检索结果-内蒙古大学图书馆

4th International Conference on Computer Vision, Image and Deep Learning, CVIDL 2023

作者： Zhan, Ruijie Lu, Jiadong Jiang, Yuchao Li, Tongfei Zhong, Guohao Lv, Wei City University of Macau Falcuty of Data Science 999078 China School of Aliyun Big Data Applications Zhuhai College of Science and Technology Zhuhai519041 China School of Computer Science Zhuhai College of Science and Technology Zhuhai519041 China

ISBN: (纸本)9798350326444

The prediction of typhoon trajectory is essential to protect people and property. However, traditional methods of typhoon track prediction are difficult to guarantee the prediction efficiency and accuracy when dealing with a large amount of complex data. With the improvement of computer computing power and the development of deep learning technology, deep neural networks are gradually applied to the field of meteorology. In this paper, we describe a typhoon trajectory prediction model named TyT (Typhoon technology with Transformer), which effectively uses large-scale multimodal historical data and advanced deep learning techniques to achieve typhoon trajectory forecasting. With the above design, Our TyT can make full use of the implicit correlation of multimodal data to realize the advantages that unimodal data-based methods do not have. Meanwhile, the structure of Transformer enables to establish long-range dependencies by attention mechanism and position encoding. Experiments on historical typhoon track data in the northwest Pacific Ocean show that our TyT has a significant improvement in accuracy compared to previous typhoon track prediction methods. Finally, four different typhoons are randomly selected to plot their tracks to visually demonstrate the prediction performance of our TyT. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Access Control Proxy Re-encryption with HRA Security from Lattice 18th

Fine-Grained Access Control Proxy Re-encryption with HRA Se...

引用

18th International Conference on Green, Pervasive, and Cloud Computing, GPC 2023

作者： Hou, Jinqiu Peng, Changgen Tan, Weijie Zhong, Chongyi Niu, Kun Li, Hu State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China Key Laboratory of Advanced Manufacturing Technology Ministry of Education Guizhou University Guiyang550025 China School of Mathematics and Big data Guizhou Education University Guiyang550025 China

ISBN: (纸本)9789819998951

With the gradual formation of the cloud computing ecosystem, the value of cloud computing is becoming increasingly evident, and the accompanying information security issues have become core elements. The challenge lies in securely transmitting, computing, and sharing data in a cloud computing environment while keeping privacy. In this paper, we propose an access control proxy re-encryption scheme that supports inner product operations based on lattices in the standard model. First, the ciphertext is linked to the attributes, and condition for transition is associated with the re-encryption key. The proxy may re-encrypt ciphertext that meets attribute conditions instead of all ciphertext, thereby limiting the proxy’s conversion permissions. Furthermore, the user outputs the inner product value after decryption. Finally, honestly re-encryption attacks (HRA) security with increased CPA security is employed to better capture the target of proxy re-encryption. In addition, we propose a new method of hiding access policy, which uses differential privacy technology to perturb the attribute values to better safeguard the privacy of users. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

A Surrogate-assisted Multi-objective Grey Wolf Optimizer for Empty-heavy Train Allocation Considering Coordinated Line Utilization Balance

引用

Journal of Bionic Engineering 2025年第1期22卷 383-397页

作者： Zhigang Du Shaoquan Ni Jeng-Shyang Pan Shuchuan Chu School of Transportation and Logistics Southwest Jiaotong UniversityChengdu610031China School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing210044China National and Local Joint Engineering Lab for Integrated Transportation Intelligence Chengdu610031China National Engineering Lab of Comprehensive Transportation Big Data Application Technology Chengdu610031China

This paper introduces the Surrogate-assisted Multi-objective Grey Wolf Optimizer(SMOGWO)as a novel methodology for addressing the complex problem of empty-heavy train allocation,with a focus on line utilization *** integrating surrogate models to approximate the objective functions,SMOGWO significantly improves the efficiency and accuracy of the optimization *** effectiveness of this approach is evaluated using the CEC2009 multi-objective test function suite,where SMOGWO achieves a superiority rate of 76.67%compared to other leading multi-objective ***,the practical applicability of SMOGWO is demonstrated through a case study on empty and heavy train allocation,which validates its ability to balance line capacity,minimize transportation costs,and optimize the technical combination of heavy *** research highlights SMOGWO's potential as a robust solution for optimization challenges in railway transportation,offering valuable contributions toward enhancing operational efficiency and promoting sustainable development in the sector.

关键词： Surrogate-assisted model Grey wolf optimizer Multi-objective optimization Empty-heavy train allocation

来源：评论

学校读者我要写书评

暂无评论

DCTNets: Deep crowd transfer networks for an approximate crowd counting

引用

Cognitive Robotics 2022年 2卷 96-111页

作者： Ali, Arslan Ou, Weihua Kanwal, Saima School of Big Data and Computer Science Guizhou Normal University Guiyang China School of Computer Science Lanzhou University of Technology Lanzhou China

Due to the numerous real-world applications of the crowd counting job, it has become a popular research topic. Modern crowd counting systems have a sophisticated structure and employ a filter on a big image size, making them difficult to use. Because these technologies are computationally intensive and difficult to implement in small surveillance systems, they are not appropriate for use in small surveillance systems. They also function poorly in a variety of sizes and densities, as well. Transfer learning and deep convolutional neural network architecture are used to create a modest but efficient network, which we describe herein. We named the proposed crowd counting architecture deep crowd transfer network (DCTNets) since it incorporates both deep learning and transfer learning principles into a single system. Among DCTNets’ key components are a detection module that is based on mask R-CNNs and an estimate module that is based on deep convolutional neural networks. In the first step, we apply transfer learning to the Mask R-CNN model using the datasets ShanghaiTech, JHU-CROWD++, and UCF-QNRF. After that, we train and evaluate the complete architecture on these datasets using the transfer learning results. Input images are sent through a Mask R-CNN, which counts individuals and segments the counted region, then through an estimation network, which estimates the population size, and finally through a merge of the outputs from the two models. According to the findings of comparative tests, the proposed model outperforms existing state-of-the-art approaches on the ShanghaiTech, JHU-CROWD++, and UCF-QNRF datasets. © 2022

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the quality of grassroots statistics based on a combined empowerment cloud model 4

Evaluation of the quality of grassroots statistics based on ...

引用

4rth International Conference on Applied Mathematics, Modelling, and Intelligent Computing, CAMMIC 2024

作者： Wang, Kexin Huang, Xing Lu, Qinghua Mao, Jiayuan Key Laboratory of Public Big Data Security Technology Chongqing College of Mobile Communication Chongqing401420 China Chongqing Key Laboratory of Public Big Data Security Technology Chongqing401420 China Chongqing College of Mobile Communication Chongqing401420 China College of Science Chongqing University of Technology Chongqing400054 China

ISBN: (纸本)9781510681637

High-quality grass-roots statistics are an important guarantee to objectively reflect the development of grass-roots social and economic operations and provide strong data support for government decision-making. A combined empowerment cloud model is constructed to evaluate the quality of grass-roots statistics. Firstly, the index system for evaluating the quality of grassroots statistics is proposed based on GB/T 36344-2018 national standard framework;secondly, to calculate the weights of subjective and objective indicators, AHP-CRITIC is used in combination with game theory to estimate combination weights;then, the cloud model is constructed to evaluate the quality of grassroots statistics;finally, the proposed method is proved to be reasonable and effective through example analysis, and the cloud The model takes into account the randomness and fuzziness of some indicators and can provide a scientific and reliable decision basis for the evaluation of the quality of grass-roots statistics. © 2024 SPIE.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

A Weighted Gridding Method for the Long-Range Lightning Location Network Accuracy Evaluation 37

A Weighted Gridding Method for the Long-Range Lightning Loca...

引用

37th International Conference on Lightning Protection, ICLP 2024

作者： Song, Lin Li, Jie Zhang, Qilin Li, Qingda Yang, Jun Qingdao Ecological and Agricultural Meteorological Center Qingdao China Jiangsu Key Laboratory of Big Data Analysis Technology Nanjing University of Information Science and Technology Nanjing China

ISBN: (纸本)9783800764174

Location accuracy is an important index to evaluate the performance of the very low frequency long-range lightning location network (VLF-LLN). However, it is impossible for us to evaluate the location accuracy of any area of the location network objectively and fairly by relying on real lightning observation data. Based on two-year lightning data of a newly built long-range lightning location network, we propose a weighted gridding method for evaluating the location network accuracy, which is different from the Monte Carlo method. We complete the following research and the results suggest the conclusions: 1) taking the location results of 11-station synchronization as a reference, it is found that the different numbers and configurations of stations have much more effect on the location results outside the network than those inside, and the deviation distance decreases with the increase of station numbers. 2) The location results of the 11-station and 13-station synchronizations were assumed to be the reference stroke points, the results of 5-to 10-station synchronizations were relocated, and the probability of deviation distance less than 1 km, 3 km, 5 km and 7 km were calculated. It is found that the proportion of the deviation distance is similar for these references, when the station numbers exceed 7-8, the median location results approximately reach a constant value, while the distribution of data samples is relatively scattered. 3) the location deviation of a large lightning samples is analyzed to statistically evaluate the location accuracy of any grid of the network by weighted gridding method, and present the percentage of deviation distance less than specific location accuracy for each grid of the network. © 2024 IEEE, © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bootstrap-Based Layerwise Refining for Causal Structure Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2708-2722页

作者： Xiang, Guodu Wang, Hao Yu, Kui Guo, Xianjie Cao, Fuyuan Song, Yukun Hefei University of Technology Key Laboratory of Knowledge Engineering with the Big Data of Ministry of Education Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Shanxi University School of Computer and Information Technology Taiyuan030006 China

Learning causal structures from observational data is critical for causal discovery and many machine learning tasks. Traditional constraint-based methods first adopt conditional independence (CI) tests to learn a global skeleton layer by layer and then orient the undirected edges to obtain a causal structure. However, the reliability of these statistical tests largely depends on the quality of data samples. In real-life scenarios, the presence of data noise or limited samples often makes many CI tests unreliable at each layer in the skeleton learning phase, leading to an inaccurate skeleton. As the number of layers increases, the inaccurate skeleton will continue to impair the skeleton construction of subsequent layers. Furthermore, an unreliable skeleton hampers the skeleton orientation procedure, resulting in an unsatisfactory causal structure. In this article, we propose a Bootstrap-based layerwise refining (BLR) algorithm for causal structure learning, which includes two new procedures to solve the above problems. First, BLR utilizes a novel layerwise skeleton refining procedure to construct the global skeleton layer by layer based on the bootstrap sampling. Second, BLR employs a collective skeleton orientation procedure that incorporates scoring techniques to collectively orient the global skeleton. The experimental results show that BLR outperforms the state-of-the-art methods on the benchmark Bayesian Network datasets. © 2020 IEEE.

关键词： Refining

来源：评论

学校读者我要写书评

暂无评论

Predictive Analysis of COVID-19 data using Machine Learning

Predictive Analysis of COVID-19 Data using Machine Learning

引用

2023 Cross Strait Radio science and Wireless technology Conference, CSRSWTC 2023

作者： Gong, Bin Zhu, Yizhao Li, Mingchao Lv, Wei City University of Macau Faculty of Data Science Macau China School of Business Shenzhen Institute of Technology Shenzhen China Alibaba Cloud College of Big Data Application Zhuhai College of Science and Technology Zhuhai China

ISBN: (纸本)9798350358971

The COVID-19 pandemic has had far-reaching health consequences, including mental health issues and long-term physical symptoms. Mental health problems such as anxiety and depression have surged due to isolation and uncertainty. Concerns are rising regarding the pandemic's lasting impact on mental well-being. Furthermore, COVID-19 patients may experience persistent symptoms like fatigue and muscle weakness, affecting their long-term health. Leveraging machine learning (ML) techniques, and analyzing post-pandemic health impacts can reveal patterns and research insights. ML can utilize extensive data from electronic health records and public health databases to identify trends and potential future health issues. Additionally, ML models can monitor medical records and public health data, aiding in the swift detection and response to disease outbreaks by public health officials. © 2023 IEEE.

关键词： Health Analytics Machine Learning Prediction Recognizing Patterns

来源：评论

学校读者我要写书评

暂无评论

A digital economy development index based on an improved hierarchical data envelopment analysis approach

引用

European Journal of Operational Research 2024年第3期316卷 1146-1157页

作者： Guo, Chuanyin Song, Qiwei Yu, Ming-Miin Zhang, Jian School of Economics and Management Beijing Information Science & Technology University Beijing 100192 China Department of Transportation Science National Taiwan Ocean University Keelung Taiwan Beijing Key Lab of Green Development Decision Based on Big Data Beijing 100192 China

The digital economy is playing an increasingly important role in the global economy. National and international organizations commonly utilize a composite index composed of multi-dimensional indicators to monitor performance, analyse policies, and communicate in the digital economy. This study introduces a hierarchical framework for constructing a Digital Economy Development Index (DEDI). One of the key challenges is determining the attribute weights to be assigned by aggregating the sub-indicators with hierarchical dimensions for DEDI. The current study shows that an H-DEA model can be transformed into a parametric linear programming problem and develops an improved golden section algorithm to search for approximate optimal solutions. The newly developed method is highly robust and provides an alternative procedure to determine the optimal weights for building a DEDI. We established a hierarchical evaluation framework and utilized a new approach to measure the DEDI of 30 provinces in China from 2015 to 2020. The results show that inter-provincial digital economy development in China shows a sequential weakening from the east, centre, and northeast to the west. The East leads the country's digital economy overall, while there is a clear gradient gap between provinces. The central region needs to create a cluster for the development of digital industries. The Northeast should enhance the competitiveness of the industry across the board. The West must strengthen the construction of innovative talent and new infrastructure for the digital economy. These findings can serve as guidelines for designing China's ongoing digital economy development. © 2024 Elsevier B.V.

关键词： data envelopment analysis

来源：评论

学校读者我要写书评

暂无评论

On-Line System of Garbage Image-Orientated Intelligent Classification, Submission and Examination 20

On-Line System of Garbage Image-Orientated Intelligent Class...

引用

20th IEEE International Conference on e-Business Engineering, ICEBE 2024

作者： Tian, Jiayin Wang, Yaozhi Liu, Jiaxin Chen, Yan School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Xi'an China Xi'an Jiaotong University Shaanxi Key Lab of Big Data Knowledge Engineering Shaanxi Xi'an China School of Computer Science and Technology Xi'an Jiaotong University Xi'an Jiaotong University Shaanxi Key Lab of Big Data Knowledge Engineering Shaanxi Xi'an China

ISBN: (纸本)9798350365856

In a world brimming with new products continually, novel waste types are ubiquitous. This makes current image-based garbage classification systems difficult to perform well due to the long-tailed effects of distribution of garbage types, and necessitates an urgent and efficient garbage classification with abilities of detecting new and rare wastes and class-incremental learning for environmental sustainability. Therefore, we propose a framework of Online System of Garbage Image-Oriented Intelligent Classification, Submission, and Examination, facilitating the incremental garbage classification efforts. In which, to identify novel garbage effectively, we also introduced few-shot object detection method with two key algorithms: Two-Stage Object Detection Learning Algorithm and Dynamic Query-based Incremental Few-shot Learning Algorithm. Our experiment results show that Both outperform the current existing ones in dataset, MS COCO. Then, a strategy of Class-Incremental learning based Residual Network is proposed to meet the need of new waste class-incremental learning. The experimental results support our strategy. Finally, a prototype system employed the above algorithms and the strategy is described. © 2024 IEEE.

关键词： Zero-shot learning

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：