检索结果-内蒙古大学图书馆

3rd International Conference on Frontiers of Electronics, Information and Computation Technologies, ICFEICT 2023

作者： Wang, Hui Ding, Di Li, Zhiwen Li, Shengchang Zeng, Shuai Huaxin Consulting Design Research Institute Group Customer Department Hangzhou China China Ordnance Industry Computer Application Technology Institute Internet and Information Technology Department Beijing China

ISBN: (纸本)9798350302356

The recommendation algorithms based on graph convolutional network can extract the association relationship between users and items by interaction data, but most of these algorithms ignore the general preferences in the review data of users and items. The recommendation algorithms based on convolutional neural network with review can learn user behaviors and item properties. In order to combine the advantages of two kinds of algorithm and make use of both review text data and user-item interaction data fully, we proposed a new model called Joint Graph Convolutional Network and Convolutional Neural Network for Recommendation (JGCR) in this paper. This model used the graph convolutional network to extract association relations, and used convolutional neural network to extract the general preferences from review text, and carried out feature fusion to improve the recommendation effect. This paper conducted comparative experiments on four datasets of amazon dataset to verify the effectiveness of the proposed model. The evaluation metric is mean square error. Experiments results demonstrate that JGCR significantly outperforms all baseline recommendation algorithms. The feature from jointing graph convolutional network and convolutional neural network can improve the recommendation effect. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Social Recommendation Algorithm Based on Fusion Graph Convolutional Neural Network and Gated Recurrent Unit Network 4

Social Recommendation Algorithm Based on Fusion Graph Convol...

引用

4th International Conference on computer, Big Data and Artificial Intelligence, ICCBD+AI 2023

作者： Ding, Di Wang, Hui Li, Zhiwen Huaxin Consulting Design & Research Institute Group Customer Department Hangzhou China China Ordnance Industry Computer Application Technology Institute Internet and Information Technology Department Beijing China

ISBN: (纸本)9798350373233

This paper proposes a fusion model named FGCN-GRU (Fusion Graph Convolutional Neural network and Gated Recurrent Unit network) to predict users' ratings on items. Firstly, FGCN-GRU constructs a new graph convolutional neural network by regarding users' ratings on items as relative ratings and introduces the GRU network by considering the fact that the user's interest in items will change over time. Then the improved graph convolutional neural network, GRU network and users' social network are used to model users, items, and social relations respectively. The experimental results on the datasets of Ciao and Epinions show that the recommendation performance of the proposed model is better. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Modalities Biometric Encryption to Secure Personal Data Offloading to the Cloud

Multi-Modalities Biometric Encryption to Secure Personal Dat...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Sahil Rampal Manmohan Sharma Parul Khurama Mukesh Kumar School of Computer Application Lovely Professional University Phagwara Punjab India Advanced Centre of Research & Innovation (ACRI) School of Computer Application Chandigarh Group of Colleges Mohali Punjab India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

Data security has remained a paramount concern for the last decade. Data security saw the introduction of biometric-based security methods. Single biometric-based security methods worked well, but the issue of biometric variability impacted these systems performance. On the other hand, multimodal biometric security systems are less affected by biometric variability than single biometric-based systems. Single biometric-based schemes have the inherent issue of a single point of failure. Multimodalities not only resolve the issue of single-point failure but also increase the reliability of the security scheme. Furthermore, the use of multimodalities enables us to use fixed and cancellable biometrics together to get the security benefits of both types of biometrics. Fixed biometrics offer high reliability; on the other hand, cancellable biometric modalities create a scope to generate different templates from the same biometric, which in terms allows to change the key in case the original key gets compromised. In this paper, we propose a novel approach for securing personal data using an encryption key derived using multi-modalities, which can be used to secure crucial personal data offloading to the cloud or storing at a local data center. Suggested approach has achieved Genuine Acceptance Rate (GAR) of 94% and Genuine Rejection Rate (GRR) of 96% which is better than the single biometric encryption.

关键词： Biometrics Hands Data security System performance Force Memory Passwords Encryption Reliability Disruptive technologies

来源：评论

学校读者我要写书评

暂无评论

Analysis of Stock Market Prediction Through the application of Machine Learning Techniques

Analysis of Stock Market Prediction Through the Application ...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Mukesh Kumar Bilal Ahmed Amit Jain Vikas Attri Rohini Mahajan Mirza Shuja Chandigarh Group of Colleges Mohali Punjab India Department of Computer Application Advanced Centre of Research & Innovation (ACRI) Chandigarh School of Business India School of Computer Applications Lovely Professional University Phagwara Punjab India Department of Computer Application Chandigarh School of Business India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

Trends in stock market forecasting are acknowledged as a noteworthy and fruitful field of study. Smart investors can profit handsomely from the ups and downs of stock prices. Investors have a formidable obstacle when trying to forecast the stock market: data that is either stagnant or uncertain. For investors seeking to optimize profitability, stock market forecasting poses a significant difficulty. Mathematical methods and state-of-the-art learning technologies are employed to produce stock market projections. Computing methods, Machine Learning (ML) algorithms, performance variables, and reputable publications are just a few of the many subjects covered in this paper's review of different research articles. Therefore, the chosen articles are helping to advance datasets and ML algorithms that are used to predict how the stock market will move in the future. Predictions about the stock market are often made with the help of Neural Networks (NNs) and Artificial Neural Network (ANNs) algorithms. Unfortunately, there are still a lot of problems with the way the stock market is currently predicted. The principal premise of the research is that there are many interrelated factors that should be given greater weight when making stock market predictions.

关键词： Surveys Support vector machines Machine learning algorithms Profitability Reviews Machine learning Prediction algorithms Resource management Stock markets Forecasting

来源：评论

学校读者我要写书评

暂无评论

Maximizing Development Efficiency: A Comprehensive Guide to Frameworks and Libraries

Maximizing Development Efficiency: A Comprehensive Guide to ...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Bilal Ahmed Rohini Mahajan Amit Jain Vikas Attri Prince Arora Mukesh Kumar School of Computer Applications Lovely Professional University Phagwara Punjab INDIA Department of Computer Application Chandigarh School of Business Chandigarh Group of Colleges Jhanjeri Mohali Punjab India Department of Computer Application Advanced Centre of Research & Innovation (ACRI) Chandigarh School of Business Chandigarh Group of Colleges Jhanjeri Mohali Punjab India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

This article discusses the differences between the baking of coding structures and libraries giving an easy-to-understand perspective for anyone. The frameworks are compared to blueprints; they determine the consistent construction of the software by emphasizing how components should be assembled as well as how they interact with each other. On the contrary, libraries appear as a box of toolkits, each containing everyday programs and functions programmers can utilize to formulate instructions corresponding to different tasks. Frameworks equip developers with standards and uniformity to make their work faster, more efficient, and more cohesive. At the same time, the framework structure may restrict developers from getting too creative or to add features that does not sit well with their projects, such as relying on conventions. In contrast, library encourages flexibility and modularity as developers are given the freedom to decide which functionalities they want and be able to integrate the libraries to provide the desired effects for their application. It enables the developers to craft solutions which cater for the specific requirements of their project and it also allows code reuse and promoting rapid development. In this way, developers express their suppositions which in essence helps to find the most suitable tool for their projects. Such comprehension grants the developers the wisdom to weight structure and freedom and thus ultimately yielding more proficient and scalable software programs.

关键词： Java Video on demand Organizations Machine learning Libraries Software Encoding Teamwork Web sites Standards

来源：评论

学校读者我要写书评

暂无评论

Wizard of Oz Prototyping for Interactive Spatial Augmented Reality in HCI Education: Experiences with Rapid Prototyping for Interactive Spatial Augmented Reality

Wizard of Oz Prototyping for Interactive Spatial Augmented R...

引用

Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems, CHI EA 2023

作者： Mast, Danića Roidl, Alex Jylha, Antti Faculty of It & Design Research Group Healthy Lifestyle in A Supporting Environment Faculty of Health Nutrition & Sports The Hague University of Applied Sciences Netherlands Leiden Institute of Advanced Computer Science Leiden University Netherlands Communication Design Mainz University of Applied Sciences Germany Faculty of It & Design The Hague University of Applied Sciences Netherlands Service Business Development and Design Haaga-Helia University of Applied Sciences Finland

ISBN: (纸本)9781450394222

In this paper we present our findings that emerged from Wizard of Oz (WOz) prototyping workshops of an undergrad course on UX design between 2017 - 2022. The purpose of these workshops is both to familiarize the students with WOz as a rapid low-complexity prototyping method and to facilitate them in designing for interactive systems beyond typical graphical user interfaces. In these workshops, students develop and test Wizard of Oz prototypes for interactive spatial augmented reality (SAR). Over the past six years, in total 93 prototypes have been created on the course. We analyzed the prototypes that emerged from the workshops based on input, purpose, play characteristics and projection surfaces. Based on the analysis and our experiences during the workshops, we conclude that the workshops stimulate creativity, enable students to rapidly create interactive SAR interfaces without being limited by their technical skills and time limitations and provide them with a tool that they apply beyond the scope of the prototyping course. We discuss advantages and limitations of the use of WOz prototyping for interactive Spatial Augmented Reality. © 2023 Owner/Author.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Archer: Adaptive Memory Compression with Page-Association-Rule Awareness for High-Speed Response of Mobile Devices 23

Archer: Adaptive Memory Compression with Page-Association-Ru...

引用

23rd USENIX Conference on File and Storage Technologies, FAST 2025

作者： Li, Changlong Zhu, Zongwei Wang, Chao Liu, Fangming Xu, Fei Sha, Edwin H.-M. Zhou, Xuehai School of Computer Science and Technology East China Normal University China Jianghuai Advance Technology Center Hefei230026 China MoE Engineering Research Center of Hardware/Software Co-Design Technology and Application China School of Software Engineering University of Science and Technology of China Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China Huazhong University of Science and Technology China Peng Cheng Laboratory China

ISBN: (纸本)9781939133458

In mobile systems, memory can be compressed page-by-page to save space. This approach is widely adopted because memory data is accessed by page. However, this paper shows that the system response speed is significantly limited by page-grained compression. In this paper, we observe that approximately a quarter of anonymous memory pages are highly correlated, even though the association is implicit. Inspired by this, we propose Archer, an association-rule-aware memory compression framework in mobile systems. Archer demonstrates that memory in mobile devices should be compressed using flexible granularity, rather than relying solely on traditional page compression. To further integrate association-rule mining techniques into system design, we redesign the LRU mechanism and propose an adaptive memory compression region. Experimental results show that the average app launching speed is 1.55x faster when enabling Archer, and the average photographic speed and frame rate increase by 1.42x and 1.31x, respectively, compared to the state-of-the-art. © 2025 FAST. All Rights Reserved.

关键词： Portable equipment

来源：评论

学校读者我要写书评

暂无评论

Social Recommendation Algorithm Based on Fusion Graph Convolutional Neural Network and Gated Recurrent Unit Network

Social Recommendation Algorithm Based on Fusion Graph Convol...

引用

computer, Big Data and Artificial Intelligence (ICCBD+AI), International Conference on

作者： Di Ding Hui Wang Zhiwen Li Group Customer Department Huaxin Consulting Design & Research Institute Hangzhou China Internet and Information Technology Department China Ordnance Industry Computer Application Technology Institute Beijing China

ISBN: (数字)9798350373233

ISBN: (纸本)9798350373240

This paper proposes a fusion model named FGCN-GRU (Fusion Graph Convolutional Neural network and Gated Recurrent Unit network) to predict users' ratings on items. Firstly, FGCN-GRU constructs a new graph convolutional neural network by regarding users' ratings on items as relative ratings and introduces the GRU network by considering the fact that the user’s interest in items will change over time. Then the improved graph convolutional neural network, GRU network and users' social network are used to model users, items, and social relations respectively. The experimental results on the datasets of Ciao and Epinions show that the recommendation performance of the proposed model is better.

关键词： Social networking (online) Computational modeling Time series analysis Predictive models Logic gates Prediction algorithms Data models

来源：评论

学校读者我要写书评

暂无评论

Joint Graph Convolutional Network and Convolutional Neural Network for Recommendation

Joint Graph Convolutional Network and Convolutional Neural N...

引用

Frontiers of Electronics, Information and Computation Technologies (ICFEICT), International Conference on

作者： Hui Wang Di Ding Zhiwen Li Shengchang Li Shuai Zeng Group Customer Department Huaxin Consulting Design & Research Institute Hangzhou China Internet and Information Technology Department China Ordnance Industry Computer Application Technology Institute Beijing China

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimisation of alloy composition for highly-formable magnesium sheet

引用

International Journal of Minerals,Metallurgy and Materials 2022年第7期29卷 1388-1395页

作者： Zhuoran Zeng Mingzhe Bian Shiwei Xu Weineng Tang Chris Davies Nick Birbilis Jianfeng Nie College of Engineering and Computer Science Australian National UniversityACT.2601Australia Department of Materials Science and Engineering Monash UniversityVIC 3800Australia State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan UniversityChangsha 410082China Research Institute(R&D Center) Baosteel Group CorporationShanghai 201999China Department of Mechanical and Aerospace Engineering Monash UniversityVIC 3800Australia

The effectiveness of Ca or Gd addition on ductility and formability of Mg-Zn-Zr based dilute alloys in deep drawing has not been systematically compared *** this study,formable Mg-Zn-Gd-Zr and Mg-Zn-Ca-Zr sheet alloys are produced by hot *** sheets have similarly weakened basal texture,but the sheet of the Mg-Zn-Gd-Zr alloys has higher ductility and formability than that of Mg-Zn-Ca-Zr *** combined addition of 0.2wt%Ca and 0.4wt%Gd to the Mg-1Zn-0.5Zr(wt%)alloy leads to a Mg-1Zn-0.4Gd-0.2Ca-0.5Zr alloy that has even better ductility,and its formability during deep drawing is comparable to the benchmark Al6016 *** increase in Ca content from 0.2wt%to 0.5wt%leads to decreased sheet ductility and formability,predominantly due to grain boundary embrittlement.

关键词： magnesium sheet alloy texture microstructure formability solute segregation

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：