检索结果-内蒙古大学图书馆

information and Education technology (ICIET), International Conference on

作者： Wu-Yuin Hwang Ika Qutsiati Utami Department of Computer Science and Information Engineering National Dong Hwa University Graduate Institute of Network Learning Technology National Central University Taiwan Graduate Institute of Network Learning Technology National Central University Taoyuan Taiwan Faculty of Advanced Technology and Multidiscipline Universitas Airlangga Indonesia

ISBN: (数字)9798350371772

ISBN: (纸本)9798350371789

This paper introduced an interactive system for generating contextualized and personalized mathematic word problems (MWP) from authentic contexts using the Generative Pre-trained Transformers (GPT). Our proposed Automatic Question Generation (AQG) system comprises (1) the authentic contextual information acquisition through image recognition by TensorFlow and augmented reality (AR) measurement through AR Core, (2) a personalized mechanism based on instructional prompts to generate three difficulty levels for learner's different needs, and (3) MWP generation through GPT with authentic contextual information and personalized needs. A quasi-experiment was conducted by recruiting 51 fifth-grade students to evaluate the effectiveness of the proposed AQG on their geometry learning performance. The results revealed that students who learned with the proposed AQG outperformed students who learned with a decontextualized way on geometry learning performances. Therefore, our proposed AQG is useful for promoting mathematic problem-solving activity in an authentic context.

关键词： Geometry Image recognition Interactive systems Education Transformer cores Transformers Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Urban Damage Detection Using Temporally Stacked Synthetic Aperture Radar Interferometric Coherence

Urban Damage Detection Using Temporally Stacked Synthetic Ap...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Ryo Natsuaki Ryu Sugimoto Masanobu Shimada Chiaki Tsutsumi Ryosuke Nakamura Department of Electrical Engineering and Information Systems The University of Tokyo Japan Digital Architecture Research Center National Institute of Advanced Industrial Science and Technology Japan Division of Architectural Civil and Environmental Engineering Tokyo Denki University Japan

In this paper, we propose a novel disaster damage detection method using Synthetic Aperture Radar (SAR) interferometric analysis. SAR interferometric coherence analysis is an effective method for disaster monitoring especially in the urban area, where the amplitude of SAR image changes only slightly unless the damage level is high. One drawback of the interferometric coherence-based analysis is the existence of the Cramér-Rao lower bound. That is, a small spatial window for its ensemble averaging leads significant bias while a large window makes its spatial resolution worse. To solve this problem, we propose to extend the ensemble average window towards temporal domain by increasing the number of interferometric pairs. Conventional methods which use multiple interferometric pairs firstly calculate coherence values independently. Instead, the proposed method unifies the interferograms first. We report some preliminary experimental results showing the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Segmentation-based method combined with dynamic programming for brain midline delineation

arXiv

引用

arXiv 2020年

作者： Wang, Shen Liang, Kongming Pan, Chengwei Ye, Chuyang Li, Xiuli Liu, Feng Yu, Yizhou Wang, Yizhou Center for Data Science Peking University Beijing China Deepwise AI Lab Beijing China Computer Science Department School of EECS Peking University Beijing China Center on Frontiers of Computing Studies Peking University Beijing China Advanced Institute of Information Technology Peking University Beijing China School of Information and Electronics Beijing Institute of Technology Beijing China

The midline related pathological image features are crucial for evaluating the severity of brain compression caused by stroke or traumatic brain injury (TBI). The automated midline delineation not only improves the assessment and clinical decision making for patients with stroke symptoms or head trauma but also reduces the time of diagnosis. Nevertheless, most of the previous methods model the midline by localizing the anatomical points, which are hard to detect or even missing in severe cases. In this paper, we formulate the brain midline delineation as a segmentation task and propose a three-stage framework. The proposed framework firstly aligns an input CT image into the standard space. Then, the aligned image is processed by a midline detection network (MD-Net) integrated with the CoordConv Layer and Cascade AtrousCconv Module to obtain the probability map. Finally, we formulate the optimal midline selection as a pathfinding problem to solve the problem of the discontinuity of midline delineation. Experimental results show that our proposed framework can achieve superior performance on one in-house dataset and one public dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Discriminative Gradient Adjustment with Coupled Knowledge Distillation for Class Incremental Learning

Discriminative Gradient Adjustment with Coupled Knowledge Di...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Hao Zhang Yanxu Hu Jiawen Peng Andy J Ma School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing China

Class Incremental Learning (CIL) is a promising approach to addressing the catastrophic forgetting problem when learning for new categories. Though recent works based on dynamic architectures achieve convincing performance, data imbalance caused by limited size of memory and compression of the increasingly growing network are challenges to be solved. In this paper, we propose the novel Discriminative Gradient Adjustment (DGA) and Coupled Knowledge Distillation strategy (CKD) for these two challengs. The DGA mitigates the data imbalance problem by designing the loss function with a static global balance factor and a ground-truth-based dynamic factor. The CKD fully utilizes intermediate layers of the dual-branch models by feature-level distillation with moving-average weight updating for network compression. Extensive experiments on CIFAR100 and ImageNet100 datasets demonstrate the superiority of our method for CIL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancement of Mechanical Performance and Low-Temperature Strengthening Mechanism: High-Entropy Alloy/Graphene Composite Material

SSRN

引用

SSRN 2024年

作者： Zhou, Shaocong Liang, Yongchao Pu, Yuanwei Zhou, Yu Zhou, Lili Tian, Zean Institute of Advanced Optoelectronic Materials and Technology School of Big Data and information engineering Guizhou University Guiyang550025 China Department of Information Engineering Gannan Medical University Ganzhou341000 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China

High-entropy alloy (HEA) /graphene (Gr) composites hold vast potential for various applications owing to their exceptional mechanical properties. However, the elucidation of their micro-mechanical mechanisms remains elusive, impeding their advancement. Therefore, this study utilizes molecular dynamics (MD) simulations to explore the tensile behavior of CoCrFeMnNi HEA and HEA/Gr composites, aiming to investigate the strengthening mechanism of the reinforcing phase and deformation behavior across different temperatures. The insertion of Gr enhances the yield strength and elasticity modulus of HEA/Gr by 57.5% and 19%, respectively, compared to pure HEA. The hindering effect of the Gr layer interface on dislocation propagation fosters the generation of numerous immobile dislocations, leading to significant disparities in atomic stress and strain distribution, thereby markedly enhancing mechanical properties. Moreover, the hindrance posed by the Gr layer facilitates out-of-plane deformation, and the fracture of Gr significantly impacts material properties. Low-temperature stretching induces FCC-BCC phase transitions in the composites, with transformation-induced plasticity (TRIP) triggering a synergistic effect on material strength and plasticity. Throughout the plastic deformation phase, phase transition promotes dislocation slip and transfer, thereby extending dislocation plasticity and augmenting material plasticity and strength. The results provide important insights into the strengthening mechanism of HEA/Gr at low temperatures, illustrating the key role of reinforcement in mechanical properties from the dual perspectives of Gr insertion and fracture. © 2024, The Authors. All rights reserved.

关键词： High-entropy alloys

来源：评论

学校读者我要写书评

暂无评论

Matrix Classifier On Dynamic Functional Connectivity For Mci Identification

Matrix Classifier On Dynamic Functional Connectivity For Mci...

引用

IEEE International Conference on Image Processing

作者： Lei Zhou Liang Zhang Xiao Bai Jun Zhou School of Computer Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing State Key Laboratory of Software Development Environment Beihang University Beijing School of Information and Communication Technology Griffith University Nathan

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

One of the most popular method for Alzheimer's disease (AD) diagnosis is exploring the Brain functional connectivity (FC) from resting-state functional magnetic resonance imaging (RS-fMRI). To early prevent AD, it is crucial to distinguish AD and and its preclinical stage, mild cognitive impairment (MCI) and early MCI (eMCI). In many existing works, dynamic functional connectivity (dFC) which contains rich spatiotemporal information has been exploited for the MCI and eMCI identification. However, most of these dFC based methods only consider the correlation between discrete brain status while ignore the valuable spatiotemporal information contained in dFC. To overcome this limitation, we propose a matrix classifier based method on the dFC signal for MCI and eMCI identification. Specifically, we first represent the dFC correlations by matrix features which contain rich spatiotemporal information and then learn the support matrix machines (SMM) to classify AD and its preclinical stage. Experiments on 600 real people data provide by the Alzheimer's Disease Neuroimaging Initiative (ADNI) demonstrate that our proposed matrix classifier based method outperforms other FC and dFC based methods for both normal controls (NC)/MCI identification and NC/eMCI identification.

关键词： Feature extraction Correlation Dementia Microsoft Windows Spatiotemporal phenomena Training

来源：评论

学校读者我要写书评

暂无评论

CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolution

CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medic...

引用

International Conference on computer Vision (ICCV)

作者： Zixuan Chen Lingxiao Yang Jian-Huang Lai Xiaohua Xie School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Medical image arbitrary-scale super-resolution (MIASSR) has recently gained widespread attention, aiming to supersample medical volumes at arbitrary scales via a single model. However, existing MIASSR methods face two major limitations: (i) reliance on high-resolution (HR) volumes and (ii) limited generalization ability, which restricts their applications in various scenarios. To overcome these limitations, we propose Cube-based Neural Radiance Field (CuNeRF), a zero-shot MIASSR framework that is able to yield medical images at arbitrary scales and free viewpoints in a continuous domain. Unlike existing MISR methods that only fit the mapping between low-resolution (LR) and HR volumes, CuNeRF focuses on building a continuous volumetric representation from each LR volume without the knowledge of the corresponding HR one. This is achieved by the proposed differentiable modules: cube-based sampling, isotropic volume rendering, and cube-based hierarchical rendering. Through extensive experiments on magnetic resource imaging (MRI) and computed tomography (CT) modalities, we demonstrate that CuNeRF can synthesize high-quality SR medical images, which outperforms state-of-the-art MISR methods, achieving better visual verisimilitude and fewer objectionable artifacts. Compared to existing MISR methods, our CuNeRF is more applicable in practice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stable Task Assignment for Socially Aware Collective Computing Systems

Stable Task Assignment for Socially Aware Collective Computi...

引用

Smart World Congress (SWC), IEEE

作者： Hao Zhou Yang Li Yunlong Zhao Chunyan Liu College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Unmanned Aerial Vehicles Research Institute Nanjing University of Aeronautics and Astronautics Nanjing China Key Laboratory of Advanced Technology for Small and Medium-Sized UAV Ministry of Industry and Information Technology Nanjing China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

Collective Computing is the latest generation of computing paradigm that has received a lot of attention recently. One of the important things in Collective Computing systems is how to assign tasks to human participants. When doing the assignment, the platform may face the challenge of inadequate availability of skilled workers. To deal with this challenge, some researchers leverage the property that workers are socially aware and consider assigning tasks to workers with the assistance of social networks. However, the objectives of task requesters and workers can conflict and may result in unstable assignments due to unhappy requesters and workers, which is ignored by most of these works. This paper leverages the influence propagation on the social network to assist task assignment and takes requesters’ preferences and workers’ preferences into consideration. Stable Matching Theory is leveraged to solve the problem of matching tasks with seed workers and an efficient task assignment algorithm is proposed. Through extensive simulations, the performance of the proposed algorithm is evaluated in different settings. Empirical studies show that the proposed algorithm outperforms the baseline algorithms in achieving stability and system efficiency.

关键词： Social networking (online) Computational modeling Approximation algorithms Stability analysis Faces

来源：评论

学校读者我要写书评

暂无评论

Comparing the optimization functions and methods of community detection

Comparing the optimization functions and methods of communit...

引用

2010 International Conference on Future information technology and Management Engineering, FITME 2010

作者： Liu, Jinxia Zeng, Jianchao Xue, Yaowen College of Electrical and Information Engineering Lanzhou University of Technology Lanzhou 730050 China Division of System Simulation and Computer Application Taiyuan University of Science and Technology Taiyuan China College of Economics and Management Sbanxi Normal University Linien China College of Economics and Management Taiyuan University of Science and Technology Taiyuan China

ISBN: (纸本)9781424490882

Detecting and characterizing the community structure of complex network is fundamental. There are many algorithms, were sorted to three types of criterion: mathematical method, mechanism of community structure and optimization method. In this paper, we discuss the optimization methods of community detection, compare and analyse the objective functions and solution methods. Based on this, we develop a new optimization function, named community quantification which is accurate for many types of networks. © 2010 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Comparison of disturbance rejection performance between sliding-mode control and equivalent-input-disturbance approach

Comparison of disturbance rejection performance between slid...

引用

International Conference on Mechatronics (ICM)

作者： Jinhua She Yaodong Pan Hiroshi Hashimoto Min Wu School of Computer Science Tokyo University of Technology Hachioji Tokyo Japan Control Systems Eng Honeywell Canada Mississauga ONT Canada Master Program of Innovation for Design and Eng Advanced Institute of Industrial Technology Tokyo Japan School of Information Science and Engineering Central South University Changsha China

Sliding mode control (SMC) has been considered as a powerful method for disturbances rejection. On the other hand, we have presented an equivalent-input disturbance (EID) approach to reject disturbances. This paper takes a dual-stage feed drive as an example to compare these two methods. The example shows that, while the EID approach obtains almost the same disturbance rejection performance for matched disturbances as that of the SMC does, it can reject unmatched disturbances. This shows the superiority of the EID approach over SMC method.

关键词： Equations Observers Manganese Frequency control

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：