检索结果-内蒙古大学图书馆

Semisupervised Few-Shot Remote Sensing Image Classification Based on KNN Distance Entropy

ieee JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2022年 15卷 8798-8805页

作者： Chao, Xuewei Li, Yang Shihezi Univ Coll Mech & Elect Engn Shihezi 832003 Peoples R China

In recent years, remote sensing image processing based on deep learning has been widely applied in many scenes, but the involved deep learning technology requires large-scale labeled data, which has been a practical problem in the remote sensing field. In this study, we proposed a novel data information quality assessment method, called K-nearest neighbor (KNN) distance entropy, to screen the remote sensing images. The evaluation metric was used to assess unlabeled data and assign the pseudolabel, which further constitutes the proposed semisupervised few-shot classification method in this article. The metatask setting was adopted to verify the validity and stability of experimental results. Specifically, the KNN distance entropy metric can be used to distinguish the samples in the core set or boundary set. Experimental results show that the core set samples are more suitable under the few-shot condition, for instance, the metatask average accuracy trained by the core set samples outperforms that by boundary samples by about 18% in the case of 45-ways and 5-shot. The proposed semisupervised few-shot method based on KNN distance entropy achieves significant improvement under different experimental conditions. The visualization of the feature distribution of screened data is shown to provide an intuitive interpretation. This article lays a meaningful foundation for screening and evaluating remote sensing images under few-shot conditions, and inspires the data-efficient few-shot learning based on high-quality data in the remote sensing field.

关键词： Entropy Remote sensing Task analysis Measurement Image quality Deep learning Sensors Entropy feature extraction image processing pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Day-Ahead Optimal Operation Strategy of Distribution Network Based on Energy Consumption Characteristics of data Centers and Guidance Price Mechanism 5

Day-Ahead Optimal Operation Strategy of Distribution Network...

引用

5th Asia Energy and Electrical Engineering symposium (AEEES)

作者： Jia, Yuqiao Li, Zheng Li, Wenbo Zhu, Xinyao Cui, Zhaoliang State Grid Jiangsu Elect Power Co Ltd Res Inst Nanjing Peoples R China Shandong Univ Sch Elect Engn Shandong Peoples R China

ISBN: (纸本)9781665490542

With the increasing penetration of distributed generation and flexible load in the distribution network, power generation and consumption plans made by different stakeholders may lead to uneven distribution of power flow in space and overload of some lines. For the increasingly large data centers in the flexible load, this paper proposes a day-ahead optimal operation strategy of distribution network based on its energy consumption characteristics and guidance price mechanism. First of all, combined with the CPU dynamic frequency modulation technology, the energy consumption characteristics of the data center and the best working mode of the internal server are analyzed. On this basis, the principle of equal consumption micro-increase rate is promoted from the perspective of economy, and the guidance price is formulated according to the profit seeking behavior of the data center operators. Guide the data load and the data center energy consumption, and realize the optimal operation of the distribution network in the day-ahead through the information interaction between the grid company and the data center operators. Finally, the ieee-33 bus distribution network system embedded with the data centers is used for simulation and analysis. The results eliminate part of the lines overload caused by the original data load plan, and verify the effectiveness of the proposed strategy.

关键词： data center guidance electricity price distribution network day-ahead optimization

来源：评论

学校读者我要写书评

暂无评论

MAD: Memory-Aware Design Techniques for Accelerating Fully Homomorphic Encryption 23

MAD: Memory-Aware Design Techniques for Accelerating Fully H...

引用

56th ieee/ACM International symposium on Microarchitecture (MICRO)

作者： Agrawal, Rashmi de Castro, Leo Juvekar, Chiraag Chandrakasan, Anantha Vaikuntanathan, Vinod Joshi, Ajay Boston Univ Boston MA 02115 USA MIT Cambridge MA 02139 USA Analog Devices Inc Boston MA USA

ISBN: (纸本)9798400703294

Cloud computing has made it easier for individuals and companies to get access to large compute and memory resources. However, it has also raised privacy concerns about the data that users share with the remote cloud servers. Fully homomorphic encryption (FHE) offers a solution to this problem by enabling computations over encrypted data. Unfortunately, all known constructions of FHE require a noise term for security, and this noise grows during computation. To perform unlimited computations on the encrypted data, we need to perform a periodic noise reduction step known as bootstrapping. This bootstrapping operation is memory-bound as it requires several GBs of data. This leads to orders of magnitude increase in the time required for operating on encrypted data as compared to unencrypted data. In this work, we first present an in-depth analysis of the bootstrapping operation in the CKKS FHE scheme. Similar to other existing works, we observe that CKKS bootstrapping exhibits a low arithmetic intensity (< 1 Op/byte). We then propose memory-aware design (MAD) techniques to accelerate the bootstrapping operation of the CKKS FHE scheme. Our proposed MAD techniques are agnostic of the underlying compute platform and can be equally applied to GPUs, CPUs, FPGAs, and ASICs. Our MAD techniques make use of several caching optimizations that enable maximal data reuse and perform reordering of operations to reduce the amount of data that needs to be transferred to/from the main memory. In addition, our MAD techniques include several algorithmic optimizations that reduce the number of data access pattern switches and the expensive NTT operations. Applying our MAD optimizations for FHE improves bootstrapping arithmetic intensity by 3x. For Logistic Regression (LR) training, by leveraging our MAD optimizations, the existing GPU design can get up to 3.5x improvement in performance for the same on-chip memory size. Similarly, the existing ASIC designs can get up to 27x and 57x improv

关键词： Fully Homomorphic Encryption CKKS Scheme Memory Bottleneck analysis Cache Optimizations SimFHE Hardware Acceleration Bootstrapping

来源：评论

学校读者我要写书评

暂无评论

data Fusion of Heterogeneous data Sources for Intelligent Transportation Systems 1

Data Fusion of Heterogeneous Data Sources for Intelligent Tr...

引用

1st International Conference on Logistics, ICL 2024

作者： Alsahfi, Tariq Elmasri, Ramez Alhajlah, Mousa Alammari, Ali Alshemaimri, Bader Aboulola, Omar College of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia College of Engineering University of Texas at Arlington Arlington United States Applied of Computer Science College King Saud University Riyadh Saudi Arabia College of Computer and Information Systems King Saud University Riyadh Saudi Arabia

ISBN: (纸本)9798331518844

Intelligent Transportation Systems (ITS) provide applications to enhance road safety, minimize travel time, and detect incidents. However, providing accurate information for road status is considered as a challenging task. These days, the availability of big data from multiple sources provides valuable information to ITS applications. These data require data fusion techniques to handle and extract useful knowledge. Additionally, deep learning approaches have been applied to the ITS field and provided promising results;but it required the input data to be in large amounts of data and in a uniform representation. In this paper, we provide data fusion techniques to integrate and extract features from heterogeneous data sources to be ready for deep learning training approaches. We also generate preprocessed real-world traffic datasets can be used to solve ITS-related problems. Furthermore, we provide two applications to show the importance of our data fusion techniques. Traffic datasets analysis and visualization, where we build a data cube to provide an in-depth analysis of the dataset. Traffic flow forecasting using deep learning;we perform a comprehensive study on how different features can improve the traffic flow prediction models. The experimental results show that deep learning approaches achieve better results when extra features are considered. © 2024 ieee.

关键词： data fusion

来源：评论

学校读者我要写书评

暂无评论

data visualization and Predictive analysis for Smart Healthcare: Tool for a Hospital

Data Visualization and Predictive Analysis for Smart Healthc...

引用

ieee Region 10 symposium (TENSYMP) - Good Technologies for Creating Future

作者： Menon, Amala Aishwarya, M. S. Joykutty, Anu Maria Yusafali, Asna A., V Yusafali, Ashifa A., V Rajagiri Sch Engn & Technol Dept Comp Sci & Engn Kochi 6823039 Kerala India

ISBN: (纸本)9781665400268

The healthcare industry is one of the most significant sources of Big data. It is not feasible to manually interpret and understand the huge amounts of data generated by hospitals accurately. This creates the need for a data analytics and visualization tool. visualizations are intuitive and help interpret the data easily. It would help the hospital to get insights from the data and to provide better service to the society. The aim of this project was to develop a data analysis and visualization tool for a hospital. This was implemented as a web application. The web application is developed using Django, which is a Python-based free and open-source web framework. For the visualizations embedded in the application, the Python library Altair was used. The application supports the upload of files that are the source for the visualizations and provides interactive visualizations based on the analysis performed. The visualizations can be exported as images using the application. Generating visualizations of choice becomes easier using navigation by menu bars in the application rather than writing complicated queries to the database. The tool ultimately attempts to help the hospital optimize time and resources effectively. Prediction using Long Short Term Memory (LSTM) for pharmacy orders and number of orders per patient will further help the hospital predict trends, patterns and outliers. analysis tools will help analysing past, current and predict future pharmacy and diagnostics in a hospital which ultimately lead to better quality, efficient smart healthcare.

关键词： data visualization data analysis Medical data Hospital Pharmaceuticals and Diagnostics Prediction LSTM

来源：评论

学校读者我要写书评

暂无评论

Advancing Near-data Processing with Precise Exceptions and Efficient data Fetching

Advancing Near-Data Processing with Precise Exceptions and E...

引用

ieee International symposium on Performance analysis of Systems and Software (ISPASS)

作者： Santos, Sairo Kepe, Tiago R. Moreira, Francis B. Santos, Paulo C. Alves, Marco A. Z. Univ Fed Parana Dept Informat Curitiba Parana Brazil Fed Rural Univ Semiarid Angicos Dept Exact Sci & Informat Technol Mossoro Brazil Univ Fed Rio Grande do Sul Inst Informat Porto Alegre RS Brazil

ISBN: (纸本)9781665459549

Near-data Processing (NDP) modifies the traditional computer system design by placing logic near the memory, bringing computation to the data. One NDP approach places such elements on the logic layer of 3D-stacked memories to quickly access data while avoiding reliance on narrow buses and better accessing the parallelism these devices offer. However, NDP architectures often fail to fully leverage available memory resources. In this work, we propose adding an instruction buffer to a common NDP design with large vector instructions. This modification allows the NDP to fetch instruction operands out of program order and delegates some responsibility regarding precise exceptions to the near-data device. Our results show our modifications cause a reduction in execution time of up to 28% while consuming up to 25% less energy.

关键词： near-data processing 3d-stacked memory computer architecture

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Big data in Transient Stability Simulation of Power Systems 4

Research on the Application of Big Data in Transient Stabili...

引用

4th International Conference on Energy, Power and Electrical Engineering, EPEE 2024

作者： Zhang, Jie Guo, Haiping Zhao, Yanjun Huang, Libin Hu, Binjiang Luo, Hui Zhang, Jingyue State Key Laboratory of Hvdc Electric Power Research Institute China Southern Power Grid Guangzhou510663 China National Energy Power Grid Technology R&d Centre Guangzhou510663 China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou510663 China Csg Key Laboratory for Power System Simulation Electric Power Research Institute China Southern Power Grid Guangzhou5106633 China

ISBN: (纸本)9798331518066

With the rapid expansion of smart grids, there is a growing complexity in power system dynamics, which increases the availability of real-time operational data and underscores the need for advanced transient stability simulations. Traditional transient stability analysis methods are constrained by their computational demands and may compromise accuracy. Furthermore, deep learning-based methods often focus on the application of a single algorithm, lacking a systematic consideration of the entire simulation process. To address these challenges, this study proposes a novel approach that leverages big data to enhance transient stability simulations. By integrating deep learning and ensemble learning techniques, the model significantly improves the accuracy and efficiency of predicting transient instabilities. The methodology utilizes a multi-source data acquisition and fusion scheme to ensure data comprehensiveness and a distributed storage architecture to handle large-scale datasets effectively. Advanced visualization technologies are also employed to enhance the interpretability of the simulation results. This comprehensive framework aims to support the safe and stable operation of power systems amid increasing complexity and data availability. © 2024 ieee.

关键词： Transient stability

来源：评论

学校读者我要写书评

暂无评论

Why Visualize? Untangling a large Network of Arguments

引用

ieee TRANSACTIONS ON visualization AND COMPUTER GRAPHICS 2021年第3期27卷 2220-2236页

作者： Streeb, Dirk El-Assady, Mennatallah Keim, Daniel A. Chen, Min Univ Konstanz Grp Data Anal & Visualizat D-78464 Constance Germany Univ Oxford Dept Engn Sci Oxford OX1 2JD England

visualization has been deemed a useful technique by researchers and practitioners, alike, leaving a trail of arguments behind that reason why visualization works. In addition, examples of misleading usages of visualizations in information communication have occasionally been pointed out. Thus, to contribute to the fundamental understanding of our discipline, we require a comprehensive collection of arguments on "why visualize?" (or "why not?"), untangling the rationale behind positive and negative viewpoints. In this paper, we report a theoretical study to understand the underlying reasons of various arguments;their relationships (e.g., built-on, and conflict);and their respective dependencies on tasks, users, and data. We curated an argumentative network based on a collection of arguments from various fields, including information visualization, cognitive science, psychology, statistics, philosophy, and others. Our work proposes several categorizations for the arguments, and makes their relations explicit. We contribute the first comprehensive and systematic theoretical study of the arguments on visualization. Thereby, we provide a roadmap towards building a foundation for visualization theory and empirical research as well as for practical application in the critique and design of visualizations. In addition, we provide our argumentation network and argument collection online at https://***, supported by an interactive visualization.

关键词： data visualization visualization Task analysis Pipelines Biology Bars Manuals visualization theory argument network cognition design

来源：评论

学校读者我要写书评

暂无评论

Development of An Automated data analysis Program in Python on the Influence of Extracts on Changes in Lipofuscin Content in the C. Elegans Organism 8

Development of An Automated Data Analysis Program in Python ...

引用

8th International symposium on Computer Science and Intelligent Control, ISCSIC 2024

作者： Milentyeva, Irina S. Nikolaeva, Elena V. Rudnev, Pavel S. Vladimirov, Alexander A. Porokhnov, Andrey N. Prosekov, Alexander Yu. Kemerovo State University Laboratory of Biotesting of Natural Nutraceuticals of Scientific and Innovative Management 6 Krasnaya St. Kemerovo Russia House of Scientific Collaboration Named after P.A. Chikhachev Kemerovo State University 73 Sovetskiy Ave. Kemerovo Russia Institute of Fundamental Sciences Kemerovo State University 6 Krasnaya St. Kemerovo Russia Kemerovo State University Scientific and Innovative Management Department 6 Krasnaya St. Kemerovo Russia

ISBN: (纸本)9798350380286

This study focuses on developing a Python program and algorithm for regression analysis to screen plantderived extracts with geroprotective properties. The Python 3.9 program generates dependencies of characteristics based on input data. Regression analysis utilizes data measuring lipofuscin autofluorescence at 340 / 420 ~nm in C. elegans after 5 and 15 days of treatment with extracts (Ginkgo biloba, St. John's wort, Baikal skullcap, forgotten pennyroyal, and true ginseng) at 10, 100, and 1000 -fold dilutions. Polynomial regression reveals data spread, with determination coefficients near 1 indicating a small spread and close to 0 indicating a large one. A significant scatter in measurements for the same extract and dilution may signal measurement errors. Increasing polynomial degree enhances accuracy until the second degree;further increases lead to decreasing determination coefficients. The regression analysis program predicts changes in lipofuscin autofluorescence post-treatment, aiding in evaluating medicinal plant extracts under varied experimental conditions. The developed automatic regression analysis program enables predicting changes in lipofuscin autofluorescence after treatment with medicinal plant extracts across diverse experimental settings. © 2024 ieee.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

A Domain Adaptation Method Based on Deep Coral for Rolling Bearing Fault Diagnosis 14

A Domain Adaptation Method Based on Deep Coral for Rolling B...

引用

14th ieee International symposium on Diagnostics for Electrical Machines, Power Electronics and Drives, SDEMPED 2023

作者： Wang, Zexiao Ming, Xinguo Shanghai Jiao Tong University School of Mechanical Engineering Department of Industrial Engineering & Management Shanghai City China

ISBN: (纸本)9798350320770

As a key component of motor, the operating status of rolling bearings directly affects the overall function and performance of each mechanism system of mechanical equipment The traditional rolling bearing intelligent fault diagnosis method has problems such as requiring a large amount of in-service data for fault analysis, poor generalization capability, etc. In addition, it is extremely costly to obtain labeled rolling bearing high quality condition data. Transfer learning is one of the methods that can effectively solve the above problems. In this paper, we propose a transfer learning model based on Coral transfer loss function as a rolling bearing fault diagnosis method. The model uses ResNet50 as the feature extractor, Coral loss function as the transfer loss function, and CrossEntropyLoss as the classification loss function. Finally, we validated the feasibility of the proposed method by using the Case Western Reserve University bearing dataset under variable operating conditions, the model was validated with correct transfer rates of over 90% for all twelve transfer types;which greatly surpasses other typical transfer learning fault diagnosis methods, which proved the rationality of the proposed method. © 2023 ieee.

关键词： Failure analysis

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：