检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Big Data, BigData 2023

作者： Qin, Zheyi Paffenroth, Randy Jayasumana, Anura P. Colorado State University Electrical and Computer Engineering Fort Collins United States Worcester Polytechnic Institute Department of Data Science Program WorcesterMA United States

ISBN: (纸本)9798350324457

Graph-based data present unique challenges and opportunities for machine learning. Graph Neural Networks (GNNs), and especially those algorithms that capture graph topology through message passing for neighborhood aggregation, have been a leading solution. However, these networks often require substantial computational resources and may not optimally leverage the information contained in the graph's topology, particularly for large-scale or complex *** propose Topology Coordinate Neural Network (TCNN) and Directional Virtual Coordinate Neural Network (DVCNN) as novel and efficient alternatives to message passing GNNs, that directly leverage the graph's topology, sidestepping the computational challenges presented by competing algorithms. Our proposed methods can be viewed as a reprise of classic techniques for graph embedding for neural network feature engineering, but they are novel in that our embedding techniques leverage ideas in Graph Coordinates (GC) that are lacking in current *** results, benchmarked against the Open Graph Benchmark Leaderboard, demonstrate that TCNN and DVCNN achieve competitive or superior performance to message passing GNNs. For similar levels of accuracy and ROC-AUC, TCNN and DVCNN need far fewer trainable parameters than contenders of the OGBN Leaderboard. The proposed TCNN architecture requires fewer parameters than any neural network method currently listed in the OGBN Leaderboard for both OGBN-Proteins and OGBN-Products datasets. Conversely, our methods achieve higher performance for a similar number of trainable parameters. These results hold across diverse datasets and edge features, underscoring the robustness and generalizability of our methods. By providing an efficient and effective alternative to message passing GNNs, our work expands the toolbox of techniques for graph-based machine learning. A significantly lower number of tunable parameters for a given evaluation metric makes TCNN and DVCNN especiall

关键词： graph analytics graph coordinate graph embedding green AI network embedding

来源：评论

学校读者我要写书评

暂无评论

Strong nonlinear optical processes with extraordinary polarization anisotropy in inversionsymmetry broken two-dimensional PdPSe

引用

Light(science & Applications) 2024年第8期13卷 1524-1533页

作者： Song Zhu Ruihuan Duan Xiaodong Xu Fangyuan Sun Wenduo Chen Fakun Wang Siyuan Li Ming Ye Xin Zhou Jinluo Cheng Yao Wu Houkun Liang Junichiro Kono Xingji Li Zheng Liu Qi Jie Wang School of Electrical and Electronic Engineering Nanyang Technological University639798 SingaporeSingapore School of Material Science and Engineering Nanyang Technological University639798 SingaporeSingapore CINTRA CNRS/NTU/THALES UMI 3288Research Techno PlazaNanyang Technological University637371 SingaporeSingapore School of Materials Science and Engineering Harbin Institute of Technology150001 HarbinChina Department of Chemistry National University of Singapore117543 SingaporeSingapore GPL Photonics Lab State Key Laboratory of Applied OpticsChangchun Institute of OpticsFine Mechanics and PhysicsChinese Academy of Sciences130033 ChangchunChina School of Electronics and Information Engineering Sichuan University610064 ChengduSichuanChina School of Physical and Mathematical Sciences Nanyang Technological University637371 SingaporeSingapore Departments of Electrical and Computer Engineering Physics and Astronomyand Materials Science and NanoEngineeringRice UniversityHoustonTXUSA

Nonlinear optical activities,especially second harmonic generation(SHG),are key phenomena in inversion-symmetrybroken two-dimensional(2D)transition metal dichalcogenides(TMDCs).On the other hand,anisotropic nonlinear optical processes are important for unique applications in nano-nonlinear photonic devices with polarization functions,having become one of focused research topics in the field of nonlinear ***,the strong nonlinearity and strong optical anisotropy do not exist simultaneously in common 2D ***,we demonstrate strong secondorder and third-order susceptibilities of 64 pm/V and 6.2×10^(-19)m^(2)/V^(2),respectively,in the even-layer PdPSe,which has not been discovered in other common TMDCs(e.g.,MoS2).Strikingly,it also simultaneously exhibited strong SHG anisotropy with an anisotropic ratio of~45,which is the largest reported among all 2D materials to date,to the best of our *** addition,the SHG anisotropy ratio can be harnessed from 0.12 to 45(375 times)by varying the excitation wavelength due to the dispersion ofχ^(2)*** an illustrative example,we further demonstrate polarized SHG imaging for potential applications in crystal orientation identification and polarization-dependent spatial *** findings in 2D PdPSe are promising for nonlinear nanophotonic and optoelectronic applications.

关键词： materials anisotropy nonlinear

来源：评论

学校读者我要写书评

暂无评论

Broadband and Tailorable THz Emission from Spintronic Photonic Crystals

Broadband and Tailorable THz Emission from Spintronic Photon...

引用

CLEO: science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

作者： Ghaffari, Abbas Thapa, Puja Collazo, Ramón Gundogdu, Kenan Sun, Dali Gu, Qing Department of Electrical and Computer Engineering North Carolina State University Raleigh27695 United States Department of Physics North Carolina State University Raleigh27695 United States Department of Materials Science and Engineering North Carolina State University Raleigh27606 United States

We explore THz generation from structured ferromagnet/ultrawide bandgap semiconductor heterostructures. The emission spectrum can span the entire THz gap, be enhanced, and tuned by changing size and periodicity of the... 详细信息

关键词： Wide band gap semiconductors

来源：评论

学校读者我要写书评

暂无评论

3D Finite Thermal Modelling of SrSnO3 Field Effect Transistors 82

3D Finite Thermal Modelling of SrSnO3 Field Effect Transisto...

引用

82nd Device Research Conference, DRC 2024

作者： Bista, Bivek Wen, Jiaxuan Golani, Prafful Liu, Fengdeng Truttmann, Tristan Jalan, Bharat Koester, Steven Pavlidis, Georges University of Connecticut School of Mechanical Aerospace and Manufacturing Engineering StorrsCT06269 United States University of Minnesota Department of Electrical and Computer Engineering MinneapolisMN55455 United States University of Minnesota Department of Chemical Engineering and Materials Science MinneapolisMN55455 United States

ISBN: (纸本)9798350373738

SrSnO3 (SSO) is an ultra-wide bandgap (≈ 4.1 eV) semiconductor that has potential applications in high power electronics and DUV optoelectronics [1]. However, the thermal properties of doped SSO thin films have not been extensively studied. Due to its high bandgap, self-heating can severely limit the device's performance and reliability. This study reports the thermal transport characteristics of SSO based metal-semiconductor field-effect transistors (MESFETs) through 3D finite modelling and compares them with experimental data obtained via Transient Thermoreflectance Imaging (TTI). TTI can be used to obtain surface temperature maps with high spatial (≈ 410 nm) and temporal (≈ 50 ns) resolution [2] , [3]. Therefore, the TTI technique was used to extract the gate and drain metal surface temperature under pulsed biasing (300 μs pulse width with 10% duty cycle), whereas the steady state temperature rise was numerically evaluated using a 3D Finite Element (FE) model in ANSYS Workbench. © 2024 IEEE.

关键词： Tin compounds

来源：评论

学校读者我要写书评

暂无评论

Short Wave Infrared Upconversion Imager with Electron Blocking Layer to Screen Electron Injection into Photosensitive Layer 5

Short Wave Infrared Upconversion Imager with Electron Blocki...

引用

5th IEEE International Conference on Flexible and Printable Sensors and Systems, FLEPS 2023

作者： Shin, Chanho Li, Ning Ng, Tse Nga University of California San Diego Material Science and Engineering Program La Jolla United States University of California San Diego Department of Electrical and Computer Engineering La Jolla United States

ISBN: (纸本)9781665457330

In this work, we demonstrated upconversion imagers integrated with shortwave infrared photodetectors paired with an electron blocking layer. The use of electron blocking layer screened charge injection to prevent recombination in photosensitive layer. The characteristics of each electron blocking layer were analyzed in aspects of noise and detectivity. For the optimized device, the parasitic luminance in the dark was efficiently suppressed, and the photon-to-photon efficiency was increased. The electron blocking layer used in this work is generally applicable for upconversion imagers using different absorption and emitting materials. © 2023 IEEE.

关键词： Photodetectors

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time-Series Deep Learning for Joint Prediction of Temperature and Relative Humidity in a Closed Space 8

Multivariate Time-Series Deep Learning for Joint Prediction ...

引用

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Gunawan, Fergianto E. Budiman, Arief S. Pardamean, Bens Juana, Endang Romeli, Sugiarto Cenggoro, Tjeng W. Purwandari, Kartika Hidayat, Alam A. Redi, Anak A.N.P. Asrol, Muhammad Industrial Engineering Department BINUS Graduate Program - Master of Industrial Engineering Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Electrical Engineering Department Faculty of Industrial Technology Universitas Trisakti Jakarta11440 Indonesia PT Impack Pratama Industri Jakarta14350 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Mathematics Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

An accurate predictive model of temperature and humidity plays a vital role in many industrial processes that utilize a closed space such as in agriculture and building management. With the exceptional performance of deep learning on time-series data, developing a predictive temperature and humidity model with deep learning is propitious. In this study, we demonstrated that deep learning models with multivariate time-series data produce remarkable performance for temperature and relative humidity prediction in a closed space. In detail, all deep learning models that we developed in this study achieve almost perfect performance with an R value over 0.99. © 2023 The Authors. Published by Elsevier B.V.

关键词： closed space deep learning humity prediction indoor temperature prediction

来源：评论

学校读者我要写书评

暂无评论

Differing vibrational properties of halide and chalcogenide perovskite semiconductors and impact on optoelectronic performance

引用

Physical Review materials 2024年第8期8卷 085402页

作者： Kevin Ye Matan Menahem Tommaso Salzillo Florian Knoop Boyang Zhao Shanyuan Niu Olle Hellman Jayakanth Ravichandran R. Jaramillo Omer Yaffe Department of Materials Science and Engineering Department of Chemical and Biological Physics Department of Industrial Chemistry “Toso Montanari” Department of Physics Chemistry and Biology (IFM) Mork Family Department of Chemical Engineering and Materials Science Department of Molecular Chemistry and Material Science Ming Hsieh Department of Electrical and Computer Engineering Core Center of Excellence in NanoImaging (CNI)

We report a comparative study of temperature-dependent photoluminescence and structural dynamics of two perovskite semiconductors, the chalcogenide BaZrS3 and the halide CsPbBr3. These materials have similar crystal structures and direct band gaps, but we find that they have quite distinct optoelectronic and vibrational properties. Both materials exhibit thermally activated nonradiative recombination, but the nonradiative recombination rate in BaZrS3 is four orders of magnitude faster than in CsPbBr3, for the crystals studied here. Raman spectroscopy reveals that the effects of phonon anharmonicity are far more pronounced in CsPbBr3 than in BaZrS3. Further, although both materials feature a large dielectric response due to low-energy polar optical phonons, the phonons in CsPbBr3 are substantially lower in energy than in BaZrS3. Our results suggest that electron-phonon coupling in BaZrS3 is more effective at nonradiative recombination than in CsPbBr3 and that BaZrS3 may also have a substantially higher concentration of nonradiative recombination centers than CsPbBr3. The low defect concentration in CsPbBr3 may be related to the ease of lattice reconfiguration, typified by anharmonic bonding. It remains to be seen to what extent these differences are inherent to the chalcogenide and halide perovskites and to what extent they can be affected by materials processing.

关键词： Electron-phonon coupling Lattice dynamics Photoemission Solar cells Photovoltaic absorbers Photoluminescence Raman spectroscopy

来源：评论

学校读者我要写书评

暂无评论

SFA-Net: A Selective Features Absorption Network for Object Detection in Rainy Weather Conditions

引用

IEEE Transactions on Neural Networks and Learning Systems 2023年第8期34卷 5122-5132页

作者： Huang, Shih-Chia Hoang, Quoc-Viet Le, Trung-Hieu National Taipei University of Technology Department of Electronic Engineering Taipei10608 Taiwan National Taipei University of Technology International Graduate Program in Electrical Engineering and Computer Science Taipei10608 Taiwan Hung Yen University of Technology and Education Faculty of Information Technology Hungyen 17000 Viet Nam

In recent years, object detection approaches using deep convolutional neural networks (CNNs) have derived major advances in normal images. However, such success is hardly achieved with rainy images due to lack of visibility. Aiming to bridge this gap, in this article, we present a novel selective features absorption network (SFA-Net) to improve the performance of object detection not only in rainy weather conditions but also in favorable weather conditions. SFA-Net accomplishes this objective by utilizing three subnetworks, where the feature selection subnetwork is concatenated with the object detection subnetwork through the feature absorption subnetwork to form a unified model. To promote further advancement in object detection impaired by rain, we propose a large-scale rainy image dataset, named srRain, which contains both synthetic rainy images and real-world rainy images for training and testing purposes. srRain is comprised of 25 900 rainy images depicting diverse driving scenarios in the presence of rain with a total of 181 164 instances interpreting five common object categories. Experimental results display that our SFA-Net reaches the highest mean average precision (mAP) of 77.53% on a normal image set, 62.52% on a synthetic rainy image set, 37.34% on a collected natural rainy image set, and 32.86% on a published real rainy image set, surpassing current state-of-the-art object detectors and the combination of image deraining and object detection models while retaining a high speed. © 2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Retired Lithium-ion Batteries for Echelon Utilization 48

Performance Evaluation of Retired Lithium-ion Batteries for ...

引用

48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022

作者： Azizighalehsari, Seyedreza Venugopal, Prasanth Pratap Singh, Deepak Rietveld, Gert Department of Electrical Engineering Mathematics and Computer Science Enschede Netherlands Inorganic Materials Science Group Department of Science and Technology Enschede Netherlands Vsl Delft Netherlands

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

With the rapid growth of the electric vehicle (EV) market, the number of Lithium-ion (Li-ion) batteries that reach their end of life (EOL) is increasing rapidly. Given the stringent capacity fading threshold of EV batteries, tools are required for better understanding and evaluating the health condition of large volume EV batteries that have reached EOL. In this paper, four modules from the same battery pack of a hybrid electric vehicle have been evaluated in terms of their current capacity and performance of the cells within each module. The results have been analyzed to find an affordable method for performance assessment of the retired batteries for echelon utilization. Electrochemical impedance spectroscopy (EIS) as an accurate and powerful technique has been used as a benchmark for the measurement to show the reliability of the tests. Experimental results are obtained from different test approaches on both modules and cell levels and show a different ageing degradation pattern for the cells inside the modules. The result shows that even for the modules with the same range of state of health, any non-uniformity of the cells inside the modules will affect the reliability of the modules for a second life. We also show there is a meaningful dependency between the voltage monitoring of the cells and other test approaches to determine the uniformity of a module. © 2022 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

SoC-Oriented Implementation of Machine Learning Based Breast Cancer Classification Algorithm 12

SoC-Oriented Implementation of Machine Learning Based Breast...

引用

12th Mediterranean Conference on Embedded Computing, MECO 2023

作者： Saeed, Abdelrahman Tawfik, Ayman Mostafa, Hassan Khalil, Ahmed Hussein Cairo University Electronics and Communications Engineering Department Giza12613 Egypt Ajman University Department of Electrical and Computer Engineering United Arab Emirates University of Science and Technology Nanotechnology and Nanoelectronics Program Zewail City of Science and Technology Giza Egypt

ISBN: (纸本)9798350322910

Convolutional Neural Networks (CNN) have drawn the attention of researchers in the medical imaging field. Many researchers have exploited CNN for breast cancer detection. This study provides an Internet of Things (IoT) friendly implementation of CNN for breast cancer detection. To achieve faster time to Market, Deep-learning Processing Unit (DPU) on Field programmable Gate Array (FPGA) is adopted for the CNN hardware implementation. CNN inference on the proposed system achieves a 1.6x speed-up factor and 91.5% reduction in energy consumption compared to the conventional general-purpose multi-core Central Processing Unit (CPU). © 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

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：