检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Bessadok, Alaa Nebli, Ahmed Mahjoub, Mohamed Ali Li, Gang Lin, Weili Shen, Dinggang Rekik, Islem BASIRA Lab Faculty of Computer and Informatics Istanbul Technical University Istanbul Turkey Higher Institute of Informatics and Communication Technologies University of Sousse 4011 Tunisia National Engineering School of Sousse University of Sousse LATIS- Laboratory of Advanced Technology and Intelligent Systems Sousse4023 Tunisia Mannouba Tunisia Department of Radiology and BRIC University of North Carolina Chapel HillNC United States School of Biomedical Engineering ShanghaiTech University Shanghai China Department of Research and Development United Imaging Intelligence Co. Ltd. Shanghai China

Charting the baby connectome evolution trajectory during the first year after birth plays a vital role in understanding dynamic connectivity development of baby brains. Such analysis requires acquisition of longitudinal connectomic datasets. However, both neonatal and postnatal scans are rarely acquired due to various difficulties. A small body of works has focused on predicting baby brain evolution trajectory from a neonatal brain connectome derived from a single modality. Although promising, large training datasets are essential to boost model learning and to generalize to a multi-trajectory prediction from different modalities (i.e., functional and morphological connectomes). Here, we unprecedentedly explore the question: "Can we design a few-shot learning-based framework for predicting brain graph trajectories across different modalities?" To this aim, we propose a Graph Multi-Trajectory Evolution Network (GmTE-Net), which adopts a teacher-student paradigm where the teacher network learns on pure neonatal brain graphs and the student network learns on simulated brain graphs given a set of different timepoints. To the best of our knowledge, this is the first teacher-student architecture tailored for brain graph multi-trajectory growth prediction that is based on few-shot learning and generalized to graph neural networks (GNNs). To boost the performance of the student network, we introduce a local topology-aware distillation loss that forces the predicted graph topology of the student network to be consistent with the teacher network. Experimental results demonstrate substantial performance gains over benchmark methods. Hence, our GmTE-Net can be leveraged to predict atypical brain connectivity trajectory evolution across various modalities. Our code is available at https://***/basiralab/GmTE-Net. © 2021, CC BY-NC-ND.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Open domain event extraction using neural latent variable models

arXiv

引用

arXiv 2019年

作者： Liu, Xiao Huang, Heyan Zhang, Yue School of Computer Science and Technology Beijing Institute of Technology Zhejiang Lab China School of Engineering Westlake University Institute of Advanced Technology Westlake Institute for Advanced Study

We consider open domain event extraction, the task of extracting unconstraint types of events from news clusters. A novel latent variable neural model is constructed, which is scalable to very large corpus. A dataset is collected and manually annotated, with task-specific evaluation metrics being designed. Results show that the proposed unsupervised model gives better performance compared to the state-of-the-art method for event schema induction. Copyright © 2019, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Class2Simi: A noise reduction perspective on learning with noisy labels

arXiv

引用

arXiv 2020年

作者： Wu, Songhua Xia, Xiaobo Liu, Tongliang Han, Bo Gong, Mingming Wang, Nannan Liu, Haifeng Niu, Gang Trustworthy Machine Learning Lab School of Computer Science University of Sydney Department of Computer Science Hong Kong Baptist University School of Mathematics and Statistics University of Melbourne ISN State Key Laboratory School of Telecommunications Engineering Xidian University Brain-Inspired Technology Co. Ltd. RIKEN Center for Advanced Intelligence Project

Learning with noisy labels has attracted a lot of attention in recent years, where the mainstream approaches are in pointwise manners. Meanwhile, pairwise manners have shown great potential in supervised metric learning and unsupervised contrastive learning. Thus, a natural question is raised: does learning in a pairwise manner mitigate label noise? To give an affirmative answer, in this paper, we propose a framework called Class2Simi: it transforms data points with noisy class labels to data pairs with noisy similarity labels, where a similarity label denotes whether a pair shares the class label or not. Through this transformation, the reduction of the noise rate is theoretically guaranteed, and hence it is in principle easier to handle noisy similarity labels. Amazingly, DNNs that predict the clean class labels can be trained from noisy data pairs if they are first pretrained from noisy data points. Class2Simi is computationally efficient because not only this transformation is on-the-fly in mini-batches, but also it just changes loss computation on top of model prediction into a pairwise manner. Its effectiveness is verified by extensive experiments. Copyright © 2020, The Authors. All rights reserved.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Comments on "A new computing approach for power signal modeling using fractional adaptive algorithms"

arXiv

引用

arXiv 2020年

作者： Wahab, Abdul Khan, Shujaat Khan, Farrukh Zeeshan Sector H-12 Islamabad44000 Pakistan Bio-Imaging Signal Processing and Learning Lab. Department of Bio and Brain Engineering Korea Advanced Institute of Science and Technology 291 Daehak-ro Yuseong-gu Daejeon34141 Korea Republic of Department of Computer Science University of Engineering and Technology Taxila Taxila47080 Pakistan

In this paper, some points to the convergence analysis performed in the paper [A new computing approach for power signal modeling using fractional adaptive algorithms, ISA Transactions 68 (2017) 189-202] are presented. It is highlighted that the way the authors prove convergence, suffers lack of correct and valid mathematical justifications. Copyright © 2020, The Authors. All rights reserved.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

TTPP: Temporal transformer with progressive prediction for efficient action anticipation

arXiv

引用

arXiv 2020年

作者： Wang, Wen Peng, Xiaojiang Su, Yanzhou Qiao, Yu Cheng, Jian School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu Sichuan611731 China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab. Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Video action anticipation aims to predict future action categories from observed frames. Current state-of-the-art approaches mainly resort to recurrent neural networks to encode history information into hidden states, and predict future actions from the hidden representations. It is well known that the recurrent pipeline is inefficient in capturing long-term information which may limit its performance in predication task. To address this problem, this paper proposes a simple yet efficient Temporal Transformer with Progressive Prediction (TTPP) framework, which repurposes a Transformer-style architecture to aggregate observed features, and then leverages a light-weight network to progressively predict future features and actions. Specifically, predicted features along with predicted probabilities are accumulated into the inputs of subsequent prediction. We evaluate our approach on three action datasets, namely TVSeries, THUMOS-14, and TV-Human-Interaction. Additionally we also conduct a comprehensive study for several popular aggregation and prediction strategies. Extensive results show that TTPP not only outperforms the state-of-the-art methods but also more efficient. Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Consistent Discretization of a Class of Predefined-Time Stable Systems

引用

IFAC-PapersOnLine 2020年第2期53卷 628-633页

作者： Esteban Jiménez-Rodríguez Rodrigo Aldana-López Juan D. Sánchez-Torres David Gómez-Gutiérrez Alexander G. Loukianov Relativity6 Inc. Computer Science & Artificial Intelligence Lab Jalisco 45040 México Department of Computer Science and Systems Engineering University of Zaragoza Zaragoza 50009 España Research Laboratory on Optimal Design Devices and Advanced Materials -OPTIMA- Department of Mathematics and Physics ITESO Jalisco 45604 México Multi-agent autonomous systems lab Intel Labs Intel Tecnología de México Jalisco 45019 Mexico Tecnologico de Monterrey Escuela de Ingeniería y Ciencias Jalisco 45138 Mexico Department of Electrical Engineering Cinvestav-Guadalajara Jalisco 45019 México

As the main contribution, this document provides a consistent discretization of a class of fixed-time stable systems, namely predefined-time stable systems. In the unperturbed case, the proposed approach allows obtaining not only a consistent but exact discretization of the considered class of predefined-time stable systems, whereas in the perturbed case, the consistent discretization preserves the predefined-time stability property. All the results are validated through simulations and compared with the conventional explicit Euler scheme, highlighting the advantages of this proposal.

关键词： Predefined-time stability Discrete-time systems Digital implementation Stability of nonlinear systems Fixed-time stability

来源：评论

学校读者我要写书评

暂无评论

High performance of supercapacitors containing an ionic liquid electrolyte by means of electrochemical and computational studies

引用

Electrochimica Acta 2025年

作者： Raissa Venâncio Débora A.C. da Silva Ludmila O. Borges Isabel A. Silva Leonardo Morais Da Silva Gustavo Doubek Leonardo J.A. Siqueira Hudson Zanin Center for Innovation on New Energies Advanced Energy Storage Division BREnergies Universidade Estadual de Campinas School of Electrical and Computer Engineering Av. Albert Einstein 400 Campinas SP 13083-852 Brazil Hybrid Materials Laboratory Chemistry Department Institute of Environmental Science Chemical and Pharmaceutical Federal University of São Paulo– Str. São Nicolau 210 2nd floor Diadema SP Department of Chemistry Laboratory of Fundamental and Applied Electrochemistry Federal University of Jequitinhonha e Mucuri’s Valley Rodovia MGT 367 km 583 5000 Alto da Jacuba 39100-000 Diamantina MG Brazil Advanced Energy Storage Division Laboratory of Advanced Batteries (LAB) Center for Innovation on New Energies School of Chemical Engineering University of Campinas (Unicamp) Campinas Sao Paulo 13083-852 Brazil

This study characterizes the electrochemical behavior of symmetric coin cells with AC-based electrodes filled with the ammonium-based ionic liquid, a promising supercapacitor electrolyte due to its large voltage window and ambient temperature operation. We employed cyclic voltammetry, single-step chronoamperometry, electrochemical impedance spectroscopy, and galvanostatic charge-discharge techniques to evaluate the electrochemical performance of the supercapacitors thoroughly. Our findings highlight the quasi-rectangular current-voltage profile up to 3.6 V, beyond which a faradaic current due to electrolyte degradation becomes significant. These results revealed a minor faradaic component, with impedance analysis showing typical behavior of well-formed electrical double layers (EDLs), influenced by the unique properties of ionic liquids. We observed that the ion dynamics and capacitance behavior align well with theoretical models, particularly the Goodwin-Kornishev mean-field theory. The study underscores the potential of ionic liquid-based supercapacitors to achieve high performance, with specific capacitance values reaching ∼2000 F g -1 and great energy and power output, comparable to lithium-ion batteries. Molecular dynamics simulations further elucidated the charging mechanisms, ion migration, and structural interactions within the EDLs. These comprehensive insights validate the suitability of butyltrimethylammonium bis(trifluoromethylsulfonyl)imide [N 1114 ][NTf 2 ] for advanced supercapacitor applications, highlighting its ability to deliver exceptional electrochemical performance under optimized conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Beyond Fourier transform: Break the axial resolution limit in optical coherence tomography

arXiv

引用

arXiv 2020年

作者： Ling, Yuye Wang, Mengyuan Gan, Yu Yao, Xinwen Schmetterer, Leopold Zhou, Chuanqing Su, Yikai John Hopcroft Center for Computer Science Shanghai Jiao Tong University Shanghai China Department of Electrical and Computer Engineering University of Alabama AL United States Singapore Institute for Health Technologies Nanyang Technological University Singapore Singapore Eye Research Institute Singapore National Eye Centre Singapore School of Chemical and Biomedical Engineering Nanyang Technological University Singapore Institute of Biomedical Engineering Shenzhen Bay Lab Shenzhen China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China State Key Lab of Advanced Optical Communication Systems and Networks Department of Electronic Engineering Shanghai Jiao Tong University Shanghai China

Optical coherence tomography (OCT) is a volumetric imaging modality that empowers clinicians and scientists to noninvasively visualize and examine the microscopic cross-sectional architectures of biological samples. By taking advantage of the coherence gating, OCT could achieve micrometer-level axial sectioning with high sensitivity. In the past decade, substantial efforts have been made to push the axial resolution of Fourier-domain OCT (FD-OCT) further into the sub-micron regime by physically extending the system's spectral bandwidth. Here, we offer a new perspective on this problem with the help of a new theoretical framework. We identified a key limitation on the reconstruction's axial resolution, which is induced by the Fourier transform-based reconstruction algorithm. To break this limit, we presented a novel optimization-based algorithm to recover the super-resolution image from ordinary FD-OCT measurements with proper physical assumptions. To prove the concept, we retrieved images at a resolution higher than the theoretical prediction in both phantoms and biological samples. Copyright © 2020, The Authors. All rights reserved.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

A Model-Free Approach for Predictive Direct Power Control of Grid-Connected Converters

A Model-Free Approach for Predictive Direct Power Control of...

引用

Annual Conference of the IEEE Industrial Electronics Society

作者： Mohammad Khalilzadeh Sadegh Vaez-Zadeh Alireza Jabbarnejad School of electrical and computer engineering Colledge of engineering University of Tehran Tehran Iran Advanced Motion Systems Research Lab The Center of Excellence on Applied Electromagnetic Systems School of Electrical and Computer Engineering Colledge of Engineering University of Tehran Tehran Iran

This paper presents a model-free finite control set predictive direct power control for grid-connected converters. As the proposed method does not use the model parameters, their uncertainties do not cause prediction error and inappropriate voltage vector selection, unlike the conventional predictive direct power control method. A new form of cost function is adopted in the method that directly uses the time-derivatives (slopes) of the active and the reactive powers. The slopes are predicted free of model parameters with low computational burden and without additional sensors. The method is evaluated through simulation and its performance is compared with the one of the conventional model predictive direct power control method. The results show the effectiveness of the proposed method and its superiority over the conventional method.

关键词： Reactive power Predictive models Cost function Mathematical model Power control Voltage control Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Road detection through CRF based LiDAR-camera fusion

Road detection through CRF based LiDAR-camera fusion

引用

2019 International Conference on Robotics and Automation, ICRA 2019

作者： Gu, Shuo Zhang, Yigong Tang, Jinhui Yang, Jian Kong, Hui PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 China Institute of Advanced Artifical Intelligence in Nanjing Horizon Robotics China

ISBN: (纸本)9781538681763

In this paper, we propose a road detection method with LiDAR-camera fusion in a novel conditional random field (CRF) framework to exploit both range and color information. In the LiDAR based part, a fast height-difference based scanning strategy is applied in the 2D LiDAR range-image domain and a dense road detection result in camera image domain can be obtained through geometric upsampling given the LiDAR-camera calibration parameters. In the camera based part, a fully convolutional network is applied in the camera image domain. Finally, we fuse the dense and binary road detection results from both LiDAR and camera in a single CRF framework. Experiments show that using a single thread of CPU, the proposed LiDAR based part can operate at a frequency of over 250Hz with sparse output in range image and 40Hz with dense result in camera image for the 64-beam Velodyne scanner. Our CRF fusion method achieves very promising road detection performance on the KITTI-Road dataset. © 2019 IEEE.

关键词： Laser radar Roads Cameras Three-dimensional displays Two dimensional displays Image segmentation Transforms

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：