检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Bai, Xueyuan Luo, Kaiyi Cui, Wen Wang, Zhengshang Ma, Zhenyu Wang, Xiaoyi Zhang, Wenchao Cui, Xudong School of Chemistry and Chemical Engineering Nanjing University of Science and Technology Nanjing210094 China Public safety laboratory Sichuan Police college Sichuan Province Luzhou646000 China Institute of Chemical Materials China Academy of Engineering Physics Mianyang621900 China Southwest Minzu University State Ethnic Affairs Commission Chengdu610041 China Key Laboratory of Radiation Physics and Technology of Ministry of Education Institute of Nuclear Science and Technology Sichuan University Chengdu610064 China

Within the realm of advancing photocatalysis, the investigation of material defects has perennially commanded paramount attention. However, a nuanced comprehension of the intricate interplay between these defects and the catalytic milieu necessitates deeper exploration. In the present study, oxygen vacancies (Vo) were adeptly harnessed to induce precise carrier localization, thereby effectuating a heightened augmentation of photocatalytic activity. This augmentation was deftly achieved through the deliberate modulation of external illumination parameters, resulting in the extension of carrier lifetimes. Specifically, the drastically enhanced carrier effective mass (m*) and the density of unoccupied state are directly uncovered by the density functional theory (DFT) calculation and Raman spectra. Through the utilization of wavelength dispersive in-situ fluorescence spectroscopy (WDIFS) experiments, it was observed that Vo-rich ZnO nanoparticles displayed noteworthy photocatalytic activity around the central frequency of Vo (5.17×1014 Hz, 580 nm), owing to the highly efficient utilization of localized carriers. Moreover, based on Einstein rate equations, the charge carrier lifetime was found to be further prolonged with increased external illumination intensity and excitation wavelength. This work provides a methodology for optimizing the functionality of point defect on photocatalysis, where the photo-induced charge carrier localization is expected to be extensively used in further photocatalysis research. © 2023, The Authors. All rights reserved.

关键词： Oxygen vacancies

来源：评论

学校读者我要写书评

暂无评论

An Expert Data Generation Method for Multi-Agent Cooperative Planning Method

An Expert Data Generation Method for Multi-Agent Cooperative...

引用

International Conference on automation and Computing (ICAC)

作者： Wenhui Zhu Qingquan Lin Xi Fu Qinggang Wu Kai Tang Weining Lu College of Mechanical Engineering Beijing Information Science and Technology University Beijing China Department of Automation Tsinghua University Beijing China Second Research Institute of Civil Aviation Administration of China Chengdu China Civil Unmanned Aircraft Traffic Management Key Laboratory of Sichuan Province Chengdu China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China

In environments with limited information, intelligent agents have restricted access to their current location, target location, and local environment details. To enhance their perception capabilities, this study introduces a fusion model called GraphSAGE-DH-Bug, which combines GraphSAGE and DH Bug algorithms. More importantly, the article presents the process of generating expert training databases and proposes three criteria for evaluating their effectiveness. These contributions establish the groundwork for applying the GraphSAGE-DH-Bug fusion model to multi-agent exploration in unknown environments. The experimental results validate the effectiveness of the generated dataset, which accurately represents the extended perception range of agents through the inclusion of neighboring agents.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simple Online Real-Time Tracking Algorithm with Improved YOLOV4 as Extractor

Simple Online Real-Time Tracking Algorithm with Improved YOL...

引用

Electronic Communications, Internet of Things and Big Data (ICEIB), International Conference on

作者： Fei Li Xiaotong Deng Feifei Shi Xiaoxue Zhou Kaijun Xia Guangdi Hu Mechanical Engineering Southwest Jiaotong University Chengdu China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China School of Nuclear Science and Technology Lanzhou University Chengdu China Jiangsu Xintongda Electronic Technology Co. LTD Jiangsu China Zhejiang Geely New Energy Commercial Vehicle Group Co. LTD Zhejiang China

ISBN: (纸本)9781665437561

Multiple target tracking algorithm is an important research field of computer vision. We improve the YOLOV4 algorithm by using the MatrixNets feature extraction module to obtain a better target detection and feature extractor and then uses the improved YOLOV4 algorithm to improve the deep sort algorithm to improve the performance of the algorithm to propose the Deep SORT-Y algorithm. The Deep SORT-Y algorithm can track the lost target object through a longer occlusion period, which greatly reduces the target loss rate. Compared with sort and deep sort algorithms, the score is reduced by 61 and 18%. Experimental evaluation shows that this algorithm still maintains the overall competitive advantage compared with other online real-time tracking algorithms at a high frame rate.

关键词： Computer vision Target tracking Object detection Big Data Feature extraction Real-time systems Data mining

来源：评论

学校读者我要写书评

暂无评论

Gesture Recognition Based on sEMG and Support Vector Machine

Gesture Recognition Based on sEMG and Support Vector Machine

引用

2021 IEEE International Conference on Robotics, automation and Artificial Intelligence, RAAI 2021

作者： Wang, Fang Jin, Jianing Gong, Zhiren Zhang, Wentao Tang, Guangyao Jia, Zesen Shanghai Institute of Microsystem and Information Technology University of Chinese Academy of Sciences Beijing China School of Information Science and Technology Southwest Jiaotong University Chengdu China College of Automation Nanjing University of Aeronautics and Astronautics Nanjing China College of Engineering University of Wisconsin–Madison Madison United States Leeds Joint School Southwest Jiaotong University Chengdu China Oaks Christian School Los Angeles United States

ISBN: (纸本)9781665425322

With the continuous development and progress of computer vision, the application scene of human gesture feature recognition is more and more widely, gesture feature recognition in human-computer interaction is a hot topic. The paper proposes a signal-vision model that combines support vector machine and gesture EMG signal to recognize different gesture features and sEMG signals. The model collects different gesture signals through the signal acquisition devices and removes noise through the design of sliding window filter which combines with the machine vision gesture detection framework. The paper also reduces the dimension through SVM models to predict and discriminate two different gesture features and visualizes them, we do the gesture detection and recognition so we can match the different gesture model and sEMG signal acquisition model. We demonstrate the potential of the approach proposed through extensive experiments and results show that the proposed model has significantly distinguish the different gesture features combined with support vector machine which can perform well in recognize and classify different gesture features. ©2021 IEEE

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

First-Principles Investigation of the Interaction between Oxygen and Alloy Atoms in [[Equation]] -Zirconium

SSRN

引用

SSRN 2023年

作者： Lu, Guodong Liu, Zhixiao Hu, Wangyu Wei, Tianguo Zhao, Yi Wang, Dong Deng, Huiqiu College of Materials Science and Engineering Hunan University Changsha410082 China Science and Technology on Reactor Fuel and Materials Laboratory Nuclear Power Institute of China Chengdu610213 China School of Physics and Electronics Hunan University Changsha410082 China

Zirconium alloys, being crucial materials in the nuclear industry, frequently encounter issues related to oxidative corrosion. Understanding the interaction between O atom and alloying atoms at the atomistic scale is helpful for optimizing Zr alloys with improved corrosion resistance. In the present study, a first-principles approach is used to understanding the stability and diffusion properties of an O atom in [[EQUATION]]-Zr with different alloy atoms (Sn, Nb, Fe and Cr). Our findings reveal that the most stable position for oxygen is always the octahedral (Oct) site whether it coordinates with an alloy atom or not. Comparing to other alloy atoms, Fe tends to exclude interstitial O even at the long range and the interaction is stronger than others, while the long-range interaction of Nb is the weakest. All alloy atoms considered in this work can enhance interstitial O diffusion rate, and promote the anisotropy of O diffusion. This work also confirms that the kinetically resolved activation method is a reliable method to predict O diffusion barrier in [[EQUATION]]-Zr. © 2023, The Authors. All rights reserved.

关键词： Atoms

来源：评论

学校读者我要写书评

暂无评论

Classification of Ship Navigation Behavior in Inland Crossing Channels

Classification of Ship Navigation Behavior in Inland Crossin...

引用

2021 International Conference on Security, Pattern Analysis, and Cybernetics, SPAC 2021

作者： Huang, Ziyi Zuo, Yi Li, Tieshan Wang, Haocheng Navigation College Dalian Maritime University Dalian China Collaborative Innovation Center of Maritime Big Data and Shipping Artificial General Intelligence Dalian China School of Automation Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781665443227

With the development of inland river transportation in China and the popularization of automatic identification systems (AIS), it has become more and more important to collect ship movement information and use it for maritime monitoring and management. However, ship movement information is complicated, and AIS data is often missing. It is very difficult to classify ship navigation behavior. This paper proposes an improved SRC model to solve it. In order to verify the performance of the model, the preprocessed data set of Huai'an section of Beijing-Hangzhou Canal is applied to the model. After comparing with other traditional classification models, the results show that the SRC model can effectively classify the navigation behavior of ships, and in most cases is better than other traditional classification models. © 2021 IEEE.

关键词： Ships

来源：评论

学校读者我要写书评

暂无评论

From Margins to Mainstream: Can Artificial Intelligence (Ai) Reshape Governance for Chittagong Hill Tracts Indigenous Communities?

SSRN

引用

SSRN 2024年

作者： Chakma, Vaskar Amin, Misbahul Rouf, Abdur Suruj, Al Mahmud Mia, Raju Rafid, Mustavi Computer Science and Technology School of Information Science and Technology Nantong University Seyuan Campus Seyuan Road – 9 Jiangsu Nantong226019 China Computer Science and Technology School of Computing and Artificial Intelligence Southwest Jiaotong University No. 999 Xi'an Road Pidu District Sichuan Chengdu611756 China Management Rabindra University Shahjadpur Upazila Sirajganj Bangladesh Machine Design Manufacturing and Automation College of Mechanical Engineering Yangzhou University Jiangsu China

Indigenous communities in the Chittagong Hill Tracts (CHT) of Bangladesh contend with multifaceted governance challenges, including representation, resource allocation, and access to services. This paper investigates the potential of Artificial Intelligence (AI) to address these issues and foster inclusive governance practices in the region. Grounded in the following research questions: 1) How are Indigenous communities currently governed in the CHT, and what are the primary challenges they face? 2) What are the opportunities and challenges of leveraging AI to enhance governance in the CHT? 3) How do Indigenous communities perceive the role of AI in governance, and what are their expectations and concerns? the study adopts a self-directed research approach, employing interviews, surveys, and online research to gather insights. Through a synthesis of existing literature and empirical findings, the paper identifies key considerations for deploying AI in governance contexts, including ethical implications, community engagement strategies, and capacity-building initiatives. The research underscores the importance of centering Indigenous perspectives and promoting participatory approaches in the design and implementation of AI-driven governance solutions. © 2024, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

An Early Two-Stage Fault Detection and Location Strategy Based on Collaboration Principal Component Analysis Method for Thermoelectric Generator System Monitoring

SSRN

引用

SSRN 2024年

作者： Meng, Jing-Hui Liu, Yan Zhang, Kai Bi, Jing-Liang Lu, Gui Beijing Key Laboratory of Emission Surveillance and Control for Thermal Power Generation North China Electric Power University Beijing102206 China School of Energy Power and Mechanical Engineering North China Electric Power University Beijing102206 China State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China CNNC Key Laboratory on Nuclear Reactor Thermal Hydraulics Technology Nuclear Power Institute of China Chengdu610213 China

Most existing research primarily focuses on enhancing the performance of thermoelectric generators (TEGs), while the significance of process monitoring, an equally vital aspect of device performance, has been neglected. This study introduces a novel two-stage monitoring approach, consisting of fault detection and fault location, based on collaboration principal component analysis (CPCA) method, to monitor the TEGs system effectively. Initially, a comprehensive mathematical model for the multi-physics TEGs system is established, and its accuracy is validated using experimental data. Subsequently, in the early stage of fault detection, a CPCA method is developed for fault monitoring and diagnosis, which can completely and effectively preserve and extract more internal information compared to conventional PCA-based methods. Finally, in the fault location stage, the CPCA method accurately identifies the faulty unit’s location by calculating its fault contribution among the TE units. By simulating the TEGss system under three different operating conditions, the results demonstrate that: 1) Abnormal operations can be detected 4-20 minutes prior to the occurrence of an actual fault;2) CPCA method shows a quite competitive effect among PCA-based methods;3) Faulty thermoelectric units can be precisely located under various working conditions. Introducing this advanced two-stage monitoring method effectively ensures safe operation and prolongs the device's lifespan. © 2024, The Authors. All rights reserved.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Unpaired PET image enhancement using an improved cycle consistent adversarial network

Unpaired PET image enhancement using an improved cycle consi...

引用

IEEE Symposium on nuclear Science (NSS/MIC)

作者： Y. Luo J. Cui D. Chen K. Shi X. Su H. Liu State Key Laboratory of Modern Optical Instrumentation College of Optical Science and Engineering Zhejiang University Hangzhou China Institute of Information Processing and Automation College of Information Engineering Zhejiang University of Technology Hangzhou China Department of Nuclear Medicine The First Affiliated Hospital Zhejiang University School of Medicine PET Center Hangzhou China Department of Nuclear Medicine Inselspital Bern University Hospital University of Bern Bern Switzerland

With the improvement of hardware technology, novel scanners such as uEXPLORER obtain significantly higher image quality than conventional scanners, but they have yet to be widespread. In addition, due to the limitations of scanning time and radiotracer dose, the PET images obtained in primary hospitals usually contains a lot of noise, which has an impact on quantitative medical analysis and diagnostic accuracy. It is of great interest to use image enhancement methods to enable primary hospitals to obtain PET images of comparable quality to the novel scanners. Obviously, in this task, we are unable to construct paired training sets, which makes common deep-learning-based methods *** overcome this challenge, we propose to use a cycle consistent generative adversarial network (CycleGAN) that does not require paired data to achieve PET image enhancement. In addition, we add correlation coefficient loss and image prior loss to the original CycleGAN model to directly constrain the structural consistency between the generated and input images. When using the proposed model for PET image enhancement, the high-quality image dataset acquired from the novel scanners is fixed as the basic high-quality training set. Since the low-and high-quality images can be unpaired, any low-quality PET images from different institutions that require enhancement can be input into the network as the low-quality set. After training, the generator can convert low-quality images into PET images with comparable image quality to that of the novel scanners. The results show that the proposed method outperforms NLM, BM3D, and DIP. Moreover, the proposed method performs better than the supervised RED-CNN and CycleGAN when implemented on a local hospital dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning based key parameters prediction in nuclear power plants

Deep learning based key parameters prediction in nuclear pow...

引用

14th International Conference on Quality, Reliability, Risk, Maintenance, and Safety engineering (QR2MSE 2024)

作者： Jing Cui Lei Song Zhanguo Ma Huayu Yuan Wenlin Wang Wenhao Jia Long Tian School of Automation Harbin University of Science and Technology Harbin People's Republic of China CNNC China Nuclear Power Engineering Co. Ltd Beijing People's Republic of China Xichang Satellite Launch Center Xichang People's Republic of China Sino-German College of Intelligent Manufacturing Shenzhen Technology University Shenzhen People's Republic of China

ISBN: (数字)9781837241958

Accurately obtaining key parameters under accident conditions in nuclear power plants (NPPs) is essential for safety analysis and is critically important for operational decision making. To enable rapid and precise forecasting of parameter trends in NPPs, we introduce an enhanced Non-stationary Transformer (NS Transformer) model. This model enhances the attention mechanism by incorporating a sparse attention mechanism. The sparse attention mechanism, which selectively focuses on key locations in the sequence, thereby significantly reducing computational complexity and memory use. In this paper, we detail the model structure and validate its effectiveness through experiments predicting key parameters in nuclear power plants. The results demonstrate that the improved prediction model can accurately forecast long-term parameter trends. This study enhances the accuracy of critical parameter predictions in NPPs during failure conditions, thereby improving the emergency response capabilities of NPPs in the event of failures and accidents.

关键词：

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：