检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Kaili Zhou Yiyun Xing Yushui Geng Jing Zhao Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong 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 Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

This study proposes a cross-modal retrieval technique, which employs an Attention Embedded Variational AutoEncoder (AE-VAE) to tackle the problem of reduced retrieval accuracy resulting from data noise and data absence in cross-modal retrieval tasks. First, the variational auto-encoder(VAE) is used as an infrastructure to transform modal data into latent variables by encoding and decoding different modal features, thus preserving the semantic structure of the raw modal data and suppressing noise and missing information in the data. Secondly, to better capture the important semantic features of image and text modalities, an improved multi-attention module is introduced in the encoder. In addition, a cross-modal alignment module is designed to further align the latent variables of different modalities in the latent space to solve the confusion problem and improve the accuracy and robustness of cross-modal retrieval. Finally, experiments are conducted on four public datasets, CUB, SUN, AwA1 and AwA2, and the experimental results show that our proposed model is effective in improving the accuracy and robustness of retrieval.

关键词： Accuracy Uncertainty Noise Semantics Transforms Probabilistic logic Robustness

来源：评论

学校读者我要写书评

暂无评论

Semantic-Enhanced Attention Network for Image-Text Matching

Semantic-Enhanced Attention Network for Image-Text Matching

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Huanxiao Zhou Yushui Geng Jing Zhao Xishan Ma Key Laboratory of Computing Power Network and Information Security 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 Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Image-text matching is an important task in cross-modal information processing, which consists of evaluating the similarity between images and text. However, the data of the two modalities have different distributions and representations, which cannot be directly compared. Therefore, the two modalities need to be processed separately. Most existing image-text matching methods extract image fragments and text fragments separately, using an attention mechanism to establish relationships between regions in the image and words in the text. Subsequently, they aggregate the similarity of these images and text fragments. Regardless, not all fragment alignment is meaningful, and irrelevant fragment alignment will bring redundancy and reduce retrieval accuracy. In addition to that, there are contextual relationships between image regions and between text words, which should also be taken into account. In this paper, we simultaneously consider these two aspects and propose a Semantic-Enhanced Attention Network (SEAN). It first focuses on each modality, mining contextual relationships between fragments within each modality and aggregating contextual information into visual and textual embeddings. Then, we compute the similarity between all image regions and text fragments, focusing all attention on the region-word pairs with the highest similarity. Finally, we summarize these to infer the similarity between the image and text. Our method achieves competitive results on two generalized image text retrieval datasets, Flickr30K and MS-COCO.

关键词： Visualization Attention mechanisms Federated learning Computational modeling Aggregates Semantics Redundancy

来源：评论

学校读者我要写书评

暂无评论

Optimal kernel choice for score function-based causal discovery 24

Optimal kernel choice for score function-based causal discov...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Wenjie Wang Biwei Huang Feng Liu Xinge You Tongliang Liu Kun Zhang Mingming Gong School of Mathematics and Statistics The University of Melbourne Australia and Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Halicioğlu Data Science Institute (HDSI) University of California San Diego School of Computing and Information Systems The University of Melbourne Australia Huazhong University of Science and Technology China School of Computer Science Faculty of Engineering The University of Sydney Australia Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates and Department of Philosophy Carnegie Mellon University

Score-based methods have demonstrated their effectiveness in discovering causal relationships by scoring different causal structures based on their goodness of fit to the data. Recently, Huang et al. (2018) proposed a generalized score function that can handle general data distributions and causal relationships by modeling the relations in reproducing kernel Hilbert space (RKHS). The selection of an appropriate kernel within this score function is crucial for accurately characterizing causal relationships and ensuring precise causal discovery. However, the current method involves manual heuristic selection of kernel parameters, making the process tedious and less likely to ensure optimality. In this paper, we propose a kernel selection method within the generalized score function that automatically selects the optimal kernel that best fits the data. Specifically, we model the generative process of the variables involved in each step of the causal graph search procedure as a mixture of independent noise variables. Based on this model, we derive an automatic kernel selection method by maximizing the marginal likelihood of the variables involved in each search step. We conduct experiments on both synthetic data and real-world benchmarks, and the results demonstrate that our proposed method outperforms heuristic kernel selection methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Study of Current Trends Writer Identification in Large-scale across Three World Major Languages with Retrieval Approaches 6

A Study of Current Trends Writer Identification in Large-sca...

引用

6th International Conference on Interactive Digital Media, ICIDM 2020

作者： Tan, Gloria Jennis Kumoi, Rosely Rahim, Mohd Shafry Mohd Wee, Tan Chi Sulong, Ghazali Universiti Malaysia Sarawak Centre for IT Development and Services Sarawak Malaysia Universiti Teknologi Malaysia School of Computing Faculty of Engineering Johor Malaysia Tunku Abdul Rahman University College Faculty of Computing and Information Technology Malaysia Centre for Cyber Security and Big Data Management and Science University Malaysia

ISBN: (纸本)9781728149288

Recent developments in writer identification have led new directions, which is writer identification integrated with retrieval mechanism for boosting the performance applications of writer identification when a database is getting larger in size and retrieval of documents from expanding databases is becoming difficult. Issues on datasets used by previous studies directly impacts accuracy of the writer identification deteriorates as database size increases. Until now, in the research on writer identification researchers have been mainly interested in 'writer identification without retrieval mechanism' approach. This paper provides a review on the state of the art for writer identification with retrieval mechanism throughout three major languages, namely English, Chinese, and Arabic. Up to date, truly little attention has been paid to the role of retrieval mechanism or documents in English language identification;the growth on Arabic and Chinese is far from satisfactory in comparison to its extensive usage. A search of the literature revealed few studies for writer identification with single retrieval mechanism. Seamless integration of such strategies in current forensic handwriting experience is yet unclear. A consistently reliable and efficient, fully automated writer recognition (AWR) and a powerful handwritten document retrieval system as an emerging technology are real challenging issues might be taken by upcoming researchers. It is still considered a fresh field and still has large room for research. © 2020 IEEE.

关键词： database systems

来源：评论

学校读者我要写书评

暂无评论

A Triangular Stable Node Network based on Self-supervised Learning for personalized prediction

A Triangular Stable Node Network based on Self-supervised Le...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Qing Liu Qian Gao Jun Fan Zhiqiang Zhang 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 Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China China Telecom Digital Intelligence Techonology Co Ltd Jinan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In recent years, research has illuminated the potency of implicit data processing in enhancing user preferences. Nevertheless, barriers remain in breaking through the constraints of implicit information. This study aims to bridge this gap by firstly constructing a triangular stable node network model, tailored to manage implicit information with precision. Recognizing the challenge of pinpointing novel structures within large-scale graphs, we propose SLTSNN— a triangular stable node network based on self-supervised learning for personalized prediction. SLTSNN innovates by maximizing mutual information between graph-level and patch-level representations, while augmenting graph representations through extended enhanced representations. Additionally, it incorporates triangular data associations and introduces a triangular allocation attention network, which emphasizes strongly correlated preference features among similar users. Furthermore, SLTSNN employs contrastive learning to maximize mutual information between graph vectors and hidden representations, distinguishing between high-order global and local representations. The model’s effectiveness in enhancing user preferences and capturing new graph structures is evidenced by its performance on hit rate and normalized discounted cumulative gain metrics across three datasets.

关键词： Measurement Bridges Contrastive learning Signal processing data processing Vectors Space exploration Resource management Speech processing Mutual information

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence for geoscience:Progress,challenges,and perspectives

引用

The Innovation 2024年第5期5卷 136-160,135页

作者： Tianjie Zhao Sheng Wang Chaojun Ouyang Min Chen Chenying Liu Jin Zhang Long Yu Fei Wang Yong Xie Jun Li Fang Wang Sabine Grunwald Bryan MWong Fan Zhang Zhen Qian Yongjun Xu Chengqing Yu Wei Han Tao Sun Zezhi Shao Tangwen Qian Zhao Chen Jiangyuan Zeng Huai Zhang Husi Letu Bing Zhang Li Wang Lei Luo Chong Shi Hongjun Su Hongsheng Zhang Shuai Yin Ni Huang Wei Zhao Nan Li Chaolei Zheng Yang Zhou Changping Huang Defeng Feng Qingsong Xu Yan Wu Danfeng Hong Zhenyu Wang Yinyi Lin Tangtang Zhang Prashant Kumar Antonio Plaza Jocelyn Chanussot Jiabao Zhang Jiancheng Shi Lizhe Wang Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China School of Computer Science China University of GeosciencesWuhan 430078China State Key Laboratory of Mountain Hazards and Engineering Resilience Institute of Mountain Hazards and EnvironmentChinese Academy of SciencesChengdu 610299China Key Laboratory of Virtual Geographic Environment(Ministry of Education of PRC) Nanjing Normal UniversityNanjing 210023China Data Science in Earth Observation Technical University of Munich80333 MunichGermany The National Key Laboratory of Water Disaster Prevention Yangtze Institute for Conservation and DevelopmentHohai UniversityNanjing 210098China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China School of Geographical Sciences Nanjing University of Information Science and TechnologyNanjing 210044China State Key Laboratory of Soil and Sustainable Agriculture Institute of Soil ScienceChinese Academy of SciencesNanjing 210008China Soil Water and Ecosystem Sciences DepartmentUniversity of FloridaPO Box 110290GainesvilleFLUSA Materials Science Engineering Program Cooperating Faculty Member in the Department of Chemistry and Department of Physics Astronomy University of CaliforniaCaliforniaRiversideCA 92521USA Institute of Remote Sensing and Geographical Information System School of Earth and Space SciencesPeking UniversityBeijing 100871China Key Laboratory of Computational Geodynamics University of Chinese Academy of SciencesBeijing 100049China International Research Center of Big Data for Sustainable Development Goals Beijing 100094China College of Geography and Remote Sensing Hohai UniversityNanjing 211100China Department of Geography The University of Hong KongHong Kong 999077SARChina Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Nanjing 210044China School of Environmental Science and Engineering Nanjing University of Information Science&TechnologyNanjing 210044China Collaborative Inno

This paper explores the evolution of geoscientific inquiry,tracing the progression from traditional physics-based models to modern data-driven approaches facilitated by significant advancements in artificial intelligence(AI)and data collection *** models,which are grounded in physical and numerical frameworks,provide robust explanations by explicitly reconstructing underlying physical ***,their limitations in comprehensively capturing Earth’s complexities and uncertainties pose challenges in optimization and real-world *** contrast,contemporary data-driven models,particularly those utilizing machine learning(ML)and deep learning(DL),leverage extensive geoscience data to glean insights without requiring exhaustive theoretical *** techniques have shown promise in addressing Earth science-related ***,challenges such as data scarcity,computational demands,data privacy concerns,and the“black-box”nature of AI models hinder their seamless integration into *** integration of physics-based and data-driven methodologies into hybrid models presents an alternative *** models,which incorporate domain knowledge to guide AI methodologies,demonstrate enhanced efficiency and performance with reduced training data *** review provides a comprehensive overview of geoscientific research paradigms,emphasizing untapped opportunities at the intersection of advanced AI techniques and *** examines major methodologies,showcases advances in large-scale models,and discusses the challenges and prospects that will shape the future landscape of AI in *** paper outlines a dynamic field ripe with possibilities,poised to unlock new understandings of Earth’s complexities and further advance geoscience exploration.

关键词： Earth utilizing landscape

来源：评论

学校读者我要写书评

暂无评论

Subspace learning using low-rank latent representation learning and perturbation theorem: Unsupervised gene selection

引用

Computers in Biology and Medicine 2025年 185卷 109567-109567页

作者： Moslemi, Amir Naeini, Fariborz Baghaei Department of Physics Toronto Metropolitan University ON Canada School of Software Design & Data Science Seneca Polytechnic TorontoONM4N 3M5 Canada Physical Sciences Sunnybrook Health Sciences Centre TorontoONM4N 3M5 Canada Faculty of Engineering Computing and the Environment Kingston University Penrhyn Road Campus Kingston Upon Thames LondonKT1 2EE United Kingdom

In recent years, gene expression data analysis has gained growing significance in the fields of machine learning and computational biology. Typically, microarray gene datasets exhibit a scenario where the number of features exceeds the number of samples, resulting in an ill-posed and underdetermined equation system. The presence of redundant features in high-dimensional data leads to suboptimal performance and increased computational time for learning algorithms. Although feature extraction and feature selection are two approaches that can be employed to deal with this challenge, feature selection has greater interpretability ability which causes it to receive more attention. In this study, we propose an unsupervised feature selection which is based on pseudo label latent representation learning and perturbation theory. In the first step, pseudo labels are extracted and constructed using latent representation learning. In the second step, the least square problem is solved for original data matrix and perturbed data matrix. Features are clustered based on the similarity between the original data matrix and the perturbed data matrix using k-means. In the last step, features in each subcluster are ranked based on information gain criterion. To showcase the efficacy of the proposed approach, numerical experiments were carried out on six benchmark microarray datasets and two RNA-Sequencing benchmark datasets. The outcomes indicate that the proposed technique surpasses eight state-of-the-art unsupervised feature selection methods in both clustering accuracy and normalized mutual information. © 2024 Elsevier Ltd

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

EDCOPA Protocol: Addressing Scalability, High-Density and Load Balancing Challenges in WSN-based IoT

EDCOPA Protocol: Addressing Scalability, High-Density and Lo...

引用

Electrical, Computer, Telecommunication and Energy Technologies (ECTE-Tech), International Conference on

作者： Foudil Mir Abderrazak Sebaa Abdelkader Laouid Ahcene Bounceur Farid Meziane Faculty of Exact Sciences LIMED Laboratory University of Bejaia Bejaia Algeria Laboratoire LITAN Ecole Supérieure en Sciences et Technologies de l'Informatique et du Numérique Bejaia Algerie LIAP Laboratory University of El Oued El Oued Algeria College of Computing and Informatics University of Sharjah Sharjah UAE Data Science Research Centre University of Derby Derby UK

ISBN: (数字)9798350388480

ISBN: (纸本)9798350388497

Energy optimization in Wireless Sensor Networks for the Internet of Things (WSN-Based IoT) is essential to extend the lifetime of networks while guaranteeing optimum performance. This paper investigates the performance of the EDCOPA protocol, which is an enhancement of the DCOPA protocol, by addressing three key aspects: the impact of scalabil-ity, network density, and load balancing. The DCOPA protocol, while powerful, has limitations in that it relies solely on residual energy and Distance to the Base Station (DistBS) to select cluster heads (CHs). To overcome this limitation, the EDCOPA protocol integrates new criteria, namely the energy consumption in the previous round Epr i and the CH role frequency Nch i of a given node. We study the effect of scalability as well as the impact of density on the Lifetime Parameters (LTP). In addition, we analyze load balancing by evaluating the distribution of CHs and clusters after the clustering process. This analysis examines how the proposed improvements affect energy efficiency and network LTP. This paper provides an in-depth look at the performance of the EDCOPA protocol in terms of properties that are extremely important in WSN-based IoT networks.

关键词： Wireless sensor networks Energy consumption Protocols Scalability Voting Load management Robustness Energy efficiency Internet of Things Optimization

来源：评论

学校读者我要写书评

暂无评论

Geometric Optimisation of Unmanned Aerial Vehicle Trajectories in Uncertain Environments

引用

Vehicular Communications 2025年 54卷

作者： Akshya, J. Sundarrajan, M. Amutha, S. Dhanaraj, Rajesh Kumar Khadidos, Adil O. Khadidos, Alaa O. Selvarajan, Shitharth Department of Computational Intelligence SRM Institute of Science and Technology Tamil Nadu Kattankulathur 603203 India Department of Networking and Communications SRM Institute of Science and Technology Tamil Nadu Kattankulathur 603203 India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Symbiosis Institute of Computer Studies and Research (SICSR) Symbiosis International (Deemed University) Pune India Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah 21589 Saudi Arabia Center of Research Excellence in Artificial Intelligence and Data Science King Abdulaziz University Jeddah Saudi Arabia School of Built Environment Engineering and Computing Leeds Beckett University LS6 3HF Leeds United Kingdom Department of Computer Science and Engineering Chennai Institute of Technology Chennai India Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura 140401 India

The problem of efficient trajectory optimisation for Unmanned Aerial Vehicles (UAVS) in dynamic and constrained environments is one where energy efficiency, spatial coverage, and path smoothness need to be balanced. The existing methods, namely RRT*, A*, and Dijkstra, are popular but generally heuristic and do not provide globally optimal solutions. They face significant limitations while dealing with complex geometries, dynamic obstacles, and multi-objective requirements. These challenges call for a mathematically sound framework that seamlessly integrates convex analysis and computational geometry to provide an optimal trajectory planning framework. This research work introduces a convex optimisation framework for UAV trajectory planning which unifies multiple objectives, like minimising energy consumption, maximising spatial coverage, and ensuring the smoothness of the path, into a single convex objective function. More importantly, it indicates that obstacle dynamics and uncertain environmental conditions are handled better by it, so it is relatively easier for safe and efficient navigation. Proven to converge faster and with higher precision than RRT*, A*, and Dijkstra, the approach proposed here enjoys intrinsic convex properties, which ensure global optimality. Qualitative measurements show the efficiency of the proposed framework. The result is energy efficiency of 90%, with 92% coverage, 98% constraint satisfaction, and 95% path smoothness, which is 15-25% better on all metrics than traditional approaches can offer. By bridging between theory in convex optimisation and practice for solving multi-objective problems in a dynamic setting, this study provides a more robust solution for UAV trajectory planning. © 2025 The Author(s)

关键词： Computational Geometry Convex Optimisation Delaunay Triangulations Spatial Coverage UAV Trajectory Voronoi Diagrams

来源：评论

学校读者我要写书评

暂无评论

On the Violation of Honesty in Mobile Apps: Automated Detection and Categories

arXiv

引用

arXiv 2022年

作者： Obie, Humphrey O. Ilekura, Idowu Du, Hung Shahin, Mojtaba Grundy, John Li, Li Whittle, Jon Turhan, Burak HumaniSE Lab Monash University Melbourne Australia Data Science Nigeria Lagos Nigeria Applied Artificial Intelligence Inst. Deakin University Melbourne Australia School of Computing Technologies RMIT University Melbourne Australia Faculty of IT Monash University Melbourne Australia CSIRO's Data61 Melbourne Australia University of Oulu Oulu Finland

Human values such as integrity, privacy, curiosity, security, and honesty are guiding principles for what people consider important in life. Such human values may be violated by mobile software applications (apps), and the negative effects of such human value violations can be seen in various ways in society. In this work, we focus on the human value of honesty. We present a model to support the automatic identification of violations of the value of honesty from app reviews from an end-user perspective. Beyond the automatic detection of honesty violations by apps, we also aim to better understand different categories of honesty violations expressed by users in their app reviews. The result of our manual analysis of our honesty violations dataset shows that honesty violations can be characterised into ten categories: unfair cancellation and refund policies;false advertisements;delusive subscriptions;cheating systems;inaccurate information;unfair fees;no service;deletion of reviews;impersonation;and fraudulent-looking apps. Based on these results, we argue for a conscious effort in developing more honest software artefacts including mobile apps, and the promotion of honesty as a key value in software development practices. Furthermore, we discuss the role of app distribution platforms as enforcers of ethical systems supporting human values, and highlight some proposed next steps for human values in software engineering (SE) research. © 2022, CC BY.

关键词： Application programs

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：