检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Wang, Rui Wei, Zhihua Duan, Haoran Ji, Shouling Long, Yang Hong, Zhen The Department of Computer Science and Technology Tongji University Shanghai201804 China The Department of Computer Science Durham University DurhamDH1 3LE United Kingdom The NESA Lab College of Computer Science and Technology Zhejiang University Hangzhou310027 China The Institute of Cyberspace Security The College of Information Engineering Zhejiang University of Technology Hangzhou310023 China

Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing, and memory. Discovering the specialized CNN that meets a specific constraint requires a substantial effort of human experts. Compared with hand-designed approaches, neural architecture search (NAS) appears as a practical technique in automating the manual architecture design process and has attracted increasing interest in spoken language processing tasks such as speaker recognition. In this paper, we propose EfficientTDNN, an efficient architecture search framework consisting of a TDNN-based supernet and a TDNN-NAS algorithm. The proposed supernet introduces temporal convolution of different ranges of the receptive field and feature aggregation of various resolutions from different layers to TDNN. On top of it, the TDNN-NAS algorithm quickly searches for the desired TDNN architecture via weight-sharing subnets, which surprisingly reduces computation while handling the vast number of devices with various resources requirements. Experimental results on the VoxCeleb dataset show the proposed EfficientTDNN enables approximate 1013 architectures concerning depth, kernel, and width. Considering different computation constraints, it achieves a 2.20% equal error rate (EER) with 204M multiply-accumulate operations (MACs), 1.41% EER with 571M MACs as well as 0.94% EER with 1.45G MACs. Comprehensive investigations suggest that the trained supernet generalizes subnets not sampled during training and obtains a favorable trade-off between accuracy and efficiency. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Turnkey deterministic soliton crystal generation

arXiv

引用

arXiv 2024年

作者： Yang, Xinyu Zhu, Xiaotian Murray, Caitlin Paryoonyong, Chawaphon Xu, Xingyuan Tan, Mengxi Morandotti, Roberto Little, Brent E. Moss, David J. Chu, Sai T. Corcoran, Bill Su, Donglin School of Electronic and Information Engineering Beihang University Beijing100191 China Department of Physics and Material Science City University of Hong Kong Tat Chee Avenue Hong Kong Department of Electrical and Computer System Engineering Monash University ClaytonVIC3168 Australia ARC Centre of Excellence in Optical Microcombs for Breakthrough Science Australia State Key Laboratory of Information Photonics and Optical Communications Beijing University of Posts and Telecommunications Beijing100876 China INRS-Énergie Matériaux et Télécommunications 1650 Boulevard Lionel-Boulet VarennesQCJ3X 1S2 Canada QXP Technologies Inc. Xi’an China Optical Sciences Centre Swinburne University of Technology HawthornVIC3122 Australia

The deterministic generation of robust soliton comb has significant meaning for the optical frequency combs to be widely used in various applications. As a novel form of microcomb, Soliton crystal holds the advantages of easy generation, high conversion efficiency, and excellent thermal robustness. Here, we report the turnkey deterministic generation of ‘Palm-like’ soliton crystal with a free-running scheme. The robustness of the turnkey soliton crystal generation is also investigated in multiple aspects, including the success rate, the thermal robustness, and the long-term stability. The experiment results reveal our turnkey soliton crystal can achieve nearly a 100% success rate with a power variation less than ±1.5 dB over one hundred trials of two samples, is insensitive to thermal effect, and is robust to the environment during four-hour laboratory time. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep semantic segmentation for MRI brain tumor

引用

AIP Conference Proceedings 2022年第1期2400卷

作者： Assef Raad Hmeed Salah A. Aliesawi Wesam M. Jasim 1Department of Students Affairs and Registration – University of Anbar – Ramadi – Iraq 2College of Computer science and Information Technology – University of Anbar – Ramadi – Iraq

The Magnetic Resonance Images (MRI) the segmentation of brain tumor is quite possibly the most troublesome medical images segmentation and it has many challenges because the tumor has no specific shape or size, not found in a specific place of the brain and contains three sub-areas (Full Tumor FT, Enhanced Tumor ET and Tumor Core TC). The Manual segmentation is extremely difficult and prone to mistakes. In this research the semantic segmentation is used by applying the U-net model, which is a "Fully Convolutional Network (FCN)" algorithm on BraTS 2018 that contains four modalities (Flair, T2, T1,T1c). The results were promised by segmenting the brain tumor within three sub-areas (FT, ET and TC) and the results evaluated using standard brain tumor segmentation metrics. The proposed system achieves "Mean Dice Similarity Coefficient" metric; It is 0.72, 0.86, 0.75 for ET, FT and TC, respectively. Additionally, the "Median Dice Similarity Coefficient" metric is 0.81, 0.91, 0.85 for ET, FT and TC, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine learning for modelling unstructured grid data in computational physics: a review

arXiv

引用

arXiv 2025年

作者： Cheng, Sibo Bocquet, Marc Ding, Weiping Finn, Tobias Sebastian Fu, Rui Fu, Jinlong Guo, Yike Johnson, Eleda Li, Siyi Liu, Che Moro, Eric Newton Pan, Jie Piggott, Matthew Quilodran, Cesar Sharma, Prakhar Wang, Kun Xiao, Dunhui Xue, Xiao Zeng, Yong Zhang, Mingrui Zhou, Hao Zhu, Kewei Arcucci, Rossella CEREA ENPC EDF R&D Institut Polytechnique de Paris Île-de-France France School of Artificial Intelligence and Computer Science Nantong University Jiangsu Nantong226019 China School of Mathematical Sciences Key Laboratory of Intelligent Computing and Applications Tongji University Shanghai200092 China School of Engineering and Materials Science Faculty of Science and Engineering Queen Mary University of London LondonE1 4NS United Kingdom Zienkiewicz Centre for Modelling Data and AI Faculty of Science and Engineering Swansea University SwanseaSA1 8EN United Kingdom Department of Computer Science and Engineering Hong Kong university of science and technology Hong Kong Department of Earth Science & Engineering Imperial College London LondonSW7 2AZ United Kingdom Tianjin Key Laboratory of Imaging and Sensing Microelectronics Technology School of Microelectronics Tianjin University Tianjin300072 China Centre for Health Informatics Cumming School of Medicine University of Calgary CalgaryABT2N 1N4 Canada Department of Community Health Sciences Cumming School of Medicine University of Calgary CalgaryABT2N 1N4 Canada Undaunted Grantham Institute for Climate Change and the Environment Imperial College London LondonSW7 2AZ United Kingdom Culham Campus AbingdonOX14 3DB United Kingdom Centre for Computational Science Department of Chemistry University College London LondonWC1E 6BT United Kingdom Concordia Institute for Information Systems Engineering Concordia University MontrealQCH3G 1M8 Canada School of Mechanical Medical and Process Engineering Faculty of Engineering Queensland University of Technology BrisbaneQLD Australia Department of Chemical Engineering University College London LondonWC1E 6BT United Kingdom

Unstructured grid data are essential for modelling complex geometries and dynamics in computational physics. Yet, their inherent irregularity presents significant challenges for conventional machine learning (ML) techniques. This paper provides a comprehensive review of advanced ML methodologies designed to handle unstructured grid data in high-dimensional dynamical systems. Key approaches discussed include graph neural networks, transformer models with spatial attention mechanisms, interpolation-integrated ML methods, and meshless techniques such as physics-informed neural networks. These methodologies have proven effective across diverse fields, including fluid dynamics and environmental simulations. This review is intended as a guidebook for computational scientists seeking to apply ML approaches to unstructured grid data in their domains, as well as for ML researchers looking to address challenges in computational physics. It places special focus on how ML methods can overcome the inherent limitations of traditional numerical techniques and, conversely, how insights from computational physics can inform ML development. To support benchmarking, this review also provides a summary of open-access datasets of unstructured grid data in computational physics. Finally, emerging directions such as generative models with unstructured data, reinforcement learning for mesh generation, and hybrid physics-data-driven paradigms are discussed to inspire future advancements in this evolving field. © 2025, CC BY-NC-SA.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Specialty optical fibers for advanced sensing applications

引用

Opto-Electronic Science 2023年第2期2卷 1-26页

作者： Huanhuan Liu Dora Juan Juan Hu Qizhen Sun Lei Wei Kaiwei Li Changrui Liao Bozhe Li Cong Zhao Xinyong Dong Yuhan Tang Yihong Xiao Gerd Keiser Perry Ping Shum Guangdong Key Laboratory of Integrated Optoelectronics Intellisense Department of Electronic and Electrical EngineeringSouthern University of Science and TechnologyShenzhen 518055China Institute for Infocomm Research(I2R) Agency for ScienceTechnology and Research(A*STAR)1 Fusionopolis Way#21-01Connexis South TowerSingapore 138632Singapore School of Electrical and Electronic Engineering Nanyang Technological University50 Nanyang AvenueSingapore 639798Singapore School of Optical and Electronic Information National Engineering Laboratory for Next Generation Internet Access SystemWuhan National Laboratory for OptoelectronicsHuazhong University of Science and TechnologyWuhan 430074China Key Laboratory of Bionic Engineering of Ministry of Education Jilin UniversityChangchun 130022China Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education/Guangdong Province College of Physics and Optoelectronic EngineeringShenzhen UniversityShenzhen 518060China Shenzhen Key Laboratory of Photonic Devices and Sensing Systems for Internet of Things Guangdong and Hong Kong Joint Research Centre for Optical Fibre SensorsShenzhen UniversityShenzhen 518060China Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ) Shenzhen 518107China Guangdong Provincial Key Laboratory of Information Photonics Technology School of Information EngineeringGuangdong University of TechnologyGuangzhou 510006China Department of Electrical&Computer Engineering Boston UniversityBoston 02215USA Pengcheng Laboratory Shenzhen 518055China

Optical fiber technology has changed the world by enabling extraordinary growth in world-wide communications and *** rapid development and wide deployment of optical fiber sensors are driven by their excellent sensing performance with outstanding flexibility,functionality,and ***,the research on specialty optical fibers is playing a critical role in enabling and proliferating the optical fiber sensing *** paper overviews recent developments in specialty optical fibers and their sensing *** specialty optical fibers are reviewed based on their innovations in special structures,special materials,and technologies to realize lab in/on a *** overview of sensing applications in various fields is *** prospects and emerging research areas of specialty optical fibers are also discussed.

关键词： specialty optical fibers photonic crystal fiber multifunctional multi-material fibers lab in/on fiber

来源：评论

学校读者我要写书评

暂无评论

Photonic real time video image signal processor at 17Tb/s based on a Kerr microcomb

arXiv

引用

arXiv 2024年

作者： Tan, Mengxi Xu, Xingyuan Boes, Andreas Corcoran, Bill Nguyen, Thach G. Chu, Sai T. Little, Brent E. Morandotti, Roberto Wu, Jiayang Mitchell, Arnan Moss, David J. School of Electronic and Information Engineering Beihang University Beijing100191 China Optical Sciences Centre Swinburne University of Technology HawthornVIC3122 Australia School of Engineering RMIT University MelbourneVIC3001 Australia State Key Laboratory of Information Photonics and Optical Communications Beijing University of Posts and Telecommunications Beijing100876 China School of Electrical and Electronic Engineering University of Adelaide Adelaide5005 SA Australia Department of Electrical and Computer System Engineering Monash University ClaytonVIC3168 Australia Department of Physics and Material Science City University of Hong Kong Tat Chee Avenue Hong Kong Xi’an Institute of Optics and Precision Mechanics CAS Xi’an China INRS-Énergie Matériaux et Télécommunications 1650 Boulevard Lionel-Boulet VarennesQCJ3X 1S2 Canada

Signal processing has become central to many fields, from coherent optical telecommunications, where it is used to compensate signal impairments, to video image processing. Image processing is particularly important for observational astronomy, medical diagnosis, autonomous driving, big data and artificial intelligence. For these applications, signal processing traditionally has mainly been performed electronically. However these, as well as new applications, particularly those involving real time video image processing, are creating unprecedented demand for ultrahigh performance, including high bandwidth and reduced energy consumption. Here, we demonstrate a photonic signal processor operating at 17 Terabits/s and use it to process video image signals in real-time. The system processes 400,000 video signals concurrently, performing 34 functions simultaneously that are key to object edge detection, edge enhancement and motion blur. As compared with spatial-light devices used for image processing, our system is not only ultra-high speed but highly reconfigurable and programable, able to perform many different functions without any change to the physical hardware. Our approach is based on an integrated Kerr soliton crystal microcomb, and opens up new avenues for ultrafast robotic vision and machine learning. © 2024, CC BY.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Intelligent decoding method for Ground-penetrating radar based on improved YOLOv5

Intelligent decoding method for Ground-penetrating radar bas...

引用

computer, Big Data and Artificial Intelligence (ICCBD+AI), International Conference on

作者： ZeYu Chen YongKang Wang HongLiang Liu Chuan Wang XinBo Jiang Ning Zhang Zhen Huang Lei Jiang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) JiNan China Technological Innovation Department Shandong Hi-Speed Group Co Ltd JiNan China School of Qilu Transportation Shandong University JiNan China No.1 Engineering Development Co. Ltd. of China Railway 14Th Bureau Group RiZhao China

ISBN: (数字)9798331533991

ISBN: (纸本)9798331534004

Ground-penetrating radar (GPR) is a non-invasive detection technique that effectively gathers information about subsurface materials. In tunneling projects, GPR can provide a fast and accurate forecast of the geological conditions in front of tunnel boring, which provides an important reference basis for tunnel construction. Currently, the interpretation of GPR images relies heavily on manual expertise, resulting in low efficiency and minimal automation. This creates an urgent need for effective and accurate identification of poor geological conditions depicted in radar images. In this study, we present the GPR-YOLOv5 model, which is designed to detect unfavorable geologic features ahead of the tunnel face from GPR images. We enhance this model with the CA attention mechanism, GSConv module, ghostC3 module, and the VariFocal loss function to improve decoding accuracy while minimizing computational load. Additionally, we integrate this algorithm with established modern object detection techniques, and our experimental results demonstrate its effectiveness.

关键词： YOLO Accuracy Ground penetrating radar Attention mechanisms Geology Computational modeling Radar imaging Tunneling Decoding Load modeling

来源：评论

学校读者我要写书评

暂无评论

Nonlinear feedforward enabling quantum computation

arXiv

引用

arXiv 2022年

作者： Sakaguchi, Atsushi Konno, Shunya Hanamura, Fumiya Asavanant, Warit Takase, Kan Ogawa, Hisashi Marek, Petr Filip, Radim Yoshikawa, Jun-Ichi Huntington, Elanor Yonezawa, Hidehiro Furusawa, Akira Department of Applied Physics School of Engineering The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo113-8656 Japan Optical Quantum Computing Research Team RIKEN Center for Quantum Computing 2-1 Hirosawa Saitama Wako351-0198 Japan Department of Optics Palacký University 17. listopadu 1192/12 Olomouc77146 Czech Republic Centre for Quantum Computation and Communication Technology and Energy and Materials Engineering College of Engineering and Computer Science Australian National University CanberraACT2600 Australia Centre for Quantum Computation and Communication Technology School of Engineering and Information Technology University of New South Wales CanberraACT2600 Australia

Measurement-based quantum computation with optical time-domain multiplexing is a promising method to realize a quantum computer from the viewpoint of scalability. Fault tolerance and universality are also realizable by preparing appropriate resource quantum states and electro-optical feedforward that is altered based on measurement results. While a linear feedforward has been realized and become a common experimental technique, nonlinear feedforward was unrealized until now. In this paper, we demonstrate that a fast and flexible nonlinear feedforward realizes the essential measurement required for fault-tolerant and universal quantum computation. Using non-Gaussian ancillary states we observed 10% reduction of the measurement excess noise relative to classical vacuum ancilla. © 2022, CC BY.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Internet connected patient healthcare monitoring in smart phones using Raspberry Pi

引用

AIP Conference Proceedings 2022年第1期2519卷

作者： Porandla Srinivas K. Kalimuthu C. Balarengadurai C. Viswanathan 1Department of Information Technology Malla Reddy Institute of Engineering and Technology Secunderabad Telangana India 2Department of Electronics and Communication Engineering SRM Institute of Science and Technology Kattankulathur Tamil Nadu India 3Department of Computer Science and Engineering Marri Laxman Reddy Institute of Technology and Management Dundigal Telangana India 4Department of Computer Science and Engineering Chennai Institute of Technology Malayambakkam Tamil Nadu India

Today the Environment of health has established research and knowledge based on technology-oriented wireless sensing node. Patients are confronted with the problem of unanticipated death because of the particular cause of cardiac difficulties and attacks that occur at the necessary time owing to a lack of adequate care for patients. In contemporary health industry, the use of medical gadgets is significant, which is causing a lot of disruption in the patient’s space as well as the doctor’s analysis. As a result, we highlight our major healthcare electronics initiatives in this paper, with an emphasis on electronic medical records. Uniqueness and ease of use characterize the designed systems, which were planned with a very high level of efficiency (so-called "smarter" gadgets). It was created as a handheld gadget to allow for real-time rescue in the event of an accident without the requirement for continuous patient care of the data. We also show a low-cost computerized healthcare practice that can analyze respiratory activities in real time, non-invasively, and continuously.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast, reliable, and secure drone communication: A comprehensive survey

arXiv

引用

arXiv 2021年

作者： Hassija, Vikas Chamola, Vinay Agrawal, Adhar Goyal, Adit Luong, Nguyen Cong Niyato, Dusit Yu, F. Richard Guizani, Mohsen Department of Computer Science and IT Jaypee Institute of Information Technology Noida201304 India Department of Electrical and Electronics Engineering APPCAIR BITS-Pilani Pilani Campus 333031 India Faculty of Information Technology PHENIKAA University Hanoi12116 Viet Nam A&A Green Phoenix Group JSC No. 167 Hoang Ngan Trung Hoa Cau Giay Hanoi11313 Viet Nam School of Computer Science and Engineering Nanyang Technological University Singapore Department of Systems and Computer Engineering Carleton University OttawaONK1S 5B6 Canada Computer Science and Engineering Department Qatar University Qatar

Drone security is currently a major topic of discussion among researchers and industrialists. Although there are multiple applications of drones, if the security challenges are not anticipated and required architectural changes are not made, the upcoming drone applications will not be able to serve their actual purpose. Therefore, in this paper, we present a detailed review of the security-critical drone applications, and security-related challenges in drone communication such as DoS attacks, Man-in-the-middle attacks, De-Authentication attacks, and so on. Furthermore, as part of solution architectures, the use of Blockchain, Software Defined Networks (SDN), Machine Learning, and Fog/Edge computing are discussed as these are the most emerging technologies. Drones are highly resource-constrained devices and therefore it is not possible to deploy heavy security algorithms on board. Blockchain can be used to cryptographically store all the data that is sent to/from the drones, thereby saving it from tampering and eavesdropping. Various ML algorithms can be used to detect malicious drones in the network and to detect safe routes. Additionally, the SDN technology can be used to make the drone network reliable by allowing the controller to keep a close check on data traffic, and fog computing can be used to keep the computation capabilities closer to the drones without overloading them. © 2021, CC BY.

关键词： Fog computing

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：