检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2023

作者： Zhao, Xin Li, Xiaobing Tie, Yun Hu, Ziqing Qi, Lin School of Electrical and Information Engineering Zhengzhou University Zhengzhou China Central Conservatory of Music Department of Music Artificial Intelligence Beijing China University of Notre Dame Department of Applied and Computational Mathematics and Statistics South Bend on Lake MI United States

ISBN: (纸本)9798350313154

People resonate more with music when exposed to visual information, and music enhances their perception of video content. Cross-modal recommendation techniques can be used to suggest appropriate background music for a given video. However, there is not a simple correspondence between the different modal data. Therefore, to explore the association between the two modalities of video and music, we propose MFF-VBMR, a video background music recommendation model based on multi-level fusion features. The model uses the cross-modal information of static, dynamic and emotional content of video and music to realize the task of matching and recommending suitable background music for a given video. Experimental results show that the proposed model outperforms other existing models in terms of performance and achieves satisfactory results for video background music recommendation. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Inferring System and Optimal Control Parameters of Closed-Loop Systems from Partial Observations 63

Inferring System and Optimal Control Parameters of Closed-Lo...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Geadah, Victor Arbelaiz, Juncal Ritz, Harrison Daw, Nathaniel D. Cohen, Jonathan D. Pillow, Jonathan W. Princeton University Department of Mechanical and Aerospace Engineering PrincetonNJ United States Princeton University Program in Applied and Computational Mathematics PrincetonNJ United States Princeton Neuroscience Institute Princeton University PrincetonNJ United States

ISBN: (纸本)9798350316339

We consider the joint problem of system identification and inverse optimal control for discrete-time stochastic Linear Quadratic Regulators. We analyze finite and infinite time horizons in a partially observed setting, where the state is observed noisily. To recover closed-loop system parameters, we develop inference methods based on probabilistic statespace model (SSM) techniques. First, we show that the system parameters exhibit non-identifiability in the infinite-horizon from closed-loop measurements, and we provide exact and numerical methods to disentangle the parameters. Second, to improve parameter identifiability, we show that we can further enhance recovery by either (1) incorporating additional partial measurements of the control signals or (2) moving to the finitehorizon setting. We further illustrate the performance of our methodology through numerical examples. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Communication-computation efficient gradient coding

arXiv

引用

arXiv 2018年

作者： Ye, Min Abbe, Emmanuel Department of Electrical Engineering Princeton University PrincetonNJ United States Program in Applied and Computational Mathematics Department of Electrical Engineering Princeton University School of Mathematics Institute for Advanced Study PrincetonNJ08544 United States

This paper develops coding techniques to reduce the running time of distributed learning tasks. It characterizes the fundamental tradeoff to compute gradients (and more generally vector summations) in terms of three parameters: computation load, straggler tolerance and communication cost. It further gives an explicit coding scheme that achieves the optimal tradeoff based on recursive polynomial constructions, coding both across data subsets and vector components. As a result, the proposed scheme allows to minimize the running time for gradient computations. Implementations are made on Amazon EC2 clusters using Python with mpi4py package. Results show that the proposed scheme maintains the same generalization error while reducing the running time by 32% compared to uncoded schemes and 23% compared to prior coded schemes focusing only on stragglers (Tandon et al., ICML 2017). Copyright © 2018, The Authors. All rights reserved.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Multi-Track Music Generation Network Based on a Hybrid Learning Module

Multi-Track Music Generation Network Based on a Hybrid Learn...

引用

2023 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2023

作者： Zhang, Donghui Hu, Ziqing Li, Xiaobing Tie, Yun Qi, Lin School of Electrical and Information Engineering Zhengzhou University Zhengzhou China University of Notre Dame Department of Applied and Computational Mathematics and Statistics South Bend on Lake MI United States Central Conservatory of Music Department of Music Artificial Intelligence Beijing China

ISBN: (纸本)9798350313154

Generative models has been widely used for symbolic music generation. However, the quality of the music produced is hindered by the inadequate modeling of the harmonic and rhythmic relationships among various instruments, as well as the neglect of musical principles. To address the aforementioned challenges, we propose an attention-based hybrid learning multitrack music generation(HL-MTMG) model that incorporates regularization of musical rules and simultaneous exploitation between intra-track and inter-track information, resulting in the generation of high-quality symbolic music that conforms to established musical principles. Through extensive examinations of musical structures, specifically rhythm, and assessments by domain experts, our study demonstrates that HL-MTMG exhibits significant improvements in musical integrity and fluency in comparison to symbolic music generation models, such as, MuseGAN and HRNN. © 2023 IEEE.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Reed-Muller codes polarize

arXiv

引用

arXiv 2019年

作者： Abbe, Emmanuel Ye, Min Mathematics Institute School of Computer and Communication Sciences Epfl Switzerland Program in Applied and Computational Mathematics Department of Electrical Engineering Princeton University United States Department of Electrical Engineering Princeton University PrincetonNJ United States

Reed-Muller (RM) codes and polar codes are generated by the same matrix Gm= [1 0/1 1]⊗mbut using different subset of rows. RM codes select simply rows having largest weights. Polar codes select instead rows having the largest conditional mutual information proceeding top to down in Gm;while this is a more elaborate and channel-dependent rule, the top-to-down ordering has the advantage of making the conditional mutual information polarize, giving directly a capacity-achieving code on any binary memoryless symmetric channel (BMSC). RM codes are yet to be proved to have such property. In this paper, we reconnect RM codes to polarization theory. It is shown that proceeding in the RM code ordering, i.e., not top-to-down but from the lightest to the heaviest rows in Gm, the conditional mutual information again polarizes. We further demonstrate that it does so faster than for polar codes. This implies that Gmcontains another code, different than the polar code and called here the twin code, that is provably capacity-achieving on any BMSC. This proves a necessary condition for RM codes to achieve capacity on BMSCs. It further gives a sufficient condition if the rows with largest conditional mutual information correspond to the heaviest rows, i.e., if the twin code is the RM code. We show here that the two codes bare similarity with each other and give further evidence that they are likely the same. Copyright © 2019, The Authors. All rights reserved.

关键词： Forward error correction

来源：评论

学校读者我要写书评

暂无评论

Finite Heisenberg-Weyl groups and golay complementary sequences 2

Finite Heisenberg-Weyl groups and golay complementary sequen...

引用

2nd International Waveform Diversity and Design Conference, WDD 2006

作者： Howard, S.D. Calderbank, A.R. Moran, W. Defence Science and Technology Organisation PO BOX 1500 Edinburgh5111 Australia Applied and Computational Mathematics Princeton University PrincetonNJ08540 United States Department of Electrical and Electronic Engineering University of Melbourne VIC3010 Australia

ISBN: (纸本)9781538648483

We provide a new way of understanding Golay pairs (of length N) of sequences in terms of the (2N + 1)-dimensional discrete Heisenberg-Weyl group over the field Z2. Our methodology provides a different insight into the nature of these sequences, as well as a mechanism for designing sequences with desirable correlation properties. Libraries of waveforms formed using these constructions are able to provide collections of ambiguity functions that cover the range-Doppler plane in an efficient way, and thus provide the basis for a suite of waveforms optimized for extraction of information from the environment in an active sensing context. © 2006 IEEE.

关键词： Hilbert space Correlation Australia Sensors Doppler radar Spaceborne radar

来源：评论

学校读者我要写书评

暂无评论

Recovery of frequency-sparse signals from compressive measurements

Recovery of frequency-sparse signals from compressive measur...

引用

Annual Allerton Conference on Communication, Control, and Computing

作者： Marco F. Duarte Richard G. Baraniuk Applied and Computational Mathematics Princeton University USA Department of Electrical and Computer Engineering Rice University USA

Compressive sensing (CS) is a new approach to simultaneous sensing and compression for sparse and compressible signals. While the discrete Fourier transform has been widely used for CS of frequency-sparse signals, it provides optimal sparse representations only for signals with components at integral frequencies. There exist redundant frames that provide compressible representations for frequency-sparse signals, but such frames are highly coherent and severely affect the performance of standard CS recovery. In this paper, we show that by modifying standard CS recovery algorithms to prevent coherent frame elements from being present in the signal estimate, it is possible to bypass the shortcomings introduced by the coherent frame. The resulting algorithm comes with theoretical guarantees and is shown to perform significantly better for frequency-sparse signal recovery than its standard counterparts. The algorithm can also be extended to similar settings that use coherent frames.

关键词： Discrete Fourier transforms Approximation methods Approximation algorithms Frequency estimation Sparse matrices Estimation Coherence

来源：评论

学校读者我要写书评

暂无评论

DCNet: Densely Connected Neural Network with Global Context for Abnormalities Prediction in Bronchoscopy Images

DCNet: Densely Connected Neural Network with Global Context ...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Wang, Ying Tie, Yun Liu, Fenghui Qi, Lin Hu, Ziqing Zhengzhou University School of Electrical and Information Engineering Zhengzhou China Zhengzhou University The First Affiliated Hospital of Zhengzhou University Zhengzhou China University of Notre Dame Department of Applied and Computational Mathematics and Statistics Notre Dame United States

ISBN: (纸本)9798350337488

Bronchoscopy plays an important role in the examination of lower respiratory tract diseases. However, the large number of medical images produced by bronchoscopy makes it a time-consuming and labor-intensive task for doctors to analyze. Therefore, developing computer-aided diagnostic algorithms to assist doctors in lung image analysis is of great *** this paper, we propose a novel densely connected convolutional network called DCNet with local and global receptive fields for the automatic prediction of bronchoscopy images. Our experimental results on the clinical bronchoscopy image analysis dataset demonstrate that our proposed method outperforms state-of-the-art algorithms in distinguishing malignant bronchoscopy images, with an accuracy rate of 92.81%. And DCNet achieved 99.31% accuracy on the public data set called Kvasir-Capsule. This model may be a valuable tool to assist medical staff in the analysis of bronchoscopy images. © 2023 IEEE.

关键词： bronchoscopy images prediction deep learning dense connection self-attention

来源：评论

学校读者我要写书评

暂无评论

Towards Cleaner Air: Pm2.5 Exposure and Disparities Around Childcare Providers in England

SSRN

引用

SSRN 2025年

作者： Cruz, Joana Li, Guangquan Rammah, Amal Zhong, Jian Shoari, Niloofar Akaraci, Selin Hajna, Samantha Hart, Caroline Chamberlain, Rosemary Mitsakou, Christina Exley, Karen Bloss, William Fry, Richard Cummins, Steven Hardelid, Pia Population Policy and Practice Research and Teaching Department Great Ormond Street Institute of Child Health UCL 30 Guilford Street LondonWC1N 1EH United Kingdom Applied Statistics Research Group Department of Mathematics Physics and Electrical Engineering Northumbria University Newcastle upon TyneNE1 8ST United Kingdom School of Geography Earth & Environmental Sciences University of Birmingham Edgbaston BirminghamB15 2TT United Kingdom Computational Science and Engineering Group University of Greenwich Old Royal Naval College Park Row LondonSE10 9LS United Kingdom Department of Health Sciences Faculty of Applied Health Sciences Brock University St Catharines ON Canada Air Quality and Public Health Environmental Hazards and Emergencies UK Health Security Agency ChiltonOX11 0RQ United Kingdom Swansea University Singleton Park Swansea WalesSA28PP United Kingdom Population Health Innovation Lab Department of Public Health Environments & Society London School of Hygiene & Tropical Medicine 15-17 Tavistock Place LondonWC1H 9SH United Kingdom GOSH Biomedical Research Centre 30 Guilford St LondonWC1N 1EH United Kingdom

Air pollution poses a significant health risk for young children, particularly in urbanareas. This study examined changes in PM2.5 concentrations around Early YearsProviders (EYPs)—including nurseries—across England from 2018 to 2022 andidentified neighbourhood characteristics associated with EYPs located in areasexceeding WHO air quality guidelines (>5 μg/m3). Geographic Information Systems(GIS) methodology integrated data on EYP locations from Ordnance Survey with airpollution data from *** analysed temporal changes in PM2.5 concentrations around EYPs, identifiedclusters exceeding WHO interim target levels of 10 μg/m3 using Local Moran’s I, andexplored associations between PM2.5 exposure and socio-demographic factors. Dataon deprivation, urbanicity, and ethnic group distribution were sourced from the 2021Census of Population for England and Wales. A Bayesian spatial regression modelincorporating random effects assessed associations between PM2.5 exposure andsmall-area socio-demographic *** 2018 and 2022, the number of EYPs ranged from 15,780 to 18,427. AveragePM2.5 levels around EYPs declined by 17.8% (from 9.4 μg/m3, SD=1.8 to 7.8 μg/m3,SD=1.5), yet over 96% of EYPs consistently recorded concentrations above the WHOannual guideline of 5 μg/m3. Temporary reductions during COVID-19 lockdowns in2020 (mean=7.5 μg/m3, SD=1.3) rebounded by ***-High clusters (EYPs with PM2.5 >10 μg/m3 surrounded by similar EYPs) wereobserved in urban centres like Greater London, Birmingham, and Southeast England,while Low-Low clusters occurred in rural regions such as Devon, Cornwall, and northern England. EYPs in deprived, urban areas with predominantly non-whitepopulations had higher PM2.5 *** findings highlight the urgent need for targeted interventions to reduce airpollution in deprived urban areas, prioritizing young children’s health. © 2025, The Authors. All rights reserved.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

Oil spill sensor using multispectral infrared imaging via ℓ1 minimization

Oil spill sensor using multispectral infrared imaging via ℓ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yingying Li Wei-Chuan Shih Zhu Han Wotao Yin Electrical & Computer Engineering Department University of Houston USA Computational and Applied Mathematics Rice University USA

Early detection of oil spill events is the key to environmental protection and disaster management. Current technology lacks the sensitivity and specificity in detecting the early onset of a small-scale oil spill event. Based on an infrared oil-water contrast model recently developed, we propose a novel non scanning computational infrared sensor that has the potential to achieve unprecedented detection sensitivity. Such a system can be very low-cost and robust for automated outdoor operations, leading to massive offshore deployment. Taking advantage of the characteristic oil thickness multispectral signatures, we have streamlined an algorithm that incorporates 3D image reconstruction and classification in a single inversion step capitalizing on the benefits of ℓ 1 minimization.

关键词： Pixel Noise Imaging TV Minimization Parallel processing Noise measurement

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：