检索结果-内蒙古大学图书馆

7th international conference on Intelligent computing and Signal Processing, ICSP 2022

作者： Yu, JinPing Yang, Haibo Jiangxi University of Science and Technology School of Information Engineering Ganzhou China

ISBN: (纸本)9781665478571

With the rapid development of information technology, there are many kinds of data. Due to the variability of unstructured data, the extraction of entity relationship is no longer based on rule. therefore, this paper combines the pre-training model BERT with the two-way GRU neural network model, and adds an attention mechanism to complete the extraction of 12 groups of character relationships in this paper. the detailed extraction results are shown in Table 1. the F1 value of character relationship as 'parent' is the highest, reaching 0.95;the F1 values of character relationships of 'SELF', 'BROthERS and SISTERS' and 'CLASSMATES' all reached more than 0.9. the results show that the proposed model has certain advantages and high stability compared with other relationship extraction models. © 2022 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Common phase error mitigation based on decision directed data subcarriers in OFDM systems 7

Common phase error mitigation based on decision directed dat...

引用

7th international conference on Communication engineering and technology, iccet 2024

作者： Koo, Jihun Ahn, Jaewoo Lee, Wooram Cho, Changhee Gyeonggi University Of Science And Technology Dept. Electronic Engineering Sihueung Korea Republic of

ISBN: (纸本)9798350373271

In this paper, we propose a method using decision-directed data subcarriers to estimate and correct common phase error. this method involves two phases: estimating pilot CPE for the current symbol using pilot subcarriers and estimating the previous symbol's CPE using data subcarriers. To derive the decision directed CPE, LLR values from the previous symbol's data subcarriers are decoded, modulated, and compared with the previous symbol. And, threshold values specific to each QAM constellation were used to select data subcarriers, preventing CPE distortion from incorrectly detected data. the DD-CPE estimated from selected data subcarriers introduces a one-symbol delay but provides more accurate CPE values compared to pilot CPE due to the increased use of data subcarriers. Simulation results indicate that for HT-MM MCS7 frame, DD-CPE estimation gains 0.59dB compared to pilot CPE estimation but experiences a 0.35dB performance loss compared to the ideal genie CPE estimation. © 2024 IEEE.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Object oriented implementation of distributed finite element analysis in .NET

引用

ADVANCES IN engineering SOFTWARE 2007年第11-12期38卷 726-737页

作者： Mackie, Robert Ian Univ Dundee Fac Engn & Phys Sci Dundee DD1 4HN Scotland

the paper describes a detailed study into the object-oriented implementation of distributed finite element analysis on desktop computers using the NET framework. the software design aspects are described in some detail for both direct and iterative solution algorithms. the use of interfaces played an important role in the software design. this, together with the NET framework, enabled remote objects to be implemented in a relatively seamless fashion. the solution routines were "blind" to whether the objects were local or remote. Numerical tests were carried out and reasonable speed-up was achieved, particularly for direct solution methods. It is concluded that NET provides a viable framework for implementing distributed computing on networks of personal computers. (c) 2006 Elsevier Ltd. and Civil-Comp Ltd. All rights reserved.

关键词： object-oriented programming finite element analysis distributed analysis parallel computing .NET

来源：评论

学校读者我要写书评

暂无评论

Research on the Strategy of Delay Rolling for Reheating Furnace based on Swarm Intelligence Algorithm 7

Research on the Strategy of Delay Rolling for Reheating Furn...

引用

7th international conference on Intelligent computing and Signal Processing, ICSP 2022

作者： Xu, Zhengguang Hua, Tong Fan, Xingyuan Zhu, Xu University of Science and Technology Beijing School of Automation & Electrical Engineering Beijing100083 China

ISBN: (纸本)9781665478571

Based on the principle of heat transfer, the mathematical model of billet heating process in regenerative reheating furnace is established to predict the state of billets in furnace after a period of delay rolling. the improved adaptive genetic algorithm and particle swarm optimization algorithm are used as the optimization methods for delay rolling and the optimization results are compared. At the same time, the on-line optimization strategy is put forward under the two conditions of stopping and backward of walking beam, so that the billet can meet specifications requirements and reduce the energy consumption at the end of delay rolling. © 2022 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

the State of the Art Text Summarization Techniques 7th

The State of the Art Text Summarization Techniques

引用

7th international conference on computing in engineering and technology, iccet 2022

作者： Saiyyad, M.M. Patil, Nitin N. Department of Computer Engineering RCPIT Shirpur Dhule425405 India

ISBN: (纸本)9789811927188

With the advent of communication technology, a tremendous amount of data is generated. the availability of a vast amount of data provides information and presents the challenge of extracting knowledge from it. the solution to such an issue is text summarization. the documents are examined, and a thorough, compact, and relevant summary is generated using in-text summarization. It is classified into two forms based on the approach used: extractive and abstractive summarization. Extractive summarization selects words and sentences from an existing document to create a summary. Semantic analysis is performed in the case of Abstractive summarization, and new words and phrases are employed to construct the summary. We’ve gone over the many types of text summarization in detail in this paper, along with a discussion of the various research approaches that have been used so far. © 2022, the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

Sleeping Node Scheduling Method Based Redundant Node Energy Reduction in Wireless Sensor Networks 7th

Sleeping Node Scheduling Method Based Redundant Node Energy ...

引用

7th international conference on computing in engineering and technology, iccet 2022

作者： Sakthi Shunmuga Sundaram, P. Vijayan, K. Department of Electronics and Communication Engineering SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India

ISBN: (纸本)9789811927188

In WSNs, the accuracy and the reduction of the energy taken by the redundant data are the more challenging parameter. To resolve the above problem, sleeping node scheduling methodology (SNSM) with some of the same measures are proposed, it reduces the energy consumption, sensors are scheduled into the active mode or sleep mode, Clustering formation is used to balance the load for energy consumption, using fuzzy similarity theory sensor nodes divide into categories, based on data integrity and a redundant node will go to a sleep state in the next round. the simulation results confirm the improvements in accuracy performance and energy consumption of the networks. © 2022, the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

A multi-controller deployment method for satellite networks based on network delay 7

A multi-controller deployment method for satellite networks ...

引用

7th international conference on Intelligent computing and Signal Processing, ICSP 2022

作者： Wan, Ying Qian, Kechang Space Engineering University Aerospace Information Institute Beijing China

ISBN: (纸本)9781665478571

Software-defined network (SDN) has the advantages of decoupling the data plane and control plane and flexible centralized control. It is considered to introduce SDN technology into satellite networks. In this paper, a satellite network architecture based on SDN is proposed. Aiming at the delay problem of satellite networks, a multi-controller deployment method of improved Marine Predator Algorithm (IMPA) is proposed, which improves the updating strategy in the initial predation stage and introduces a simulated annealing algorithm to further optimize the convergence speed and accuracy of the algorithm. Simulation results show that IMPA can achieve load balancing while reducing network delay compared with MPA and HPSO. © 2022 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Research on the motor fault diagnosis method based on feature engineering and machine learning 7

Research on the motor fault diagnosis method based on featur...

引用

7th international conference on Intelligent computing and Signal Processing, ICSP 2022

作者： Ji, Dezheng Hu, Minfei Wang, Miao Hebei University of Technology School of Electrical Engineering Tianjin China Southwest University of Science and Technology School of Information Engineering Sichuan China Zhengzhou University of Aeronautics School of Aerospace Engineering Zhengzhou China

ISBN: (纸本)9781665478571

Bearing failure is the most common type of motor failure. Decision tree algorithm is a machine learning algorithm with the advantages of insensitivity to missing values and high efficiency. this research uses the bearing failure experimental data of the Bearing Data Center of Case Western Reserve University in the United States. the result shows that feature extraction of the data using time domain, frequency domain and wavelet singular entropy can effectively reduce the data dimensionality and improve the overall accuracy by about 41.1% and training time by 7.687 seconds compared with the original data without feature engineering. In addition, two algorithms, random forest feature selection and principal component analysis (PCA), were used for feature selection after feature extraction. the results after feature selection show that the combination of random forest feature selection algorithm and decision tree classification model improves the accuracy by 2.5%. And the model training time is reduced by 2.053s. this method is an effective fault diagnosis method for motor bearings, which can diagnose faults accurately and efficiently. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Application of Distance Measure in KNN Motor Fault Diagnosis 7

Application of Distance Measure in KNN Motor Fault Diagnosis

引用

7th international conference on Intelligent computing and Signal Processing, ICSP 2022

作者： Yu, Siliang Jia, Chenxiao Hou, Runsen Suzhou University of Science and Technology School of Electronic Information Engineering Suzhou215000 China North China Electric Power University School of Control and Computer Engineering Beijing102206 China Beijing University of Chemical Technology Institute of International Education Beijing102202 China

ISBN: (纸本)9781665478571

Motor bearings play an important role in industrial production. Regular inspection and fault diagnosis can provide reliable guarantee for the normal operation of the motor. If the potential or early bearing failures are not detected in time, they will bring safety hazards to production operations. In this thesis, distance measure method for feature extraction and KNN (k-nearest neighbor) algorithm for recognition are combined for the purpose of diagnosis of motor bearing. through experimental verification, the medium KNN algorithm has the most obvious improvement, and the accuracy has increased from 39. 1% to 99. 8% with the help of the proposed feature extraction. Using the KNN algorithm, the effect of time domain feature extraction, frequency domain feature extraction and distance feature extraction are verified. After comparison, it is concluded that the distance feature extraction method can effectively improve the accuracy rate and speed up the training speed of the model. © 2022 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Framework of CNN Architecture for Fashion Image Classification 7th

Framework of CNN Architecture for Fashion Image Classificati...

引用

7th international conference on computing in engineering and technology, iccet 2022

作者： Janjua, Juhi Patankar, Archana Department of Computer Engineering Thadomal Shahani Engineering College Maharashtra Mumbai India

ISBN: (纸本)9789811927188

Nowadays, online shopping is booming due to the pandemic. As stores are not operational during the lockdown, retailers try to sell everything online. Also, competition is increasing between them, allowing retailers to enhance their online application features. the fashion business has recently added many features like clothes search, clothes recommendation, etc. All these features can be implemented with the help of image classification. Clothes have many attributes and hidden features which can be extracted and classified with the help of Deep learning. this paper implements a CNN-based architecture, a deep learning approach, to classify images. this architecture is trained on the Fashion MNIST dataset. Proposed CNN architecture is examined, and substantial results are obtained. © 2022, the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image classification

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：