检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Yang, Chenxiao Wu, Qitian Wipf, David Sun, Ruoyu Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Lab of AI Shanghai Jiao Tong University China Amazon Web Services United States School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data China

A long-standing goal in deep learning has been to characterize the learning behavior of black-box models in a more interpretable manner. For graph neural networks (GNNs), considerable advances have been made in formalizing what functions they can represent, but whether GNNs will learn desired functions during the optimization process remains less clear. To fill this gap, we study their training dynamics in function space. In particular, we find that the gradient descent optimization of GNNs implicitly leverages the graph structure to update the learned function, as can be quantified by a phenomenon which we call kernel-graph alignment. We provide theoretical explanations for the emergence of this phenomenon in the overparameterized regime and empirically validate it on real-world GNNs. This finding offers new interpretable insights into when and why the learned GNN functions generalize, highlighting their limitations in heterophilic graphs. Practically, we propose a parameter-free algorithm that directly uses a sparse matrix (i.e. graph adjacency) to update the learned function. We demonstrate that this embarrassingly simple approach can be as effective as GNNs while being orders-of-magnitude faster. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate Bolt Classification for a Retail Motorcycle Shop in Thailand

Fast and Accurate Bolt Classification for a Retail Motorcycl...

引用

International computer science and engineering Conference (ICSEC)

作者： Monchai Angkapiyasiri Suphakant Phimoltares Department of Mathematics and Computer Science Advanced Virtual and Intelligent Computing (AVIC) Research Center Faculty of Science Chulalongkorn University Bangkok Thailand

People have begun to improve their purchase of products and food via online applications because of the ongoing global pandemic. Especially, purchasing products through online applications is popular due to their convenience. Hence, numerous riders need motorcycles to work for delivery. As a result, critical spare parts such as durable and beautiful bolts are highly demanded for maintenance. We collect the best-selling bolts of 19 classes from a motorcycle shop to develop a bolt classification procedure and improve business opportunities. A combination of principal component analysis, median cut algorithm, and structural analysis, is used for extracting a set of features. Then, five classification models, which are multi-layer perceptron, random forest, decision tree, support vector machine, and logistic regression, are used to assign the most appropriate class for each bolt. The experiment results show that the multi-layer perceptron performs better than the other classification models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lightweight Deep Residual Network for Motorcyclist Behavior Recognition Using Inertial Sensors 8

Lightweight Deep Residual Network for Motorcyclist Behavior ...

引用

8th International Conference on Information Technology, InCIT 2024

作者： Hnoohom, Narit Mekruksavanich, Sakorn Jitpattanakul, Anuchit Mahidol University Faculty of Engineering Image Information and Intelligence Laboratory Department of Computer Engineering Nakhon Pathom Thailand University of Phayao Department of Computer Engineering School of Information and Communication Technology Phayao Thailand King Mongkut's University of Technology Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics North Bangkok Thailand

ISBN: (纸本)9798350366303

Motorcyclist behavior recognition (MBR) is a significant factor in improving road safety and preventing accidents. Inertial sensors, such as accelerometers, gyroscopes, and magnetometers, have shown promising potential for capturing the dynamic behavior of motorcyclists. However, existing approaches often require complex models and significant computational resources, limiting their deployment in real-world scenarios. This study presents a MotoNeXt architecture, which is a light deep residual network for correctly identifying the behavior of motorcyclists using data from inertial sensors. Our approach leverages the power of deep learning while maintaining a compact model size, making it suitable for resource-constrained environments. The proposed network incorporates multi-kernel residual blocks to facilitate the learning of hierarchical features and improve gradient flow during training. We evaluate our method on a publicly available benchmark dataset, MB-IMU, collected from multiple riders under various riding conditions. Experimentation has shown that our lightweight model achieves cutting-edge performance, outperforming a variety of existing techniques. In Scenario I, using accelerometer, gyroscope, and magnetometer data, MotoNeXt achieved an accuracy result of 78.90088% along with an F1-score of 81.56738%. According to Scenario II, which included additional sensor data such as VelInc, OriInc, and Euler angles, MotoNeXt further improved its performance, achieving an accuracy result of 83.29735% along with an F1-score of 84.95352%. The proposed approach offers a practical solution for real-time MBR, enabling the development of intelligent transportation systems and rider assistance technologies. Our experiments highlight the effectiveness of lightweight deep learning models in extracting meaningful patterns from inertial sensor data. This opens up opportunities for further investigation in this field. © 2024 IEEE.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

Silicon Nitride Integrated Photonics with Intrinsic Quantum Emitters

Silicon Nitride Integrated Photonics with Intrinsic Quantum ...

引用

Optica Quantum 2.0 Conference and Exhibition, Quantum 2.0

作者： Senichev, Alexander Martin, Zachariah O. Peana, Samuel Yesilyurt, Omer Matthiessen, Owen M. Sychev, Demid Lawrie, Benjamin Lagutchev, Alexei S. Boltasseva, Alexandra Shalaev, Vladimir M. Elmore Family School of Electrical and Computer Engineering Birck Nanotechnology Center Purdue Quantum Science and Engineering Institute Purdue University West LafayetteIN47907 United States Quantum Science Center Department of Energy a National Quantum Information Science Research Center of the U.S. Oak RidgeTN37931 United States Materials Science and Technology Division Oak Ridge National Laboratory Oak RidgeTN37831 United States

We create intrinsic quantum emitters in silicon nitride, study their structure and temperature-dependent optical properties, and demonstrate monolithic integration with photonic waveguides to evaluate the potential of... 详细信息

ISBN: (纸本)9781957171272

关键词： Integrated photonics Optical properties Photonic integrated circuits Quantum information Quantum light sources Silicon nitride

来源：评论

学校读者我要写书评

暂无评论

Quantum-dot and organic hybrid light-emitting diodes employing a blue common layer for simple fabrication of full-color displays

引用

Nano research 2022年第7期15卷 6477-6482页

作者： Suhyeon Lee Donghyo Hahm Suk-Young Yoon Heesun Yang Wan Ki Bae Jeonghun Kwak Department of Electrical and Computer Engineering Seoul National UniversitySeoul 08826Republic of Korea Inter-university Semiconductor Research Center(ISRC) Seoul National UniversitySeoul 08826Republic of Korea SKKU Advanced Institute of Nanotechnology(SAINT) School of Nano Science&TechnologySungkyunkwan University(SKKU)Suwon 16419Republic of Korea Department of Materials Science and Engineering Hongik UniversitySeoul 04066Republic of Korea

Colloidal quantum-dot(QD)light-emitting diodes(QLEDs)have been in the forefront of future display devices due to their outstanding optoelectronic ***,a complicated solution-process for patterning the red,green,and blue QDs deteriorates the QLED performance and limits the resolution of full-color ***,we report a novel concept of QD–organic hybrid light-emitting diodes by introducing an organic blue common layer(BCL)which is deposited through a common mask over the entire *** from the optimized device structure,red and green QLEDs retained their color coordinates despite the presence of the ***,adopting the BCL improved the external quantum efficiency of green and red QLEDs by 38.4%and 11.7%,respectively,due to the Förster resonance energy transfer from the BCL to the adjacent QD *** the BCL structure,we could simply demonstrate a full-color QD-organic hybrid device in a single *** believe that this device architecture is practically applicable for easier fabrication of solution-processed,highresolution,and full-color displays with reduced process steps.

关键词： quantum-dot light-emitting diode(QLEDs) organic light-emitting diode blue common layer full-color display reduced process step

来源：评论

学校读者我要写书评

暂无评论

Size-dependent cellular uptake and sustained drug release of PLGA particles

引用

Particuology 2023年第2期73卷 1-7页

作者： Rui Sun Xia Liu Yu Zhang Qian Li Ying Zhu Chunhai Fan Division of Physical Biology CAS Key Laboratory of Interfacial Physics and TechnologyShanghai Institute of Applied PhysicsChinese Academy of SciencesShanghai 201800China The Interdisciplinary Research Center Shanghai Synchrotron Radiation FacilityZhangjiang LaboratoryShanghai Advanced Research InstituteChinese Academy of SciencesShanghai 201210China University of Chinese Academy of Sciences Beijing 100049China School of Chemistry and Chemical Engineering Frontiers Science Center for Transformative Molecules and National Center for Translational MedicineShanghai Jiao Tong UniversityShanghai 200240China

Poly(lactic-co-glycolic)acid(PLGA)particles have become a commonly used drug delivery strategy in the pharmaceutical *** this work,we aim to investigate the size-dependent cellular internalization of PLGA particles and its effects on sustained drug *** prepared three different-sized particles using PLGA(200,500 and 2000 nm)ranging from submicrometer to ***(DEX)with excellent anti-inflammatory properties was used as a model drug to prepare DEX-loaded PLGA particles(DPs).We comprehensively investigated the encapsulation efficiency,cellular uptake and in vitro drug release *** assessment revealed that,in the lipopolysaccharide(LPS)-induced RAW 264.7 cells model,500 nm DPs showed sustained anti-inflammatory *** work provides important information for designing PLGA-based drug delivery systems for biomedical applications.

关键词： DEX-loaded PLGA particles(DPs) Sustained release Anti-inflammatory efficacy

来源：评论

学校读者我要写书评

暂无评论

Deep Phase Mapping 3D based on Single-Frame Digital Moiré Fringe 4

Deep Phase Mapping 3D based on Single-Frame Digital Moiré F...

引用

4th International Conference on Electronic Information engineering and computer Communication, EIECC 2024

作者： Di, Rui Hu, Hailing Hu, Meili Song, Baoan Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China Ningbo University Key Laboratory of Photoelectric Detection Materials and Devices of Zhejiang Province Ningbo315211 China Engineering Research Center for Advanced Infrared Photoelectric Materials and Devices of Zhejiang Province Ningbo315211 China

ISBN: (纸本)9798331534622

To enhance three-dimensional(3D) measurement precision with minimal fringes, the deep phase mapping 3D based on single-frame digital moiré fringe method (DDM) is proposed. By projecting just one high-frequency fringe and combining wrapped phase with fringe order to calculate continuous phase, it achieves 3D reconstruction through training on three process variables, thereby enhancing measurement precision. Experimental DDM measurements of 3D contours for fox and complex face models surpassed traditional single-frame methods in accuracy. Further evaluation on standard planes confirmed DDM's precision through lower RMSE (root mean square error) and MAE (mean absolute error) values, underlining its superior reconstruction accuracy. It holds great promise for its potential applications in real-time industrial measurements. © 2024 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Unconventional excitonic states with phonon sidebands in layered silicon diphosphide (Jun, 10.1038/s41563-022-01285-3, 2022)

引用

NATURE MATERIALS 2022年第10期21卷 1212-1212页

作者： Zhou, Ling Huang, Junwei Windgaetter, Lukas Ong, Chin Shen Zhao, Xiaoxu Zhang, Caorong Tang, Ming Li, Zeya Qiu, Caiyu Latini, Simone Lu, Yangfan Wu, Di Gou, Huiyang Wee, Andrew T. S. Hosono, Hideo Louie, Steven G. Tang, Peizhe Rubio, Angel Yuan, Hongtao National Laboratory of Solid State Microstructures Jiangsu Key Laboratory of Artificial Functional Materials College of Engineering and Applied Sciences and Collaborative Innovation Center of Advanced Microstructures Nanjing University Nanjing China Max Planck Institute for the Structure and Dynamics of Matter Center for Free Electron Laser Science Hamburg Germany Department of Physics University of California Berkeley CA USA Materials Sciences Division Lawrence Berkeley National Laboratory Berkeley CA USA School of Materials Science and Engineering Peking University Beijing China Materials Research Center for Element Strategy Tokyo Institute of Technology Yokohama Japan College of Materials Science and Engineering National Engineering Research Center for Magnesium Alloys Chongqing University Chongqing China Center for High Pressure Science and Technology Advanced Research Beijing China Department of Physics National University of Singapore Singapore Singapore School of Materials Science and Engineering Beihang University Beijing China Center for Computational Quantum Physics Simons Foundation Flatiron Institute New York NY USA

Complex correlated states emerging from many-body interactions between quasiparticles (electrons, excitons and phonons) are at the core of condensed matter physics and material science. In low-dimensional materials, quantum confinement affects the electronic, and subsequently, optical properties for these correlated states. Here, by combining photoluminescence, optical reflection measurements and ab initio theoretical calculations, we demonstrate an unconventional excitonic state and its bound phonon sideband in layered silicon diphosphide (SiP2), where the bound electron–hole pair is composed of electrons confined within one-dimensional phosphorus–phosphorus chains and holes extended in two-dimensional SiP2 layers. The excitonic state and emergent phonon sideband show linear dichroism and large energy redshifts with increasing temperature. Our ab initio many-body calculations confirm that the observed phonon sideband results from the correlated interaction between excitons and optical phonons. With these results, we propose layered SiP2 as a platform for the study of excitonic physics and many-particle effects.

关键词： Electronic properties and materials Electronic structure Optical spectroscopy Two-dimensional materials

来源：评论

学校读者我要写书评

暂无评论

Optimisation of alloy composition for highly-formable magnesium sheet

引用

International Journal of Minerals,Metallurgy and Materials 2022年第7期29卷 1388-1395页

作者： Zhuoran Zeng Mingzhe Bian Shiwei Xu Weineng Tang Chris Davies Nick Birbilis Jianfeng Nie College of Engineering and Computer Science Australian National UniversityACT.2601Australia Department of Materials Science and Engineering Monash UniversityVIC 3800Australia State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan UniversityChangsha 410082China Research Institute(R&D Center) Baosteel Group CorporationShanghai 201999China Department of Mechanical and Aerospace Engineering Monash UniversityVIC 3800Australia

The effectiveness of Ca or Gd addition on ductility and formability of Mg-Zn-Zr based dilute alloys in deep drawing has not been systematically compared *** this study,formable Mg-Zn-Gd-Zr and Mg-Zn-Ca-Zr sheet alloys are produced by hot *** sheets have similarly weakened basal texture,but the sheet of the Mg-Zn-Gd-Zr alloys has higher ductility and formability than that of Mg-Zn-Ca-Zr *** combined addition of 0.2wt%Ca and 0.4wt%Gd to the Mg-1Zn-0.5Zr(wt%)alloy leads to a Mg-1Zn-0.4Gd-0.2Ca-0.5Zr alloy that has even better ductility,and its formability during deep drawing is comparable to the benchmark Al6016 *** increase in Ca content from 0.2wt%to 0.5wt%leads to decreased sheet ductility and formability,predominantly due to grain boundary embrittlement.

关键词： magnesium sheet alloy texture microstructure formability solute segregation

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Approach for Dynamic research Insight Path Generation

Multi-Agent Approach for Dynamic Research Insight Path Gener...

引用

IEEE International Conference on Agents (ICA)

作者： Jinghong Li Prarinya Siritanawan Wen Gu Shinobu Hasegawa Division of Advanced Science and Technology Japan Advanced Institute of Science and Technology Ishikawa Japan Faculty of Engineering Shinshu University Nagano Japan Center for Innovative Distance Education and Research Japan Advanced Institute of Science and Technology Ishikawa Japan

ISBN: (数字)9798331539917

ISBN: (纸本)9798331539924

In recent years, researchers have witnessed rapid advancements in conducting paper surveys using generative AI, enhancing survey efficiency to some extent. However, today’s generative AI lacks deep research training to analyze logical threads woven across multiple papers. A concise visualization method is also expected to present logical connections among various papers. These logical threads are often implicit in the issue ontology authors commonly employ when writing papers. Building on this issue ontology, our method utilizes Dynamic Programming with multiple agents to generate an insight path. The key feature of this approach is the collaboration of multiple agents to adapt to a complex environment and make optimized decisions on issue ontology selection. This path aims to succinctly express longitudinal logical connections among multiple papers, including commonality, difference, and inheritance.

关键词： Surveys Training Visualization Generative AI Collaboration Ontologies Writing Programming Weaving Dynamic programming

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：