[1]高全力,高岭,石美红,等.多特征的核线性判别分析推荐方法[J].东南大学学报(自然科学版),2019,49(5):883-889.[doi:10.3969/j.issn.1001-0505.2019.05.010]
 Gao Quanli,Gao Ling,Shi Meihong,et al.Recommendation method based on multi-feature linear discriminant analysis of kernels[J].Journal of Southeast University (Natural Science Edition),2019,49(5):883-889.[doi:10.3969/j.issn.1001-0505.2019.05.010]
点击复制

多特征的核线性判别分析推荐方法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
49
期数:
2019年第5期
页码:
883-889
栏目:
计算机科学与工程
出版日期:
2019-09-20

文章信息/Info

Title:
Recommendation method based on multi-feature linear discriminant analysis of kernels
作者:
高全力1高岭1石美红1朱欣娟1陈锐2赵雪青1
1西安工程大学计算机科学学院, 西安 710048; 2西北大学信息科学与技术学院, 西安 710127
Author(s):
Gao Quanli1 Gao Ling1 Shi Meihong1 Zhu Xinjuan1 Chen Rui2 Zhao Xueqing1
1School of Computer Science, Xi’an Polytechnic University, Xi’an 710048, China
2School of Information Science and Technology, Northwest University, Xi’an 710127, China
关键词:
核函数 线性判别分析 多特征融合 特征偏好 推荐方法
Keywords:
kernel function linear discriminant analysis multi-feature fusion feature preference recommendation method
分类号:
TP391.9
DOI:
10.3969/j.issn.1001-0505.2019.05.010
摘要:
为提高在非线性可分数据上的推荐质量,采用基于核函数的多特征线性判别分析建立推荐模型.基于多维特征数据,采用非线性映射转换到高维特征空间,通过构建基于核的映射函数,将特征映像转换为内积空间的特征子集,最终建立基于核函数的多特征线性判别分析的分类准则,对于用户喜好的物品进行分类判别并生成推荐.实验结果表明:在20%、40%、60%、80%的数据作为训练集,其余为测试集的实验条件下,随着推荐列表长度R的增加,推荐准确率呈现先升后降的趋势,在25≤R≤35区间内,能够取得最优的平均绝对误差0.34.所提方法与现有方法相比准确率平均提升18.01%,多样性平均提升42.29%,而所用时间开销仅增加6.21%.对历史偏好数据进行特征映射,有助于提高推荐准确率与多样性.
Abstract:
To improve the quality of recommendation on non-linear separable data, a recommendation model based on multi-feature linear discriminant analysis of kernels is established. The nonlinear mapping is used to convert to high-dimensional feature space based on the multi-dimensional feature data. By constructing a kernel-based mapping function, the feature maping is transformed into a feature subset of the inner product space. Finally, a classification criterion of multi-feature linear discriminant analysis based on the kernel function is established. The user’s preference items are separated and a recommendation structure is generated. Experimental results show that under the experimental conditions of 20%, 40%, 60%, and 80% data as training set and the rest as test set, with the increase of the recommendation list length R, the accuracy of recommendation increases first and then decreases. The optimal mean absolute deviation value of 0.34 can be obtained in the range of 25≤R≤35. Compared with the existing methods, the accuracy and the diversity of the proposed method increase by 18.01% and 42.29%, on average, and the time cost increases by only 6.21%. The feature mapping of historical preference data is helpful to improve the accuracy and the diversity of recommendation.

参考文献/References:

[1] Tarus J K, Niu Z D, Mustafa G. Knowledge-based recommendation: A review of ontology-based recommender systems for e-learning[J]. Artificial Intelligence Review, 2018, 50(1): 21-48. DOI:10.1007/s10462-017-9539-5.
[2] 高全力,高岭,杨建锋,等.上下文感知推荐系统中基于用户认知行为的偏好获取方法[J].计算机学报,2015,38(9):1767-1776. DOI:10.11897/SP.J.1016.2015.01767.
Gao Q L, Gao L, Yang J F, et al. A preference elicitation method based on users’ cognitive behavior for context-aware recommender system[J]. Chinese Journal of Computers, 2015, 38(9): 1767-1776. DOI:10.11897/SP.J.1016.2015.01767. (in Chinese)
[3] 吴慧,卞艺杰,赵喆,等.基于信任的协同过滤算法[J].计算机系统应用,2014,23(7):131-135. DOI:10.3969/j.issn.1003-3254.2014.07.025.
Wu H, Bian Y J, Zhao Z, et al. Collaborative filtering algorithm based on trust[J]. Computer Systems & Applications, 2014, 23(7): 131-135. DOI:10.3969/j.issn.1003-3254.2014.07.025. (in Chinese)
[4] Wiranto P, Winarko E, Hartati S, et al. Improving the prediction accuracy of multicriteria collaborative filtering by combination algorithms[J]. International Journal of Advanced Computer Science and Applications, 2014, 5(4): 51-58. DOI:10.14569/IJACSA.2014.050409.
[5] Bahramian Z, Ali Abbaspour R, Claramunt C. A context-aware tourism recommender system based on a spreading activation method[J]. ISPRS—International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017, XLII-4/W4: 333-339. DOI:10.5194/isprs-archives-xlii-4-w4-333-2017.
[6] Colombo-Mendoza L O, Valencia-García R, Rodríguez-González A, et al. RecomMetz: A context-aware knowledge-based mobile recommender system for movie showtimes[J]. Expert Systems With Applications, 2015, 42(3): 1202-1222. DOI:10.1016/j.eswa.2014.09.016.
[7] Inzunza S, Juárez-Ramírez R, Ramírez-Noriega A. User and context information in context-aware recommender systems: A systematic literature review[C]//World Conference on Information Systems and Technologies(World CIST). Recife, Brazil, 2016, 444: 649-658. DOI:10.1007/978-3-319-31232-3_61.
[8] Bibbins-Domingo K, Grossman D C, Curry S J, et al. Screening for colorectal cancer: US preventive services task force recommendation statement[J]. JAMA—Journal of the American Medical Association, 2016, 315(23): 2564-2575. DOI: 10.1001/jama.2016.5989.
[9] Zheng L, Zhu F X, Huang S, et al. Context neighbor recommender: Integrating contexts via neighbors for recommendations[J]. Information Sciences, 2017, 414: 1-18. DOI:10.1016/j.ins.2017.05.034.
[10] Sermanet P, Lynch C, Hsu J, et al. Time-contrastive networks: Self-supervised learning from multi-view observation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops(CVPRW). Honolulu, HI, USA, 2017: 486-487. DOI:10.1109/cvprw.2017.69.
[11] Larrosa J M, Garcia-Martin E, Bambo M P, et al. Potential new diagnostic tool for Alzheimer’s disease using a linear discriminant function for Fourier domain optical coherence tomography[J]. Investigative Ophthalmology & Visual Science, 2014, 55(5): 3043-3051. DOI:10.1167/iovs.13-13629.
[12] Jiang L L, Luo M F, Zhang Y, et al. Identification of transmission fluid based on NIR spectroscopy by combining sparse representation method with manifold learning[J]. Spectroscopy and Spectral Analysis, 2014, 34(1): 64-68. DOI:10.3964/j.issn.1000-0593(2014)01-0064-05.
[13] 赵志华,陈莉.融合Fisher线性判别分析的多维特征融合情景感知推荐方法[J].西安交通大学学报,2017,51(8):40-46. DOI:10.7652/xjtuxb201708007.
Zhao Z H, Chen L. A context-aware recommendation method with multi-feature fusion based on Fisher linear discriminant analysis[J]. Journal of Xian Jiaotong University, 2017, 51(8): 40-46. DOI:10.7652/xjtuxb201708007. (in Chinese)

相似文献/References:

[1]张昕然,查诚,徐新洲,等.基于LDA+kernel-KNNFLC的语音情感识别方法[J].东南大学学报(自然科学版),2015,45(1):5.[doi:10.3969/j.issn.1001-0505.2015.01.002]
 Zhang Xinran,Zha Cheng,Xu Xinzhou,et al.Speech emotion recognition based on LDA+kernel-KNNFLC[J].Journal of Southeast University (Natural Science Edition),2015,45(5):5.[doi:10.3969/j.issn.1001-0505.2015.01.002]

备注/Memo

备注/Memo:
收稿日期: 2019-03-19.
作者简介: 高全力(1988—),男,博士,讲师,gaoquanli@nwu.edu.cn.
基金项目: 国家重点研发计划资助项目(2018YFB1004501)、国家自然科学基金资助项目(61672426)、陕西省教育厅科学研究计划资助项目(18JX006).
引用本文: 高全力,高岭,石美红,等.多特征的核线性判别分析推荐方法[J].东南大学学报(自然科学版),2019,49(5):883-889. DOI:10.3969/j.issn.1001-0505.2019.05.010.
更新日期/Last Update: 2019-09-20