检索结果-内蒙古大学图书馆

Deep Learning Aided SID in Near-Field Power Internet of Things Networks With Hybrid recommendation algorithm

COMPUTATIONAL INTELLIGENCE 2025年第1期41卷

作者： Chen, Chuangang Wu, Qiang Wang, Hangao Chen, Jing Elect Power Res Inst Hainan Power Grid Co Ltd Haikou Peoples R China Joint Lab Smart Grid & Isl Microgrid Haikou Peoples R China

In the realm of power Internet of Things (IoT) networks, secure inspection detection (SID) is paramount for maintaining system integrity and security. This paper presents a novel framework that leverages deep learning-based semi-autoencoders in conjunction with a hybrid recommendation algorithm to enhance SID tasks. Our proposed method utilizes the deep learning-based semi-autoencoder to effectively capture and learn complex patterns from high-dimensional power IoT data, facilitating the identification of anomalies indicative of potential security threats. The hybrid recommendation algorithm, which combines collaborative filtering and content-based filtering, further refines the detection process by cross-verifying the identified anomalies with historical data and contextual information, thereby improving the accuracy and reliability of the SID tasks. Through extensive simulations and practical data evaluations, our proposed framework demonstrates superior performance over conventional methods, achieving higher detection accuracy. In particular, the detection accuracy of the proposed scheme is more than 20% higher than that of the competing schemes.

关键词： deep learning IoT networks recommendation algorithm semi-autoencoder

来源：评论

学校读者我要写书评

暂无评论

A recommendation algorithm for Improved Residual Networks Based on Matrix Factorization 4th

A Recommendation Algorithm for Improved Residual Networks Ba...

引用

4th International Conference on Data and Information in Online Environments

作者： Mao, Chengzhi Wu, Zhifeng Tianjin Univ Technol & Educ Sch Informat Technol Engn Tianjin Peoples R China

ISBN: (纸本)9783031807121;9783031807138

Recommender system is widely used in e-commerce, news consulting, social networking, tourism, film, music and other fields because it can effectively deal with the problem of information overload. According to the practical problems in the recommendation system, various recommendation algorithms are produced. Traditional recommendation algorithms are divided into content-based recommendation, collaborative filtering based recommendation and hybrid recommendation. Collaborative filtering algorithms are favored because they can extract and process relevant information features to accurately predict user preferences. However, collaborative filtering algorithms generally have problems such as sparse data, cold start and data scalability. This paper presents the Associated Residual Matrix Factorization (ARMF) model, which can solve the common cold start problem and improve the recommended performance. The model uses associative residual neural networks (ARNs) to model higher-order interactions between the user and the underlying features of the item and to avoid network layer gradients exploding or disappearing and overfitting problems. In order to verify the validity and correctness of the model, this paper conducts tests on Movielens100k and Movielens10M datasets, and the experimental results show that the prediction results are 17%similar to 23% better than other comparison algorithms.

关键词： recommendation algorithm Matrix factorization residual network

来源：评论

学校读者我要写书评

暂无评论

Personalized recommendation algorithm Based on Knowledge Graphs with High-Order Information 42nd

Personalized Recommendation Algorithm Based on Knowledge Gra...

引用

42nd National Conference on Theoretical Computer Science

作者： Zhang, Siyao Wang, Zhihui Hu, Jinru Chen, Jianrui Shaanxi Normal Univ Sch Comp Sci Xian 710199 Peoples R China

ISBN: (纸本)9789819614899;9789819614905

With the rapid development of network technology, recommendation systems attract increasing research because of its wide applications in e-commerce. Nevertheless, most existing recommendation models based on graph neural networks do not consider the transitivity of subgraph structures in interactive data. This makes the models unable to capture the complex dependencies and mutual influences between users and items, resulting in the inability to achieve high-quality personalized recommendations. To address the above challenge, we propose a novel recommendation algorithm based on knowledge graph with high-order graph convolutional network, named KG(2)CN. Firstly, we introduce the subgraph structure on the knowledge graph to capture high-order contextual information between users and items. Secondly, the mined subgraph information and graph convolutional network are combined to learn high-order features of users and items. Finally, the decoder is applied to predict the ratings of target users on the uninteracted items, thereby recommending the Top-K items. Experimental results on the Book-Crossing and *** datasets show that the proposed KG(2)CN obtains better performance in F1 score and AUC metrics.

关键词： recommendation algorithm Knowledge Graph Graph Convolutional Network High-order Pattern

来源：评论

学校读者我要写书评

暂无评论

Analysis and Application of Spark Fast Data recommendation algorithm Based on Hadoop Platform

Analysis and Application of Spark Fast Data Recommendation A...

引用

2025 Asia-Europe Conference on Cybersecurity, Internet of Things and Soft Computing, CITSC 2025

作者： Yan, Jialu Decoded Advertising New York10005 United States

ISBN: (纸本)9798331504205

With the rapid advancement of information technology, efficient management and precise formulation of personalized recommendations have become the focus of attention in many fields. This article explains the core principles of Hadoop architecture and Spark technology, as well as the mechanism of their joint operation. We analyzed the multi-level architecture of Spark technology and its parallel processing model's contribution to driving algorithm performance. In terms of algorithm construction, the implementation process of a recommendation algorithm based on collaborative filtering and content matching on the Spark platform was described in detail, and its excellent performance was confirmed through experimental methods. We discussed the application examples of Hadoop Spark platform in multiple fields such as e-commerce, social networks, financial services, and online teaching, demonstrating the effectiveness of the algorithm in improving recommendation accuracy and accelerating system feedback speed. © 2025 IEEE.

关键词： Fast data Hadoop platform recommendation algorithm Spark

来源：评论

学校读者我要写书评

暂无评论

Exploring Factors Driving Satisfaction from recommendation algorithm on Netflix

Exploring Factors Driving Satisfaction from Recommendation A...

引用

International Conference on Marketing and Technologies, ICMarkTech 2023

作者： Olma, Karolina Rizun, Mariia Strzelecki, Artur Department of Informatics University of Economics in Katowice 1 Maja 50 40-287 Katowice Poland

ISBN: (纸本)9789819736973

The present study aims to evaluate customer satisfaction with the recommendation algorithm used by Netflix. Online streaming platforms have revolutionized the way people consume media content. With the multiplication of choices and the abundance of content, it has become difficult for users to find the materials they are interested in watching. To address this problem, recommendation algorithms have been developed to suggest the content that the user is most likely to find entertaining. The research is conducted through structural modeling equations and data analysis, with the use of data from 274 Netflix users. The results show a positive relationship between personalization, use of search engine, homepage usefulness and satisfaction from using Netflix’s recommendation algorithm. The results of this research contribute to our understanding of customer satisfaction with the recommendation system of online streaming platforms. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Media content Netflix recommendation algorithm recommendation system

来源：评论

学校读者我要写书评

暂无评论

Application of recommendation algorithm in the construction of specialized innovation and integration courses 3

Application of recommendation algorithm in the construction ...

引用

3rd International Conference on Artificial Intelligence and Education, ICAIE 2024

作者： Shi, Wei Wang, Tong Huang, Lili School of Architecture and Art Ningbo Polytechnic Zhejiang Ningbo China School of Computer and Information Engineering Shanghai Polytechnic University Shanghai China

ISBN: (纸本)9798400712692

Universities play a vital role in promoting the implementation of the "innovation-driven development strategy", and it is particularly urgent to lead the reform of the education and teaching of mass innovation (innovation and entrepreneurship) in universities with innovative thinking. This paper focuses on "personalized learning"as a new engine to promote the teaching practice of mass entrepreneurship education, and puts forward a curriculum construction scheme of "combining professional and innovation and entrepreneurship"with recommendation algorithm. Through the use of recommendation algorithms, this program effectively matches "innovation needs"with "professional needs", so as to tailor a personalized learning path for each student, and comprehensively enhance students' independent learning ability and innovative problem-solving ability. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Innovation and integration Personalized learning recommendation algorithm Teaching reform

来源：评论

学校读者我要写书评

暂无评论

Exploration of a personalised ideological and political education model based on a recommendation algorithm 3

Exploration of a personalised ideological and political educ...

引用

3rd International Conference on Artificial Intelligence and Education, ICAIE 2024

作者： Luo, Yi Xi'an Fanyi University Shanxi Xi'an China

ISBN: (纸本)9798400712692

In response to the problems of "efficiency bottleneck"and insufficient "personalization"in ideological and political education in universities under the background of the information age, this project innovatively integrates data mining and machine learning methods to establish a deep level user behavior analysis and recommendation method system based on big data. It fully collects students' online learning trajectories and social media data, and accurately captures individual interests and needs through refined portrait construction and cluster analysis. On this basis, the optimal collaborative screening technique is adopted to personalize the matching and recommendation of different types of educational resources, and provide students with personalized learning paths. The experimental results show that this teaching mode can fully mobilize students' learning enthusiasm, improve the pertinence and effectiveness of teaching, and the average academic performance of students is between 3-7 points, which tests its overall effect. The research results of this project will further expand the application scope of educational recommendation algorithms, provide new ideas for optimizing resource allocation and improving the quality of personalized education, and provide important technical and theoretical support for promoting the reform and development of ideological and political education in Chinese universities. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： cluster analysis method personalised ideological and political education recommendation algorithm user profile

来源：评论

学校读者我要写书评

暂无评论

Optimization of MOOC resource recommendation algorithm for art studies based on the google dataflow architecture 5

Optimization of MOOC resource recommendation algorithm for a...

引用

5th International Conference on Telecommunications, Optics, and Computer Science, TOCS 2024

作者： Han, Tingting Zhang, Qilong Harbin Institute of Petroleum Harbin China Harbin Huade University Harbin China

ISBN: (纸本)9781510691667

As online education continues to rapidly grow, MOOCs (Massive Open Online Courses) platforms have become a crucial part of arts education. However, the existing arts MOOCs recommendation systems face several challenges, including data processing delays, limited scalability, and inadequate real-time performance, which negatively impact user experience and learning efficiency. Existing studies largely depend on traditional algorithms such as collaborative filtering and content-based recommendations, which are prone to performance bottlenecks when handling large datasets and fail to fully meet the demands for personalized and efficient learning. To address these challenges, this paper proposes an optimization strategy for arts MOOCs resource recommendation algorithms based on the Google Dataflow architecture, aimed at enhancing user satisfaction and learning efficiency. This approach utilizes the robust real-time computing and scalability features of Google Dataflow to design and implement a novel recommendation algorithm capable of efficiently processing large-scale data streams and continuously updating user preference models. By integrating the benefits of collaborative filtering with content-based recommendations, the proposed system achieves significant improvements in recommendation accuracy and personalization. Experimental results demonstrate that the recommendation system based on Google Dataflow architecture outperforms traditional methods in processing speed, accuracy, and user satisfaction, showcasing its potential for application in arts MOOCs platforms and contributing to the advancement of personalized learning experiences. © 2025 SPIE.

关键词： Arts MOOC google dataflow architecture personalized learning real-time computing recommendation algorithm

来源：评论

学校读者我要写书评

暂无评论

Short video content and recommendation algorithm based on deep learning

引用

JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2025年

作者： Yang, Yang Manzhouli Russian Vocat Coll Chinese Dept 6Huafeng St Manzhouli City Inner Mongolia Peoples R China

Existing short video content analysis methods often struggle with integrating multimodal data, resulting in incomplete content understanding and limited recommendation accuracy. To address these challenges, this study proposes a deep learning-based short video content analysis and recommendation algorithm that enhances feature extraction and personalization. CNN and LSTM are employed to automatically capture and extract multimodal features from short videos, generating a comprehensive feature representation through weighted fusion. Meanwhile, DNN is utilized to model user behavior, extracting deep behavioral features to enhance preference prediction. By jointly modeling video content and user behavior, a multimodal recommendation algorithm is developed to optimize content delivery. Experimental results show that, compared to CF, MF, and Content-Based Filtering benchmark algorithms, the proposed method improves average precision by 4.7%, 3.3%, and 4.0%, and recall by 3.5%, 1.2%, and 2.1%, respectively. These findings confirm that the deep learning-driven approach effectively enhances multimodal content understanding, meets personalized user preferences, and significantly improves recommendation accuracy, offering a more intelligent and adaptive short video recommendation framework.

关键词： Short video content analysis recommendation algorithm deep learning Deep Neural Network

来源：评论

学校读者我要写书评

暂无评论

recommendation algorithm of Industry Stock Trading Model with TODIM

引用

INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION MAKING 2024年第3期23卷 1301-1334页

作者： Lv, Dongdong Gong, Yingli Chen, Jianting Xiang, Yang Ningbo Univ Technol Sch Cyber Sci & Engn Ningbo 315211 Peoples R China Tongji Univ Sch Econ & Management Shanghai 201804 Peoples R China Tongji Univ Coll Elect & Informat Engn Shanghai 201804 Peoples R China

In stock trading, a common phenomenon is that the trends of stocks in the same industry are very similar. In contrast, the movements of stocks in different industries are often different. Therefore, applying the same model to all stock trading is inappropriate without distinguishing the industries in which the stocks belong. However, recommending an optimal industry stock trading model is very challenging based on performance evaluation indicators. First, the indicators of the trading model are diverse. Second, the ranking of multiple indicators is often inconsistent. In the paper, we model the problem to be solved as a multi-criteria decision-making process. Therefore, we first divide stock dataset into nine industries according to their main business. Then, we apply several machine learning algorithms as candidate models to generate trading signals. Second, we conduct daily trading backtesting based on the trading signals to obtain multiple performance evaluation indicators. Third, we propose an optimal recommendation algorithm for the industry stock trading model with TODIM. The experimental results in the US stock market and China's A-share market show that the proposed algorithm can get a better trading model out-of-sample industry stock. Moreover, we effectively evaluate the generalization ability of the algorithm based on the proposed metrics. Finally, the proposed long-short portfolios based on the algorithm have achieved returns exceeding the benchmark on most out-of-sample datasets.

关键词： Stock trading recommendation algorithm TODIM trading strategy

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：