检索结果-内蒙古大学图书馆

38th International Cosmic Ray Conference, ICRC 2023

作者： Sako, T.K. Pogorelov, N.V. Amenomori, M. Bao, Y.W. Bi, X.J. Chen, D. Chen, T.L. Chen, W.Y. Chen, Xu Chen, Y. Cirennima Cui, S.W. Danzengluobu Ding, L.K. Fang, J.H. Fang, K. Feng, C.F. Feng, Zhaoyang Feng, Z.Y. Gao, Qi Gou, Q.B. Guo, Y.Q. Guo, Y.Y. Hayashi, Y. He, H.H. He, Z.T. Hibino, K. Hotta, N. Hu, Haibing Hu, H.B. Hu, K.Y. Huang, J. Jia, H.Y. Jiang, L. Jiang, P. Jin, H.B. Kasahara, K. Katayose, Y. Kato, C. Kato, S. Kawahara, I. Kawashima, T. Kawata, K. Kozai, M. Labaciren Le, G.M. Li, A.F. Li, H.J. Li, W.J. Li, Y. Lin, Y.H. Liu, B. Liu, C. Liu, J.S. Liu, L.Y. Liu, M.Y. Liu, W. Lu, H. Makishima, T. Masuda, Y. Matsuhashi, S. Matsumoto, M. Meng, X.R. Meng, Y. Mizuno, A. Munakata, K. Nakamura, Y. Nanjo, H. Ning, C.C. Nishizawa, M. Noguchi, R. Ohnishi, M. Okukawa, S. Ozawa, S. Qian, X. Qian, X.L. Qu, X.B. Saito, T. Sakata, M. Sako, T. Sako, T.K. Sasaki, T. Shao, J. Shibasaki, T. Shibata, M. Shiomi, A. Sugimoto, H. Takano, W. Takita, M. Tan, Y.H. Tateyama, N. Torii, S. Tsuchiya, H. Udo, S. Usui, R. Wang, H. Wang, S.F. Wang, Y.P. Wangdui Wu, H.R. Wu, Q. Xu, J.L. Xue, L. Yang, Z. Yao, Y.Q. Yin, J. Yokoe, Y. Yu, Y.L. Yuan, A.F. Zhai, L.M. Zhang, H.M. Zhang, J.L. Zhang, X. Zhang, X.Y. Zhang, Y. Zhang, Yi Zhang, Ying Zhao, S.P. Zhaxisangzhu Zhou, X.X. Zou, Y.H. Department of Space Science Center for Space Plasma and Aeronomic Research University of Alabama in Huntsville 320 Sparkman Drive HuntsvilleAL35899 United States Department of Physics Hirosaki University Hirosaki036-8561 Japan School of Astronomy and Space Science Nanjing University Nanjing210093 China Key Laboratory of Particle Astrophysics Institute of High Energy Physics Chinese Academy of Sciences Beijing100049 China National Astronomical Observatories Chinese Academy of Sciences Beijing100101 China Department of Mathematics and Physics Tibet University Lhasa850000 China Department of Physics Hebei Normal University Shijiazhuang050016 China University of Chinese Academy of Sciences Beijing100049 China Shandong University Qingdao266237 China Institute of Modern Physics SouthWest Jiaotong University Chengdu610031 China Department of Physics Shinshu University Matsumoto390-8621 Japan Faculty of Engineering Kanagawa University Yokohama221-8686 Japan Faculty of Education Utsunomiya University Utsunomiya321-8505 Japan Faculty of Systems Engineering Shibaura Institute of Technology Omiya330-8570 Japan Faculty of Engineering Yokohama National University Yokohama240-8501 Japan Institute for Cosmic Ray Research University of Tokyo Kashiwa277-8582 Japan Polar Environment Data Science Center Joint Support-Center for Data Science Research Research Organization of Information and Systems Tachikawa190-0014 Japan National Center for Space Weather China Meteorological Administration Beijing100081 China School of Information Science and Engineering Shandong Agriculture University Taian271018 China Department of Astronomy School of Physical Sciences University of Science and Technology of China Hefei230026 China National Institute of Informatics Tokyo101-8430 Japan National Institute of Information and Communications Technology Tokyo184-8795 Japan Department of Mechanical and Electrical Engineering Shangdong Management University Jinan

It has been established by high-statistics cosmic-ray experiments that the distribution of arrival directions of TeV cosmic rays have small anisotropic features with amplitudes of ∼0.1%. In this presentation, we use the intensity-mapping method based on Liouville’s theorem for the modeling of the TeV cosmic-ray anisotropy. Our results derived from the data of the Tibet ASγ experiment and the calculation of cosmic-ray trajectories in an MHD model heliosphere indicate that the relative intensity distibution of cosmic rays at the outer boundary of the heliosphere contains small-scale ansiotropic features with angular scales of smaller than ∼10◦, which does not seem realistic. A possible problem would be that the MHD model heliosphere used in this presentation is a single snapshot of the positive polarity phase of a solar cycle, while the experimental data covers ten years during the negative polarity phase of the 23rd solar cycle. In order to improve our intensity-mapping method, it would be necessary to have multiple snapshots of the MHD model heliosphere corresponding to the negative polarity phase, perform the intensity-mapping for each of the snapshots and take the average of the results. © Copyright owned by the author(s) under the terms of the Creative Commons.

关键词： Cosmic rays

来源：评论

学校读者我要写书评

暂无评论

Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimization

arXiv

引用

arXiv 2023年

作者： Du, Hongyang Zhang, Ruichen Liu, Yinqiu Wang, Jiacheng Lin, Yijing Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Cui, Shuguang Ai, Bo Zhou, Haibo Kim, Dong In The School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The School of Computer Science and Engineering Nanyang Technological University Singapore The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China The School of Information and Communication Engineering University of Electronic Sciences and Technology of China Chengdu China The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Shenzhen China The State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China School of Electronic Science and Engineering Nanjing University Jiangsu Nanjing210093 China The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Generative Diffusion Models (GDMs) have emerged as a transformative force in the realm of Generative Artificial Intelligence (GenAI), demonstrating their versatility and efficacy across various applications. The ability to model complex data distributions and generate high-quality samples has made GDMs particularly effective in tasks such as image generation and reinforcement learning. Furthermore, their iterative nature, which involves a series of noise addition and denoising steps, is a powerful and unique approach to learning and generating data. This paper serves as a comprehensive tutorial on applying GDMs in network optimization tasks. We delve into the strengths of GDMs, emphasizing their wide applicability across various domains, such as vision, text, and audio generation. We detail how GDMs can be effectively harnessed to solve complex optimization problems inherent in networks. The paper first provides a basic background of GDMs and their applications in network optimization. This is followed by a series of case studies, showcasing the integration of GDMs with Deep Reinforcement Learning (DRL), incentive mechanism design, Semantic Communications (SemCom), Internet of Vehicles (IoV) networks, etc. These case studies underscore the practicality and efficacy of GDMs in real-world scenarios, offering insights into network design. We conclude with a discussion on potential future directions for GDM research and applications, providing major insights into how they can continue to shape the future of network optimization. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Sentiment analysis over collaborative relationships in open source software projects 32

Sentiment analysis over collaborative relationships in open ...

引用

32nd International Conference on Software engineering and Knowledge engineering, SEKE 2020

作者： Li, Lingjia Cao, Jian Lo, David Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China School of Information Systems Singapore Management University 178902 Singapore

ISBN: (纸本)1891706500

Sentiments and collaboration efficiency are key factors in the success of the open source software (OSS) development process. However, in the software engineering domain, no studies have been conducted to analyze the effect between collaborators' sentiments, and the role of sentiment in collaborative relationships during the development process. In this study, we apply sentiment analysis and statistical analysis on collaboration artifacts over five projects on GitHub. We use sentiment consistency to quantify the relation between sentiments in collaborative relationships. It is found that sentiment consistency is positively correlated with the closeness of collaborative relationships and collaborators' overall sentiment states. We also perform the Granger causality test and network analysis to study the impact of sentiment consistency on a time series basis. It is found that positive consistent sentiments not only improve collaboration willingness to the utmost extent, followed by inconsistent and negative consistent sentiments, they also boost the closeness of the entire project community. These findings can be applied to develop better OSS project monitoring tools and improve project management by taking developers' sentiments during collaborations into consideration. © 2020 Knowledge systems Institute graduate School. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Managing Evacuation of Mixed Traffic Flow: Fleet Configuration, Lane Allocation, Lane Reversal, and Cross Elimination

SSRN

引用

SSRN 2022年

作者： Liu, Jialin Jiang, Rui Jia, Bin Liu, Yang Li, Xingang Wang, Ting Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Beijing Jiaotong University Beijing100044 China Department of Industrial Systems Engineering and Management National University of Singapore Singapore117516 Singapore School of Automotive and Transportation Engineering Hefei University of Technology Hefei230009 China

Mixed traffic dynamic evacuation is a challenging task considering heterogeneous populations and traffic congestion. Based on a novel objective function of minimum evacuation network clearance time (ENCT), this paper proposes a mixed traffic dynamic evacuation planning (MTDEP) model, which determines both fleet demand and road supply management strategies, including mixed fleet configuration, lane allocation, lane reversal, and cross-elimination intersections. In this model, a road network is discretized into a multi-size cell network to load mixed traffic, and the holding-back problem of the relaxed CTM is eliminated by adding the penalty term. Then, the proposed model is linearized as a mixed-integer linear program, and a Kriging surrogate-based optimization (KSBO) algorithm is developed. Numerical experiments are conducted on a six-link network and the Sioux-Falls network to validate the effectiveness of our proposed model and solution method. The results show that: (a) the evacuation efficiency of using a mixed fleet is better than that of using a homogeneous fleet in a certain evacuation demand range;(b) while the collaborative management strategies could improve evacuation efficiency, they also take into account the evacuation fairness of the mixed fleet;and (c) the holding-back problem does not affect ENCT but increases the total travel time of all evacuees (ETTT), which should be completely eliminated. © 2022, The Authors. All rights reserved.

关键词： Kriging

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Plant Phenotyping by Combining Domain Adaptation with 3D Plant Model Simulations: Application to Wheat Leaf Counting at Seedling Stage

引用

Plant Phenomics 2023年第2期5卷 226-238页

作者： Yinglun Li Xiaohai Zhan Shouyang Liu Hao Lu Ruibo Jiang Wei Guo Scott Chapman Yufeng Ge Benoit de Solan Yanfeng Ding Frédéric Baret Plant Phenomics Research Centre Academy for Advanced Interdisciplinary StudiesJiangsu Collaborative Innovation Center for Modern Crop ProductionNanjing Agricultural UniversityNanjingChina Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhanChina Graduate School of Agricultural and Life Sciences The University of Tokyo1-1-1 Midori-choNishitokyo CityTokyoJapan School of Agriculture and Food Sciences The University of QueenslandSt.LuciaQueensland 4072Australia Department of Biological Systems Engineering University of Nebraska-LincolnLincolnNebraska 68583United States INRAE Avignon UniversitéUMR EMMAHUMT CAPTE228route de l’aérodrome-CS 4050984914 Avignon Cedex 9France ARVALIS Institut du Végétal 3 Rue Joseph et Marie Hackin75116 ParisFrance

The number of leaves at a given time is important to characterize plant growth and *** this work,we developed a high-throughput method to count the number of leaves by detecting leaf tips in RGB *** digital plant phenotyping platform was used to simulate a large and diverse dataset of RGB images and corresponding leaf tip labels of wheat plants at seedling stages(150,000 images with over 2 million labels).The realism of the images was then improved using domain adaptation methods before training deep learning *** results demonstrate the efficiency of the proposed method evaluated on a diverse test dataset,collecting measurements from 5 countries obtained under different environments,growth stages,and lighting conditions with different cameras(450 images with over 2,162 labels).Among the 6 combinations of deep learning models and domain adaptation techniques,the Faster-RCNN model with cycle-consistent generative adversarial network adaptation technique provided the best performance(R^(2)=0.94,root mean square error=8.7).Complementary studies show that it is essential to simulate images with sufficient realism(background,leaf texture,and lighting conditions)before applying domain adaptation ***,the spatial resolution should be better than 0.6 mm per pixel to identify leaf *** method is claimed to be self-supervised since no manual labeling is required for model *** self-supervised phenotyping approach developed here offers great potential for addressing a wide range of plant phenotyping *** trained networks are available at https://***/YinglunLi/Wheat-leaf-tip-detection.

关键词： Wheat seedling Plant

来源：评论

学校读者我要写书评

暂无评论

Self-adaptive 2D-3D ensemble of fully convolutional networks for medical image segmentation

Self-adaptive 2D-3D ensemble of fully convolutional networks...

引用

Medical Imaging 2020: Image Processing

作者： Baldeon Calisto, Maria G. Lai-Yuen, Susana K. Department of Industrial and Management Systems Engineering University of South Florida 4202 E. Fowler Ave. TampaFL33620 United States

ISBN: (纸本)9781510633933

Segmentation is a critical step in medical image analysis. Fully Convolutional Networks (FCNs) have emerged as powerful segmentation models achieving state-of-the art results in various medical image datasets. Network architectures are usually designed manually for a specific segmentation task so applying them to other medical datasets requires extensive expertise and time. Moreover, the segmentation requires handling large volumetric data that results in big and complex architectures. Recently, methods that automatically design neural networks for medical image segmentation have been presented;however, most approaches either do not fully consider volumetric information or do not optimize the size of the network. In this paper, we propose a novel self-adaptive 2D-3D ensemble of FCNs for 3D medical image segmentation that incorporates volumetric information and optimizes both the models performance and size. The model is composed of an ensemble of a 2D FCN that extracts intra-slice and long-range information, and a 3D FCN that exploits inter-slice information. The architectures of the 2D and 3D FCNs are automatically adapted to a medical image dataset using a multiobjective evolutionary based algorithm that minimizes both the expected segmentation error and number of parameters in the network. The proposed 2D-3D FCN ensemble was tested on the task of prostate segmentation on the image dataset from the PROMISE12 Grand Challenge. The resulting network is ranked in the top 10 submissions, surpassing the performance of other automatically-designed architectures while having 13.3 fewer parameters. © 2020 SPIE. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Addressing challenges for operating electrochemical solar fuels technologies under variable and diurnal conditions

引用

Frontiers in Energy Research 2024年 12卷

作者： Yap, Kyra M. K. Lee, Sol A. Kistler, Tobias A. Collins, Darci K. Warren, Emily L. Atwater, Harry A. Jaramillo, Thomas F. Xiang, Chengxiang Nielander, Adam C. Department of Chemical Engineering Stanford University StanfordCA United States SUNCAT Center for Interface Science and Catalysis SLAC National Accelerator Laboratory Menlo ParkCA United States Department of Applied Physics and Materials Science California Institute of Technology PasadenaCA United States Chemical Sciences Division Lawrence Berkeley National Laboratory BerkeleyCA United States Chemistry and Nanoscience Center National Renewable Energy Laboratory GoldenCO United States Advanced Energy Systems Graduate Program Colorado School of Mines GoldenCO United States

The outdoor operation of electrochemical solar fuels devices must contend with challenges presented by the cycles of solar irradiance, temperature, and other meteorological factors. Herein, we discuss challenges associated with these fluctuations presented over three timescales, including the effects of diurnal cycling over the course of many days, a single diurnal cycle over the course of hours, and meteorological phenomena that cause fluctuations on the order of seconds to minutes. We also highlight both reaction-independent and reaction-specific effects of variable conditions for the hydrogen evolution reaction and CO2 reduction reaction. We identify key areas of research for advancing the outdoor operation of solar fuels technology and highlight the need for metrics and benchmarks to enable the comparison of diurnal studies across systems and geographical locations. Copyright © 2024 Yap, Lee, Kistler, Collins, Warren, Atwater, Jaramillo, Xiang and Nielander.

关键词： Hydrogen fuels

来源：评论

学校读者我要写书评

暂无评论

Trends, Opportunities, and Challenges in Detecting Depressive Disorders Through Mobile Devices: A Review

Trends, Opportunities, and Challenges in Detecting Depressiv...

引用

Computer System, Information Technology, and Electrical engineering (COSITE), International Conference on

作者： Gregorius Natanael Elwirehardja Mahmud Isnan Anzaludin Samsinga Perbangsa Kahlil Muchtar Bens Pardamean Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Information System Department School of Information Systems Bina Nusantara University Jakarta Indonesia Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh Indonesia Computer Science Department BINUS Graduate Program -Master of Computer Science Bina Nusantara University Jakarta Indonesia

Depressive Disorders (DD) is one of the most prevalent mental disorders in the world that may lead to suicide cases. To prevent the latter, ubiquitous early detection systems may be effective. Recent studies have since researched the development of such systems by exploiting several forms of data, including video, audio, Ecological Momentary Assessments (EMA), and passive sensing data using sensors embedded in mobile devices. To summarize the trends, opportunities, and existing challenges in this field, this study reviewed 15 papers to answer four research questions. EMA was the most popular data to be used in this task, but other approaches, such as using video, audio, and typing behaviors, may be considered due to the subjectivity of EMA. These data were typically recorded using smartphones and analyzed using Machine Learning (ML). However, most of the developed systems had yet to be implemented. Overall, it was concluded that further studies may need to explore usages of more objective data in multimodal approaches as well as consider using Mobile Cloud Computing (MCC) to deploy these systems to provide more effective and efficient diagnoses. Future studies must also take into account the existing challenges of the data and infrastructures, such as the weaknesses of several data types, limitations of mobile devices, as well as the challenges of diagnosis approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VAENAR-TTS: Variational auto-encoder based non-autoregressive text-to-speech synthesis

arXiv

引用

arXiv 2021年

作者： Lu, Hui Wu, Zhiyong Wu, Xixin Li, Xu Kang, Shiyin Liu, Xunying Meng, Helen Dept. of Systems Engineering & Engineering Management Chinese University of Hong Kong Hong Kong Centre for Perceptual and Interactive Intelligence CUHK Hong Kong Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems Shenzhen International Graduate School Tsinghua University Shenzhen China Department of Engineering University of Cambridge United Kingdom Huya Inc. Guangzhou China

This paper describes a variational auto-encoder based nonautoregressive text-to-speech (VAENAR-TTS) model. The autoregressive TTS (AR-TTS) models based on the sequenceto-sequence architecture can generate high-quality speech, but their sequential decoding process can be time-consuming. Recently, non-autoregressive TTS (NAR-TTS) models have been shown to be more efficient with the parallel decoding process. However, these NAR-TTS models rely on phoneme-level durations to generate a hard alignment between the text and the spectrogram. Obtaining duration labels, either through forced alignment or knowledge distillation, is cumbersome. Furthermore, hard alignment based on phoneme expansion can degrade the naturalness of the synthesized speech. In contrast, the proposed model of VAENAR-TTS is an end-to-end approach that does not require phoneme-level durations. The VAENAR-TTS model does not contain recurrent structures and is completely non-autoregressive in both the training and inference phases. Based on the VAE architecture, the alignment information is encoded in the latent variable, and attention-based soft alignment between the text and the latent variable is used in the decoder to reconstruct the spectrogram. Experiments show that VAENARTTS achieves state-of-the-art synthesis quality, while the synthesis speed is comparable with other NAR-TTS models. Copyright © 2021, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Mapping Carbon Stock of Individual Street Trees Using Lidar-Camera Fusion-Based Mobile Mapping System

SSRN

引用

SSRN 2024年

作者： Yang, Tackang Ryu, Youngryel Kwon, Ryoungseob Choi, Changhyun Zhong, Zilong Nam, Yunsoo Jo, Seongwoo Interdisciplinary Program in Landscape Architecture Seoul National University Korea Republic of Integrated Major in Smart City Global Convergence Seoul National University Seoul Korea Republic of Department of Landscape Architecture and Rural Systems Engineering Seoul National University Seoul Korea Republic of Research Institute of Agriculture and Life Sciences Seoul National University Seoul Korea Republic of

Urban street trees account for a significant fraction of trees in urban areas, yet the carbon stocks of street trees remain largely unexamined. This study introduces a framework utilizing a Light Detection and Ranging (LiDAR)-camera fusion-based Mobile Mapping System (MMS) to estimate carbon stocks in individual street trees. This system allows simultaneous collection of species information and structural parameters on a city-wide scale, enabling the estimation of carbon stock. The framework comprises two principal components: the detection of individual street trees and the estimation of their respective carbon stocks. To detect individual street trees, we initially employed image-based deep learning model to diminish the effort needed in constructing point cloud training data and designing a universal rule applicable to complex and diverse urban streetscapes. In the carbon stock estimation phase, we used species-specific allometric equations based on species information derived from Yolo-v3 and Diameter at Breast Height (DBH) measurements from trunk point cloud circle fitting. Applying our method in Suwon, Republic of Korea, we mapped 34,124 street trees, revealing a total carbon stock of 6.18 GgC, despite some streets remaining unscanned. The proposed detection method achieved an F1-score of 81.9%, precision of 86.3%, and recall of 78.5% in city-scale experiments. Additionally, the Root Mean Square Error for the estimates of DBH and tree height was 3.2 cm (11.4%) and 1.8 m (18.3%), respectively. The results underscore the accuracy and scalability of the framework, highlighting its potential to facilitate efficient urban carbon management. © 2024, The Authors. All rights reserved.

关键词： Cameras

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：