检索结果-内蒙古大学图书馆

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Tripathi, Amrita Singh, Tripty Bhanu Prakash, K.N. Rajamani, Kumar Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Bengaluru India AStar Bioinformatic Institute Bioinformatics Institute Singapore Marwadi Education Foundation's Group of Institutions Faculty of Engineering and Technology Gujarat India

ISBN: (纸本)9798350335095

After emerging in Wuhan, China, in December 2019, the coronavirus 2019 (COVID-2019) quickly spread throughout the world and sparked a pandemic. Covid-19 The pandemic affected human health globally. In a few cases of Covid19 humans faced death situations also. The Respiratory system of the human body gets affected by Covid-19 and the severity of Covid-19 leads to death so there is urgent need of fast and efficient automatic diagnosis system of Covid-19 to help medical experts to diagnose this disease quickly and efficiently. This paper's main objective is to provide a Binary Classification of Covid-19 disease using a dataset obtained from computed tomography. Four Deep Learning existing models ResNet50, Inception V3, DenseNet121 and Efficient Net B0 are employed here. Compared to ResNet50, InceptionV3, and Efficient Net B0, DenseNet121 performs better. DenseNet121 model showed 96.83% as training accuracy and 92% as validation accuracy. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Machine learning assisted identification of homobilayer sliding ferroelectrics with large out-of-plane polarization and low sliding energy barriers

引用

Physical Review B 2025年第9期111卷 094106-094106页

作者： Xian Wang Yifan Li Ying Zhang Peng Wang Yi-Ming Zhao Jun Zhou Jie Yang Xuesen Wang Lei Shen Department of Physics National University of Singapore Singapore 117551 Singapore Department of Mechanical Engineering National University of Singapore Singapore 117575 Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore 117576 Singapore National University of Singapore (Chongqing) Research Institute Chongqing 401123 China College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao 266590 China Institute of Materials Research and Engineering (IMRE) Agency for Science Technology and Research (ASTAR6) Singapore 138634 Singapore Key Laboratory of Material Physics Ministry of Education School of Physics Zhengzhou University Zhengzhou 450001 China

Two-dimensional (2D) ferroelectric materials hold great promise for ultrahigh-density data storage and ultrafast memory applications in flexible or wearable electronic devices. Because of depolarizing field effects and high-energy barriers for switching, only a handful of 2D ferroelectrics have been reported experimentally, such as In2Se3 and CuInP2S6. Through high-throughput calculations we identified a catalog of 25 synthesizable sliding ferroelectrics with large out-of-plane polarization and low sliding energy barriers. The high-throughput process started with 6351 monolayer materials in 2dmatpedia, narrowed down to 79 monolayer semiconductors with honeycomb structures, leading to the construction of 474 homobilayers sliding ferroelectrics, and ultimately identifying 25 high-performance 2D sliding ferroelectrics. Using big-data analysis and machine learning, we also revealed strong correlations between polarization and key physical properties, especially a hidden factor of effective van der Waals radius, which has been overlooked in previous fewer-sample studies. Based on these mechanistic insights, we proposed machine learning descriptors for predicting sliding ferroelectric properties.

关键词： Van der Waals forces

来源：评论

学校读者我要写书评

暂无评论

Enabling All-to-Circular Polarization Up-Conversion by Nonlinear Chiral Metasurfaces with Rotational Symmetry

引用

Physical Review Letters 2025年第2期134卷 023804-023804页

作者： Dmitrii Gromyko Jun Siang Loh Jiangang Feng Cheng-Wei Qiu Lin Wu Science Mathematics and Technology (SMT) Singapore University of Technology and Design (SUTD) 8 Somapah Road 487372 Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore 4 Engineering Drive 3 117583 Singapore Singapore Institute of High Performance Computing ASTAR (Agency for Science Technology and Research) 1 Fusionopolis Way No. 16-16 Connexis 138632 Singapore Singapore

We introduce a stacking strategy to design nonlinear chiral metasurfaces with high rotational symmetry, enabling degenerate quasi-bound-in-the-continuum resonances of absolute chirality. This symmetry allows for converting a circularly polarized pump into a circularly polarized nonlinear signal. Consequently, our rotation-symmetric bilayered metasurface design, tailored to respond solely to one specific circular polarization, can up-convert a linear or arbitrary polarized pump into circularly polarized nonlinear signals. The intensity ratios of these signals scale as the fourth (second) power of the chiral resonance amplitude for the second (third) harmonic.

关键词： Circular polarization

来源：评论

学校读者我要写书评

暂无评论

Jamming Mitigation in JRC Systems via Deep Reinforcement Learning and Backscatter-supported Intelligent Deception Strategy 6

Jamming Mitigation in JRC Systems via Deep Reinforcement Lea...

引用

6th IEEE International Conference on computer and Communication Systems, ICCCS 2021

作者： Ismail, Lotfi Niyato, Dusit Sun, Sumei Hoang, Dinh Thai Kim, Dong In Liang, Ying-Chang School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Institute for Infocomm Research Astar Singapore Singapore School of Electrical and Data Engineering University of Technology Sydney SydneyNSW Australia Sungkyunkwan University Department of Electrical and Computer Engineering Suwon Korea Republic of Center for Intelligent Networking and Communications University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9780738126043

In this paper, we develop a framework to optimize the trade-off between radar sensing and data transmission in Joint Radar-Communication (JRC) systems under smart and reactive jamming attacks. First, we propose a novel JRC design architecture that uses backscatter technology and deception strategy to leverage jamming attacks for a JRC system. The deception strategy is used to predict the jammer's action and adopt appropriate counterattack instantaneously, while backscatter technology is used to transmit data on the jamming signals. To deal with the jamming strategy uncertainty (e.g., jamming capability), we then develop a deep reinforcement learning algorithm to quickly find the optimal defense policy for the JRC system. Our in-depth investigation reveals that the proposed design not only significantly undermines the jamming attacks, but also utilises jamming signals to improve the system performances. Compared with conventional anti-jamming methods, our proposed design significantly improves data throughput while maintaining a satisfactory radar sensing performance in dynamic environments. Moreover, the proposed deep reinforcement learning based solution can converge four times faster than a conventional deep Q- Learning based solution. © 2021 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval

arXiv

引用

arXiv 2022年

作者： Satar, Burak Zhu, Hongyuan Zhang, Hanwang Lim, Joo Hwee The School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Institute for Infocomm Research Astar Singapore Singapore The University of Macau China The Department of Computer Science Columbia University United States The National University of Singapore Singapore

Seas of videos are uploaded daily with the popularity of social channels;thus, retrieving the most related video contents with user textual queries plays a more crucial role. Most methods consider only one joint embedding space between global visual and textual features without considering the local structures of each modality. Some other approaches consider multiple embedding spaces consisting of global and local features separately, ignoring rich inter-modality correlations. We propose a novel mixture-of-expert transformer RoME that disentangles the text and the video into three levels;the roles of spatial contexts, temporal contexts, and object contexts. We utilize a transformer-based attention mechanism to fully exploit visual and text embeddings at both global and local levels with mixture-of-experts for considering inter-modalities and structures' correlations. The results indicate that our method outperforms the state-of-the-art methods on the YouCook2 and MSR-VTT datasets, given the same visual backbone without pre-training. Finally, we conducted extensive ablation studies to elucidate our design choices. © 2022, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Experimental Study of Outdoor Radio Wave Propagation Scenario Near the L-Shaped Building

Experimental Study of Outdoor Radio Wave Propagation Scenari...

引用

Microwaves Antennas and Propagation Conference (MAPCON)

作者： Kaushal Kishore Tiwari Venkata Charan Gowthukatla Sai Teja Avadhootha Raja Vara Prasad Yerra Divyabramham Kandimalla Electronics and Communication Engineering IIIT Sri City Chittoor Sri City India Member of Technical staff Altiostar A Rakuten Symphony Company Bangalore India Computer Science Department University of North Carolina Charlotte Charlotte NC USA

ISBN: (纸本)9781665452045

The radio wave Propagation scenario around an L-shaped building has been demonstrated in this work. The experimental study has been carried-out using the long-range technology. The theoretical results are computed by employing uniform theory of diffraction based formulations, in a deterministic manner, to incorporate the multiple wedge diffracted rays in the shadow region of the building. The theoretical and experimental results are also compared with results obtained using the Method of moments based Electromagnetic simulation tool.

关键词： Microwave antennas Microwave technology Diffraction Propagation Computational modeling Buildings Electromagnetics

来源：评论

学校读者我要写书评

暂无评论

The Power Of Triply Complementary Priors For Image Compressive Sensing

The Power Of Triply Complementary Priors For Image Compressi...

引用

IEEE International Conference on Image Processing

作者： Zhiyuan Zha Xin Yuan Joey Tianyi Zhou Jiantao Zhou Bihan Wen Ce Zhu School of Electrical & Electronic Engineering Nanyang Technological University Singapore Nokia Bell Labs 600 Mountain Avenue Murray Hill NJ USA Institute of High Performance Computing A&STAR Singapore Department of Computer and Information Science University of Macau Macau China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

Recent works that utilized deep models have achieved superior results in various image restoration applications. Such approach is typically supervised which requires a corpus of training images with distribution similar to the images to be recovered. On the other hand, the shallow methods which are usually unsupervised remain promising performance in many inverse problems, e.g., image compressive sensing (CS), as they can effectively leverage non-local self-similarity priors of natural images. However, most of such methods are patch-based leading to the restored images with various ringing artifacts due to naive patch aggregation. Using either approach alone usually limits performance and generalizability in image restoration tasks. In this paper, we propose a joint low-rank and deep (LRD) image model, which contains a pair of triply complementary priors, namely external and internal, deep and shallow, and local and nonlocal priors. We then propose a novel hybrid plug-and-play (H-PnP) framework based on the LRD model for image CS. To make the optimization tractable, a simple yet effective algorithm is proposed to solve the proposed H-PnP based image CS problem. Extensive experimental results demonstrate that the proposed H-PnP algorithm significantly outperforms the state-of-the-art techniques for image CS recovery such as SCSNet and WNNM.

关键词： Image restoration Optimization Inverse problems Standards Noise reduction Compressed sensing Sensors

来源：评论

学校读者我要写书评

暂无评论

IoT-enabled multimodal sensing headwear system 4

IoT-enabled multimodal sensing headwear system

引用

4th IEEE World Forum on Internet of Things, WF-IoT 2018

作者： Wai, Aung Aung Phyo Dajiang, He Huat, Ng Soon Computational Intelligence Lab School of Computer Science and Engineering Nanyang Technological University Singapore Neural and Biomedical Technology Department Institute for Infocomm Research ASTAR Singapore

ISBN: (纸本)9781467399449

With the proliferation of Internet of Things (IoT) paradigm, wearable devices and solutions aim to resolve unmet needs from military, automotive to healthcare domains. Particularly, there are growing interests in wearable Brain computer Interface (BCI) from both commercial and research applications. Still uphill challenges lie ahead to bring such BCI technologies to mass market due to lack of technical, usability and application aspects. To fill these gaps, this paper presents design, development and evaluation of an IoT-enabled multimodal headwear system, iMESH. Our solution senses user's neural, physiological and physical states through direct measurements and derives health parameters. We then developed driving fatigue assessment application as exemplar to illustrate applicability and feasibility of the proposed solution. Initial results are promising and with ongoing development on methodologies, we are hoping to further develop and validate iMESH functionalities in different applications. © 2018 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

VC-I2R@ImageCLEF2017: Ensemble of deep learned features for lifelog video summarization 18

VC-I2R@ImageCLEF2017: Ensemble of deep learned features for ...

引用

18th Working Notes of CLEF Conference and Labs of the Evaluation Forum, CLEF 2017

作者： Del Molino, Ana Garcia Mandal, Bappaditya Lin, Jie Lim, Joo Hwee Subbaraju, Vigneshwaran Chandrasekhar, Vijay Visual Computing Department Institute for Infocomm Research ASTAR Singapore School of Computer Science and Engineering NTU Singapore Singapore Bioimaging Consortium ASTAR Singapore

In this paper we describe our approach for the ImageCLEF-lifelog summarization task. A total of ten runs were submitted, which used only visual features, only metadata information, or both. In the first step, a set of relevant frames are drawn from the whole lifelog. Such frames must be of good visual quality, and match the given task semantically. For the automatic runs, this subset of images is clustered into events, and the key-frames are selected from the clusters iteratively. In the interactive runs, the user can select which frames to keep or discard in each interaction, and the clustering is adapted accordingly. We observe that the more relevant features to be used depend on the context and the nature of the input lifelog.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Statistical Parametric Speech Synthesis Using Generative Adversarial Networks under A Multi-Task Learning Framework

arXiv

引用

arXiv 2017年

作者： Yang, Shan Xie, Lei Chen, Xiao Lou, Xiaoyan Zhu, Xuan Huang, Dongyan Li, Haizhou School of Computer Science Northwestern Polytechnical University Xi'an China Language Computing Lab Samsung R&D Institute of China Beijing China Institute for Infocomm Research ASTAR Singapore Department of Electrical and Computer Engineering National University of Singapore

In this paper, we aim at improving the performance of synthesized speech in statistical parametric speech synthesis (SPSS) based on a generative adversarial network (GAN). In particular, we propose a novel architecture combining the traditional acoustic loss function and the GAN's discriminative loss under a multi-task learning (MTL) framework. The mean squared error (MSE) is usually used to estimate the parameters of deep neural networks, which only considers the numerical difference between the raw audio and the synthesized one. To mitigate this problem, we introduce the GAN as a second task to determine if the input is a natural speech with specific conditions. In this MTL framework, the MSE optimization improves the stability of GAN, and at the same time GAN produces samples with a distribution closer to natural speech. Listening tests show that the multi-task architecture can generate more natural speech that satisfies human perception than the conventional methods. Copyright © 2017, The Authors. All rights reserved.

关键词： Generative adversarial networks

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：