检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Wenyue Hu Zhenyu Yang Yan Huang Zhibo Zhang Baojie Xu Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong 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)9798350359312

ISBN: (纸本)9798350359329

The objective of sequential recommendation is to predict user preferences for items based on historical interaction sequences. This process often leads to a phenomenon known as popularity bias, where popular items are excessively recommended. Conformity, the tendency of users to follow popular items, is a significant factor contributing to this issue. Previous methods have not adequately disentangled conformity and interest, failing to accurately model users’ true intent. To address this, we propose a novel Disentangled Interest and Conformity Sequential Recommendation method (DICSRec) to mitigate the popularity bias. Specifically, we first design an Intent Encoding Module (IEM), which includes two independent encoders for conformity and interest to model their representations. To better disentangle these two factors, we design a disentangling task with proxy-based self-supervised learning and orthogonal regularization. Furthermore, to provide the Intent Encoding Module with more global information, we design a Global Conformity-aware Module (GCM), which supplies item popularity information and aids in enhancing user conformity representation. Lastly, recognizing the varying significance of user conformity and interest, we propose an adaptive Fusion Prediction Module (FPM) that adaptively aggregates user conformity and interest representations for final prediction. Experiments on four real-world datasets consistently demonstrate the superiority of our method over advanced sequential recommendation models. Code implementation is available at: https://***/lyra0611/DICSRec.

关键词： Adaptation models Codes Fuses Aggregates Neural networks Self-supervised learning Multitasking

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

Squeeze-and-Excitation Hybrid Network for Biometric Identification via Photoplethysmography

Squeeze-and-Excitation Hybrid Network for Biometric Identifi...

引用

research, Invention, and Innovation Congress (RI2C)

作者： Sakorn Mekruksavanich Wikanda Phaphan Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Research Group in Statistical Learning and Inference Department of Applied Statistics Faculty of Applied Science King Mongkut's University of Technology North Bangkok Bangkok Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science King Mongkut's University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331506018

ISBN: (纸本)9798331506025

Biometric identity verification is critical in security, healthcare, and personalized services. Photoplethysmography (PPG) signals, measuring blood volume changes in small vessels, offer a promising, non-invasive biometric method but often need more accuracy and robustness. To address this, we propose the ResNet-BiGRU-SE framework, which enhances PPG-based biometric identification through a s queeze-and-excitation (SE) attention mechanism. This architecture integrates convolutional neural networks (CNNs), bidirectional gated recurrent units (BiGRUs), and SE attention modules to extract spatial and temporal features from PPG signals. ResNet architecture in CNN layers extracts local patterns and mitigates vanishing gradients with residual connections, while BiGRU layers capture temporal dependencies and contextual information. The SE attention mechanism enhances focus on informative PPG signal parts by adjusting feature responses per channel. Evaluated on a standardized dataset of PPG signals from various patients, the ResNet-BiGRU-SE model demonstrates superior accuracy (95.26%), low loss (0.24), and a high F1-score (95.25 %), outper-forming recent methods. Comprehensive ablation studies confirm the model's robust and reliable performance.

关键词： Technological innovation Attention mechanisms Accuracy Biological system modeling Volume measurement Logic gates Feature extraction Photoplethysmography Biometric identification Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Nitrogen‐doped graphene aerogel‐supported ruthenium nanocrystals for pH‐universal hydrogen evolution reaction

引用

Chinese Journal of Catalysis 2022年第6期43卷 1535-1543页

作者： Yu Ding Kai‐Wen Cao Jia‐Wei He Fu‐Min Li Hao Huang Pei Chen Yu Chen Key Laboratory of Macromolecular Science of Shaanxi Province Key Laboratory of Applied Surface and Colloid Chemistry(Ministry of Education)Shaanxi Key Laboratory for Advanced Energy DevicesShaanxi Engineering Lab for Advanced Energy TechnologySchool of Materials Science and EngineeringShaanxi Normal UniversityXi’an 710062ShaanxiChina School of Sustainable Energy Materials and Science Jinhua Advanced Research InstituteJinhua 321000ZhejiangChina

The design and synthesis of high‐performance and low‐cost electrocatalysts for the hydrogen evolution reaction(HER),a key half‐reaction in water electrolysis,are *** to their modest hydrogen adsorption energy,ruthenium(Ru)‐based nanomaterials are considered outstanding candidates to replace the expensive platinum(Pt)‐based HER *** this study,we developed an adsorption‐pyrolysis method to construct nitrogen(N)‐doped graphene aerogel(N‐GA)‐supported ultrafine Ru nanocrystal(Ru‐NC)nanocomposites(Ru‐NCs/N‐GA).The particle size of the Ru‐NCs and the conductivity of the N‐GA substrate can be controlled by varying the pyrolysis *** experiments reveal revealed that 10 wt%Ru‐NCs/N‐GA nanocomposites require overpotentials of only 52 and 36 mV to achieve a current density of 10 mA cm^(−2) in 1 mol/L HClO4 and 1 mol/L KOH electrolytes for HER,respectively,which is comparable to 20 wt%Pt/C *** from the ultrafine size and uniform dispersion of the Ru‐NCs,the synergy between Ru and the highly conductive substrate,and the anchoring effect of the N atom,the Ru‐NCs/N‐GA nanocomposites exhibit excellent activity and durability in the pH‐universal HER,thereby opening a new avenue for the production of commercial HER electrocatalysts.

关键词： Water electrolysis Graphene aerogels Nitrogen doping Ruthenium nanocrystals Hydrogen evolution reaction

来源：评论

学校读者我要写书评

暂无评论

Dynamics of liquid crystal vortex in a layered superconductor

引用

Physical Review B 2024年第17期109卷 174505-174505页

作者： Hiroyoshi Nobukane Erika Uno Yuichi Tabata Kyosuke Takahashi Daiki Sakabe Satoshi Tanda Department of Physics Hokkaido University Sapporo 060-0810 Japan Center of Education and Research for Topological Science and Technology Hokkaido University Sapporo 060-8628 Japan Department of Applied Physics Hokkaido University Sapporo 060-8628 Japan

We report the dynamics of liquid crystal vortices in layered dilute Fe-doped NbS2 superconductors. We observed enhanced superconductivity with Fe atom doping. The thermally activated vortex flow causes a broad resistive transition. The temperature dependence of the melting field Hm on the applied magnetic field exhibits an upturn behavior as the temperature decreases. The result indicates that the vortex has transitioned from solid to liquid crystal phase. The in-plane anisotropy with twofold symmetry results from the different number of vortex pairs that stably exist on conduction planes when liquid crystal vortices move between neighboring layers. We suggest that under high magnetic fields, the resistance is suppressed due to the pinning of three-dimensional vortices formed by aligned vortex loops.

关键词： Electrical properties Superconductivity Vortex dynamics Transition metal dichalcogenides

来源：评论

学校读者我要写书评

暂无评论

A Hybrid SARIMAX Model in Conjunction with Neural Networks for the Forecasting of Life Insurance Industry Growth in Thailand

A Hybrid SARIMAX Model in Conjunction with Neural Networks f...

引用

International ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI-NCON)

作者： Supika Huadsri Sakorn Mekruksavanich Anuchit Jitpattanakul Wikanda Phaphan Department of Applied Statistics Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Department of Mathematics Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Research Group in Statistical Learning and Inference

This article is conducted with the primary aim of comparing various forecasting models to identify the optimal model for forecasting the growth of the life insurance industry in Thailand. The models under consideration include the SARIMAX model, the Recurrent Neural Network (RNN), and a hybrid model introduced as RNN-SARIMAX. The dataset utilized for this investigation is extensive, consisting of monthly direct premium data from the Thai life insurance sector spanning January 2003 to December 2022. The dataset is segregated into two distinct segments. Initially, data from January 2003 to December 2021 is employed for constructing the forecasting model. Subsequently, data from January 2022 to December 2022 is utilized for a comparative analysis of the forecasting models, to determine the most suitable and accurate model for predicting the growth of the life insurance industry in Thailand. The evaluation criteria for comparing models include the Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and the Coefficient of Determination (R-squared). The consistent findings from our analysis indicate that the SARIMAX model consistently outperforms both the RNN and RNN-SARIMAX models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights

arXiv

引用

arXiv 2024年

作者： Hu, Jingjing Guo, Dan Si, Zhan Liu, Deguang Diao, Yunfeng Zhang, Jing Zhou, Jinxing Wang, Meng School of Computer Science and Information Engineering Hefei University of Technology China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China Department of Chemistry Centre for Atomic Engineering of Advanced Materials Anhui University China Department of Applied Chemistry University of Science and Technology of China China

Molecular representation learning plays a crucial role in various downstream tasks, such as molecular property prediction and drug design. To accurately represent molecules, Graph Neural Networks (GNNs) and Graph Transformers (GTs) have shown potential in the realm of self-supervised pretraining. However, existing approaches often overlook the relationship between molecular structure and electronic information, as well as the internal semantic reasoning within molecules. This omission of fundamental chemical knowledge in graph semantics leads to incomplete molecular representations, missing the integration of structural and electronic data. To address these issues, we introduce MOL-Mamba, a framework that enhances molecular representation by combining structural and electronic insights. MOL-Mamba consists of an Atom & Fragment Mamba-Graph (MG) for hierarchical structural reasoning and a Mamba-Transformer (MT) fuser for integrating molecular structure and electronic correlation learning. Additionally, we propose a Structural Distribution Collaborative Training and E-semantic Fusion Training framework to further enhance molecular representation learning. Extensive experiments demonstrate that MOL-Mamba outperforms state-of-the-art baselines across eleven chemical-biological molecular datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Models for Solar Power Generation Prediction

Comparative Analysis of Machine Learning Models for Solar Po...

引用

International Conference on Smart Computing & Communications (ICSCC)

作者： Goodness Chinaza Orish Samuel Nii Tackie Devrim Kayali Kezban Alpan Lida Ebrahimi Vafaei Kamil Dimililer Department of Electrical and Electronic Engineering Near East University Nicosia North Cyprus Department of Electrical and Electronic Engineering Near East University Research Center for Science Technology and Engineering Nicosia North Cyprus Department of Software Engineering Near East University Research Center for Science Technology and Engineering Nicosia North Cyprus Department of Alternative Energy Resources Technology Near East University Research Center for Science Technology and Engineering Nicosia North Cyprus Department of Electrical and Electronic Engineering Applied Artificial Intelligence Research Centre (AAIRC) Research Center for Science Technology and Engineering Near East University Nicosia North Cyprus

ISBN: (数字)9798350363104

ISBN: (纸本)9798350363111

When constructing renewable energy facilities, it is important to predict the amount of solar electricity generated precisely. To make these precise solar power output forecasts, varying weather patterns should be considered. In this study, the effectiveness of three well-known machine learning methods: K nearest neighbour, Random Forest, and support vector regression was examined and assessed. According to the obtained R2 values, Random Forest performed better compared to the other techniques with 98% on training data and 88.7% on testing data. This shows that when compared to SVR and KNN, the generalization of Random Forest is better when capturing the connection between the input and output data.

关键词： Radio frequency Training Accuracy Electricity Measurement uncertainty Training data Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Distributed private preserving learning based chaotic encryption framework for cognitive healthcare IoT systems

引用

Informatics in Medicine Unlocked 2024年 49卷

作者： Nabi, Shaik Abdul Kalpana, Ponugoti Chandra, N. Subhash Smitha, L. Naresh, K. Ezugwu, Absalom E. Abualigah, Laith Department of Computer Science and Engineering AVN Institute of Engineering and Technology Department of Computer Science and Engineering CVR College of Engineering Department of Information Technology G Narayanamma Institute of Technology and Science Department of Computer Science and Engineering TKR College of Engineering & Technology Unit for Data Science and Computing North-West University Computer Science Department Al Al-Bayt University MEU Research Unit Middle East University Applied Science Research Center Applied Science Private University Jadara Research Center Jadara University Artificial Intelligence and Sensing Technologies (AIST) Research Center University of Tabuk School of Engineering and Technology Sunway University Malaysia

In the field of cognitive healthcare Internet of Things (CH-IoT), there is a strong demand for reliable and minimally intrusive smart gadgets that consistently acquire, analyse, and obtain the confidential health details of the individual. In fact, CH-IoT is empowered with artificial intelligence (AI) to transmute a fewer operational inputs into actionable, intelligent actions through the digitization of medical healthcare data. However, these systems consume more network complexity, interaction, and overhead costs, while inducing a blend of susceptibility and confidentiality issues. In support of this complexity, these cognitive systems need centralised data collection and to be gathered and analysed, which affects scalability issues and adds fuel to privacy and security breaches. Even though it possesses greater intricacy in its potential application, a substantial factor is maintaining the private preservation of healthcare data against the growing attacks. Thus, this paper presents a distributed privacy-preserving, chaotic encryption-based framework that can be deployed for CH-IoT systems to safeguard sensitive data against message modification, denial of service (DoS), and man-in-the-middle attacks (MIM), guaranteeing privacy and data integrity. The proposed framework integrated the federated learning layered hybrid chaotic encryption strategies by investigating through examination the learning infrastructure of convolutional neural networks (CNN). In the examination, the complete framework was carried out in the Tensorflow Federated Learning Libraries (FLL), and numerous performance metrics such as accuracy, precision, recall, f1-score, transmission efficiency, and overhead ratio were measured and contrasted with the various existing frameworks. For the intensive analysis, formal and informal security experiments were also conducted by NIST (National Institute of science and technology). The analytical results illustrate the importance of the proposed framewor

关键词： Cognitive health care Distributed learning Federated learning libraries Internet of things NIST Privacy and security breaches

来源：评论

学校读者我要写书评

暂无评论

On Laves phase in a 9Cr3W3CoB martensitic heat resistant steel when aged at high temperatures

引用

Journal of Materials science & technology 2021年第26期85卷 129-140页

作者： Ye Liang Wei Yan Xianbo Shi Yanfen Li Quanqiang Shi Wei Wang Yiyin Shan Ke Yang Shi-changxu Innovation Center for Advanced Materials Institute of Metal ResearchChinese Academy of SciencesShenyang 110016China School of Materials Science and Engineering University of Science and Technology of ChinaShenyang 110016China CAS Key Laboratory of Nuclear Materials and Safety Assessment Institute of Metal ResearchChinese Academy of SciencesShenyang 110016China

9Cr3W3 CoB steels are developed to serve at the temperature range of 620-650℃,and have been recognized as the most promising martensitic heat-resistant steels for supercritical power *** to the high W and Co contents,the Fe_(2)W Laves phase in such 9Cr3W3 CoB steel possesses some specialties in *** the present research,it was found that even when aged at 800℃in the 9Cr3W3 CoB steel,instead of dissolving,Laves phase formed after 50 h and kept on increasing in size and number density until 1000 h,indicating that the Laves phase was marching for the thermodynamic equilibrium during *** this thermodynamic process,the W-rich M_(3)B_(2)borides in as-received steel and M23C6 carbides were revealed to dissolve,supporting the growth of Laves *** investigation indicates that Laves phase tended to form clusters,and finally grow as a unit bulk Laves phase with an irregular ***,Laves phase nucleated next to M23C6 carbides and enwrapped them inside at 800℃.In addition,the growth processes of Laves phase and M23C6 carbides were a competitive procedure,the coarsening of M23C6 carbides was prior to the growth of Laves phase at 750℃while the growth of Laves phase was prior to the coarsening of M23C6 carbides at 800℃.

关键词： 9Cr3W3Co steel Aging Laves phase Cobalt M23C6 carbides

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：