检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5267-5276页

作者： Yang, Shuai Jiang, Tingting Dang, Qianlong Gu, Lichuan Wu, Xindong Anhui Agricultural University School of Information and Artificial Intelligence Hefei230036 China Anhui Provincial Engineering Research Center for Agricultural Information Perception and Intelligent Computing Hefei230036 China Northwest A & F University College of Science Yangling712100 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China

Stable learning aims to learn a model that generalizes well to arbitrary unseen target domain by leveraging a single source domain. Recent advances in stable learning have focused on balancing the distribution of confounders for each feature to eliminate spurious correlations. However, previous studies treat all features equally without considering the difficulties of confounder balancing associated with different features, and regard irrelevant features as confounders, deteriorating generalization performance. To tackle these issues, this article proposes a novel triplex learning (TriL) based stable learning algorithm, which performs sample reweighting, causal feature selection, and representation learning to remove spurious correlations. Specifically, first, TriL adaptively assigns weights to the confounder balancing term of each feature in accordance with the difficulties of confounder balancing, and aligns the confounder distribution of each feature by learning a group of sample weights. Second, TriL integrates the sample weights into a weighted cross-entropy model to compute causal effects of features for excluding irrelevant features from the confounder set. Finally, TriL relearns a set of sample weights and uses them to guide a new supervised dual-autoencoder containing two classifiers to learn feature representations. TriL forces the results of two classifiers to remain consistent for removing spurious correlations by using a cross-classifier consistency regularization. Extensive experiments on synthetic and two real-world datasets show the superiority of TriL compared with seven methods. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Measuring China's Real Estate Financial Innovation from the Perspective of Government,Enterprises and the Public:Index Compilation and Its Spatial-Temporal Characteristics Analysis

引用

Journal of Systems Science and Information 2023年第1期11卷 1-34页

作者： Jichang DONG Lijun YIN Xiaoting LIU Xiuting LI School of Economics and Management University of Chinese Academy of SciencesBeijing 100190China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of SciencesBeijing 100190China China Construction Second Engineering Bureau Co.Ltd Beijing 100070China

In recent years,China has witnessed the rapid development in housing finance,and there have emerged constantly real estate finance innovations;however,there exists no relevant index for measuring the innovations of China's real estate *** on the perspectives of the governments,enterprises and the public,this paper constructs the"innovation index of real estate finance"on a quarterly basis from 2009 to 2019,with the method of empowerment which combines the subjective method(analytic hierarchy process)and the objective one(range coefficient method).It clearly and concretely depicts the innovations in housing finance and the related temporal-spatial characteristics in China since the outbreak of the financial crisis in *** index covers 30 provinces,autonomous regions and municipalities directly under the central government,and analyzes its temporal and spatial *** findings show that there exist a strong spatial autocorrelation and a big regional difference in innovations.

关键词： governments enterprises public real estate finance innovation

来源：评论

学校读者我要写书评

暂无评论

Fast incremental structure from motion based on parallel bundle adjustment

Fast incremental structure from motion based on parallel bun...

引用

作者： Cao, Mingwei Zheng, Liping Jia, Wei Liu, Xiaoping Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei230009 China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei University of Technology Hefei230009 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

Structure from motion has attracted a lot of research in recent years, with new state-of-the-art approaches coming almost every year. One of its advantages over 3D reconstruction is that it can be used for any cameras (UAVs, depth sensor, light field) and produces relatively accurate point clouds and camera parameters. One of its disadvantages compared to other approaches is that it is computationally expensive. In this paper, we design a novel structure-from-motion framework to reduce the computational cost and implement a parallel bundle adjustment on GPU device for large-scale optimization. In our framework, the local bundle adjustment is added into the architecture of the incremental structure from motion;namely, the point clouds and camera’s parameters are optimized when an additional number of images was added. Then, the purpose is not only to improve the quality of the produced point clouds but also to reduce computation time via parallel bundle adjustment. We conduct extensively experiments on several challenging datasets and make comparison with the state-of-the-art methods. Experimental results show that the proposed method has the best performance in terms of accuracy and efficiency. © 2020, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Notice of Retraction: Studies of knowledge management methods from literature

Notice of Retraction: Studies of knowledge management method...

引用

IEEE International Conference on Advanced Management Science (ICAMS)

作者： Jing Zhang Liuqi Ye Business School Hohai University HHU Nanjing Jiangsu China Key Laboratory of Data Engineering and Knowledge Engineering Renmin University of China Beijing China

This article has been retracted by the publisher.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Economic Semantic Web Platform

An Economic Semantic Web Platform

引用

International Conference on Grid and Cooperative Computing Workshops (GCCW)

作者： Xiaoyong Du He Hu Man Li Wenjuan Wu Guo Qin Key Laboratory of Data Engineering and Knowledge Engineering MOE School of Information Renmin University of China Beijing China

The paper describes an ongoing project which implements a subject-oriented semantic Web platform at Renmin Univ. of China. The economic semantic Web platform (ESWP) contains three components: collaborative ontology developing environment and repository system (CODERS); economic ontology annotation Web services (ConAnnotator); economic ontology and annotated resources. We describe each of these components in detail and illustrate some use cases of the ESWP

关键词： Semantic Web Ontologies Environmental economics Web services Collaboration Humans Software agents Application software Helium Laboratories

来源：评论

学校读者我要写书评

暂无评论

Computing Degree of Association Based on Different Semantic Relationships

Computing Degree of Association Based on Different Semantic ...

引用

International Workshop on database and Expert Systems Applications

作者： Xuan Tian Xiaoyong Du Haihua Li School of Information Key Laboratory of Data Engineering and Knowledge Engineering MOE Renmin University of China Beijing China

In domain ontologies, there is usually no weight assigned to the link between two concepts. This has been considered as one of main obstacles in using ontologies. Semantic Association (SA) is to depict the correlation of two concepts, and can be measured as the weight of the link. In this paper, we defined Degree of Association (DOA) to measure SA from a concept to its direct-related concept in domain ontology, and proposed a Language-Model-Based Method (LMBM) to compute DOA. Our idea comes from the intuition that the semantic relationship between two concepts implies certain semantic association of them. We took probabilistic model for computing DOA, and used Maximum Likelihood Estimation to estimate parameters. We tested the proposed method on two different domain ontologies, and applied it in experiments of semantic query expansion. Experimental results show the benefit of our approach and demonstrate the promising effectiveness over semantic query expansion.

关键词： Ontologies Information retrieval Direction of arrival estimation Parameter estimation data mining databases Expert systems Computer applications Laboratories data engineering

来源：评论

学校读者我要写书评

暂无评论

In-Network Execution of External Join for Sensor Networks

In-Network Execution of External Join for Sensor Networks

引用

International Conference on Web-Age Information Management Workshops (WAIM)

作者： Yongxuan Lai Yilong Chen Hong Chen School of Information Key Laboratory of Data Engineering and Knowledge Engineering MOE Renmin University of China Beijing China

ISBN: (纸本)9781424432004;9780769531854

Recently there have been growing interests in the applications of wireless sensor networks such as traffic tracking, environmental surveillance, and network monitoring. In these applications, the exploration of the relationship and linkage of sensing data with other data sources can be naturally expressed by the external join, where the sensory tuples join with an external table at the base station. However, executing such kind of join queries in a highly distributed and resource-constraint sensor network is a challenging task. In this paper, we propose a partition-based algorithm called NEJA (in-network external join algorithm) for the external join processing in sensor networks. NEJA organizes the sensory data of the network through an optimized "value-to-storage" mapping, according to which each storage point stores the tuples that belong to the same subrange on the joint attribute. Then the subrange of each storage point is further partitioned into unit ranges, and tuples in the same unit range wisely choose their joining point that incurs the least communication cost based on a cost metric according to the latest historical statistics. Also, NEJA adopts some optimization techniques to handle the changes of sensory data and uses approximate approaches to cut down the maintenance cost of the mechanism. The experimental results indicate that our scheme is effective in reducing the amount of transmissions for the real time external join processing, especially when the external table has a relatively large size.

关键词： Base stations Joints Wireless sensor networks Sensors Partitioning algorithms Distributed databases Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Page Query Language Generation for Structural Extraction

Page Query Language Generation for Structural Extraction

引用

The 2014 10th International Conference on Natural Computation (ICNC 2014) and the 2014 11th International Conference on Fuzzy Systems and knowledge Discovery (FSKD 2014)(第十届自然计算和第十一届模糊系统与知识发现国际会议)

作者： He Hu Xiaoyong Du School of Information Renmin University of China Key Laboratory of Data Engineering and Knowledge EngineeringMOE BeijingChina

ISBN: (纸本)9781479951499

The information on the Web is usually fabricated to be understandable by human users rather than ***'s not easy to automatically catalogue and extract the Web information solely with a software *** on these observations,we present an approach that uses human guided operations to automatically generate a PQL query,a SQL like query language focusing on Web pages,to extract the interested information fragments on Web *** PQL query uses XPath expressions to locating the target HTML *** develop a K-Medoid clustering algorithm to process PQL queries to generate the structural *** extracted information is structured as a relational table(in CSV format)which can be manipulated smoothly with spreadsheet software or a relational DBMS system.

关键词： PQL Structural Extraction Browser Extension

来源：评论

学校读者我要写书评

暂无评论

CARDnet: A denoiser based on contrast-aware and residual-dense block 19th

CARDnet: A denoiser based on contrast-aware and residual-den...

引用

19th Chinese Intelligent Systems Conference, CISC 2023

作者： Cai, Qiang Cao, Ying Wang, Chen Li, Haisheng Ma, Mengxu School of Computer Science and Engineering Beijing Technology and Business University Beijing100048 China Beijing Key Laboratory of Big Data Technology for Food Safety Beijing100048 China National Engineering Laboratory for Agri-Product Quality Traceability Beijing100048 China

ISBN: (纸本)9789819968817

In recent years, deep convolutional neural networks have shown good performance on images with spatially invariant noise, but their performance is limited on real-world noisy images. In order to improve the practicality of denoising algorithms, this paper proposes a simple one-stage blind real image denoising network with a modular structure, which combines the local modeling capability of residual dense convolutional layers with the global modeling capability of spatial and channel attention blocks and inserts them as the main building blocks into widely used encoder–decoder architectures to achieve end-to-end denoising. To preserve image structure information as much as possible during the denoising process, this paper uses different lengths of residuals between different modules to mitigate the flow of low-frequency information, and applies Contrast-Aware channel attention to enhance the dependency relationship of channel activation. Furthermore, this paper evaluates state-of-the-art algorithms on different noise datasets using quantitative metrics and visual quality, experimental results demonstrate the superiority of the proposed algorithm. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

What's the Real: A Novel Design Philosophy for Robust AI-Synthesized Voice Detection 24

What's the Real: A Novel Design Philosophy for Robust AI-Syn...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Hai, Xuan Liu, Xin Tan, Yuan Liu, Gang Li, Song Niu, Weina Zhou, Rui Zhou, Xiaokang School of Information Science and Engineering Lanzhou University Lanzhou China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Faculty of Business Data Science Kansai University Osaka Japan

ISBN: (纸本)9798400706868

Voice is one of the most widely used media for information transmission in human society. While high-quality synthetic voices are extensively utilized in various applications, they pose significant risks to content security and trust building. Numerous studies have concentrated on AI-synthesized voice detection to mitigate these risks, with many claiming to achieve promising performance. However, recent research has demonstrated that fake voice detectors suffer from serious overfitting to speaker-irrelative features (SiFs) and cannot be used in real-world scenarios. In this paper, we analyze the limitations of existing fake voice detectors and propose a new design philosophy, guiding the detection model to prioritize learning human voice features rather than the difference between the human voice and the synthetic voice. Based on this philosophy, we propose a novel AI-synthesized voice detection framework named SiFSafer, which uses pre-trained speech representation models to enhance the learning of feature distribution in human voices and the adapter fine-tuning to optimize the performance. The evaluation shows that the average EERs of existing fake voice detectors in the ASVspoof datasets can exceed 20% if the SiFs like silence segments are removed, while SiFSafer achieves an EER of less than 8%, indicating that SiFSafer is robust to SiFs and strongly resistant to existing attacks. © 2024 ACM.

关键词： Fake detection

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：