检索结果-内蒙古大学图书馆

Modeling of Virtual Characters in the Animation Design Instructional System Based on Deep Learning

computer-Aided Design and Applications 2024年第S10期21卷 256-270页

作者： Hao, Gang Cao, Ling Xiao, Zhenghong School of Computer Science Guangdong Polytechnic Normal University Guangdong Guangzhou510665 China Information Engineering School Guangzhou Vocational College of Technology & Business Guangdong Guangzhou511442 China

With the growth of computer technology, 3D animation character modeling technology has become an important part in the field of animation production. However, the traditional modeling method needs a lot of time and manpower, which becomes the bottleneck in the animation production process. This article introduces an animation design instructional system based on deep learning (DL), which involves the technology of animation role CAD modeling. The system can use DL algorithm to model automatically, which provides a convenient and efficient animation role modeling platform for learners. This article introduces the implementation stage of the algorithm in detail, and verifies the effectiveness and feasibility of the algorithm through simulation results. The results show that this method has high precision and low error. The error is reduced by more than 25%, and the highest precision can reach 97.66%. The algorithm can well restore the shape and details of animated characters, and has high precision and robustness. The animation design instructional system can provide valuable technical support and instructional tools for animation industry and education, which is helpful to improve the efficiency of animation production and reduce the cost. © 2024 U-turn Press LLC.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Named Entity Recognition Method based on Bert-Bilstm-Attention-CRF for Education field 4

Named Entity Recognition Method based on Bert-Bilstm-Attenti...

引用

4th International Conference on Big Data, Artificial Intelligence and Internet of Things engineering, ICBAIE 2023

作者： Zhang, Jun Jing, Shuyang Hu, Jianhua Guangdong Polytechnic of Science and Technology Computer Engineering Technical College Artificial Intelligence College Guangdong Zhuhai519090 China

ISBN: (纸本)9798350343618

With the rapid development of the new generation of information technology, the educational information system has accumulated a large amount of educational data information, which makes learners have low cognitive efficiency, difficulty concentrating, and eventually deviate from learning goals and fail to complete specific learning tasks. This paper proposes a named entity recognition method in the education field combined with Bert-BiLSTM-Attention-CRE to improve learners' learning efficiency. Firstly, BERT language model is used to extract text features to obtain the word granularity vector matrix;Then use Bi-directional Long Short-Term Memory (BiLSTM) to extract the word-to-word relationship between the input statements and the context;Thirdly, Attention mechanism is introduced to better utilize local contextual clues by assigning different weights to the text feature vectors, and strengthen the correlation between current information and context information;Finally uses the Conditional Random Field (CRF) model to extract the globally optimal output label sequence according to the dependency between labels;and the named entity of the education field is obtained in the end. The experimental results show that the Precision, Recall and F1 value of the model are 82.25%, 79.73%, 80.39% respectively, the overall recognition performance is high, and the effect is better than that of BiLSTM-CRF, CNN-BiLSTMCRF, HIDCNN, BERT-BiLSTM-CRF. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Optimization model of urban road signal lights based on non dominated sorting genetic algorithm 2

Optimization model of urban road signal lights based on non ...

引用

2nd IEEE International Conference on Electrical, Automation and computer engineering, ICEACE 2024

作者： Duan, Banxiang Li, Lintao Zhang, Zhouqi Li, Jiamei Guangdong Institute of Science and Technology Computer Engineering Technical College Zhuhai519090 China

ISBN: (纸本)9798350368208

This article explores the optimization of urban traffic flow control. On the basis of data preprocessing, the K-Means clustering analysis algorithm was used to divide a day into several time periods and estimate the traffic flow at the intersections of Jingzhong Road and Weizhong Road. The use of non dominated sorting genetic algorithm for signal light optimization significantly improved the average speed of vehicles. A random forest model for identifying parade vehicles was established using vehicle characteristics such as threshold setting and turnover rate. A classifier was used to train and classify the vehicles, and the parade vehicles for each day of the May Day Golden Week were calculated. Finally, the effectiveness of the control measures was evaluated based on indicators such as the average speed, delay time, and queue length of vehicles. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Parameter Tuned Deep Learning Based Traffic Critical Prediction Model on Remote Sensing Imaging

引用

computers, Materials & Continua 2023年第5期75卷 3993-4008页

作者： Sarkar Hasan Ahmed Adel Al-Zebari Rizgar R.Zebari Subhi R.M.Zeebaree Computer Networks Department Sulaimani Polytechnic UniversitySulaimaniIraq Information Technology Department Technical College of Informatics-AkreDuhok Polytechnic UniversityIraq Computer Science Department College of ScienceNawroz UniversityDuhokIraq Energy Eng.Department Technical College of EngineeringDuhok Polytechnic UniversityDuhokIraq

Remote sensing(RS)presents laser scanning measurements,aerial photos,and high-resolution satellite images,which are utilized for extracting a range of traffic-related and road-related *** has a weakness,such as traffic fluctuations on small time scales that could distort the accuracy of predicted road and traffic *** article introduces an Optimal Deep Learning for Traffic Critical Prediction Model on High-Resolution Remote Sensing Images(ODLTCP-HRRSI)to resolve these *** presented ODLTCP-HRRSI technique majorly aims to forecast the critical traffic in smart *** attain this,the presented ODLTCP-HRRSI model performs two major *** the initial stage,the ODLTCP-HRRSI technique employs a convolutional neural network with an auto-encoder(CNN-AE)model for productive and accurate traffic ***,the hyperparameter adjustment of the CNN-AE model is performed via the Bayesian adaptive direct search optimization(BADSO)*** experimental outcomes demonstrate the enhanced performance of the ODLTCP-HRRSI technique over recent approaches with maximum accuracy of 98.23%.

关键词： Remote sensing images traffic prediction deep learning smart cities intelligent transportation systems

来源：评论

学校读者我要写书评

暂无评论

MGOD: Multi-Granular Outlier Detection with Clustlier Analysis

MGOD: Multi-Granular Outlier Detection with Clustlier Analys...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Chen, Qingsheng Zhao, Mingjie Ji, Yuzhu Luo, Xiaopeng Zhang, Yiqun Zhang, Yue Guangdong University of Technology School of Computer Science and Technology China Guangzhou Huali College School of Computer Engineering China Guangdong Polytechnic Normal University School of Computer Science China

ISBN: (纸本)9798350386226

Unsupervised Outlier Detection (UOD) is crucial for the analysis of biomedical and health data with undesirable outliers. However, the complex distribution of real data often brings difficulties to UOD where the "masking effect", i.e., only a small number of densely distributed outliers (also called clustliers) can collectively mask themselves from being detected, is particularly challenging. Another difficulty derived from this is how to distinguish clustliers from small clusters. Therefore, we propose a novel Multi-Granular Outlier Detector (MGOD). It first partitions the dataset into subsets with natural neighbor topological relationships to circumvent the non-trivial neighbor range setting. Then it effectively detects both clustliers and isolated samples (also called scatliers) based on a newly designed anomaly score. The score comprehensively takes into account the density and connectivity of samples to reflect different extents and types of abnormality. It turns out that MGOD is accurate and highly interpretable. The performance of MGOD is also robust to the involved hyper-parameters, which are easy to set. Comprehensive evaluations have been conducted to compare seven counterparts on 15 datasets, most of which are biomedical datasets. The results of significance tests confirm the effectiveness and superiority of MGOD. The source code is opened at https://***/r/MGOD-C531. © 2024 IEEE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

COMPARING WSN PERFORMANCE: TRADITIONAL VS. SDN APPROACH

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer science 2024年第4期86卷 81-94页

作者： Hamad, Diyar Jamal Yalda, Khirota Gorgees Okumus, Ibrahim Taner Tapus, Nicolae Faculty of Automatic Control and Computer Science University of Science and Technology POLITEHNICA Bucharest Soran Technical college Erbil Polytechnic University Erbil Iraq Computer Engineering Kahramanmaras Sutcu Imam University Kahramanmaras Turkey Dept. of Computer Science University of Science and Technology POLITEHNICA Bucharest Romania

The proliferation of Wireless Sensor Networks (WSN) in various applications has necessitated the exploration of network architectures that can ensure efficient, scalable, and reliable communication. This study presents a comparative performance evaluation of traditional networking paradigms and Software-Defined Networking (SDN)-based architectures within WSN. Utilizing the Floodlight SDN controller and Mininet-WiFi emulator, we conducted a series of experiments across three different network topologies, varying the number of hosts and access points. The performance metrics focused on are average latency, packet loss percentage, and throughput. The results demonstrate a considerable improvement in all measured parameters under the SDN-based environment compared to the traditional setup. Specifically, SDN environments consistently showcased lower latency, minimal packet loss, and higher throughput, with the most notable difference observed in smaller network configurations. The findings suggest that SDN, with its centralized control plane, can significantly enhance the performance of WSNs, particularly in scenarios demanding rapid scalability and dynamic traffic management. This study underscores the potential of SDN architectures in optimizing WSN operations and lays the groundwork for future research in this domain. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Floodlighting

来源：评论

学校读者我要写书评

暂无评论

Digital Asset Management Tool for Film Animation and Game Development

引用

computer-Aided Design and Applications 2023年第S8期20卷 89-99页

作者： Cao, Ling Hao, Gang Liang, Yaner School of Information Engineering Guangzhou Vocational College of Technology & Business Guangdong Guangzhou511442 China School of computer Science Guangdong Polytechnic Normal University Guangdong Guangzhou510665 China

With the continuous development of China's economy and technology, China's market has also produced a large number of excellent film and television works with beautiful pictures. Once launched, it has been loved by consumers and promoted the further development of China's economy. Through research, it is found that this has a great relationship with the application of game engine to the design of film and television animation. This paper discusses the design and implementation of video animation of game engine. This paper uses the CAD game engine to create an animation example "Pipi's Creation" to illustrate the whole process of using the game engine to create film and television animation. In the process of creation, it focuses on describing the different processes of video animation produced by game engine and traditional animation, as well as the different links in the creation, and completes the creation of examples. Based on the above research, on the basis of 3D software CAD, a digital asset management system for computer-aided video animation and game development has been developed and implemented. © 2023 CAD Solutions, LLC.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

A visual data analysis system of used cars based on Python and ECharts

A visual data analysis system of used cars based on Python a...

引用

2022 International Conference on computer Application and Information Security, ICCAIS 2022

作者： Fan, Luqiao Duan, Banxiang Gao, Jie Computer Engineering and Technical College Guangdong Institute of Science and Technology Guangdong Guangzhou510640 China

ISBN: (纸本)9781510663459

This paper develops a data visualization and analysis system for used cars data in response to the requirement that used cars information is complex and buyers need to obtain objective and comprehensive used cars information in a short period of time. Selenium+XPath crawler was used to crawl the used cars data in ***, and then import the data. The dirty data was cleaned using the Pandas data analysis toolkit in Python. The data is then stored as the corresponding CSV file and converted into JSON file. Finally, ECharts is used to read JSON files for data visualization and HTML for web display. © 2023 SPIE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Production model based on the combined prediction of time series and XGBoost neural networks 2

Production model based on the combined prediction of time se...

引用

2nd IEEE International Conference on Electrical engineering, Big Data and Algorithms, EEBDA 2023

作者： Duan, Banxiang Zhang, Jingyu Zeng, Zhaobin Guangdong Institute of Science and Technology Computer Engineering Technical College Guangdong Zhuhai519090 China

ISBN: (纸本)9781665462532

This paper discusses the production problem of multi-variety materials. With the continuous development of economic globalization, the production and operation mode of many varieties of small batch materials has been loved by the company, and the market demand for materials determines the quantity of our production materials. In the code of small-batch materials in the given sample, we first use Python data to analyze the trend level of the material, establish the entropy right Topsis model to objectively score the material, and screen out the six materials that should be paid attention to in the materials that meet the requirements. Secondly, with the week as the time unit, the time series and XGBoost neural network are used to establish a weekly prediction model to predict the six material demand, and the reciprocal mean square error method is used to combine the two models to ensure the accuracy of the model and improve the credibility of the model, to build the combined prediction model. © 2023 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Correlation model of maternal and infant health indicators based on random forest and TOPSIS

Correlation model of maternal and infant health indicators b...

引用

2023 International Conference on Electronics and Devices, Computational science, ICEDCS 2023

作者： Duan, Banxiang Tang, Shangchun Qiu, Tianci Chen, Hongpei Guangdong Institute of Science and Technology Computer Engineering Technical College Zhuhai China

ISBN: (纸本)9798350343038

This paper discusses the influence of mother's physical and mental health on baby's growth. Using Spearman correlation analysis, the law is obtained;Using random forest method, the relationship model between infant behavior characteristics and mother's physical index and psychological index is constructed to judge the type of behavior characteristics. The linear programming model of disease score and treatment cost is established to solve the cost of treatment scheme to adjust behavior characteristics. The correlation model of infant's comprehensive sleep quality with mother's physical index and psychological index is constructed to predict infant's comprehensive sleep quality. In addition, we analyze the sensitivity and error of the model, and evaluate, improve and popularize it objectively and fairly. © 2023 IEEE.

关键词： Linear programming

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：