计算机科学 ›› 2019, Vol. 46 ›› Issue (9): 195-200.doi: 10.11896/j.issn.1002-137X.2019.09.028
吴振宇, 李云雷, 吴凡
WU Zhen-yu, LI Yun-lei, WU Fan
摘要: 传统的机器学习方法所使用的数据大多是基于向量空间的。支持向量机(Support Vector Machine,SVM)作为一种重要的机器学习方法,在解决小样本、非线性、高维数据等问题时具有较好的性能。但在实际应用中,图像和视频等数据都是用张量形式表示的,如果将这些张量数据直接转换成向量数据,往往会丢失一些原有的结构和相关性信息,有可能造成维度灾难和小样本问题。为了设法保持尽量多的张量结构信息,提出了一种采用Tucker分解的支持张量机(Support Tensor Machine,STM)算法。实验表明,该方法可以明显提高分类器性能;同时,支持张量机作为监督学习方式,存在无法利用未标记数据的缺点,往往受限于训练数据不足的情况。因此,将半监督学习方法与支持张量机相结合,进而提出了基于Tucker分解的半监督支持张量机算法(Semi-Supervised STM,S3TM)。该算法既可以保持较多的张量结构信息,又能充分利用未标记数据。实验表明,采用该算法的预测准确率达到90.26%,从而验证了所提算法的有效性。
中图分类号:
[1]GUO X,HUANG X,ZHANG L,et al.Support Tensor Machines for Classification of Hyperspectral Remote Sensing Imagery[J].IEEE Transactions on Geoscience & Remote Sen-sing,2016,54(6):3248-3264. [2]ZHANG J,HAN Y,JIANG J.Tucker decomposition-based ten-sor learning for human action recognition[J].Multimedia Systems,2016,22(3):343-353. [3]RAJWADE A,RANGARAJAN A,BANERJEE A.Image De-noising Using the Higher Order Singular Value Decomposition[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2013,35(4):849-862. [4]BISWAS S K,MILANFAR P.Linear Support Tensor Machine with LSK Channels: Pedestrian Detection in Thermal Infrared Images[J].IEEE Transactions on Image Processing,2017,26(9):4229-4242. [5]CAI D,HE X F,WEN J R,et al.Support Tensor Machines for Text Categorization[J].International Journal of Academic Research in Business & Social Sciences,2006,2(12):2222-6990. [6]LUO L,XIE Y,ZHANG Z,et al.Support matrix machines[C]//International Conference on International Conference on Machine Learning.JMLR.org,2015:938-947. [7]TAO D,LI X,HU W,et al.Supervised Tensor Learning[C]//IEEE International Conference on Data Mining.IEEE,2005. [8]KOTSIA I,PATRAS I.Support tucker machines[C]//The24th IEEE Conference on Computer Vision and Pattern Recognition(CVPR 2011).Colorado Springs,CO,USA,IEEE,2011. [9]HAO Z,HE L,CHEN B,et al.A Linear Support Higher-Order Tensor Machine for Classification[J].IEEE Transactions on Image Processing,2013,22(7):2911-2920. [10]CHEN Y,LU L,ZHONG P.One-class support higher ordertensor machine classifier[J].Applied Intelligence,2017,47(7):1-9. [11]CHEN Z,BATSELIER K,SUYKENS J A K,et al.Parallelized Tensor Train Learning of Polynomial Classifiers[J].IEEE Transactions on Neural Networks & Learning Systems,2016,PP(99):1-12. [12]SHU T.Research on Regression Problem and ClassificationProblem Algorithm with Input Tensor Data[D].Urumqi :Xinjiang University,2017.(in Chinese)舒托.输入为张量的回归问题和分类问题算法研究[D].乌鲁木齐:新疆大学,2017. [13]YU J,LIU G S.Text Classification Research Based on Support Tensor[J].Information Technology,2016(9):10-13.(in Chinese)俞炯,刘功申.基于支持张量机的文本分类研究[J].信息技术,2016(9):10-13. [14]LIU J W,LIU Y,LUO X L.Semi-supervised learning algorithm[J].Chinese Journal of Computers,2015,38(8):1592-1617.(in Chinese)刘建伟,刘媛,罗雄麟.半监督学习方法[J].计算机学报,2015,38(8):1592-1617. [15]CHEN Y H.Research on Semi-supervised learning classification algorithm[D].Zhenjiang:Jiangsu University,2017.(in Chinese)陈英豪.半监督学习分类算法的研究[D].镇江:江苏大学,2017. [16]WIDMANN N,VERBERNE S.Graph-based Semi-supervisedLearning for Text Classification[C]//Acm Sigir International Conference on Theory of Information Retrieval.ACM,2017. [17]HADY M F A,SCHWENKER F.Semi-supervised Learning[J].Intelligent Systems Reference Library,2013,49(2):215-239. [18]XU C,TAO W.Combining Active Learning and Semi-Super-vised Learning by Using Selective Label Spreading [C]//IEEE International Conference on Data Mining Workshops.IEEE,2017. [19]TUCKER L R.Extension of factor analysis to three-dimensional matrices[M]// Contributions to Mathematical Psychology.New York:Helt Rinehart & Winston,1964. [20]TUCKER L R.Some mathematical notes on three-mode factor analysis[J].Psychometrika,1966,31(3):279-311. [21]YANG B.Research and Application of Machine Learning Method Based on Tensor Data[D].Beijing:China Agricultural University,2014.(in Chinese)杨兵.基于张量数据的机器学习方法研究与应用[D].北京: 中国农业大学,2014. [22]ERFANI S M,BAKTASHMOTLAGH M,RAJASEGARAR S,et al.R1STM:One-class Support Tensor Machine with Randomised Kernel[C]//SIAM International Conference on Data Mining.Philadelphia:Society for Industrial and Applied Mathematics Conference,2016. |
[1] | 武红鑫, 韩萌, 陈志强, 张喜龙, 李慕航. 监督和半监督学习下的多标签分类综述 Survey of Multi-label Classification Based on Supervised and Semi-supervised Learning 计算机科学, 2022, 49(8): 12-25. https://doi.org/10.11896/jsjkx.210700111 |
[2] | 侯夏晔, 陈海燕, 张兵, 袁立罡, 贾亦真. 一种基于支持向量机的主动度量学习算法 Active Metric Learning Based on Support Vector Machines 计算机科学, 2022, 49(6A): 113-118. https://doi.org/10.11896/jsjkx.210500034 |
[3] | 庞兴龙, 朱国胜. 基于半监督学习的网络流量分析研究 Survey of Network Traffic Analysis Based on Semi Supervised Learning 计算机科学, 2022, 49(6A): 544-554. https://doi.org/10.11896/jsjkx.210600131 |
[4] | 王宇飞, 陈文. 基于DECORATE集成学习与置信度评估的Tri-training算法 Tri-training Algorithm Based on DECORATE Ensemble Learning and Credibility Assessment 计算机科学, 2022, 49(6): 127-133. https://doi.org/10.11896/jsjkx.211100043 |
[5] | 许华杰, 陈育, 杨洋, 秦远卓. 基于混合样本自动数据增强技术的半监督学习方法 Semi-supervised Learning Method Based on Automated Mixed Sample Data Augmentation Techniques 计算机科学, 2022, 49(3): 288-293. https://doi.org/10.11896/jsjkx.210100156 |
[6] | 杨洋, 邸一得, 刘俊晖, 易超, 周维. 基于张量分解的排序学习在个性化标签推荐中的研究 Study on Learning to Rank Based on Tensor Decomposition in Personalized Tag Recommendation 计算机科学, 2020, 47(11A): 515-519. https://doi.org/10.11896/jsjkx.191100181 |
[7] | 秦悦, 丁世飞. 半监督聚类综述 Survey of Semi-supervised Clustering 计算机科学, 2019, 46(9): 15-21. https://doi.org/10.11896/j.issn.1002-137X.2019.09.002 |
[8] | 沈鸿, 刘军发, 陈益强, 蒋鑫龙, 黄正宇. 基于多模融合的半监督场景识别方法 Semi-supervised Scene Recognition Method Based on Multi-mode Fusion 计算机科学, 2019, 46(12): 306-312. https://doi.org/10.11896/jsjkx.191200500C |
[9] | 喻影, 陈珂, 寿黎但, 陈刚, 吴晓凡. 基于关键词和关键句抽取的用户评论情感分析 Sentiment Analysis of User Comments Based on Extraction of Key Words and Key Sentences 计算机科学, 2019, 46(10): 19-26. https://doi.org/10.11896/jsjkx.191000531C |
[10] | 刘枭, 王晓国. 基于概率图的银行电信诈骗检测方法 Probabilistic Graphical Model Based Approach for Bank Telecommunication Fraud Detection 计算机科学, 2018, 45(7): 122-128. https://doi.org/10.11896/j.issn.1002-137X.2018.07.020 |
[11] | 蔡毅,朱秀芳,孙章丽,陈阿娇. 半监督集成学习综述 Semi-supervised and Ensemble Learning:A Review 计算机科学, 2017, 44(Z6): 7-13. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.002 |
[12] | 成英超,王瑞胡,胡章平. 一种基于高斯混合模型的协同过滤算法 Novel Approach on Collaborative Filtering Based on Gaussian Mixture Model 计算机科学, 2017, 44(Z6): 451-454. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.101 |
[13] | 李锋,万小强. 基于关联矩阵的短信自动分类 SMS Automatic Classification Based on Relational Matrix 计算机科学, 2017, 44(Z6): 428-432. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.096 |
[14] | 张维,苗夺谦,高灿,李峰. 一种处理部分标记数据的粗糙集属性约简算法 Rough Set Attribute Reduction Algorithm for Partially Labeled Data 计算机科学, 2017, 44(1): 25-31. https://doi.org/10.11896/j.issn.1002-137X.2017.01.005 |
[15] | 朱常宝,程勇,高强. 基于半监督深度信念网络的图像分类算法研究 Research on Image Classification Algorithm Based on Semi-supervised Deep Belief Network 计算机科学, 2016, 43(Z6): 46-50. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.010 |
|