the Deep Reinforcement learning - PPO algorithm. To guard against data poisoning, unauthorized data sources, and mistakes in data aggregation, we use a set of encrypted data auditing tools. We have also performed analysis, evaluated many prospective security strategies, and suggested the best security measures for certain 6G situations. the Krull Herd-Advanced Encryption Standard (KH-AES) algorithm for secure data transmissions. To use IDS, this study makes use of the NSL-KDD dataset. Probing, normal, U2R, DoS, R2L, and unidentified were the six assaults used to categorize the data. Classification results are heavily affected by the weights in HCNN layers. When compared to well-known methods, the suggested system outperforms them when it comes of FS, classifications, and data sharing security.

关键词： 6G mobile communication Training Data privacy Accuracy Uncertainty Soft sensors Network security Real-time systems Encryption Standards

来源：评论

学校读者我要写书评

暂无评论

A Review Analysis: Comparative Study On Various Machine Learning Techniques for Load Forecasting In Electric Power Distribution System with Multiprocessing

A Review Analysis: Comparative Study On Various Machine Lear...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Anjali Naudiyal Kapil Joshi Ajay Singh Gunjan Chhabra Harishchander Anandaram Anil Kumar School of Applied and Life Sciences Uttaranchal University Dehradun Premnagar India Computer Science and Engineerig Uttaranchal University Premnagar Dehradun India Deptt. of CSE Graphic Era Hill University Dehradun Centre for Computational Engineering and Networking Amrita School of Artificial Intelligence Coimbatore Amrita Vishwa Vidyapeetham India School of Computing DIT University Dehradun India

Contemporary electricity usage is rising every day, making it more challenging to predict it in advance. Grids have been replaced with smart meters to provide electricity estimation. Industrial, residential, and commercial loads are primarily calculated load in these three sectors. Electricity was simple to estimate as long as the consumption was minimal, but as consumption has increased, electricity has now evolved into a dataset. Using past performance and probabilistic data, load forecasting is used to forecast future outcomes. Three categories exist for load forecasting where first is long-term load forecasting which is also known as LTLF, predicted to last for three to five years; second is medium-term load forecasting which is also known as MTLF, predicted to last for three months to three years; and third is short-term load forecasting which is also known as STLF, predicted to one day to six weeks are covered under the predicting period. Several variables, like the weather, the rate of expansion, and new clients, have an impact on STLF. In this study, machine learning methods are used to analyze data from smart meters related to energy consumption. This study illustrates how accurate future forecasts of electricity consumption or production may be produced using machine learning techniques by contrasting the multiprocessing machine learning techniques used in STLF with data variables.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Coded Aperture-Based Self-wavefront Interference Using Transverse Splitting Holography

Coded Aperture-Based Self-wavefront Interference Using Trans...

引用

Next Generation Electronics (NEleX), International Conference on

作者： Narmada Joshi Agnes Pristy Ignatius Xavier Francis Gracy Arockiaraj Aravind Simon John Francis Rajeswary Saulius Juodkazis Joseph Rosen Aile Tamm Vijayakumar Anand Institute of Physics University of Tartu Estonia School of Electrical and Computer Engineering Ben Gurion University of the Negev Israel Optical Sciences Center and ARC Training Centre in Surface Engineering for Advanced Materials (SEAM) Swinburne University of Technology Australia Tokyo Tech World Research Hub Initiative (WRHI) School of Materials and Chemical Technology Tokyo Institute of Technology Japan Optical Sciences Center and ARC Training Centre in Surface Engineering for Advanced Materials (SEAM) School of Science Computing and Engineering Technologies Swinburne University of Technology Hawthorn Melbourne Australia

Self-wavefront interference transverse splitting holography (SWITSH) is a recently developed holographic technique to solve a fundamental problem in the manufacturing of large-area diffractive lenses. In SWITSH, a low NA diffractive lens modulates the light from an object, and the modulated light is interfered with light from the same object that reaches beyond the aperture of the diffractive lens. The resulting self-interference hologram is processed with the pre-recorded point spread hologram using the Lucy-Richardson-Rosen algorithm. Since the self-interference hologram is formed by collecting light beyond the NA of the diffractive lens, it acquires the object information corresponding to the higher spatial frequencies of the object. Consequently, a higher imaging resolution is obtained in SWITSH compared to that of direct imaging with a diffractive lens. In the proof-of-concept study, a resolution improvement of an order was demonstrated. However, the optical architecture of the first version of SWITSH was not optimal, as the strength of the self-interference signal was weak. In this study, we improve SWITSH using different coded apertures, such as axicon and spiral element. An improvement in the strength of the self-interference signal was noticed with the axicon and spiral element. Simulation and experimental results using a diffractive lens, axicon and spiral element are presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence for geoscience:Progress,challenges,and perspectives

引用

The Innovation 2024年第5期5卷 136-160,135页

作者： Tianjie Zhao Sheng Wang Chaojun Ouyang Min Chen Chenying Liu Jin Zhang Long Yu Fei Wang Yong Xie Jun Li Fang Wang Sabine Grunwald Bryan MWong Fan Zhang Zhen Qian Yongjun Xu Chengqing Yu Wei Han Tao Sun Zezhi Shao Tangwen Qian Zhao Chen Jiangyuan Zeng Huai Zhang Husi Letu Bing Zhang Li Wang Lei Luo Chong Shi Hongjun Su Hongsheng Zhang Shuai Yin Ni Huang Wei Zhao Nan Li Chaolei Zheng Yang Zhou Changping Huang Defeng Feng Qingsong Xu Yan Wu Danfeng Hong Zhenyu Wang Yinyi Lin Tangtang Zhang Prashant Kumar Antonio Plaza Jocelyn Chanussot Jiabao Zhang Jiancheng Shi Lizhe Wang Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China School of Computer Science China University of GeosciencesWuhan 430078China State Key Laboratory of Mountain Hazards and Engineering Resilience Institute of Mountain Hazards and EnvironmentChinese Academy of SciencesChengdu 610299China Key Laboratory of Virtual Geographic Environment(Ministry of Education of PRC) Nanjing Normal UniversityNanjing 210023China Data Science in Earth Observation Technical University of Munich80333 MunichGermany The National Key Laboratory of Water Disaster Prevention Yangtze Institute for Conservation and DevelopmentHohai UniversityNanjing 210098China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China School of Geographical Sciences Nanjing University of Information Science and TechnologyNanjing 210044China State Key Laboratory of Soil and Sustainable Agriculture Institute of Soil ScienceChinese Academy of SciencesNanjing 210008China Soil Water and Ecosystem Sciences DepartmentUniversity of FloridaPO Box 110290GainesvilleFLUSA Materials Science Engineering Program Cooperating Faculty Member in the Department of Chemistry and Department of Physics Astronomy University of CaliforniaCaliforniaRiversideCA 92521USA Institute of Remote Sensing and Geographical Information System School of Earth and Space SciencesPeking UniversityBeijing 100871China Key Laboratory of Computational Geodynamics University of Chinese Academy of SciencesBeijing 100049China International Research Center of Big Data for Sustainable Development Goals Beijing 100094China College of Geography and Remote Sensing Hohai UniversityNanjing 211100China Department of Geography The University of Hong KongHong Kong 999077SARChina Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Nanjing 210044China School of Environmental Science and Engineering Nanjing University of Information Science&TechnologyNanjing 210044China Collaborative Inno

This paper explores the evolution of geoscientific inquiry,tracing the progression from traditional physics-based models to modern data-driven approaches facilitated by significant advancements in artificial intelligence(AI)and data collection *** models,which are grounded in physical and numerical frameworks,provide robust explanations by explicitly reconstructing underlying physical ***,their limitations in comprehensively capturing Earth’s complexities and uncertainties pose challenges in optimization and real-world *** contrast,contemporary data-driven models,particularly those utilizing machine learning(ML)and deep learning(DL),leverage extensive geoscience data to glean insights without requiring exhaustive theoretical *** techniques have shown promise in addressing Earth science-related ***,challenges such as data scarcity,computational demands,data privacy concerns,and the“black-box”nature of AI models hinder their seamless integration into *** integration of physics-based and data-driven methodologies into hybrid models presents an alternative *** models,which incorporate domain knowledge to guide AI methodologies,demonstrate enhanced efficiency and performance with reduced training data *** review provides a comprehensive overview of geoscientific research paradigms,emphasizing untapped opportunities at the intersection of advanced AI techniques and *** examines major methodologies,showcases advances in large-scale models,and discusses the challenges and prospects that will shape the future landscape of AI in *** paper outlines a dynamic field ripe with possibilities,poised to unlock new understandings of Earth’s complexities and further advance geoscience exploration.

关键词： Earth utilizing landscape

来源：评论

学校读者我要写书评

暂无评论

Anisotropy in the Human Placenta in Pregnancies Complicated by Fetal Growth Restriction

Anisotropy in the Human Placenta in Pregnancies Complicated ...

引用

Workshop on Visualization and Processing of Anisotropy in Imaging, Geometry, and Astronomy, 2018

作者： Slator, Paddy J. Ho, Alison Bakalis, Spyros Jackson, Laurence Chappell, Lucy C. Alexander, Daniel C. Hajnal, Joseph V. Rutherford, Mary Hutter, Jana Centre for Medical Image Computing Department of Computer Science University College London London United Kingdom Women’s Health Department King’s College London London United Kingdom Centre for the Developing Brain School of Biomedical Engineering and Imaging Sciences King’s College London London United Kingdom Biomedical Engineering Department School of Biomedical Engineering and Imaging Sciences King’s College London London United Kingdom

ISBN: (纸本)9783030562144

The placenta has a unique structure, which enables the transfer of oxygen and nutrients from the mother to the developing fetus. Abnormalities in placental structure are associated with major complications of pregnancy;for instance, changes in the complex branching structures of fetal villous trees are associated with fetal growth restriction. Diffusion MRI has the potential to measure such fine placental microstructural details. Here, we present in-vivo placental diffusion MRI scans from controls and pregnancies complicated by fetal growth restriction. We find that after 30 weeks’ gestation fractional anisotropy is significantly higher in placentas associated with growth restricted pregnancies. This shows the potential of diffusion MRI derived measures of anisotropy for assessing placental function during pregnancy. © 2021, The Author(s).

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Automated Controller Placement for Software-Defined Networks to Resist DDoS Attacks

引用

computers, Materials & Continua 2021年第9期68卷 3147-3165页

作者： Muhammad Reazul Haque Saw Chin Tan Zulfadzli Yusoff Kashif Nisar Lee Ching Kwang Rizaludin Kaspin Bhawani Shankar Chowdhry Rajkumar Buyya Satya Prasad Majumder Manoj Gupta Shuaib Memon Faculty of Computing&Informatics Multimedia UniversityPersiaran MultimediaCyberjaya63100SelangorMalaysia Faculty of Engineering Multimedia UniversityPersiaran MultimediaCyberjaya63100SelangorMalaysia Faculty of Computing and Informatics University Malaysia SabahJalan UMSKota Kinabalu Sabah88400Malaysia Telekom Malaysia Research&Development TM Innovation CentreCyberjaya63000SelangorMalaysia National Center of Robotics and Automation Mehran University of Engineering&TechnologyJamshoroPakistan Department of Computer Science and Engineering Hanyang UniversitySeoul04763South Korea School of Electrical and Electronic Engineering Nanyang Technological University639798Singapore Cloud Computing and Distributed Systems Laboratory The University of MelbourneMelbourneVIC 3053Australia Department of Electrical and Electronic Engineering Bangladesh University of Engineering and Technology(BUET)Dhaka1205Bangladesh Department of Electronics and Communication Engineering JECRC UniversityVidhaniJaipur303905India Auckland Institute of Studies Mt AlbertAucklandNew Zealand

In software-defined networks(SDNs),controller placement is a critical factor in the design and planning for the future Internet of Things(IoT),telecommunication,and satellite communication *** research has concentrated largely on factors such as reliability,latency,controller capacity,propagation delay,and energy ***,SDNs are vulnerable to distributed denial of service(DDoS)attacks that interfere with legitimate use of the *** ever-increasing frequency of DDoS attacks has made it necessary to consider them in network design,especially in critical applications such as military,health care,and financial services networks requiring high *** propose a mathematical model for planning the deployment of SDN smart backup controllers(SBCs)to preserve service in the presence of DDoS *** a number of input parameters,our model has two distinct ***,it determines the optimal number of primary controllers to place at specific locations or nodes under normal operating ***,it recommends an optimal number of smart backup controllers for use with different levels of DDoS *** goal of the model is to improve resistance to DDoS attacks while optimizing the overall cost based on the *** simulated results demonstrate that the model is useful in planning for SDN reliability in the presence of DDoS attacks while managing the overall cost.

关键词： SDN automated controller placement SBC ILP DDoS attack

来源：评论

学校读者我要写书评

暂无评论

Preprocessing Techniques for Enhancing Vision-Based Detection System for Tire Sidewall Extraction

Preprocessing Techniques for Enhancing Vision-Based Detectio...

引用

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Jia Hao Loo Veronica Lestari Jauw Chin Seong Lim Khairul-Rijal Sarmin Nunung Nurul Qomariyah Ahmad Nurul Fajar Department of Mechanical Materials and Manufacturing Engineering University of Nottingham Malaysia Malaysia Continental Tyre Technology Centre Malaysia Petaling Jaya Malaysia Computer Science Department School of Computing and Creative Arts Bina Nusantara University Jakarta Indonesia Information System Management Department BINUS Graduate Program-Master Information Systems Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

This study aims to develop a system for extracting crucial information from tire sidewalls using Optical Character Recognition (OCR). Initially, images of tire were captured manually by smartphone cameras, including Redmi 9T, iPhone 11, and Galaxy S23 Ultra. The captured images are then transferred to a computer for storage. Subsequently, these images were cropped according to the boundaries identified by Hough Circle Transform (HCT). The cropped images were then further pre-processed. During the pre-processing phase, geometrical transformation and image sharpening techniques are applied to enhance the clarity and readability of the text images. The text is then extracted using Google Vision, with the extracted text categorized by size, DOT, brand and pattern. The results indicated that the effectiveness of image pre-processing was constrained by the accuracy of circle detection, which reached a maximum rate of 87.1%. This causes parts of the text to be cut out inaccurately, leading to a suboptimal extraction accuracy of 55.65%. It is also observed that the Redmi 9T camera produced inconsistent results compared to other devices. Specifically, the iPhone 11 and Samsung Galaxy S23 Ultra demonstrated superior extraction accuracies of 69.71% and 66.37%, respectively, whereas the Redmi 9T achieved a lower extraction accuracy of 37.76%.

关键词： Accuracy Optical character recognition Text categorization Lighting Transforms US Department of Transportation Cameras Tires Internet Data mining

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：