基于注意力模型的多模态特征融合雷达知识推荐
作者:
中图分类号:

TP520.20

基金项目:

国防基础科研资助项目(A1120131044)。


A multi-modal feature fusion radar knowledge recommendation method based on attention mode
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [14]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    为了能够在数量庞大的雷达技术资料中快速准确地找到科研人员感兴趣的雷达知识信息并进行推荐,提出了一种基于注意力模型的多模态特征融合雷达知识推荐方法,学习高层次的雷达知识的多模态融合特征表示,进而实现雷达知识推荐。该方法主要包括数据预处理、多模态特征提取、多模态特征融合和雷达知识推荐4个阶段。实验结果表明:与只利用单一模态特征以及简单串联多模态特征的方法相比,利用文中方法学习到的多模态融合特征进行雷达知识推荐,推荐结果的准确率、召回率和综合评价指标(F1值)均有显著提高,表明提出的基于注意力模型的多模态特征融合方法对于知识推荐任务更加有效,体现了算法的优越性。

    Abstract:

    In order to quickly and accurately find the radar knowledge and information that researchers are interested in and make recommendations from a large number of radar knowledge data, this paper proposes a multi-modal feature fusion radar knowledge recommendation method based on attention model, which can learn high-level fusion feature representation from multiple modalities for the radar knowledge. Then the radar knowledge recommendation can be performed using the learned fusion feature. The proposed method consists of four stages, i.e., data preprocessing, multi-modal feature extraction, multi-modal feature fusion, and radar knowledge recommendation. Extensive experiments demonstrate that, compared to the existing methods using only single-modal features and simple concatenation of multi-modal features, the multi-modal fusion features learned by the proposed method achieves significant improvement in precision, recall, and F1 value for radar knowledge recommendation, suggesting its effectiveness for radar knowledge recommendation.

    参考文献
    [1] Lahat D, Adlt T, Jutten C. Multimodal data fusion:An overview of methods, challenges, and prospects[J]. Proceedings of the IEEE, 2015, 103(9):1449-1447.
    [2] 赵磊. 基于深度学习的多模态数据特征提取与选择方法研究[D]. 天津:天津大学, 2016. Zhao L. Feature extraction and selection from multi-modality data based on deep learning[D]. Tianjin:Tianjin University, 2016. (in Chinese)
    [3] 奠雨洁, 金琴, 吴慧敏. 基于多文本特征融合的中文微博的立场检测[J]. 计算机工程与应用, 2017, 53(21):77-84. Dian Y J, Jin Q, Wu H M. Stance detection in Chinese microblogs via fusing multiple text features[J]. Computer Engineering and Applications, 2017, 53(21):77-84. (in Chinese)
    [4] 陈毅, 符磊, 代云霞, 等. 基于特征融合的中文简历解析方法研究[J]. 计算机工程与应用, 2019, 55(10):244-249. Chen Y, Fu L, Dai Y X, et al. Research of Chinese resume analysis based on feature fusion[J]. Computer Engineering and Applications, 2019, 55(10):244-249. (in Chinese)
    [5] Yuan Y, Sun Q. Multiset canonical correlations using globality preserving projections with applications to feature extraction and recognition[J]. IEEE Transactions on Neural Networks and Learning Systems, 2014, 25(6):1131-1146.
    [6] Feng C, Khan M, Rahman A U, et al. News recommendation systems-accomplishments, challenges & future directions[J]. IEEE Access, 2020, 8(1):16702-16725.
    [7] 艾楚涵, 姜迪, 吴建德. 基于主题模型和文本相似度计算的专利推荐研究[J]. 信息技术, 2020, 44(4):65-70.Ai C H, Jiang D, Wu J D. Patent recommendation research based on topic model and text similarity calculation[J]. Information Technology, 2020, 44(4):65-70. (in Chinese)
    [8] 吴磊, 岳峰, 王含茹, 等.一种融合科研人员标签的学术论文推荐方法[J]. 计算机科学, 2020, 47(2):51-57.Wu L, Yue F, Wang H R, et al. Academic paper recommendation method combined with research tag[J]. Computer Science, 2020, 47(2):51-57. (in Chinese)
    [9] Shao H, Sun D, Wu J, et al. Paper2repo:github repository recommendation for academic papers[C]. Proceedings of The Web Conference 2020. 2020:629-639.
    [10] Li S, Brusilovsky P, Su S, et al. Conference paper recommendation for academic conferences[J]. IEEE Access, 2018, 6:17153-17164.
    [11] Ji Z, Lin Z, Wang H, et al. Multi-modal memory enhancement attention network for image-text matching[J]. IEEE Access, 2020, 8:38438-39447.
    [12] 黄露,周恩国,李岱峰. 融合特定任务信息注意力机制的文本表示学习模型[J/OL]. 数据分析与知识发现:1-23[2020-06-10].http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2020.0204. Huang L, Zhou E G, Li D F. Fusion of task-specific information based attention mechanism for text representation learning model[J/OL]. Data Analysis and Knowledge Discovery:1-23[2020-06-10].http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2020.0204. (in Chinese)
    [13] 王娜, 何晓明, 刘志强, 等.一种基于用户播放行为序列的个性化视频推荐策略[J].计算机学报, 2020, 43(1):123-135. Wang N, Huang X M, Liu Z Q, et al. Personalized video recommendation strategy bases on user's playback behavior sequence[J]. Chinese Journal of Computer, 2020, 43(1):123-135.(in Chinese)
    [14] 春妮, 冯朝胜. 结合句法特征和卷积神经网络的多意图识别模型[J]. 计算机应用, 2018, 38(7):1839-1845, 1852. Chun N, Feng C S. Multi-intention recognition model with combination of syntactic feature and convolution neural network[J]. Journal of Computer Applications, 2018, 38(7):1839-1845, 1852. (in Chinese)
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

李稳安,陈柳柳,陈实.基于注意力模型的多模态特征融合雷达知识推荐[J].重庆大学学报,2021,44(7):34-42.

复制
分享
文章指标
  • 点击次数:583
  • 下载次数: 861
  • HTML阅读次数: 870
  • 引用次数: 0
历史
  • 收稿日期:2020-06-14
  • 在线发布日期: 2021-07-28
文章二维码