检索结果-内蒙古大学图书馆

12th International Symposium on Project Management, ISPM 2024

作者： Zhang, Kehong Wang, Min Zhou, Chenjie School of Information Engineering and Artificial Intelligence Lanzhou University of Finance and Economics Gansu Lanzhou730030 China Gansu Provincial Key Laboratory of Intelligent Business China "Belt and Road" Intellectual Property Protection and Data Utilization Industrial Research Institute China

ISBN: (纸本)9798331302344

Emergency resource management is a very important part of the public affairs emergency management system, once the emergence of public emergencies requires timely and efficient emergency rescue response, and rapid emergency rescue capabilities must rely on scientific and reasonable emergency resource management scheduling. Therefore, this paper addresses the problem of emergency resource management scheduling, the application of knowledge mapping technology to build an emergency resource decision-making system, combining the government, enterprises and other social forces, collaborative cooperation, to ensure a rapid response in the event of emergencies, and improve the efficiency of emergency rescue. In this paper, we obtain the original text from the emergency management website through web crawlers and label the entity relationship types to complete the construction of the dataset;on this basis, the entity relationships are objectively displayed through the Neo4j graph database to complete the creation of the knowledge graph of emergency resource scheduling. The constructed knowledge graph is reliable and can provide a scientific program for emergency management scheduling. © 2024 ISPM. All Rights Reserved.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

RECC: A Relationship-Enhanced Content Caching Algorithm Using Deep Reinforcement Learning 6

RECC: A Relationship-Enhanced Content Caching Algorithm Usin...

引用

6th Asian Conference on Artificial Intelligence Technology, ACAIT 2022

作者： Ren, Jiarui Zhang, Haiyan Zhou, Xiaoping Zhu, Menghan Ningxia University School of Information Engineering Yinchuan China Beijing University of Civil Engineering and Architecture Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing China

ISBN: (纸本)9781665453110

Mobile edge caching (MEC) is a promising technology to alleviate traffic congestion in the network. Current studies explored deep reinforcement learning (DRL)-based MEC methods. These methods consider the dynamics of the request size to maximize the cache hit rate. However, they usually ignored the potential request relationships among contents. Two contents with a strong relationship are usually requested sequentially. Inspired by this assumption, this paper proposes a relationship-enhanced content caching algorithm using DRL, named RECC. Our RECC infers user preferences by mining the request relationships among contents. In this work, the relationships are modeled as request sequences, and the request features are learned by using graph embedding. These features will be used as input of state in our DRL-based algorithm. We utilize the Wolpertinger architecture to solve the limitation of large discrete action space. The simulation results indicate that our RECC outperformed the traditional cache policies and state-of-the-art DRL-based method in cache hit rate. Furthermore, the proposed RECC has advantages in long-term stability in the environment where content popularity changes dynamically, and also has a higher cache hit rate when handling the requests with number changes dynamically. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Review of Atmospheric Electricity Research in china from 2019 to 2022

引用

Advances in Atmospheric Sciences 2023年第8期40卷 1457-1484页

作者： Weitao LYU Dong ZHENG Yang ZHANG Wen YAO Rubin JIANG Shanfeng YUAN Dongxia LIU Fanchao LYU Baoyou ZHU Gaopeng LU Qilin ZHANG Yongbo TAN Xuejuan WANG Yakun LIU Shaodong CHEN Lyuwen CHEN Qingyong LI Yijun ZHANG State Key Laboratory of Severe Weather Chinese Academy of Meteorological SciencesBeijing 100081China Laboratory of Lightning Physics and Protection Engineering Chinese Academy of Meteorological SciencesBeijing 100081China Key Laboratory of Middle Atmosphere and Global Environment Observation Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China Key Laboratory of Transportation Meteorology of China Meteorological Administration Nanjing Joint Institute for Atmospheric SciencesNanjing 210041China Chinese Academy of Sciences Key Laboratory of Geospace Environment School of Earth and Space SciencesUniversity of Science and Technology of ChinaHefei 230026China Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters(CIC-FEMD) Nanjing University of Information Science&TechnologyNanjing 210044China Department of Electrical Engineering Shanghai Jiao Tong UniversityShanghai 200030China Institute of Tropical and Marine Meteorology China Meteorological AdministrationGuangzhou 510641China Beijing Key Lab of Transportation Data Analysis and Mining Beijing Jiaotong UniversityBeijing 100044China Department of Atmospheric and Oceanic Sciences and Institute of Atmospheric Sciences Fudan UniversityShanghai 200438China

Atmospheric electricity is composed of a series of electric phenomena in the *** advances in atmospheric electricity research conducted in china have been achieved in recent *** this paper,the research progress on atmospheric electricity achieved in china during 2019-22 is reviewed focusing on the following aspects:(1)lightning detection and location techniques,(2)thunderstorm electricity,(3)lightning forecasting methods and techniques,(4)physical processes of lightning discharge,(5)high energy emissions and effects of thunderstorms on the upper atmosphere,and(6)the effect of aerosol on lightning.

关键词： atmospheric electricity thunderstorm lightning lightning detection lightning physics

来源：评论

学校读者我要写书评

暂无评论

A Color Image Encryption Scheme Based on Block Compressive Sensing and Chaotic Systems 2

A Color Image Encryption Scheme Based on Block Compressive S...

引用

2nd International Conference on Applied Statistics, Computational Mathematics, and Software engineering, ASCMSE 2023

作者： Tian, Junfeng Chen, Keke Key Laboratory of Big Data Analysis and Processing of Henan Province Henan University Kaifeng475004 China College of Computer and Information Engineering Henan University Kaifeng475004 China Henan Province Engineering Research Center of Spatial Information Processing Henan University Kaifeng475004 China

ISBN: (数字)9781510668195

ISBN: (纸本)9781510668188

The traditional compressive sensing theory does not take full advantage of the differences in image block information features for sampling, and the measurement matrix does not adequately measure the image based on the image information features. To solve these problems, we design a color image encryption scheme based on block compressive perception and chaotic systems. First, the color image is divided into three channels of RGB and into 8*8 blocks respectively. Then, a zigzag transform is applied to each block so that each pixel value is evenly distributed. Each block is sparsified by the discrete cosine transform, and the measurement matrix generated by the Chen chaotic system is sampled to compress the image blocks to CR times the original block size according to different compression ratios (CR). The resulting chunked compressed samples are further distributed across the pixel values of the image using a cross-channel confusion dislocation method. Finally, the size of the pixel values is changed by a dissimilarity operation. The experimental results show that the scheme can balance the security of image information transmission and the integrity of reception, and has good resistance to various attacks. © 2023 SPIE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Forecasting of exchange rate time series based on event-aware transformer mode

引用

Soft Computing 2025年第6期29卷 3035-3045页

作者： Zhang, Siyi Che, Tong Zhu, Zhiliang Luo, Guoli Feng, Ping Virtual Reality and Interactive Techniques Institute East China Jiaotong University Nanchang330013 China Department of Engineering Mathematics University of Bristol Northern Ireland BristolBS8 1TH United Kingdom Guizhou Key Laboratory of Big Data Statistical Analysis Guizhou University of Finance and Economics Guiyang550025 China

Accurately forecasting exchange rate time series is crucial for effective risk management. The longer the forecast time window and the higher the frequency, the more valuable it is for managers to make timely decisions. In light of the task characteristics of exchange rate forecasting, this paper proposes an improved transformer-based model for addressing long sequence time series forecasting problems. Specifically, we introduce a position embedding method for events, which integrates the traditional coding context vector to perform joint location representation learning. Additionally, we explore a periodic enhancement method of features to jointly enhance the transformer-like model architecture’s ability to adaptively learn the long-term and hidden correlations of long sequence time series data. Extensive experimental results on the prediction of four exchange rate data for pairs of opening, high, low, and closing prices at a frequency of 5 min show that our model outperforms the prediction of the baseline method. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

Cooperative Physical Layer Authentication for Massive MIMO Machine-Type Communications 23

Cooperative Physical Layer Authentication for Massive MIMO M...

引用

23rd IEEE International Conference on Communication Technology, ICCT 2023

作者： Zhang, Haotian Wang, Junjie Han, Gangtao Wang, Ning School of Electrical and Information Engineering Zhengzhou University Zhengzhou450001 China Henan Joint International Research Laboratory of Intelligent Networking and Data Analysis Zhengzhou450001 China Southeast University State Key Laboratory of Millimeter Waves Nanjing210096 China

ISBN: (纸本)9798350325959

Aiming to improve the identity security of massive machine-type communications networks, a two-user cooperative physical layer authentication (PLA) scheme is proposed for the uplink transmission of a massive multiple-input multiple-output (MIMO) systems. In the proposed scheme, two single-antenna users synchronously transmit signals to the base station which is equipped with a large number of antennas, and fast varying channels are considered. A space-time modulation scheme is adopted for the two users to implement cooperative PLA, in which tags are selectively embedded into the transmitted signals based on the bit-relationships between the tags and the messages in order to improve the covertness of tags. A minimum Riemannian distance detector is proposed to implement the tag detection, while a fast noncoherent maximum likelihood (ML) detector is introduced to carry out the messages estimation. Binary hypothesis test is carried out for authentication by comparing the detected tags to the regenerated ones, in which the PLAs of the two users are handled as a whole. The closed-form bit error probability of the message is derived, while the authentication performance is analyzed. Computer simulation results demonstrate that the proposed scheme performs better on signal detection as well as identity authentication. © 2023 IEEE.

关键词： cooperative physical layer authentication massive MIMO noncoherent detection selective tag

来源：评论

学校读者我要写书评

暂无评论

Lightweight Remote Sensing Target Detection Algorithm Based on Improved YOLOv5 16th

Lightweight Remote Sensing Target Detection Algorithm Based ...

引用

16th International Conference on Genetic and Evolutionary Computing, ICGEC 2024

作者： Wang, Chaomin Dong, Fang Liang, Sheng Yu, Wanxin Wu, Kaixian Yu, Long Wenfeng, Wang School of Information Engineering Nanchang Institute of Technology Nanchang330099 China Jiangxi Province Key Laboratory of Smart Water Conservancy Nanchang Institute of Technology Nanchang330099 China School of Statistics and Data Science Jiangxi University of Finance and Economics Nanchang330013 China

ISBN: (纸本)9789819615346

Aiming at the problems of large memory space occupied by remote sensing image detection models in complex scenes, high computational complexity, and detection speed that is difficult to meet the real-time target detection requirements, a model compression algorithm based on dynamic detection head and channel pruning is proposed. Based on YOLOv5s, the head of the original YOLOv5 is replaced by the DyHead detection head, which improves the detection performance of the model by combining and unifying the three attention mechanisms of scale, space and task. Secondly, the Focaler-IoU loss function is introduced to further improve the predictive regression ability of the model. Finally, the channel pruning algorithm is used to eliminate the redundant parameters in the network to further compress the parameters and computation of the model, and the accuracy of the pruned model is improved by model fine-tuning. The experimental results show that there is a large improvement on the DOTAV1.0 dataset, and the validity is further verified on the RSOD dataset. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Jurassic

来源：评论

学校读者我要写书评

暂无评论

TraSculptor: Visual Analytics for Enhanced Decision-Making in Road Traffic Planning

引用

IEEE Transactions on Visualization and Computer Graphics 2025年 PP卷 PP页

作者： Deng, Zikun Liu, Yuanbang Zhu, Mingrui Xiang, Da Yu, Haiyue Su, Zicheng Lu, Qinglong Schreck, Tobias Cai, Yi South China University of Technology School of Software Engineering China South China University of Technology Ministry of Education Key Laboratory of Big Data and Intelligent Robot China Tongji University Key Laboratory of Road and Traffic Engineering of the Ministry of Education China National University of Singapore Department of Civil and Environmental Engineering Singapore Graz University of Technology Austria

The design of urban road networks significantly influences traffic conditions, underscoring the importance of informed traffic planning. Traffic planning experts rely on specialized platforms to simulate traffic systems, assessing the efficacy of the road network across various states of modifications. Nevertheless, a prevailing issue persists: many existing traffic planning platforms exhibit inefficiencies in flexibly interacting with the road network's structure and attributes and intuitively comparing multiple states during the iterative planning process. This paper introduces TraSculptor, an interactive planning decision-making system. To develop TraSculptor, we identify and address two challenges: interactive modification of road networks and intuitive comparison of multiple network states. For the first challenge, we establish flexible interactions to enable experts to easily and directly modify the road network on the map. For the second challenge, we design a comparison view with a history tree of multiple states and a road-state matrix to facilitate intuitive comparison of road network states. To evaluate TraSculptor, we provided a usage scenario where the Braess's paradox was showcased, invited experts to perform a case study on the Sioux Falls network, and collected expert feedback through interviews. © 1995-2012 IEEE.

关键词： Visual analytics

来源：评论

学校读者我要写书评

暂无评论

Texture Features and Machine Learning Based Environmental Microorganism Microscopic Image Classification

Texture Features and Machine Learning Based Environmental Mi...

引用

International Conference on Image, Vision and Intelligent Systems, ICIVIS 2023

作者： Ouyang, Xinyu Yuan, Huaqian Zhou, Shangqi Fu, Yanyu Yang, Jinzhu Grzegorzek, Marcin Wang, Yuexi Li, Chen Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China Institute of Medical Informatics University of Luebeck Luebeck Germany Department of Knowledge Engineering University of Economics in Katowice Katowice Poland Department of Rehabilitation Shengjing Hospital of China Medical University Shenyang China

ISBN: (纸本)9789819708543

In recent years, with the continuous development of molecular biology technology, the effective use of environmental microorganisms to solve the problem of pollution in the ecological environment has been widely used. However, the original microbial cultivation, environmental application and monitoring have the disadvantages of high degree of specialization, long time and high cost. In this case, the use of computer image processing and machine learning techniques for microbial identification and classification becomes a more efficient, economical and necessary method. This paper presents an environmental microorganism microscopic image classification method based on texture features and machine learning. In the research and experiments, microscopic images of microorganisms are cropped, grayed, data augmented, target areas segmented and extracted four types of texture features. The training set and test set are divided in a 1:1 ratio, and different recognition results are obtained based on different texture feature vectors and classifier models. Ultimately, the gradient-gray co-occurrence matrix feature combined with the Random Forest algorithm classifier achieves an F1-measure value of nearly 40%, which improves the work efficiency of environmental microbial researchers and related field workers. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Microorganisms

来源：评论

学校读者我要写书评

暂无评论

The “Bi-drifting” Subpulses of PSR J0815+0939 Observed with the Fivehundred-meter Aperture Spherical Radio Telescope

引用

Research in Astronomy and Astrophysics 2022年第2期22卷 195-203页

作者： Lun-Hua Shang Jun-Tao Bai Shi-Jun Dang Qi-Jun Zhi School of Physics and Electronic Science Guizhou Normal UniversityGuiyang 550001China School of Electronic and Optical Engineering Nanjing University of Science and TechnologyNanjing 210094China Guizhou Provincial Key Laboratory of Radio Astronomy and Data Processing Guizhou Normal UniversityGuiyang 550001China

We report the "Bi-drifting" subpulses observed in PSR J0815+0939 using the Five-hundred-meter Aperture Spherical radio Telescope(FAST). The observation at band from 1050 to 1450 MHz is evenly divided into two bands, i.e., the bands at center frequencies of 1150 and 1350 MHz. The mean pulse profiles and the "Bi-drifting"subpulses at these two bands are investigated. It is found that the pulse profiles at these two frequencies show four emission components, and the peak separations between four emission components decrease with the increase of frequency. In addition, the ratio of peak intensity of each component to the intensity of component Ⅳ at 1150 MHz is larger than that at 1350 MHz. We carry out an analysis of the longitude-resolved fluctuation spectrum and twodimensional fluctuation spectrum for each emission component, and find that the P3 of components Ⅰ,Ⅱ and Ⅲ is about 10.56, 10.57 and 10.59 s at 1150 and 1350 MHz. However, the reliable measurements of P3 of component IV and P2 for these four components were not obtained due to the low signal-to-noise ratio of observation *** pulse energy distributions at frequencies 1150 and 1350 MHz are presented, and it is found that no nulling phenomenon has been found in this pulsar. With our observation from the FAST, the "Bi-drifting" subpulse phenomenon of PSR J0815+0939 is expanded from 400 to 1350 MHz, which is helpful for the relevant researchers to test and constrain the pulsar emission model, especially the model of "Bi-drifting" subpulse.

关键词： (stars:)pulsars:general (stars:)pulsars:individual(PSR J0815+0939) radiation mechanisms:nonthermal

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：