检索结果-内蒙古大学图书馆

Data Intelligence and Innovative Application (DIIA), IEEE International Conference on

作者： Yixian He Jianhui Jiang Dingjia Chen Molan Tang Biquan Chen Weiqing Chen School of System and Computer Engineering North China Electric Power University Beijing China Guangxi Academy Sciences Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning China Guangxi Zhuang Autonomous Region Communication Industry Service Co. Ltd. Nanning China Guangxi Technology and Business Vocational College Nanning China

ISBN: (数字)9798331504434

ISBN: (纸本)9798331504441

To address the problem of insufficient node feature recognition and shallow network layers in Chinese text classification, this paper proposes a Chinese text classification method called Dual Preprocessing Graph Information Aggregation Network (DPGIAN). This method solves the problem of insufficient initial feature recognition of nodes and the inability of edge weights to highlight the weight ratio between keywords through a dual preprocessing strategy of node preprocessing and edge weight preprocessing; At the same time, a deeper graph information aggregation feature extraction method was used to solve the problem of excessive feature smoothing when obtaining deep semantic features in graph structured networks, improving the accuracy of Chinese text classification. By conducting experiments on multiple Chinese text classification datasets and comparing the experimental results with multiple mainstream text classification methods on the same dataset, our method outperforms the current mainstream text classification methods on the same dataset. Multiple ablation comparison experiments were also conducted to further verify the effectiveness of our method.

关键词： Smoothing methods Accuracy Text recognition Text categorization Semantics Feature extraction Graph neural networks Data models

来源：评论

学校读者我要写书评

暂无评论

MSA-GCN:Multiscale Adaptive Graph Convolution Network for Gait Emotion Recognition

arXiv

引用

arXiv 2022年

作者： Yin, Yunfei Jing, Li Huang, Faliang Yang, Guangchao Wang, Zhuowei The School of of Computer Science and Technology Chongqing University Chongqing China Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision Nanning Normal University Nanning530001 China Faculty of Engineering and Information Technology University of Technology Sydney Australia

Gait emotion recognition plays a crucial role in the intelligent system. Most of the existing methods recognize emotions by focusing on local actions over time. However, they ignore that the effective distances of different emotions in the time domain are different, and the local actions during walking are quite similar. Thus, emotions should be represented by global states instead of indirect local actions. To address these issues, a novel MultiScale Adaptive Graph Convolution Network (MSA-GCN) is presented in this work through constructing dynamic temporal receptive fields and designing multiscale information aggregation to recognize emotions. In our model, a adaptive selective spatial-temporal graph convolution is designed to select the convolution kernel dynamically to obtain the soft spatiotemporal features of different emotions. Moreover, a Cross-Scale mapping Fusion Mechanism (CSFM) is designed to construct an adaptive adjacency matrix to enhance information interaction and reduce redundancy. Compared with previous state-of-the-art methods, the proposed method achieves the best performance on two public datasets, improving the mAP by 2%. We also conduct extensive ablations studies to show the effectiveness of different components in our methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Incremental Feature Selection for Dynamic Incomplete Data Using Sub-Tolerance Relations

SSRN

引用

SSRN 2023年

作者： Zhao, Jie Ling, Yun See-To, Wing-Kuen Eric Huang, Faliang Wang, Jiahai School of Management Guangdong University of Technology Guangzhou China Department of Computing and Decision Sciences Faculty of Business Lingnan University Hong Kong Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

Feature selection is an important problem in Rough Set and is widely used in data analysis. The extended theory of tolerance relations can effectively deal with the realistic problem of incomplete data. However, the space and time complexity of computing the positive region using TRS increases dramatically. Simultaneously, redundant features are allowed to enter the feature subset, resulting in poor classification accuracy, because the positive region-based significance measure neglects uncertain information. To overcome these drawbacks, this paper introduces a subrelation-based tolerance class (STC) approach. STC transforms the TRS positive region calculation into a two-stage certainty measurement of objects, and thus divides the entire universe into two regions of certainty and uncertainty at each stage, by decomposing the tolerance relation into two subrelations. The computational space is reduced by progressively filtering out of the regions of certainty. Using STC, a new incremental mechanism is proposed. Furthermore, we propose a new significance measure using both certain and uncertain information, which effectively reduces the number of redundant features and subsequently improves computational efficiency and classification accuracy. Experiments on real data sets and comparisons with existing algorithms have been conducted to verify the superiority of the method. © 2023, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "DSTF: A diversified spatio-temporal feature extraction model for traffic flow prediction" [Neurocomputing 621 (2025) 129280] (Neurocomputing (2025) 621, (S0925231224020514), (10.1016/***.2024.129280))

引用

Neurocomputing 2025年 638卷

作者： Wang, Xing Wang, Xiaojun Huang, Faliang Zou, Fumin Liao, Lyuchao Zeng, Ruihao Fujian Normal University College of Computer and Cyber Security China Fujian Normal University Digital Fujian Institute of Big Data Security Technology China Nanning Normal University Guangxi Key Lab of Human-machine Interaction and Intelligent Decision China Fujian University of Technology Fujian Key Laboratory of Automotive Electronic and Electrical Drive Technology China The University of Sydney School of Civil Engineering Sydney Australia

The authors regret to inform that: (1) During the resubmission stage of the revised manuscript, in compliance with reviewers' recommendations to show standard deviations in the experimental results (In Section 5. Experiment implementation), a batch replacement operation (intended to replace "+" with "±" for data formatting) inadvertently replaced the "+" symbols in the mathematical formulas and the explanatory text with "±" symbols (In Section 3. Problem statement and Section 4. Methodology). (2) In proof stage, we sincerely apologize for failing to identify this issue during the final proofreading stage. Correction statement and details: As this error may affect readers' understanding, we request a corrigendum to rectify this error. In Section 3. Problem statement and Section 4. Methodology, all instances of "±" symbols within mathematical formulas and their explanatory text should be reverted to the original "+" symbols. The authors would like to apologize for any inconvenience caused. © 2025 The Authors

关键词：

来源：评论

学校读者我要写书评

暂无评论

Touchless Gestures for Interactive Messaging: Gesture Interface for Sending Emoji 20

Touchless Gestures for Interactive Messaging: Gesture Interf...

引用

22nd International Conference on human-computer interaction with Mobile Devices and Services

作者： Vyacheslav Olshevsky Ivan Bondarets Andrii Kozyr Oleksandr Trunov Artem Shcherbina Igor Tolmachov Svitlana Alkhimova Human-Computer Interaction Lab Samsung R&D Institute Ukraine (SRK) Ukraine Samsung R&D Institute Ukraine (SRK) Ukraine

ISBN: (纸本)9781450380522

Touchless gesture interaction has been featured in some recent smartphone models. We extend the domain of application of touchless gestures in smartphones by adopting gesture recognition for sending emoji. A hand-resembling emoji can be sent in just two seconds using a touchless interface. The proposed solution allows enhancing the expressiveness of the communication by sending an image of the user's hand instead of an emoji pictogram. The usability study reveals a strong user preference towards touchless gesture input as compared to the conventional touch.

关键词： Mobile Emoji computer vision Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Consistency Approximation: Incremental Feature Selection Based on Fuzzy Rough Set Theory

SSRN

引用

SSRN 2023年

作者： Zhao, Jie Wu, Daiyang Wu, JiaXin Ye, Wenhao Huang, Faliang Wang, Jiahai See-To, Wing-Kuen Eric Department of Data Science and Business Intelligence Guangdong University of Technology Guangzhou China Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Department of Computing and Decision Sciences Faculty of Business Lingnan University Hong Kong

Fuzzy Rough Set Theory (FRST)-based feature selection has been widely used as a preprocessing step to handle dynamic and large datasets. However, large-scale or high-dimensional datasets remain intractable for FRST-based feature selection approaches due to high space complexity and unsatisfactory classification performance. To overcome these challenges, we propose a Consistency Approximation (CA)-based framework for incremental feature selection. By exploring CA, we introduce a novel significance measure and a tri-accelerator. The CA-based significance measure provides a mechanism for each sample in the universe to keep members with different class labels within its fuzzy neighbourhood as far as possible, while keeping members with the same label as close as possible. Furthermore, our tri-accelerator reduces the search space and decreases the computational space with a theoretical lower bound. The experimental results demonstrate the superiority of our proposed algorithm compared to state-of-the-art methods on efficiency and classification accuracy, especially for large-scale and high-dimensional datasets. © 2023, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Incremental Feature Selection for Dynamic Incomplete Data Using Sub-Tolerance Relation

SSRN

引用

SSRN 2023年

作者： Zhao, Jie Ling, Yun Huang, Faliang Wang, Jiahai See-To, Eric Wing kuen Department of Data Science and Business Intelligence Guangdong University of Technology Guangzhou China Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Department of Computing and Decision Sciences Faculty of Business Lingnan University Hong Kong

TRS theory is widely used for feature selection with incomplete data. However, the traditional positive region-based measure ignores uncertainty, resulting in redundant features and poor classification accuracy. In addition, the computation of the positive region incurs significant time and space costs. To address these limitations, we extend the tolerance class to a Subrelation Tolerance Class (STC) by decomposing the tolerance relation into two subrelations. STC transforms feature selection into a two-stage certainty measurement by partitioning the universe into certainty and uncertainty regions. By progressively filtering out certain regions, the computational space is reduced. Furthermore, we propose a new significance measure that incorporates both certain and uncertain information. This measure effectively reduces redundant features, resulting in improved computational efficiency and classification accuracy. Using STC and our measure, we develop an incremental feature selection algorithm for dealing with incomplete streaming data, which is validated through extensive experiments and comparisons. © 2023, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Constrained maximum weighted bipartite matching:a novel approach to radio broadcast scheduling

引用

Science China(Information Sciences) 2019年第7期62卷 156-169页

作者： Shaojiang WANG Tianyong WU Yuan YAO Dongbo BU Shaowei CAI State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of Sciences School of Computer Science and Technology University of Chinese Academy of Sciences Beijing Key Lab of Human-Computer Interaction Institute of SoftwareChinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences

Given a set of radio broadcast programs, the radio broadcast scheduling problem is to allocate a set of devices to transmit the programs to achieve the optimal sound quality. In this article, we propose a complete algorithm to solve the problem, which is based on a branch-and-bound(BnB) algorithm. We formulate the problem with a new model, called constrained maximum weighted bipartite matching(CMBM),i.e., the maximum matching problem on a weighted bipartite graph with constraints. For the reduced matching problem, we propose a novel BnB algorithm by introducing three new strategies, including the highest quality first, the least conflict first and the more edge first. We also establish an upper bound estimating function for pruning the search space of the algorithm. The experimental results show that our new algorithm can quickly find the optimal solution for the radio broadcast scheduling problem at small scales, and has higher scalability for the problems at large scales than the existing complete algorithm.

关键词： radio broadcast scheduling branch-and-bound algorithm constrained maximum weighted bipartite matching Kuhn-Munkres algorithm strategy combinations

来源：评论

学校读者我要写书评

暂无评论

Incremental Matrix Factorization for Recommender Systems

Incremental Matrix Factorization for Recommender Systems

引用

International CSI computer Conference, CSICC

作者： Ghazalak Eslami Foad Ghaderi Human Computer Interaction Lab. Tarbiat Modares University Tehran Iran

ISBN: (数字)9781728159379

ISBN: (纸本)9781728159386

With the help of recommender systems, users can find information they do not know about, but they are interested in. These systems are a specific type of intelligent systems that track each user's behavior and discover their behavioral patterns. Among different approaches for implementing recommender systems, Matrix-Factorization (MF) based methods are so popular due to their high accuracy and scalability. However, in real world applications that new ratings are continuously coming, processing the huge amount of data is a computationally expensive task. In this paper, we present a novel incremental matrix factorization method to learn only parts of the data that have been changed or added recently. This way, there is no need to train the system from the scratch. The input data to the proposed recommender system is of two types, batch data and stream data. Batch data is the rating data that is already saved in the system and relates to the activities of users in the past. Stream data is the rating data that enters the system in each time interval. The method is evaluated on two versions of popular MovieLens dataset from GroupLens research. The experimental results confirm that our method reduces the execution time significantly while keeping the prediction error intact.

关键词： data handling matrix decomposition recommender systems Recommender systems matrix decomposition data processing execution time Consumers

来源：评论

学校读者我要写书评

暂无评论

Design implications for technology-mediated audience participation in live music 14

Design implications for technology-mediated audience partici...

引用

14th Sound and Music Computing Conference, SMC 2017

作者： Hödl, Oliver Fitzpatrick, Geraldine Kayali, Fares Holland, Simon Human Computer Interaction Group Austria Open University Music Computing Lab

ISBN: (纸本)9789526037295

Mobile and sensor-based technologies have created new interaction design possibilities for technology-mediated audience participation in live music performance. However, there is little if any work in the literature that systematically identifies and characterises design issues emerging from this novel class of multi-dimensional interactive performance systems. As an early contribution towards addressing this gap in knowledge, we present the analysis of a detailed survey of technology-mediated audience participation in live music, from the perspective of two key stakeholder groups - musicians and audiences. Results from the survey of over two hundred spectators and musicians are presented, along with descriptive analysis and discussion. These results are used to identify emerging design issues, such as expressiveness, communication and appropriateness. Implications for interaction design are considered. While this study focuses on musicians and audiences, lessons are noted for diverse stakeholders, including composers, performers, interaction designers, media artists and engineers. © 2017 Oliver Hödl, Geraldine Fitzpatrick and Fares Kayali et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

关键词： Surveys

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：