检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Zhu, Mengxiao Shu, Qi Shen, Shuanghong Huang, Zhenya Wu, Jiancan Feng, Li Institute of Advanced Technology University of Science and Technology of China Hefei230026 China School of Data Science University of Science and Technology of China Hefei230026 China School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei230026 China School of Information Science and Technology University of Science and Technology of China Hefei230026 China

In recent years, live streaming develops rapidly, attracting an increasing number of users. Providing personalized live streaming recommendations is crucial for platform improvement in enhancing user experience and increasing profitability. In live streaming scenarios, users often enter the same live streaming room multiple times, send chat messages and give virtual gifts repeatedly. However, existing recommendation models fail to effectively model the complex multiple types of repeated behaviors of users in live streaming scenarios, thus failing to achieve optimal recommendation results. To address this issue, we propose a novel live recommendation model called MRB4LS based on multiple types of repeated behaviors data. Specifically, we first construct three bipartite graphs to better capture the effects of multiple types of users' repeated behaviors, including enter, chat, and gift. Second, we introduce a graph attention network named RepGAT, which explicitly learns from users' repeated behaviors. RepGAT incorporates the number of repeated interactions between nodes when computing normalized attention coefficients, enabling a deeper exploration of users' preferences and the heterogeneous strength of the interaction relationship between users and live streaming rooms. Then, we design two embedding fusion strategies, namely concatenation-based and attention-based methods, to integrate node representations generated by different repeated behaviors. Finally, we adopt a multi-task learning approach to enhance the prediction effectiveness of gift behavior by leveraging predictions from enter behavior and chat behavior. To validate our approach, we construct two live streaming datasets from a large-scale game live streaming platform. Extensive experiments on two real-world datasets with different scales show that our method can significantly outperform various baseline approaches. © 2024, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Detection of Alzheimer's Disease progression from Structural MRIs using ConvMixer based Deep Learning Model

Detection of Alzheimer's Disease progression from Structural...

引用

3rd International Conference on Machine Learning and data Engineering, ICMLDE 2024

作者： Lashkary, Mahak Bansal, Kanika Jain, Samyak Shukla, Praveen Kumar Tekchandani, Hitesh Dhaka, Vijaypal Singh School of Computing and Intelligent Systems Manipal University Jaipur Rajasthan Jaipur303007 India School of Computer Science and Engineering Manipal University Jaipur Rajasthan Jaipur303007 India Department of Artificial Intelligence and Data Science Koneru Lakshmaiah Education Foundation Telangana Hyderabad500075 India

Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that significantly impacts cognitive functions and quality of life. Affecting over 50 million people worldwide, early and accurate detection of AD progression is crucial for timely intervention and management. This paper presents a reliable method for classifying Alzheimer's stages using Deep Learning based ConvMixer model on structural MRI data. The proposed deep learning based convmixer model significantly utilizes the patch based learning with depthwise separable convolution to achieve improved performance. The dataset used in this work has been extracted from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and comprises of three classes: Alzheimer's Disease (AD), Cognitive Impairment (CI), and Cognitively Normal (CN). The proposed approach demonstrated exceptional performance, achieving an accuracy of 99.88%, specificity of 99.87%, sensitivity of 99.90 and precision of 99.95%. The achieved results demonstrate the proposed model's accuracy in distinguishing Alzheimer's stages, making it a promising tool for early diagnosis and disease progression monitoring. © 2025 The Author(s).

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Environment-aware dynamic graph learning for out-of-distribution generalization 23

Environment-aware dynamic graph learning for out-of-distribu...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Haonan Yuan Qingyun Sun Xingcheng Fu Ziwei Zhang Cheng Ji Hao Peng Jianxin Li Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University and School of Computer Science and Engineering Beihang University Key Lab of Education Blockchain and Intelligent Technology Guangxi Normal University Department of Computer Science and Technology Tsinghua University Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

Dynamic graph neural networks (DGNNs) are increasingly pervasive in exploiting spatio-temporal patterns on dynamic graphs. However, existing works fail to generalize under distribution shifts, which are common in real-world scenarios. As the generation of dynamic graphs is heavily influenced by latent environments, investigating their impacts on the out-of-distribution (OOD) generalization is critical. However, it remains unexplored with the following two major challenges: (1) How to properly model and infer the complex environments on dynamic graphs with distribution shifts? (2) How to discover invariant patterns given inferred spatio-temporal environments? To solve these challenges, we propose a novel Environment-Aware dynamic Graph LEarning (EAGLE) framework for OOD generalization by modeling complex coupled environments and exploiting spatiotemporal invariant patterns. Specifically, we first design the environment-aware EADGNN to model environments by multi-channel environments disentangling. Then, we propose an environment instantiation mechanism for environment diversification with inferred distributions. Finally, we discriminate spatio-temporal invariant patterns for out-of-distribution prediction by the invariant pattern recognition mechanism and perform fine-grained causal interventions node-wisely with a mixture of instantiated environment samples. Experiments on real-world and synthetic dynamic graph datasets demonstrate the superiority of our method against state-of-the-art baselines under distribution shifts. To the best of our knowledge, we are the first to study OOD generalization on dynamic graphs from the environment learning perspective.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Squared families: Searching beyond regular probability models

arXiv

引用

arXiv 2025年

作者： Tsuchida, Russell Liu, Jiawei Ong, Cheng Soon Sejdinovic, Dino Data Science and AI Group Monash University ClaytonVIC3800 Australia School of Computing Australian National University CanberraACT2600 Australia Data61 CSIRO Australian National University CanberraACT2600 Australia School of Computer and Mathematical Sciences The University of Adelaide AdelaideSA5005 Australia

We introduce squared families, which are families of probability densities obtained by squaring a linear transformation of a statistic. Squared families are singular, however their singularity can easily be handled so that they form regular models. After handling the singularity, squared families possess many convenient properties. Their Fisher information is a conformal transformation of the Hessian metric induced from a Bregman generator. The Bregman generator is the normalising constant, and yields a statistical divergence on the family. The normalising constant admits a helpful parameter-integral factorisation, meaning that only one parameter-independent integral needs to be computed for all normalising constants in the family, unlike in exponential families. Finally, the squared family kernel is the only integral that needs to be computed for the Fisher information, statistical divergence and normalising constant. We then describe how squared families are special in the broader class of g-families, which are obtained by applying a sufficiently regular function g to a linear transformation of a statistic. After removing special singularities, positively homogeneous families and exponential families are the only g-families for which the Fisher information is a conformal transformation of the Hessian metric, where the generator depends on the parameter only through the normalising constant. Even-order monomial families are the only infinitely differentiable positively homogeneous families, and also admit natural parameter-integral factorisations, unlike exponential families. Finally, we study parameter estimation and density estimation in squared families, in the well-specified and misspecified settings. We use a universal approximation property to show that squared families can learn sufficiently well-behaved target densities at an asymptotic rate of O(N−1/2) + Cn−1/4, where N is the number of datapoints, n is the number of parameters, and C is some data-independ

关键词： Fisher information matrix

来源：评论

学校读者我要写书评

暂无评论

The impact of entrepreneurship education on entrepreneurship intention in the engineering studies 27

The impact of entrepreneurship education on entrepreneurship...

引用

27th International Conference on Knowledge Based and Intelligent Information and Engineering Sytems, KES 2023

作者： Kurata, Karin Kota, Kodama Morinaga, Takashi Ohnishi, Hiromasa SouTakahashi Sato, Jun Yajima, Kuniaki Dept. of Creative Engineering National Institute of Technology Tsuruoka College Tsuruoka997-8511 Japan Dept. of Creative Engineering National Institute of Technology Sendai College Sendai989-3128 Japan School of Data Science Nagoya City University Nagoya467-8501 Japan

Entrepreneurship education is characterized by interactive learning linked to business and community initiatives. In entrepreneurship course, activity sessions include (1) Causation, and effectuation (2) Devil's River, Valley of Death, and Darwin's Sea, (3) Case Studies, (4) Guest Speaker Sessions, (5) Lean Startup, Business Model Canvas (BMC), Value Proposition Canvas (VPC), etc. are often addressed. The goal of entrepreneurship education is to change students' mindsets in terms of how they view innovative and risk-taking activities in business. There are several ways to measure the change derived from entrepreneurship education, including affective, cognitive, and skill-based outcomes. A previous study examined the effect of entrepreneurship education on entrepreneurship in relation to three independent variables: perceived behavioral control (PBC), attitude (AT), and subjective norm (SN). Combined with the results of the Generic Skill measure, this study proposes an evaluation method for entrepreneurship education that focuses on entrepreneurship intention. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine-learning-assisted intelligent synthesis of UiO-66(Ce):Balancing the trade-off between structural defects and thermal stability for e hydrogenation of Dicyclopentadiene

引用

Materials Genome Engineering Advances 2024年第3期2卷 96-106页

作者： Jing Lin Tao Ban Tian Li Ye Sun Shenglan Zhou Rushuo Li Yanjing Su Jitti Kasemchainan Hongyi Gao Lei Shi Ge Wang Beijing Key Laboratory of Function Materials for Molecule&Structure Construction Beijing Advanced Innovation Center for Materials Genome EngineeringSchool of Materials Science and EngineeringUniversity of Science and Technology BeijingBeijingChina Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and EngineeringBeihang UniversityBeijingChina Beijing Advanced Innovation Center for Materials Genome Engineering Institute for Advanced Materials and TechnologySchool of Materials Science and EngineeringUniversity of Science and Technology BeijingBeijingChina Department of Chemical Technology Chulalongkorn UniversityBangkokThailand

Metal-organic frameworks(MOFs),renowned for structural diversity and design flexibility,exhibit potential in ***,the pursuit of higher catalytic activity through defects often compromises stability,requiring a delicate *** trial-and-error method for optimizing synthesis parameters within the complex chemical space is ***,taking the typical MOF UiO-66(Ce)as an illustrative example,a closed loop workflow is built,which integrates ma-chine learning(ML)-assissted prediction,multi-objective optimization(MOO)and experimental preparation to synergistically optimize the defect content and thermal stability of UiO-66(Ce)for efficient hydrogenation of dicyclopentadiene(DCPD).An automatic data extraction program ensures data accuracy,establishing a high-quality *** is employed to explore the intricate synthesis-structure-property correlations,enabling precise delineation of pure-phase subspace and accurate predictions of *** two iterations,MOO model identifies optimal protocols for high defect content(>40%)and thermal stability(>300℃).The optimized UiO-66(Ce)exhibits superior catalytic performance in hydroge-nation of DCPD,validating the precision and reliability of our *** ML-assisted approach offers a valuable paradigm for solving the trade-off riddle in materials field.

关键词： defect content machine learning metal-organic frameworks multi-objective optimization thermal stability

来源：评论

学校读者我要写书评

暂无评论

Hybrid data-Driven SSM for Interpretable and Label-Free mmWave Channel Prediction

引用

IEEE Transactions on Mobile computing 2025年

作者： Sun, Yiyong He, Jiajun Lin, Zhidi Pu, Wenqiang Yin, Feng So, Hing Cheung The Chinese University of Hon g Kong School of Science and Engineering Shenzhen518172 China BelfastBT3 9DT United Kingdom National University of Singapore Department of Statistics and Data Science 117546 Singapore Shenzhen Research Institute of Big Data Shenzhen518172 China City University of Hong Kong Department of Electrical Engineering Hong Kong

Accurate prediction of mmWave time-varying channels is essential for mitigating the issue of channel aging in highly dynamic scenarios. Existing channel prediction methods have limitations: classical model-based methods often struggle to track highly nonlinear channel dynamics due to limited expert knowledge, while emerging data-driven methods typically require substantial labeled data for effective training and often lack interpretability. To address these issues, this paper proposes a novel hybrid method that integrates a data-driven neural network into a conventional model-based workflow based on a state-space model (SSM), implicitly tracking complex channel dynamics from data without requiring precise expert knowledge. Additionally, a novel unsupervised learning strategy is developed to train the embedded neural network solely with unlabeled data. Theoretical analyses and ablation studies are conducted to interpret the enhanced benefits gained from the hybrid integration. Numerical simulations based on the 3GPP mmWave channel model corroborate the superior prediction accuracy of the proposed method, compared to state-of-the-art methods that are either purely model-based or data-driven. Furthermore, extensive experiments validate its robustness against various challenging factors, including among others severe channel variations. © 2002-2012 IEEE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Transformer for Object Re-Identification: A Survey

arXiv

引用

arXiv 2024年

作者： Ye, Mang Chen, Shuoyi Li, Chenyue Zheng, Wei-Shi Crandall, David Du, Bo National Engineering Research Center for Multimedia Software School of Computer Science Hubei Luojia Laboratory Wuhan University Wuhan China School of Data and Computer Science Sun Yat-sen University Guangzhou China Luddy School of Informatics Computing and Engineering Indiana University United States

Object Re-identification (Re-ID) aims to identify specific objects across different times and scenes, which is a widely researched task in computer vision. For a prolonged period, this field has been predominantly driven by deep learning technology based on convolutional neural networks. In recent years, the emergence of Vision Transformers has spurred a growing number of studies delving deeper into Transformer-based Re-ID, continuously breaking performance records and witnessing significant progress in the Re-ID field. Offering a powerful, flexible, and unified solution, Transformers cater to a wide array of Re-ID tasks with unparalleled efficacy. This paper provides a comprehensive review and in-depth analysis of the Transformer-based Re-ID. In categorizing existing works into Image/Video-Based Re-ID, Re-ID with limited data/annotations, Cross-Modal Re-ID, and Special Re-ID Scenarios, we thoroughly elucidate the advantages demonstrated by the Transformer in addressing a multitude of challenges across these domains. Considering the trending unsupervised Re-ID, we propose a new Transformer baseline, UntransReID, achieving state-of-the-art performance on both single/cross modal tasks. For the under-explored animal Re-ID, we devise a standardized experimental benchmark and conduct extensive experiments to explore the applicability of Transformer for this task and facilitate future research. Finally, we discuss some important yet under-investigated open issues in the large foundation model era, we believe it will serve as a new handbook for researchers in this field. A periodically updated website will be available at https://***/mangye16/ ReID-Survey. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Bayesian Functional Analysis for Untargeted Metabolomics data with Matching Uncertainty and Small Sample Sizes

arXiv

引用

arXiv 2023年

作者： Ma, Guoxuan Kang, Jian Yu, Tianwei Department of Biostatistics University of Michigan Ann ArborMI48109 United States School of Data Science The Chinese University of Hong Kong – Shenzhen Guangdong Shenzhen518172 China Shenzhen Research Institute of Big Data Guangdong Shenzhen518172 China Guangdong Provincial Key Laboratory of Big Data Computing Shenzhen518172 China

Untargeted metabolomics based on liquid chromatography-mass spectrometry technology is quickly gaining widespread application given its ability to depict the global metabolic pattern in biological samples. However, the data is noisy and plagued by the lack of clear identity of data features measured from samples. Multiple potential matchings exist between data features and known metabolites, while the truth can only be one-to-one matches. Some existing methods attempt to reduce the matching uncertainty, but are far from being able to remove the uncertainty for most features. The existence of the uncertainty causes major difficulty in downstream functional analysis. To address these issues, we develop a novel approach for Bayesian Analysis of Untargeted Metabolomics data (BAUM) to integrate previously separate tasks into a single framework, including matching uncertainty inference, metabolite selection, and functional analysis. By incorporating the knowledge graph between variables and using relatively simple assumptions, BAUM can analyze datasets with small sample sizes. By allowing different confidence levels of feature-metabolite matching, the method is applicable to datasets in which feature identities are partially known. Simulation studies demonstrate that, compared with other existing methods, BAUM achieves better accuracy in selecting important metabolites that tend to be functionally consistent and assigning confidence scores to feature-metabolite matches. We analyze a COVID-19 metabolomics dataset and a mouse brain metabolomics dataset using BAUM. Even with a very small sample size of 16 mice per group, BAUM is robust and stable. It finds pathways that conform to existing knowledge, as well as novel pathways that are biologically plausible. © 2023, CC BY.

关键词： Functional analysis

来源：评论

学校读者我要写书评

暂无评论

FaceCaps for facial expression recognition

FaceCaps for facial expression recognition

引用

作者： Wu, Fangyu Pang, Chaoyi Zhang, Bailing College of Computer Science and Technology Zhejiang University HangzhouZhejiang China School of Computing and Data Engineering NingboTech University NingboZhejiang China

Facial expression recognition (FER) is a significant research task in the computer vision field. In this paper, we present a novel network FaceCaps for facial expression recognition with the following novel characteristics: an embedding structure based on a Capsule network which encodes relative spatial relationships between features;incorporates the feature polymerization property of FaceNet, thus offering a more efficient approach to discriminate complex facial expressions;a target reconstruction loss as a better regularization term for Capsule networks. Experimental results on both lab-controlled datasets (CK+) and real-world databases (RAF-DB and SFEW 2.0) demonstrate that the method significantly outperforms the state-of-the-art. © 2021 John Wiley & Sons, Ltd.

关键词： Face recognition

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：