检索结果-内蒙古大学图书馆

22nd International Conference on Human-Computer Interaction,HCII 2020

作者： Charles, Darryl Cowley, Benjamin Ultan School of Computing Engineering and Intelligent Systems Ulster University Newtownabbey United Kingdom Data Science Faculty of Educational Sciences University of Helsinki Helsinki Finland Cognitive Science Faculty of Arts University of Helsinki Helsinki Finland

ISBN: (纸本)9783030601270

Players exhibit varying behaviour from each other when playing games. Indeed, a player’s own behaviour will change as they learn to play and changing behaviour may also be indicative of when they are prematurely about to quit playing permanently (known as ‘churn’). There can be many reasons for player churn including finding a game too easy, too hard, or just not understanding what they must do. The accurate prediction of player churn is important as it allows a publisher or developer to understand and intervene to improve retention and thus increase revenue. Profiling player behaviours through their actions in-game can facilitate personalization, by adapting gameplay for different types of player to enhance player enjoyment and reduce churn rate. Behavlets are data-features that encode short activity sequences (‘atoms’ of play), which represent an aspect of playing style or player personality traits, e.g. aggressiveness or cautiousness tendencies. Previously we have shown how Behavlets can be used to model variation between players. In this paper, we focus on Behavlet sequences and how process mining and entropy-based analysis can profile evolving behaviour, predict player churn, and adapt play to potentially increase enjoyment. © 2020, Springer Nature Switzerland AG.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Autoregressive Diffusion Networks for Trustworthy Node Identification and Optimized Routing in Wireless Sensor Networks

Autoregressive Diffusion Networks for Trustworthy Node Ident...

引用

Advancement in Computation & Computer Technologies (InCACCT), International Conference on

作者： M. Satheesh Kumar P. Ganesh Kumar S. Amudha T. Kavitha P. Ravikumar M. Raghini Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of IT K.L.N. College of Engineering Department of Computational Intelligence School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Electronics and Instrumentation K.L.N. College of Engineering Department of Artificial Intelligence and Data Science Velammal College of Engineering and Technology

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

Finding and eliminating unwanted nodes is a foremost challenge in wireless sensor networks (WSNs). This paper proposes an Autoregressive Diffusion Network (ADN) to find and categorize the nodes in the network as affected or trustworthy. Here, the proposed ADN provides a strong foundation for finding uncommon or insecure actions by effectively recording the characteristics of the sensor over a period of time. Thus, using the capability to capture successive data. In addition, an improved routing mechanism is developed using the Low-Energy Adaptive Clustering Hierarchy (LEACH) protocols. Then, the Pelican Optimisation Algorithm (POA) is used to optimize the cluster heads optimally. To further improve the routing mechanism using fitness proportional selection technique to transfer the data safely and effectively. Simulation results show that the proposed technique enhances the performance by reducing energy consumption and increasing the detection accuracy of affected nodes. The proposed LEACH + POA + ADN model shows the improved detection accuracy of 77%, false positive rate of 7.50%, average energy consumption of 8.02 J, network lifetime of 92.94 rounds, and packet delivery ratio of 92.97%, which is high compared to other benchmark models.

关键词： Wireless sensor networks Energy consumption Accuracy Protocols Simulation Clustering algorithms Routing Energy efficiency Security Reliability

来源：评论

学校读者我要写书评

暂无评论

MedX-Net: Hierarchical Transformer with Large Kernel Convolutions for 3D Medical Image Segmentation

MedX-Net: Hierarchical Transformer with Large Kernel Convolu...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Lin Lu Qingzhi Zou Key Laboratory of Computing Power Network and Information Se-curity Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Due to the exceptional performance of Transform-ers in 2 $D$ medical image segmentation, recent work has also introduced them into 3D medical segmentation tasks. For instance, Swin UNETR and other hierarchical Transformers have reintroduced prior knowledge from several convolutional networks, further enhancing the volume segmentation capabilities of models. The efficacy of these hybrid methodologies is primarily attributed to the substantial quantity of parameters and the nonlocal self-attention mechanism with a large receptive field. We argue that the behavior of these methods' large receptive fields can be simulated by employing fewer parameters through the utilization of depth-wise convolutions with large kernel. Within this manuscript, we introduce a lightweight volume segmentation model called MedX-Net, which uses convolutional network modules to simulate hierarchical Transformers for robust volume segmentation. Firstly, inspired by the hierarchical Transformer module of Swin UNETR, we investigate large-kernel depth-wise convolutions with different sizes to achieve a reduced model parameter count while maintaining a large global receptive field. Secondly, we replace the multilayer perceptron (MLP) in the hierarchical Transformer module with Inverted Bottleneck with Depthwise Convolution Enhancement(DWCE) to improve model performance with fewer activation and normalization layers, further reducing the parameter count. We validate the effectiveness and efficiency of our model for volume segmentation on three public datasets: Synapse, BTCV and ACDC. On the Synapse dataset, compared to Swin UNETR, our model achieves an improvement from 83.48% to 87.21% in Dice score. Compared to the result of 86.57% achieved by nnFormer, our model achieves superior performance while reducing the model parameter count by 64%.

关键词： Image segmentation Solid modeling Visualization Three-dimensional displays Current transformers Multilayer perceptrons Convolutional neural networks Kernel Synapses Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

CSLP: Collaborative Solution to Long-Tail Problem and Popularity Bias in Sequential Recommendation

CSLP: Collaborative Solution to Long-Tail Problem and Popula...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Yan Huang Zhenyu Yang Wenyue Hu Baojie Xu Zhibo Zhang The Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Sequential Recommender Systems (SRS), leveraging the temporal information from users' behaviors, have noticeably improved user experience against traditional systems. However, these behaviors often follow long-tail distribution, making the systems biased towards popular items (i.e., popularity bias). Moreover, popularity bias would amplify the neglect of long-tail recommendations, thereby sharpening the long-tail problem. Previous researches usually address these challenges independently, focusing on reducing the over-recommendation of popular items or enhancing the representation quality of tail items. Indeed, it is possible to incorporate their merits to achieve the best of both worlds. Thus, we propose a novel and unified framework, named Collaborative Solution to Long tailed problem and Popularity bias (CSLP), to tackle both the long-tail problem and popularity bias simultaneously. To achieve this, we first introduce a representation enhancement module featuring dual generators to enhance user and item representations, particularly for those in the tail. On the other hand, a debiasing module incorporating an Inverse Propensity Score (IPS) with a clipping strategy is introduced to further alleviate the popularity bias. Specifically, this clipping strategy demonstrates a clear decrease in the original IPS method's variance, effectively improving the recommendation for stability and accuracy. Experiments on three widely-used datasets show CSLP's effectiveness in solving both issues. CSLP surpasses all baselines (traditional, popularity bias, and long-tail problem) in overall performance, significantly enhancing recommendation accuracy for both tail users and items, and achieving a more balanced ratio of recommendations between popular and tail items. Code is available at https://***/Echohuangyan/CSLP.

关键词： Hands Heavily-tailed distribution Accuracy Collaboration Tail Linear programming Generators User experience IP networks Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Secure Authentication Framework for Consumer Mobile Crowdsourcing Networks

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Aldosary, Abdallah Tanveer, Muhammad Ahmad, Musheer Maghrabi, Louai A. Ahmed, Emad A. Hussain, Amir El-Latif, Ahmed A. Abd Department of Computer Engineering Prince Sattam bin Abdulaziz University Riyadh Wadi Addwasir11991 Saudi Arabia University of Management and Technology Department of Computer Science Lahore54770 Pakistan Jamia Millia Islamia Department of Computer Engineering New Delhi110025 India University of Business and Technology College of Engineering Department of Software Engineering Jeddah Saudi Arabia South Valley University Faculty of Computers and Information Department of Computer Science Qena Egypt Edinburgh Napier University United Kingdom Prince Sultan University EIAS Data Science Lab College of Computer and Information Sciences Center of Excellence in Quantum and Intelligent Computing Riyadh11586 Saudi Arabia Menoufia University Faculty of Science Department of Mathematics and Computer Science Shebin El-Koom32511 Egypt

The Mobile crowdsourcing network (MCN) leverages collaborative intelligence to solve complex tasks through group cooperation. It comprises three main components: the end-user, the service provider, and the mobile user. The end-user requests crowd-sensing and computing services from the service provider, who handles task decomposition, distribution, re-composition, and recommendation. Mobile users perform the crowd sensing and computing tasks. Despite its benefits, MCN faces significant security and privacy challenges. Communications between the service provider and the end-user involve sensitive data, and mobile users and service providers communicate over open channels, making them vulnerable to security threats. To address these concerns, we propose a secure authentication framework for MCN, called SAF-MCN. This framework combines the lightweight cryptographic primitive ' ASCON' with elliptic curve cryptography. SAF-MCN allows the service provider to authenticate mobile users before they join the MCN. Once authenticated, a secure channel is established for encrypted communication over the public Internet. The security of SAFMCN is validated using both formal and informal methods, demonstrating its resilience against potential attacks. The use of Scyther further ensures the security of SAF-MCN. Comparative analysis shows that SAF-MCN is superior in terms of security features, computational efficiency, and communication cost. © 1975-2011 IEEE.

关键词： ASCON Authenticated Encryption Authentication Mobile Crowdsourcing Network Scyther Security

来源：评论

学校读者我要写书评

暂无评论

A Collaborative Heterogeneous Graph Neural Network for Personalized News Recommendation

A Collaborative Heterogeneous Graph Neural Network for Perso...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Chenglong Shi Haibin Geng Wenfeng Jiang Jinbao Li Chao Wu Song Liu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Personalized news recommendation is the process of predicting the relevance of news to users and recommending news to user to fulfill their information needs. However, existing news recommendation methods extract semantic information from users and candidate news respectively, ignoring semantic interaction information between users and candidate news. Furthermore, previous models only use same node types for message passing, ignoring different characteristics and topology between different node types. In addition, existing methods learn news representations through text representations, ignoring semantic correlation information between entity relationships and texts. To solve these problems, we propose a personalized news recommendation model named CoHG. In our model, we design a collaborative fusion module to obtain semantic interaction information through interacting user history news with candidate news. Furthermore, we design a heterogeneous gated graph neural network that maps different node types into a same space to extract higher-order information in user graphs for message passing. Moreover, we design an enhanced relevant attention module to enhance semantic correlation information of text content by aggregating text representation and entity representation into a unified representation. Finally, we conducted experiments on MIND and Adressa datasets to compare with other baseline models.

关键词： Correlation Message passing Semantics Collaboration Logic gates Graph neural networks Topology History data mining Cybernetics

来源：评论

学校读者我要写书评

暂无评论

A Cross-Modal Interactive Memory Network Based on Fine-Grained Medical Feature Extraction for Radiology Report Generation

A Cross-Modal Interactive Memory Network Based on Fine-Grain...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Xitong Ma Yuansen Kuang Lin Yuan Cheng Tian Yijie Zeng Song Liu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Radiology report generation is an essential task in the medical field, which aims to automate the generation of medical terminology descriptions of radiology images. However, this task currently suffers from several problems: 1) existing methods need to manually build knowledge graphs or templates (consuming time and effort) to introduce medical or prior knowledge to assist in report generation; 2) previous models cannot handle the problem of data bias well (anomaly reports and anomaly descriptions make up only a tiny portion of the dataset), causing the models to ignore the learning of anomaly descriptions easily; 3) existing approaches cannot robustly supervise the model, resulting in incomplete and inconsistent reports being generated. To address these issues, we propose a cross-modal interactive memory network based on fine-grained medical feature extraction. In our model, we design a cross-modal interactive memory network to automatically store and remember the required medical text knowledge and use this medical knowledge to help generate reports. Furthermore, we design an abnormal medical knowledge enhancement module to enhance the learning of abnormal fine-grained knowledge through the interaction of disease topics and their states to interact with text features. In addition, we design a cross-modal joint semantic loss unit to reduce semantic differences between different features and improve the visual representation ability of the model. We experimented and evaluated our model on MIMIC-CXR and IU-Xray datasets to compare with other baseline models.

关键词： Knowledge engineering Visualization Terminology Semantics MIMICs Memory management Radiology Feature extraction data models Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

A Generalization of Multi-Source Fusion-Based Framework to Stock Selection

SSRN

引用

SSRN 2023年

作者： Snášel, Václav Velasquez Silva, Juan Domingo Pant, Millie Georgiou, Dimitrios Kong, Lingping Faculty of Electrical Engineering and Computer Science VŠB-Technical University of Ostrava Czech Republic Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Uttarakhand Roorkee247667 India Departament of Industrial Engineering University of Chile Santiago Chile Faculty of Electrical Engineering and Computer Science National Technical University of Athens Greece Chile Department of Applied Mathematics and Scientific Computing Indian Institute of Technology Uttarakhand Roorkee247667 India

Selecting outstanding tech stocks for investment is challenging. Specifically, studying the investment for academic purposes is not mature enough due to the disarray of the publications and the `over' informative experience from profit-making websites. Often some authors entitle stock price prediction subject as a stock selection problem;both prediction and selection are just sub-section of portfolio management. Moreover, stock websites provide tons of potential criteria showing their perspective evaluation to simulate and monitor the stock market professionally, which causes an extra problem for academic studies screening out the less informative criteria. The paper generalizes a novel framework with a user-interactive interface for stock selection problems based on multi-source data fusion and decision-level fusion to enhance reliability that is limited by the narrow criteria performance and to enhance the strength of a model overcoming the weakness of a single-performed model. This framework benefits the time-series prediction and decision-making study. Besides, we propose adopting dynamic time warping to assist a task-learning process by customizing a loss function that improves the accuracy of data prediction. The experiment shows that the proposed method reduces the prediction log error by 28\% in a best case of real-situation data and decreases the warping cost by 20\%. Finally, we illustrate the proposed framework by implementing it in a real-world stock data selection. The results are practical and effective, further justified through a detailed ablation study. © 2023, The Authors. All rights reserved.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

NQNR: News Recommendation Method Based on News Quality-Aware Modeling

NQNR: News Recommendation Method Based on News Quality-Aware...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Baojie Xu Zhenyu Yang Yan Huang Wenyue Hu Zhibo Zhang The Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Personalized News Recommendation (PNR) can enhance user experience by alleviating information overload. Traditional news recommendation methods consider all clicking behaviors as user interests, resulting in biased user modeling that fails to accurately capture user interests. In addition, although there are methods to reduce the impact of low-quality news at the representation level by simply filtering it through the attention mechanism. However, this only implicitly models the news in the interaction sequence without specifically considering the quality of each news, and thus has very limited effect in identifying noise. To address these issues, this paper proposes News Recommendation method based on News Quality-aware modeling (NQNR). We attempt to explicitly model the news in the click sequence and candidate ranking one by one to visually assess the quality of each news. Specifically, we design a detection module to detect whether the input news is low-quality news. Then, by reducing the influence of low-quality news in user modeling and candidate ranking, user interests are modeled more accurately, while recommendations of such news are reduced for users. In addition, to capture the similarity of vectors more accurately, we also design a similarity computation method based on the multiple attention mechanism in the detection module. Experiments on a large real-world Microsoft News dataset (MIND) show that our model significantly outperforms previous models. Our code is posted at the following URL: https://***/xxbbjj/NQNR-.

关键词： Uniform resource locators Attention mechanisms Codes Accuracy Filtering Computational modeling Noise Vectors User experience Cybernetics

来源：评论

学校读者我要写书评

暂无评论

An Entity Relation Extraction Framework Based on Large Language Model and Multi-Tasks Iterative Prompt Engineering

An Entity Relation Extraction Framework Based on Large Langu...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Haibin Geng Chenglong Shi Xuesong Jiang Zan Kong Song Liu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Document-level entity relation extraction is an important task in the field of natural language processing, which plays an important role in semantic understanding and knowledge graph construction. However, existing deep neural networks and graph neural networks models are limited by their performance and parameters number, which can not capture global semantics and have poor generalization ability. Furthermore, existing methods employing large language model for entity relation extraction do not establish good relationships among multi-tasks of entity relation extraction task, resulting in more information can not be effectively shared and transmitted between tasks. In addition, previous approaches can not effectively eliminate false entities and relationships. To solve these problems, we propose an entity relation extraction framework based on large language model and multi-tasks iterative prompt engineering. In our model, we design an iterative prompt engineering, which can better establish the relationship among multi-tasks, and ensure every task to obtain the optimal results. Moreover, we design semantic merging, group disambiguation and self-verification modules to eliminate the false entity relations and noise nodes. Additionally, we design summary prompts to provide sufficient global semantics for better text segmentation. Finally, we evaluated our model on wikiann, wikineural, ACE2005, CoNLL2003, CoNLL2004, and SciERC datasets and compared it with other baseline models.

关键词： Large language models Semantics Noise Merging Knowledge graphs Multitasking Natural language processing Iterative methods Prompt engineering data mining

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：