检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Lohit, Suhas Singh, Rajhans Kulkarni, Kuldeep Turaga, Pavan Department of Electrical Computer and Electrical Engineering Department of Arts Media and Engineering Arizona State University TempeAZ United States Department of Electrical and Computer Engineering Carnegie Mellon University PittsburghPA United States

In resource-constrained environments, one can employ spatial multiplexing cameras to acquire a small number of measurements of a scene, and perform effective reconstruction or high-level inference using purely data-driven neural networks. However, once trained, the measurement matrix and the network are valid only for a single measurement rate (MR) chosen at training time. To overcome this drawback, we answer the following question: How can we jointly design the measurement operator and the reconstruction/inference network so that the system can operate over a range of MRs? To this end, we present a novel training algorithm, for learning rate-adaptive networks. Using standard datasets, we demonstrate that, when tested over a range of MRs, a rate-adaptive network can provide high quality reconstruction over a the entire range, resulting in up to about 15 dB improvement over previous methods, where the network is valid for only one MR. We demonstrate the effectiveness of our approach for sample-efficient object tracking where video frames are acquired at dynamically varying MRs. We also extend this algorithm to learn the measurement operator in conjunction with image recognition networks. Experiments on MNIST and CIFAR-10 confirm the applicability of our algorithm to different tasks. Copyright © 2018, The Authors. All rights reserved.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Fractal Graphene Patch Antennas and the THz Communications Revolution

引用

IOP Conference Series: Materials Science and engineering 2021年第1期1060卷

作者： J M Blackledge A Boretti L Rosa S Castelletto School of Electrical and Electronic Engineering Technological University Dublin Ireland Department of Computer Science University of Western Cape South Africa School of Mathematics Statistics and Computer Science University of KwaZulu-Natal South Africa Faculty of Arts Science and Technology Wrexham Glyndwr University of Wales UK Department of Mechanical Engineering College of Engineering Prince Mohammad Bin Fahd University Al Khobar Saudi Arabia Department of Engineering 'Enzo Ferrari' University of Modena and Reggio Emilia Modena Italy and Applied Plasmonics Laboratory Center for Micro-Photonics Swinburne University of Technology Australia School of Engineering Royal Melbourne Institute of Technology Australia

Fractal antennas have and are continuing to receive attention in regard to the future of wireless communications. This is because of their wide- and multi-band capabilities, the opportunity of fractal geometries to drive multiple resonances, and, the ability to make smaller and lighter antennas with fewer components and radiative elements with higher gains. Small scale (i.e. on the micro- and nano-scale) and ultra high frequency (in the Terahertz or THz range) fractal antennas composed of Graphene have the potential to enhance wireless communications at a data rate that is unprecedented, i.e. ∼ 1012 bits per second. A Fractal Graphene antenna is a high-frequency tuneable antenna for radio communications in the THz spectrum, enabling unique applications such as wireless nano-networks. This is because (mono-layer) Graphene is a one-atom-thick two-dimensional allotrope of Carbon with the highest known electrical conductivity that is currently unavailable in any other material, including metals such as Gold and Silver. Thus, combining the properties of Graphene with the self-affine characteristics of a fractal at the micro- and nano-scale, provides the potential to revolutionise communications, at least in the near field (the order of a few metres) for low power systems. In this paper, we consider the basic physics and some of the principle mathematical models associated with the development of this new disruptive technology in order to provide a guide to those engaged in current and future research, a fractal Graphene antenna being an example of an advanced material for demanding applications. This includes some example simulations on the THz field patterns generated by a fractal patch antenna composed of Graphene whose conductivity is taken to scale with the inverse of the frequency according to a 'Drude' model. The approach to generating THz sources using Graphene is also explored based on Infrared laser pumping to induce a THz photo-current.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Residual-guided in-loop filter using convolution neural network

arXiv

引用

arXiv 2019年

作者： Jia, Wei Li, Li Li, Zhu Zhang, Xiang Liu, Shan The Department of Computer Science and Electrical Engineering University of Missouri Kansas CityMO64110 United States The Department of Electronic Engineering and Informance Science University of Science and Technology of China China The Tencent Media Lab 2747 Park Blvd Palo AltoCA94306 United States

The block-based coding structure in the hybrid video coding framework inevitably introduces compression artifacts such as blocking, ringing, etc. To compensate for those artifacts, extensive filtering techniques were proposed in the loop of video codecs, which are capable of boosting the subjective and objective qualities of reconstructed videos. Recently, neural network based filters were presented with the power of deep learning from a large magnitude of data. Though the coding efficiency has been improved from traditional methods in High-Efficiency Video Coding (HEVC), the rich features and information generated by the compression pipeline has not been fully utilized in the design of neural networks. Therefore, in this paper, we propose the Residual-Reconstruction-based Convolutional Neural Network (RRNet) to further improve the coding efficiency to its full extent, where the compression features induced from bitstream in form of prediction residual is fed into the network as an additional input to the reconstructed frame. In essence, the residual signal can provide valuable information about block partitions and can aid reconstruction of edge and texture regions in a picture. Thus, more adaptive parameters can be trained to handle different texture characteristics. The experimental results show that our proposed RRNet approach presents significant BD-rate savings compared to HEVC and the state-of-the-art CNN-based schemes, indicating that residual signal plays a significant role in enhancing video frame reconstruction. Copyright © 2019, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Abdomen MRI Synthesis Based on Conditional GAN

Abdomen MRI Synthesis Based on Conditional GAN

引用

International Conference on Computational Science and Computational Intelligence (CSCI)

作者： Huan Yang Kaijian Xia Bi Anqi Pengjiang Qian Mohammad R. Khosravi School of Digital Media Jiangnan University Wuxi P.R. China The affiliated changshu hospital of soochow university Changshu China School of Computer Science and Engineering Changshu Institute of Technology Changshu P.R. China Department of Electrical and Electronic Engineering Telecommunications Group Shiraz University of Technology Shiraz Iran

ISBN: (数字)9781728155845

ISBN: (纸本)9781728155852

Obtaining different contrast images of the same anatomical location of the same subject can increase the diversity of diagnostic information. However, due to the cost constraints, it is often not possible to obtain sufficient different contrast images, and images in some contrasts may be corrupted by noise and artifacts. In this case, if these images with different contrasts can be generated from existing images, the diagnostic accuracy will be greatly improved. Here, we explore an end-to-end deep convolutional neural networks for multi-contrast MRI synthesis based on conditional generative adversarial networks (cGAN). The proposed approach preserves high-frequency details via an adversarial loss and a pixel-wise loss, to transform abdomen CT into abdomen MR. Paired MR-CT volumes of 10 patients are analyzed. A quantitative evaluation showed that the approach is capable to synthesize MR images that closely similar to reference MR images.

关键词： Computed tomography Magnetic resonance imaging Training Generative adversarial networks Fats Abdomen Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

The Potential of Generative Artificial Intelligence Across Disciplines: Perspectives and Future Directions

引用

The Journal of Data Education 2025年第1期65卷

作者： Keng-Boon Ooi Garry Wei-Han Tan Mostafa Al-Emran Mohammed A. Al-Sharafi Alexandru Capatina Amrita Chakraborty Yogesh K. Dwivedi Tzu-Ling Huang Arpan Kumar Kar Voon-Hsien Lee Xiu-Ming Loh Adrian Micu Patrick Mikalef Emmanuel Mogaji Neeraj Pandey Ramakrishnan Raman Nripendra P. Rana Prianka Sarker Anshuman Sharma Ching-I Teng Samuel Fosso Wamba Lai-Wan Wong a UCSI Graduate Business School UCSI University Kuala Lumpur Malaysiab FORE School of Management New Delhi Indiac Faculty of Business Design and Arts Swinburne University of Technology Sarawak Campus Kuching Malaysia a UCSI Graduate Business School UCSI University Kuala Lumpur Malaysiac Faculty of Business Design and Arts Swinburne University of Technology Sarawak Campus Kuching Malaysiad College of Business Administration Adamson University Manila Philippines e Faculty of Engineering & IT The British University in Dubai Dubai UAEf Department of Computer Techniques Engineering Dijlah University College Baghdad Iraq g Institute of Informatics and Computing in Energy Universiti Tenaga Nasional Selangor Malaysia h Department of Business Administration “Dunarea de Jos” University of Galati Galati Romania i Tech Talk New Delhi India j Digital Futures for Sustainable Business & Society Research Group School of Management Swansea University Bay Campus Swansea UKk Department of Management Symbiosis International (Deemed University) Pune India l Department of Information Management National Central University Taoyuan Taiwan m Department of Management Studies Indian Institute of Technology Delhi New Delhi India n Faculty of Business and Finance Universiti Tunku Abdul Rahman Kampar Malaysia o Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology Trondheim Norwayp Department of Technology Management SINTEF Digital Trondheim Norway q Keele Business School Keele University Keele UK r Indian Institute of Management Mumbai Mumbai India k Department of Management Symbiosis International (Deemed University) Pune India s College of Business and Economics Qatar University Doha Qatar t Business School Manchester Metropolitan University Manchester UK u Department of Marketing College of Business Administration Ajman university Ajman UAE v Graduate Institute of Management Chang Gung University Taoyuan Taiw

ABSTRACTIn a short span of time since its introduction, generative artificial intelligence (AI) has garnered much interest at both personal and organizational levels. This is because of its potential to cause drastic and widespread shifts in many aspects of life that are comparable to those of the Internet and smartphones. More specifically, generative AI utilizes machine learning, neural networks, and other techniques to generate new content (e.g. text, images, music) by analyzing patterns and information from the training data. This has enabled generative AI to have a wide range of applications, from creating personalized content to improving business operations. Despite its many benefits, there are also significant concerns about the negative implications of generative AI. In view of this, the current article brings together experts in a variety of fields to expound and provide multi-disciplinary insights on the opportunities, challenges, and research agendas of generative AI in specific industries (i.e. marketing, healthcare, human resource, education, banking, retailing, the workplace, manufacturing, and sustainable IT management).

关键词： Generative artificial intelligence machine learning large language model ChatGPT Bard

来源：评论

学校读者我要写书评

暂无评论

Coupling Rendering and Generative Adversarial Networks for Artificial SAS Image Generation

Coupling Rendering and Generative Adversarial Networks for A...

引用

OCEANS

作者： Albert Reed Isaac D. Gerg John D. McKay Daniel C. Brown David P. Williamsk Suren Jayasuriya School of Electrical Computer & Energy Engineering Arizona State University Tempe AZ USA School of Electrical Engineering and Computer Science Pennsylvania State University State College PA USA Applied Research Laboratory Pennsylvania State University State College PA USA Graduate Program in Acoustics Pennsylvania State University State College PA USA NATO STO Centre for Maritime Research & Experimentation La Spezia Italy School of Arts Media & Engineering Arizona State University Tempe AZ USA

There is a growing demand for large-scale Synthetic Aperture Sonar (SAS) datasets. This demand stems from data-driven applications such as Automatic Target Recognition (ATR) [1]-[3], segmentation [4] and oceanographic research of the seafloor, simulation for sensor prototype development and calibration [5], and even potential higher level tasks such as motion estimation [6] and micronavigation [7]. Unfortunately, the acquisition of SAS data is bottlenecked by the costly deployment of SAS imaging systems, and even when data acquisition is possible, the data is often skewed towards containing barren seafloor rather than objects of interest. This skew introduces a data imbalance problem wherein a dataset can have as much as a 1000-to-1 ratio of seafloor background to object-of-interest SAS image chips.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discussion and Practice of Film and Television Production:Innovation with Big-data

Discussion and Practice of Film and Television Production:In...

引用

作者： Fangjiao Li Yuqiang Zhu Xiang Zhang Rao Fu Litian Deng Digital Film and TV Production Faculty of International MediaCommunication University of China Computer Science and Technology Department of Computer Science and TechnologyTsinghua University Digital Media Arts School of Arts and MediaBeijing Normal University Software Engineering School of Computer Science and CybersecurityCommunication University of China

The significance of big data analysis strategy has been extended to more than the information conveyed by the data itself,particularly with the development of information *** the overall level of society and economy in contemporary world,practitioners for the film and television production industry are required to conduct an intrinsic and comprehensive analysis of market concerns and user needs to form a more scientific and perfect data analysis *** paper delves into the capabilities indispensable for the art and communication industry regarding the technology background and proposes effective methods for the market mechanism of film and television production.

关键词： big data Film and TV production discussion and practice

来源：评论

学校读者我要写书评

暂无评论

Music, Computing, and Health: A Roadmap for the Current and Future Roles of Music technology for Health Care and Well-Being

引用

Music and Science 2021年 4卷

作者： Agres, Kat R. Schaefer, Rebecca S. Volk, Anja van Hooren, Susan Holzapfel, Andre Dalla Bella, Simone Müller, Meinard de Witte, Martina Herremans, Dorien Ramirez Melendez, Rafael Neerincx, Mark Ruiz, Sebastian Meredith, David Dimitriadis, Theo Magee, Wendy L. Yong Siew Toh Conservatory of Music National University of Singapore Singapore Social and Cognitive Computing Department Institute of High Performance Computing A*STAR Singapore Institute for Psychology Health Medical Neuropsychology Unit Leiden University Leiden Netherlands Leiden Institute for Brain and Cognition Leiden University Leiden Netherlands Academy of Creative and Performing Arts Leiden University Leiden Netherlands Department of Information and Computing Sciences Utrecht University Utrecht Netherlands Faculty of Health care Department of Arts Therapies Zuyd University of Applied Sciences Heerlen Netherlands KenVaK Research Centre for the Arts Therapies and Psychomotricity Heerlen Netherlands Faculty of Psychology Open University of The Netherlands Heerlen Netherlands Division of Media Technology and Interaction Design KTH Royal Institute of Technology Stockholm Sweden International Laboratory for Brain Music and Sound Research (BRAMS) Outremont QC Canada Department of Psychology University of Montreal Montreal QC Canada Centre for Research on Brain Language and Music (CRBLM) Montreal QC Canada University of Economics and Human Sciences in Warsaw Warsaw Poland International Audio Laboratories Erlangen Friedrich-Alexander Universität Erlangen-Nürnberg Erlangen Germany HAN University of Applied Sciences Department of Arts Therapies and Psychological Studies Nijmegen Netherlands University of Amsterdam Research Institute of Child Development and Education Amsterdam Netherlands Treatment Centre for People with Mild Intellectual Disabilities and Psychiatric and Behavioral Disorders Gennep Netherlands Information Systems Technology and Design Singapore University of Technology and Design Singapore Music and Machine Learning Lab Music Technology Group Universitat Pompeu Fabra Barcelona Spain Faculty of EEMCS Interactive Intelligence Group Delft University of Technology Delft Netherlands Centre for Digital Music School of Electronic Engineerin

The fields of music, health, and technology have seen significant interactions in recent years in developing music technology for health care and well-being. In an effort to strengthen the collaboration between the involved disciplines, the workshop “Music, Computing, and Health” was held to discuss best practices and state-of-the-art at the intersection of these areas with researchers from music psychology and neuroscience, music therapy, music information retrieval, music technology, medical technology (medtech), and robotics. Following the discussions at the workshop, this article provides an overview of the different methods of the involved disciplines and their potential contributions to developing music technology for health and well-being. Furthermore, the article summarizes the state of the art in music technology that can be applied in various health scenarios and provides a perspective on challenges and opportunities for developing music technology that (1) supports person-centered care and evidence-based treatments, and (2) contributes to developing standardized, large-scale research on music-based interventions in an interdisciplinary manner. The article provides a resource for those seeking to engage in interdisciplinary research using music-based computational methods to develop technology for health care, and aims to inspire future research directions by evaluating the state of the art with respect to the challenges facing each field. © The Author(s) 2021.

关键词： health care interdisciplinarity MedTech music information retrieval (MIR) music neuroscience Music psychology music technology music therapy well-being

来源：评论

学校读者我要写书评

暂无评论

Coupling rendering and generative adversarial networks for artificial SAS image generation

arXiv

引用

arXiv 2019年

作者： Reed, Albert Gerg, Isaac D. McKay, John D. Brown, Daniel C. Williams, David P. Jayasuriya, Suren School of Electrical Computer & Energy Engineering Arizona State University TempeAZ United States School of Arts Media & Engineering Arizona State University TempeAZ United States Applied Research Laboratory Pennsylvania State University State College PA United States Graduate Program in Acoustics Pennsylvania State University State College PA United States School of Electrical Engineering and Computer Science Pennsylvania State University State College PA United States NATO STO Centre for Maritime Research & Experimentation La Spezia Italy

来源：评论

学校读者我要写书评

暂无评论

IoT-based Smart and Complex Systems：A Guest Editorial Report

引用

IEEE/CAA Journal of Automatica Sinica 2018年第1期5卷 69-73页

作者： Naiqi Wu Zhiwu Li Kamel Barkaoui Xiaoou Li Tadahiko Murata MengChu Zhou Institute of Systems Engineering Macao University of Science and Technology Macao 999078 China School of Electro-Mechanical Engineering Xidian University Xi'an 710071 China Conservatoire national des arts et mtiers Professeur des universit6s EPN5 Informatique Lab. Cedric-Vespa 2 rue Cont6 75141 Pads Cedex 03 France CINVESTAV-IPN Mexico Kansai University Japan Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ 07102-1982 USA IEEE

THE Industrial Revolution starting from about 1760 and ending at around 1840 has been viewed as the first Industrial *** features with the replacement of human and animal muscle power with steam and mechanical *** inc... 详细信息

关键词： In IoT-based Smart and Complex Systems:A Guest Editorial Report

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：