检索结果-内蒙古大学图书馆

6th International Conference on Information Science and Control Engineering (ICISCE)

作者： Zhang, Chenyan Guan, Huanmei Li, Ni Wuhan Univ Sch Comp Sci Wuhan Peoples R China China Elect Power Res Inst State Key Lab Power Grid Environm Protect Wuhan Peoples R China

ISBN: (纸本)9781728157122

Traditional recommendation algorithms generate a recommendation list for the user by rating prediction or ranking based on their historical record However, most of these methods still faced with two problems: (1) only considering users' positive feedback;(2) seeking to maximize the immediate recommendation effect To address the above issues, we propose a novel deep reinforcement learning based interactive recommendation model, named DDQN-AM. Specifically, we first use long short-term memory network to capture positive and negative interest signals from user's historical behavior as Deep Double Q-Network(DDQN)'s input states. Secondly, we also propose an attentional mechanism(AM) to learn the effects of contextual information for weight calculation. Extensive experiments on real data show that the proposed DDQN-AM model outperforms the state-of-the-art algorithms, and verify the importance of attention mechanism.

关键词： deep reinforcement learning recommendation algorithms weight calculation attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Mobile Gift recommendation Algorithm 19

Mobile Gift Recommendation Algorithm

引用

19th International Conference on Enterprise Information Systems (ICEIS)

作者： Pereira, Caique de Paula da Costa, Ruyther Parente Canedo, Edna Dias Univ Brasilia Fac UnB Gama Gama DF Brazil

ISBN: (纸本)9789897582479

The mobile application market and e-commerce sales have grown steadily, along with the growth of studies and product recommendation solutions implemented in e-commerce systems. In this context, this paper proposes a recommendation algorithm for mobile devices based on the COREL framework. The proposed recommendation algorithm is a customization of the COREL framework, based on the complexity of the implementation associated with iOS mobile applications. Therefore, this work aims to customize a gift recommendation algorithm in the context of mobile devices using as main input the user preferences for the gifts recommendation in the Giftr application.

关键词： recommendation algorithms e-Commerce Mobile Software Development iOS Giftr

来源：评论

学校读者我要写书评

暂无评论

A graph comparison learning recommendation algorithm based on knowledge graph enhancement 7

A graph comparison learning recommendation algorithm based o...

引用

7th International Conference on Electronic Information Technology and Computer Engineering (EITCE)

作者： Cai, Xiaodong Xue, Yun Zhang, Yanyan Ye, Qing Guilin Univ Elect Technol Guilin Peoples R China

ISBN: (纸本)9798400708305

The recommender system's overall suggestion results may be erroneous and weakly robust due to the sparse interaction behavior between users and items in the system and the noise inherent in interaction samples. This research suggests a graph comparison learning recommendation method based on knowledge graph augmentation to address the aforementioned issues. First, a knowledge graph-based data improvement method is created to make use of the rich entity attribute data and help the recommendation system solve its data sparsity issue. In order to help the model better capture the crucial information contained in the nodes and to lessen the effect of noisy links between interaction samples on the quality of node representation, a graph self-attentive augmented network is also proposed. In order to test the algorithm's efficacy, experiments are carried out on three datasets: Yelp2018, Amazon-Book, and MIND. The results show that the recommendation algorithm is effective in enhancing recommendation accuracy in the case of small sample sizes and the presence of noisy data scenarios. The Recall metrics are improved by 8.59%, 7.08%, and 15.47%, respectively, compared with the state-of-the-art model.

关键词： computer software and theory recommendation algorithms graph neural networks comparative learning personalized recommendations knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Recruiting PE Teachers Based on Regional Socio-Economic Status Evaluation and recommendation Algorithm

引用

Journal of Artificial Intelligence and Technology 2024年第1期4卷 49-55页

作者： Haitao Long Yinfu Lu National University(Philippines) ManilaPhilippines Physical Education Institute Hunan Institute of Science and TechnologyYueyangChina

The most important step in creating a teaching force for physical education(PE)is finding enough qualified *** order to better absorb the PE teaching talents who aremore suitable for the job requirements,the ability variables of sports talents,the expected regional social and economic status,and historical data are considered,the intelligent matching of talents and positions is made,and the Bayesian variational network recommendation model considering the needs is *** to the experimental findings,this model’s highest recommendation accuracy in the normal scenario is 0.5888 and its maximum recommendation accuracy in the training and test sets is roughly 0.6 and *** model has good convergence and high accuracy of recommendation,which is conducive to matching PE teaching talents and teaching positions,providing job seekers with positions that meet their needs,providing teaching talents to meet the requirements,and creating a team of PE teachers that match people and posts.

关键词： Bayesian networks PE teachers recommendation algorithms social–economic status workforce development

来源：评论

学校读者我要写书评

暂无评论

A Graph-Based recommendation Algorithm on Quaternion Algebra

引用

SN Computer Science 2022年第4期3卷 299页

作者： Kurt, Zuhal Gerek, Ömer Nezih Bilge, Alper Özkan, Kemal Department of Computer Engineering Atılım University Ankara Turkey Department of Electrical and Electronics Engineering Eskişehir Technical University Eskişehir Turkey Department of Computer Engineering Akdeniz University Antalya Turkey Department of Computer Engineering Eskişehir Osmangazi University Eskişehir Turkey

This study presents a novel Quaternion-based link prediction method to be used in different recommendation systems. The method performs Quaternion algebra-based computations while making use of expressive and wide-ranged learning properties of the Hamilton products. The proposed key capabilities rely on link prediction to boost performance in top-N recommendation tasks. According to the achieved experimental results, the proposed method allows for highly improved performance according to three quality measurements: (i) hits rate, (ii) coverage, and (iii) novelty;when applied to two datasets, namely the Movielens and Hetrec datasets. To assess the flexibility level of the proposed algorithm in terms of incorporating alternative sources of information, further wide-scale tests are carried out on three subsets of the Amazon dataset. Hence, the effectiveness of Quaternion algebra in graph-based recommendation algorithms is verified. The algorithms suggested here are further enhanced using similarity and dissimilarity factors between users and items, as well as ‘like’ and ‘dislike’ relationships between users and items. It is observed that this approach is adaptable by incorporating different information sources and can successfully overcome the drawbacks of conventional graph-based recommender systems. It is argued that the proposed novel idea of Quaternion-based link prediction method stands as a superior alternative to existing methods. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Graphs Link prediction Quaternions recommendation algorithms

来源：评论

学校读者我要写书评

暂无评论

Aurora: Conformity-based Configuration recommendation to Improve LTE/5G Service 22

Aurora: Conformity-based Configuration Recommendation to Imp...

引用

22nd ACM Internet Measurement Conference (IMC)

作者： Mahimkar, Ajay Ge, Zihui Liu, Xuan Shaqalle, Yusef Xiang, Yu Yates, Jennifer Pathak, Shomik Reichel, Rick AT&T Dallas TX 75202 USA

ISBN: (纸本)9781450392594

Cellular service operators frequently tune the network configuration to optimize coverage, support seamless handovers, minimize channel interference, and improve the service performance experience to the end-users. Tuning such a complicated network is highly challenging because of the many configuration parameters, evolving complexity of cellular networks, and diverse requirements across voice, video, and data applications. Any misconfigurations or even poor settings can significantly negatively impact service quality. In this paper, we propose a new approach Aurora that derives best practices knowledge from exploration of the massive existing configuration in the network and uses conformity-based recommendation with performance-based filtering to improve cellular service. We implemented and evaluated Aurora using data from a very large LTE and 5G cellular service provider. Our operational experience over the last one year highlights the benefits of Aurora and exposes exciting research opportunities and challenges in configuration tuning and performance management.

关键词： Network configuration conformity collaborative filtering performance impact assessment recommendation algorithms

来源：评论

学校读者我要写书评

暂无评论

A Multiobjective Genetic Algorithm based Hybrid recommendation Approach

A Multiobjective Genetic Algorithm based Hybrid Recommendati...

引用

IEEE Symposium Series on Computational Intelligence (IEEE SSCI)

作者： Wang, Pan Zuo, Xingquan Guo, Congcong Li, Ruihong Zhao, Xinchao Luo, Chaomin Beijing Univ Posts & Telecommun Sch Comp Sci Beijing Peoples R China Minist Educ Key Lab Trustworthy Distributed Comp & Serv Beijing Peoples R China Beijing Univ Posts & Telecommun Sch Sci Beijing Peoples R China Univ Detroit Mercy Dept Elect & Comp Detroit MI 48221 USA

ISBN: (纸本)9781538627266

Personalized recommendation approaches have received much attention over the years. In this paper, we propose a hybrid recommendation approach that integrates an item-based collaborative filtering, a user-based collaborative filtering and a matrix factorization method. The approach considers the two objectives of recommendation's accuracy and diversity simultaneously. First, a set of items is created separately by each of the three methods. Then, items produced by the three methods are combined into a set of candidate items. Finally, a multiobjective genetic algorithm is adopted to choose a set of Pareto recommendation lists from the set. Experimental results show that the proposed approach is very effective and is able to produce better Pareto solutions than those comparative approaches.

关键词： recommendation algorithms multiobjective optimization algorithms hybrid algorithm

来源：评论

学校读者我要写书评

暂无评论

A recommendation Algorithm Based on Cross-View Contrastive Learning 27

A Recommendation Algorithm Based on Cross-View Contrastive L...

引用

27th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)

作者： Wang, Yuying Zhou, Jing Liu, Qian Commun Univ China Sch Comp & Cyber Sci Beijing Peoples R China

ISBN: (纸本)9798350391961;9798350391954

Graph Neural Networks (GNNs), which possess the ability to capture the connectivity and topological features between nodes in a graph structure, have been widely used in the field of Knowledge Graph (KG)-enhanced recommendation. However, the advantages of GNNs are largely limited by the quality of the introduced KG. For example, (1) in real recommendation scenarios, often a small number of popular items interact with a large number of users, which leads to sparse supervisory signals;(2) approaches using GNNs mostly focus on coarse-grained relationship modeling under the global structure and are susceptible to the interference of neighboring noisy information in the KG. Inspired by self-supervised learning, we propose a recommendation algorithm based on cross-view contrastive learning and apply it to a KG-enhanced recommendation task. By promoting mutual supervision of node features in different semantic spaces under local and global structures, the algorithm learns discriminative node representations and reduces noise interference during iterative propagation. Meanwhile, we utilize multi-task learning to promote co-training and shared learning between the recommendation task and contrastive learning to improve the overall generalization ability and the quality of recommendations. To verify the effectiveness of the proposed work, we conduct experiments on two public datasets, MovieLens and Book-Crossing. The experimental results show that our recommendation algorithm outperforms the baseline model in most cases in terms of AUC, recall@k, and F1, and the recommendation performance is improved by 1.7%-10.4%.

关键词： recommendation algorithms contrastive learning knowledge representation graph neural networks

来源：评论

学校读者我要写书评

暂无评论

SOCIAL TAGGING recommendation SYSTEM FOR SMART CITY ENVIRONMENTS

SOCIAL TAGGING RECOMMENDATION SYSTEM FOR SMART CITY ENVIRONM...

引用

IEEE International Conference on Multimedia & Expo (ICME)

作者： Alhamid, Mohammed F. King Saud Univ Software Engn Dept CCIS Riyadh Saudi Arabia

ISBN: (纸本)9781509015528

The increasing use of social network resources has increased the users demands through these networks. Analyzing social media enables us to benefit from the rich source of multimedia in a personalized, adaptive and systematic way for building smart cities environments. This paper proposes an algorithm to fill the gap between the social media resources, user personalized preferences and the collaborative opinions. The algorithm utilizes social tagging to contribute in increasing the quality for searching for places, services, and the discovering communities of the same interest. By exploiting social tagging, we propose a model which analyzes comments and feedback of posts published by users online. We demonstrate how the proposed algorithm can better utilize social information to improve the discovering of relevant items for a given user. The experiment results show feasibility of filtering and matching items of a similar interest for individual users and a social community.

关键词： Smart city social media collaborative analysis recommendation algorithms

来源：评论

学校读者我要写书评

暂无评论

Low-Rank and Sparse Matrix Completion for recommendation 24th

Low-Rank and Sparse Matrix Completion for Recommendation

引用

24th International Conference on Neural Information Processing (ICONIP)

作者： Zhao, Zhi-Lin Huang, Ling Wang, Chang-Dong Lai, Jian-Huang Yu, Philip S. Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou Peoples R China Univ Illinois Dept Comp Sci Chicago IL USA Tsinghua Univ Inst Data Sci Beijing Peoples R China

ISBN: (纸本)9783319701394;9783319701387

Recently, recommendation algorithms have been widely used to improve the benefit of businesses and the satisfaction of users in many online platforms. However, most of the existing algorithms generate intermediate output when predicting ratings and the error of intermediate output will be propagated to the final results. Besides, since most algorithms predict all the unrated items, some predicted ratings may be unreliable and useless which will lower the efficiency and effectiveness of recommendation. To this end, we propose a Low-rank and Sparse Matrix Completion (LSMC) method which recovers rating matrix directly to improve the quality of rating prediction. Following the common methodology, we assume the structure of the predicted rating matrix is low-rank since rating is just connected with some factors of user and item. However, different from the existing methods, we assume the matrix is sparse so some unreliable predictions will be removed and important results will be retained. Besides, a slack variable will be used to prevent overfitting and weaken the influence of noisy data. Extensive experiments on four real-world datasets have been conducted to verify that the proposed method outperforms the state-of-the-art recommendation algorithms.

关键词： recommendation algorithms Low-rank Sparse

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：