检索结果-内蒙古大学图书馆

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Obe, Ruth Kaufmann, Brandt Baird, Kaelen Kadel, Sam Soltani, Yasmin Cham, Mostafa Gobbert, Matthias K. Barajas, Carlos A. Jiang, Zhuoran Sharma, Vijay R. Ren, Lei Peterson, Stephen W. Poif, Jerimy C. U. of Houston-Clear Lake Dept. of Computer Science and of Software Engineering United States U. of San Francisco Dept. of Mathematics and Statistics United States Skidmore College Dept. of Computer Science and of Mathematics United States Mount Holyoke College Dept. of Computer Science and of Psychology United States U. of Houston Dept. of Biomedical Engineering United States U. of Maryland Dept. of Information Systems Baltimore County United States U. of Maryland Dept. of Mathematics and Statistics Baltimore County United States Medical Physics Graduate Program Duke University United States U. of Maryland School of Medicine Dept. of Radiation Oncology United States U. of Maryland School of Medicine Department of Radiation Oncology United States U. of Cape Town Dept. of Physics South Africa H3D Inc. United States

ISBN: (纸本)9798350345346

Proton beam therapy is an advanced form of cancer radiotherapy that uses high-energy proton beams to deliver precise and targeted radiation to tumors. This helps to mit-igate unnecessary radiation exposure in healthy tissues. Real-time imaging of prompt gamma rays with Compton cameras has been suggested to improve therapy efficacy. However, the camera's non-zero time resolution leads to incorrect interaction classifications and noisy images that are insufficient for accurately assessing proton delivery in patients. To address the challenges posed by the Compton camera's image quality, machine learning techniques are employed to classify and refine the generated data. These machine-learning techniques include recurrent and feedforward neural networks. A PyTorch model was designed to improve the data captured by the Compton camera. This decision was driven by PyTorch's flexibility, powerful capabilities in handling sequential data, and enhanced G PU usage. This accelerates the model's computations on large-scale radiotherapy data. Through hyperparameter tuning, the validation accuracy of our PyTorch model has been improved from an initial 7 % to over 60 %. Moreover, the PyTorch Distributed Data Parallelism strategy was used to train the RNN models on multiple G PU s, which significantly reduced the training time with a minor impact on model accuracy. © 2023 IEEE.

关键词： Clas-sification Compton camera Distributed Data Parallelism Proton beam therapy PyTorch Recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

Mine-to-client planning with Markov Decision Process 18

Mine-to-client planning with Markov Decision Process

引用

18th European Control Conference, ECC 2020

作者： Leal Gomes Leite, Joao Marcelo Arruda, Edilson F. Bahiense, Laura Marujo, Lino G. Federal University of Rio de Janeiro Industrial Engineering Program Alberto Luiz Coimbra Institute Graduate School and Research in Engineering Rio de Janeiro Brazil Federal University of Rio de Janeiro Systems Engineer and Computer Science Program Alberto Luiz Coimbra Institute Graduate School and Research in Engineering Rio de Janeiro Brazil

ISBN: (纸本)9783907144015

This works presents an innovative application of Markov Decision Process (MDP) to a medium-term mining logistics planning problem considering the mine-to-client supply chain. We implemented three distinct algorithms based on state-of-the-art approaches to solve large-scale problems, and compared their results. Furthermore, we combined all three variants in a single novel algorithm that attained fast convergence and may be an alternative to circumvent the curse of dimensionality underlying large scale problems. © 2020 EUCA.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

Towards Robust and Scalable Dispatch Modeling of Long-Duration Energy Storage

arXiv

引用

arXiv 2024年

作者： Guerra, Omar J. Dalvi, Sourabh Thatte, Amogh A. Cowiestoll, Brady Jorgenson, Jennie Hodge, Bri-Mathias National Renewable Energy Laboratory 15013 Denver West Parkway GoldenCO80401 United States Colorado School of Mines Advanced Energy Systems Graduate Program 1500 Illinois Street GoldenCO80401 United States Renewable and Sustainable Energy Institute University of Colorado BoulderCO80309 United States Department of Electrical Computer & Energy Engineering University of Colorado BoulderCO80309 United States

Energy storage technologies, including short-duration, long-duration, and seasonal storage, are seen as technologies that can facilitate the integration of larger shares of variable renewable energy, such as wind and solar photovoltaics, in power systems. However, despite recent advances in the techno-economic modeling of energy storage (particularly for short-duration applications), the operation and economics of long-duration energy storage are still incomplete in power systems modeling platforms. For instance, existing modeling approaches for long-duration storage are often based either on an oversimplified representation of power system operations or limited representation of storage technologies, e.g., evaluation of only a single application. This manuscript presents an overview of the challenges of modeling long-duration energy storage technologies, as well as a discussion regarding the capabilities and limitations of existing approaches. We used two test power systems with high shares of both solar photovoltaics- and wind (70% - 90% annual variable renewable energy shares) to assess long-duration energy storage dispatch approaches. Our results estimate that better dispatch modeling of long-duration energy storage could increase the associated operational value by 4% - 14% and increase the standard capacity credit by 14% - 34%. Thus, a better long-duration energy storage dispatch could represent significant cost saving opportunities for electric utilities and system operators. In addition, existing long-duration dispatch modeling approaches were tested in terms of both improved system value (e.g., based on production cost and standard capacity credit) and scalability (e.g., based on central processing unit time and peak memory usage). Both copper plate and nodal representations of the power system were considered. Although the end volume target dispatch approach, i.e., based on mid-term scheduling, showed promising performance in terms of both improved system

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Electromagnetic textile absorber applied to 4G and 5G bands

引用

Scientific reports 2025年第1期15卷 18768页

作者： Paulo H B Carvalho Ewaldo E C Santana Allan K D Barros Filho Paulo F Silva Júnior Keyll C R Martins Talita C Azevedo Waldemir P Martins Mauro A Medeiros Rubens S Gonçalves Lourival M Sousa Filho Gricirene S Correia Gabrielle M Fernandes Talita C Pinheiro Brenda A S Rodrigues Carlos A M Cruz Graduate Program in Electrical Engineering Federal University of Maranhão (UFMA) São Luís MA Brazil. phenrique@ifma.edu.br. Graduate Program in Electrical Engineering Federal University of Maranhão (UFMA) São Luís MA Brazil. Graduate Program in Computer and Systems Engineering Maranhão State University (UEMA) São Luís MA Brazil. Graduate Program in Mechanical Engineering Federal Institute of Maranhão (IFMA) São Luís MA Brazil. Department of Electrical Engineering Federal Institute of Paraíba (IFPB) João Pessoa PB Brazil. Graduate Program in Electrical Engineering Federal University of Amazonas (UFAM) Manaus AM Brazil. Department of Electronics and Computation Federal University of Amazonas (UFAM) Manaus AM Brazil.

Absorber materials are developed to reduce electromagnetic radiation and ensure the compatibility of the operation of electronic equipment in environments subject to interference. This work presents the development of a low-cost textile electromagnetic absorber for 4G and 5G technologies, operating at frequencies of 2.5 GHz and 3.5 GHz. The proposed electromagnetic absorber utilizes a 1 mm-thick Denim substrate, with a graphite composite used in the agricultural and commercial polyvinyl acetate glue industry, with the relationship of 25 wt%. The measurements were carried out in a Vector Network Analyzer, model E5071C Agilent Technologies, with the characterization of the Denim substrate, the glue, and the identification of the best parameters for the construction of the absorber. In the project, three low-cost textile absorbers prototypes were fabricated, with G1 = 0.25 mm, G2 = 0.35 mm, and G3 = 0.5 mm of thickness layers of the composite deposited on a Denim fabric. The results indicate that the absorber prototypes G2 presents great results in the frequency range of 4G and 5G band, with a maximum absorption of 26.6 dB in 3.94 GHz, with a structure 98.83% thinner than the commercial absorber LF-75. The variation in absorption performance may be attributed to the different mechanisms by which the absorbers operate: the commercial absorber LF-75 primarily interacts with the magnetic field, whereas the textile prototype predominantly affects the electric field.

关键词： 4G and 5G bands Electromagnetic Low-cost Textile absorber

来源：评论

学校读者我要写书评

暂无评论

Terahertz Magnetospectroscopy of Gadolinium Gallium Garnet in Fields up to 25 T

Terahertz Magnetospectroscopy of Gadolinium Gallium Garnet i...

引用

JSAP-OSA Joint Symposia, JSAP 2021

作者： Bao, J. Peraca, N. Marquez Tay, F. Kritzell, T.E. Li, X. Noe, G.T. Katayama, I. Takeda, J. Nojiri, H. Yamahara, H. Tabata, H. Baydin, A. Kono, J. Department of Physics and Astronomy Rice University HoustonTX United States Department of Electrical and Computer Engineering Rice University HoustonTX United States Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX United States Department of Physics Graduate School of Engineering Science Yokohama National University Yokohama Japan Institute for Materials Research Tohoku University Sendai Japan Department of Electrical Engineering and Information Systems Graduate School of Engineering University of Tokyo Japan Smalley-Curl Institute Rice University HoustonTX United States Department of Materials Science and NanoEngineering Rice University HoustonTX United States

来源：评论

学校读者我要写书评

暂无评论

AVTENet: Audio-Visual Transformer-based Ensemble Network Exploiting Multiple Experts for Video Deepfake Detection

arXiv

引用

arXiv 2023年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Academia Sinica Taipei11529 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu30013 Taiwan The Department of Computer Science National Chengchi University Taipei11605 Taiwan The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Forged content shared widely on social media platforms is a major social problem that requires increased regulation and poses new challenges to the research community. The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous work on detecting AI-generated fake videos only utilizes visual modality or audio modality. While there are some methods in the literature that exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multi-modal datasets of deepfake videos involving acoustic and visual manipulations. Moreover, these existing methods are mostly based on CNN and suffer from low detection accuracy. Inspired by the recent success of Transformer in various fields, to address the challenges posed by deepfake technology, in this paper, we propose an Audio-Visual Transformer-based Ensemble Network (AVTENet) framework that considers both acoustic manipulation and visual manipulation to achieve effective video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multi-modal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that our best model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. © 2023, CC BY.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Economics of Semantic Communication System: An Auction Approach

arXiv

引用

arXiv 2022年

作者： Liew, Zi Qin Du, Hongyang Yang, Wei Lim, Bryan Xiong, Zehui Niyato, Dusit Miao, Chunyan Kim, Dong In Alibaba-NTU Singapore Joint Research Institute Nanyang Technological Univerity Singapore The School of Computer Science and Engineering The Energy Research Institute NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The School of Computer Science and Engineering Nanyang Technological University Singapore The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore Nanyang Technological University Singapore639798 Singapore The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Semantic communication technologies enable wireless edge devices to communicate effectively by transmitting semantic meaning of data. Edge components, such as vehicles in next-generation intelligent transport systems, use well-trained semantic models to encode and decode semantic information extracted from raw and sensor data. However, the limitation in computing resources makes it difficult to support the training process of accurate semantic models on edge devices. As such, edge devices can buy the pretrained semantic models from semantic model providers, which is called "semantic model trading". Upon collecting semantic information with the semantic models, the edge devices can then sell the extracted semantic information, e.g., information about urban road conditions or traffic signs, to the interested buyers for profit, which is called "semantic information trading". To facilitate both types of the trades, effective incentive mechanisms should be designed. Thus, in this paper, we propose a hierarchical trading system to support both semantic model trading and semantic information trading jointly. The proposed incentive mechanism helps to maximize the revenue of semantic model providers in the semantic model trading, and effectively incentivizes model providers to participate in the development of semantic communication systems. For semantic information trading, our designed auction approach can support the trading between multiple semantic information sellers and buyers, while ensuring individual rationality, incentive compatibility, and budget balance, and moreover, allowing them achieve higher utilities than the baseline method. Copyright © 2022, The Authors. All rights reserved.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

FluxProg 2.0 - Teaching Introductory programming Using Flowcharts with Real and Simulated Robots for The Brazilian Robotics Olympiad (OBR)

FluxProg 2.0 - Teaching Introductory Programming Using Flowc...

引用

IEEE Latin American Robotics Symposium, LARS

作者： João Alberto Fabro Matheus Biscaya Gutierrez Fernando Henrique Ratusznei Caetano DAINF - Academic Department of Informatica PPGCA - Graduate Program on Applied Computing LASER-Laboratory for Advanced Robotics and Embedded Systems UTFPR - Federal University of Technology - Paraná Curitiba PR - Brazil Information Systems academic - UTFPR - Federal University of Technology - Paraná Curitiba PR - Brazil Computer Engineering academic - UTFPR - Federal University of Technology - Paraná Curitiba PR - Brazil

ISBN: (数字)9781665462808

ISBN: (纸本)9781665462815

In this paper, an approach to aid in introductory programming courses is presented, focused on students that had never had any contact with computer programming. The approach, that was introduced in a previous paper [3], presents programming concepts using icons and “flowcharts”, and a 3D robotics simulator (CoppeliaSim), that has free educational use. This time, a real version of the simulated robot, built using Arduino and cheap, easily obtainable electronic components, is also presented. The programs to control the robot are developed by graphically constructing flowcharts on the visual editor, and then following the execution of programs using the simulated (or real) robot, step by step. This graphic program editor is named “FluxProg”, and its 2nd version is now available online, with new features comprising variables, arithmetic and logic expressions, thus providing a complete programming environment.

关键词： Flowcharts Visualization Three-dimensional displays Conferences Education Electronic components Robots

来源：评论

学校读者我要写书评

暂无评论

Speaker-Specific Articulatory Feature Extraction Based on Knowledge Distillation for Speaker Recognition

引用

APSIPA Transactions on Signal and Information Processing 2023年第2期12卷

作者： Qian-Bei Hong Hsin-Min Wang Chung-Hsien Wu Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Taiwan Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica and Department of Computer Science and Information Engineering National Cheng Kung University Taiwan

This paper proposes a novel speaker-specific articulatory feature (AF) extraction model based on knowledge distillation (KD) for speaker recognition. First, an AF extractor is trained as a teacher model for extracting the AF profiles of the input speaker dataset. Next, a KD-based speaker embedding extraction method is proposed to distill the speaker-specific information from the AF profiles in the teacher model to a student model based on multi-task learning, in which the lower layers not only capture the speaker characteristics from acoustic features, but also learn the speaker-specific features from the AF profiles for robust speaker representation. Finally, speaker embeddings are extracted from the high-level layer, and the obtained speaker embeddings are further used to train a probabilistic linear discriminant analysis (PLDA) model for speaker recognition. In the experiments, speaker embedding models were trained using the VoxCeleb2 dataset and the AF extractor was trained based on the LibriSpeech dataset, and the performance was evaluated using the VoxCeleb1 dataset. The experiments showed that the proposed KD-based models outperformed the baseline models without KD. Furthermore, feature concatenation of multimodal results can further improve the performance.

关键词： Speaker recognition articulatory feature knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

Scalable Crystal Structure Relaxation Using an Iteration-Free Deep Generative Model with Uncertainty Quantification

arXiv

引用

arXiv 2024年

作者： Yang, Ziduo Zhao, Yi-Ming Wang, Xian Liu, Xiaoqing Zhang, Xiuying Li, Yifan Lv, Qiujie Chen, Calvin Yu-Chian Shen, Lei Department of Mechanical Engineering National University of Singapore Singapore117575 Singapore Artificial Intelligence Medical Research Center School of Intelligent Systems Engineering Shenzhen Campus of Sun Yat-sen University Shenzhen518107 China Department of Physics National University of Singapore Singapore117551 Singapore -Preferred Program School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen518055 China State Key Laboratory of Chemical Oncogenomics School of Chemical Biology and Biotechnology Peking University Shenzhen Graduate School Shenzhen518055 China Department of Medical Research China Medical University Hospital Taichung40447 Taiwan Department of Bioinformatics and Medical Engineering Asia University Taichung41354 Taiwan Guangdong L-Med Biotechnology Co. Ltd. Guangdong Meizhou514699 China Research Institute Chongqing401123 China

In computational molecular and materials science, determining equilibrium structures is the crucial first step for accurate subsequent property calculations. However, the recent discovery of millions of new crystals and complex twisted structures has challenged traditional computational methods, both ab initio and machine-learning-based, due to their computationally intensive iterative processes. To address these scalability issues, here we introduce DeepRelax, a deep generative model capable of performing geometric crystal structure relaxation rapidly and without iterations. DeepRelax learns the equilibrium structural distribution, enabling it to predict relaxed structures directly from their unrelaxed ones. The ability to perform structural relaxation at the millisecond level per structure, combined with the scalability of parallel processing, makes DeepRelax particularly useful for large-scale virtual screening. We demonstrate DeepRelax's reliability and robustness by applying it to five diverse databases, including oxides, Materials Project, two-dimensional materials, van der Waals crystals, and crystals with point defects. DeepRelax consistently shows high accuracy and efficiency, validated by density functional theory calculations. Finally, we enhance its trustworthiness by integrating uncertainty quantification. This work significantly accelerates computational workflows, offering a robust and trustworthy machine-learning method for material discovery and advancing the application of AI for science. Code for DeepRelax is available at https://***/Shen-Group/DeepRelax. Copyright © 2024, The Authors. All rights reserved.

关键词： Point defects

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：