检索结果-内蒙古大学图书馆

The Equivalent Representation of the Breadth-One D-Invariant Polynomial Subspace and Its Discretization

Journal of Systems Science & Complexity 2016年第5期29卷 1436-1445页

作者： JIANG Xue ZHANG Shugong Institute of Mathematics Key Laboratory of Symbolic Computation and Knowledge Engineering (Ministry of Education) Jilin University

This paper demonstrates the equivalence of two classes of D-invariant polynomial subspaces, i.e., these two classes of subspaces are different representations of the breadth-one D-invariant subspace. Moreover, the authors solve the discrete approximation problem in ideal interpolation for the breadth-one D-invariant subspace. Namely, the authors find the points, such that the limiting space of the evaluation functionals at these points is the functional space induced by the given D-invariant subspace, as the evaluation points all coalesce at one point.

关键词： Breadth-one D-invariant polynomial subspace discrete approximation problem idealinterpolation.

来源：评论

学校读者我要写书评

暂无评论

A prediction approach based on long short-term memory networks for dynamic multiobjective optimization

引用

Expert Systems with Applications 2025年 283卷

作者： Xu, Biao Rang, Gejie Xie, Ruijie Li, Wenji Gong, Dunwei Fan, Zhun Yang, Shengxiang He, Jie College of Engineering Shantou University Shantou515063 China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou543002 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Automation and Electronic Engineering Qingdao University of Science and Technology Qingdao266100 China Shenzhen institute for Advanced Study University of Electronic Science and Technology of China Shenzhen518110 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

Dynamic multiobjective optimization problems (DMOPs) present significant challenges to conventional evolutionary optimization methods because of the continuous changes in their Pareto-optimal sets (PSs) and fronts (PFs). Prediction-driven approaches have demonstrated potential in rapidly adapting to these changes. However, many existing methods depend on linear models to forecast the evolving PSs, which may be restrictive. To counteract this limitation, this research presents a novel dynamic multiobjective evolutionary optimization algorithm that incorporates predictions from long short-term memory (LSTM) networks. Initially, in our methodology, the PS for each problem is segmented into multiple clusters, and the centroid of each cluster is identified. These cluster centroids, representing the PSs across various environmental conditions, are then transformed into a series of time series data. The LSTM network models are subsequently trained on this time series data as input samples. Utilizing these refined models, the centroids of the evolving PSs are predicted with improved precision. Moreover, to enhance the performance of the algorithm, an innovative population-generation strategy is also introduced that guarantees a well-converged and diverse starting population. Our proposed algorithm undergoes rigorous testing using benchmark functions, and the outcomes validate its proficiency in tackling DMOPs, showing superior performance compared to existing state-of-the-art algorithms. © 2025 Elsevier Ltd

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A Chinese online document clustering algorithm based on hidden sentiment vector

引用

Journal of computational Information Systems 2011年第6期7卷 1974-1981页

作者： Yang, Hui Wang, Zhe Zhou, Xu Wang, Zuo Zhou, Tong College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory for Symbol Computation and Knowledge Engineering Ministry of Education China

The core idea of clustering algorithm is the division of data into groups of similar objects. Some clustering algorithms are proven good performance on document clustering, such as k-means and UPGMA etc. However, few document clustering algorithms pay attention to the hidden sentiment which is a very important feature of the documents. This paper presents an improved k-means algorithm (HSK-Means) based on hidden sentiment vector for Chinese document clustering. Chinese dependency grammar rules are used to extract document feature and evaluate hidden sentiment. A new method for selecting initial cluster centroids based on rank mechanism of similarity is also proposed to improve accuracy of clustering algorithm. The experimental results on real online document sets illustrate that the performance of HSK-Means algorithm is better than classic document clustering algorithms. Copyright © 2011 Binary Information Press.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Speech separation in the vehicle environment based on fastICA algorithm

引用

Journal of Multimedia 2012年第1期7卷 33-40页

作者： Zhang, Jindong Qin, Guihe Liu, Ye College of computer science and technology Jilin University Changchun China Key Laboratory of Symbol Computation Knowledge Engineering of the Ministry of Education Changchun China

The speech interaction in-vehicle was mainly realized by the speech recognition. The human-machine interaction around was usually disturbed by the noise, and the speech received by the receiver was not the original pure speech, so compared to the pure environment, the accuracy of the speech recognition declined so sharply that it could not meet the demand of the practical application of human- machine interaction. So the speech recognition was required to have the strong adaptability and processing capacity to the speech with noise. In this paper, the FastICA algorithm in signal process and statistics was studied and used to separate the driver's speech in the vehicle environment, and realizes the pretreatment in recognizing driver's speech. The effectiveness of the method had been validated in actual vehicle experimental configuration. © 2012 Academy Publisher.

关键词： Speech processing

来源：评论

学校读者我要写书评

暂无评论

UAV-assisted Joint Mobile Edge Computing and Data Collection via Matching-enabled Deep Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Wang, Boxiong Kang, Hui Li, Jiahui Sun, Geng Sun, Zemin Wang, Jiacheng Niyato, Dusit College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University 639798 Singapore College of Computing and Data Science Nanyang Technological University Singapore

Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) and data collection (DC) have been popular research issues. Different from existing works that consider MEC and DC scenarios separately, this paper investigates a multi-UAV-assisted joint MEC-DC system. Specifically, we formulate a joint optimization problem to minimize the MEC latency and maximize the collected data volume. This problem can be classified as a non-convex mixed integer programming problem that exhibits long-term optimization and dynamics. Thus, we propose a deep reinforcement learning-based approach that jointly optimizes the UAV movement, user transmit power, and user association in real time to solve the problem efficiently. Specifically, we reformulate the optimization problem into an action space-reduced Markov decision process (MDP) and optimize the user association by using a two-phase matching-based association (TMA) strategy. Subsequently, we propose a soft actor-critic (SAC)-based approach that integrates the proposed TMA strategy (SAC-TMA) to solve the formulated joint optimization problem collaboratively. Simulation results demonstrate that the proposed SAC-TMA is able to coordinate the two subsystems and can effectively reduce the system latency and improve the data collection volume compared with other benchmark algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

arXiv

引用

arXiv 2025年

作者： Chen, Haipeng Wu, Sifan Wang, Zhigang Yin, Yifang Jiao, Yingying Lyu, Yingda Liu, Zhenguang College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Computer Science and Technology Zhejiang Gongshang University China A*STAR Singapore Public Computer Education and Research Center Jilin University China The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China

Video-based human pose estimation has long been a fundamental yet challenging problem in computer vision. Previous studies focus on spatio-temporal modeling through the enhancement of architecture design and optimization strategies. However, they overlook the causal relationships in the joints, leading to models that may be overly tailored and thus estimate poorly to challenging scenes. Therefore, adequate causal reasoning capability, coupled with good interpretability of model, are both indispensable and prerequisite for achieving reliable results. In this paper, we pioneer a causal perspective on pose estimation and introduce a causal-inspired multitask learning framework, consisting of two stages. In the first stage, we try to endow the model with causal spatio-temporal modeling ability by introducing two self-supervision auxiliary tasks. Specifically, these auxiliary tasks enable the network to infer challenging keypoints based on observed keypoint information, thereby imbuing causal reasoning capabilities into the model and making it robust to challenging scenes. In the second stage, we argue that not all feature tokens contribute equally to pose estimation. Prioritizing causal (keypoint-relevant) tokens is crucial to achieve reliable results, which could improve the interpretability of the model. To this end, we propose a Token Causal Importance Selection module to identify the causal tokens and non-causal tokens (e.g., background and objects). Additionally, non-causal tokens could provide potentially beneficial cues but may be redundant. We further introduce a non-causal tokens clustering module to merge the similar non-causal tokens. Extensive experiments show that our method outperforms state-of-the-art methods on three large-scale benchmark datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Recognizing the agent's goals incrementally:planning graph as a basis

引用

中国高等学校学术文摘·计算机科学 2007年第1期1卷 26-36页

作者： SUN Jigui YIN Minghao College of Computer Science Jilin UniversityChangchun 130012China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Changchun 130012China College of Computer Science Jilin UniversityChangchun 130012China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Changchun 130012China College of Computer Northeast Normal UniversityChangchun 130024China

Plan recognition,the inverse problem of plan synthesis,is important wherever a system is expected to produce a kind of cooperative or competitive *** plan recognizers,however,suffer the problem of acquisition and hand-coding a larger plan *** paper is aims to show that modern planning techniques can help build plan recognition systems without suffering such ***,we show that the planning graph,which is an important component of the classical planning system Graphplan,can be used as an implicit,dynamic planning library to represent actions,plans and *** also show that modern plan generating technology can be used to find valid plans in this *** this sense,this method can be regarded as a bridge that connects these two research *** and theoretical results also show that the method is efficient and scalable.

关键词： Graphplan plan recognition constraints automated planning

来源：评论

学校读者我要写书评

暂无评论

Dual Space Representation Learning for Skeleton-based Action Recognition

引用

IEEE Signal Processing Letters 2025年

作者： Yang, Yuheng Chen, Haipeng Liu, Zhenguang Hu, Sihao Jiao, Yingying Jilin University College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China Zhejiang University School of Cyber Science and Technology Hangzhou310007 China Georgia Institute of Technology College of Computing GA United States

Skeleton-based action recognition is crucial for machine intelligence. Current methods generally learn from 3D articulated motion sequences in the straightforward Euclidean space. Yet, the vanilla Euclidean space may not be the optimal choice for modeling the intricate correlations among human body joints. This challenge arises from the non-Euclidean nature of human anatomy, where joint correlations often vary non-linearly during movement. To address this, we propose a dual space representation learning method. Specifically, we represent the motion sequences in Hyperbolic space, leveraging its intrinsic properties to capture the non-Euclidean latent anatomy of human motions. We then incorporate the motion features from both Hyperbolic and Euclidean spaces, allowing us to precisely model the non-linear joint correlations while effectively sketching human poses. The proposed method empirically achieves state-of-the-art performance on the NTU RGB+D 60, NTURGB+D 120, and NW-UCLA datasets. © 1994-2012 IEEE.

关键词： Digital arithmetic

来源：评论

学校读者我要写书评

暂无评论

Inference and learning in hybrid probabilistic network

引用

中国高等学校学术文摘·计算机科学 2007年第4期1卷 429-435页

作者： WANG Limin WANG Xuecheng LI Xiongfei Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin UniversityChangchun 130012China The Institute of Information Spreading Engineering Changchun University of TechnologyChangchun 130012China

This paper proposed a novel hybrid probabilistic network,which is a good tradeoff between the model complexity and learnability in *** relaxes the conditional independence assumptions of Naive Bayes while still permitting efficient inference and *** studies on a set of natural domains prove its clear advantages with respect to the generalization ability.

关键词： hybrid probabilistic network conditional independence assumption Bayesian network probabilistic neural network

来源：评论

学校读者我要写书评

暂无评论

Mapping integrity constraint ontology to relational databases

引用

The Journal of China Universities of Posts and Telecommunications 2010年第6期17卷 113-121页

作者： OUYANG Dan-tong College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Jilin University Changchun 130012 China

Integrity constraint is a formula that checks whether all necessary information has been explicitly provided. It can be added into ontology to guarantee the data-centric application. In this paper,a set of constraint axioms called IC-mapping axioms are stated. Based on these axioms,a special ontology with integrity constraint,which is adapted to map ontology knowledge to data in relational databases,is defined. It＇s generated through our checking and modification. Making use of the traditional mapping approaches,it can be mapped to relational databases as a normal ontology. Unlike what in the past,a novel mapping approach named IC-based mapping is proposed in accordance with such special ontology. The detailed algorithm is put forward and compared with other existing approaches used in Semantic Web applications. The result shows that our method is advanced to the traditional approaches.

关键词： Semantic Web integrity constraint ontology relational database

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：