深度置信网络优化模型在人才评价中的应用

doi:10.19678/j.issn.1000-3428.0053625

计算机工程 ›› 2020, Vol. 46 ›› Issue (2): 80-87,102. doi: 10.19678/j.issn.1000-3428.0053625

深度置信网络优化模型在人才评价中的应用

李娜娜^1,2, 胡坚剑¹, 顾军华^1,2, 张亚娟¹

1. 河北工业大学人工智能与数据科学学院, 天津 300401;
2. 河北省大数据计算重点实验室, 天津 300401

收稿日期:2019-01-09 修回日期:2019-03-18 发布日期:2020-02-12
作者简介:李娜娜(1980-),女,副教授,主研方向为数据挖掘;胡坚剑,硕士研究生;顾军华,教授、博士生导师;张亚娟(通信作者),实验师。
基金资助:
河北省人力资源和社会保障课题（JRSHZ-2019-02014）。

Application of Optimized Deep Belief Network Model in Talent Evaluation

LI Nana^1,2, HU Jianjian¹, GU Junhua^1,2, ZHANG Yajuan¹

1. School of Artificial Intelligence and Data Science, Hebei University of Technology, Tianjin 300401, China;
2. Key Laboratory of Big Data Computation of Hebei Province, Tianjin 300401, China

Received:2019-01-09 Revised:2019-03-18 Published:2020-02-12

摘要/Abstract

摘要： 针对深度置信网络（DBN）权值随机初始化容易使网络陷入局部最优的问题，引入改进的和声搜索（IHS）算法，提出基于IHS的DBN模型（IHS-DBN）。在和声搜索算法的基础上，利用全局自适应的和声音调调整方式，提升算法收敛速度和后期局部搜索能力。将DBN重构误差函数作为IHS算法的优化目标函数，通过不断迭代优化解向量为DBN寻找一组较优的初始权值进行网络训练，并在MNIST数据集上验证IHS-DBN模型的有效性。IHS-DBN模型在高校人才评价中的应用结果表明，与DBN、SVM和BP神经网络评价模型相比，IHS-DBN模型的评价准确率分别提高3.6%、7.3%和16.4%。

关键词: 深度置信网络, 随机初始化, 和声搜索算法, 音调调整, 人才评价

Abstract: Traditional Deep Belief Networks(DBN) are often limited within local optimum due to the random initialization of weights.To address the problem,this paper introduces an improved Improved Harmony Search(IHS) algorithm into traditional DBN to construct an IHS-based DBN model,called IHS-DBN.Firstly,to improve the convergence speed and local search ability of the Harmony Search(HS) algorithm,the globally adaptive method of adjusting harmony tone is used.Secondly,the reconstruction error function of DBN is taken as the optimization objective function of the IHS algorithm.Then the solution vector is iteratively optimized to find a set of more optimal initial weights for DBN training.The proposed model is tested on the MNIST dataset for talent evaluation in colleges to verify its effectiveness.Results show that the accuracy of the HIS-DBN model is improved by 3.6%,7.3% and 16.4% respectively compared with DBN,SVM and BP neural network evaluation models.

Key words: Deep Belief Network(DBN), random initialization, Harmony Search(HS) algorithm, tone adjustment, talent evaluation

中图分类号:

TP393

李娜娜, 胡坚剑, 顾军华, 张亚娟. 深度置信网络优化模型在人才评价中的应用[J]. 计算机工程, 2020, 46(2): 80-87,102.

LI Nana, HU Jianjian, GU Junhua, ZHANG Yajuan. Application of Optimized Deep Belief Network Model in Talent Evaluation[J]. Computer Engineering, 2020, 46(2): 80-87,102.

http://www.ecice06.com/CN/Y2020/V46/I2/80

图/表 11

20200218141554

20200218141722

20200218141725

20200218141729

20200218141733

20200218141736

20200218141740

20200218141743

20200218141746

20200218141750

20200218141753

参考文献

[1] LIU Y.Research on application of fuzzy mathematics in performance evaluation of human resource management[J].Journal of Advanced Oxidation Technologies,2018,21(2):42-51.
[2] CUI Y.Study on innovative capability evaluation of knowledge-innovation talents based on AHP:a case study on henan province[C]//Proceedings of International Conference on Business Computing and Global Informatization.Washington D.C.,USA:IEEE Press,2012:562-564.
[3] CHEN Suchao,XUE Ye.Research on the evaluation of high-level innovative scientific talents based on the method of fuzzy neural network[J].Journal of Taiyuan University of Technology,2014,45(3):420-424.(in Chinese) 陈苏超,薛晔.基于模糊神经网络的高层次创新型科技人才的评价[J].太原理工大学学报,2014,45(3):420-424.
[4] HU Hua,YE Jing,CHAI Chunlai.A talent classification method based on SVM[C]//Proceedings of 2009 International Symposium on Intelligent Ubiquitous Computing and Education.Washington D.C.,USA:IEEE Press,2009:160-163.
[5] YANG Chunde,ZHANG Lei.Image classification algorithm based on adaptive deep belief network[J].Computer Engineering and Design,2015,36(10):2832-2837.(in Chinese) 杨春德,张磊.基于自适应深度置信网络的图像分类方法[J].计算机工程与设计,2015,36(10):2832-2837.
[6] HU Zhen,FU Kun,ZHANG Changshui.Audio classical composer identification by deep neural network[J].Computer Research and Development,2014,51(9):1945-1954.(in Chinese) 胡振,傅昆,张长水.基于深度学习的作曲家分类问题[J].计算机研究与发展,2014,51(9):1945-1954.
[7] DENG Lei,FU Shanshan,ZHANG Ruxia.Application of deep belief network in polarimetric SAR image classification[J].Journal of Image and Graphics,2016,21(7):933-941.(in Chinese) 邓磊,付姗姗,张儒侠.深度置信网络在极化SAR图像分类中的应用[J].中国图象图形学报,2016,21(7):933-941.
[8] SHEN Furao,CHAO Jing,ZHAO Jinxi.Forecasting exchange rate using deep belief networks and conjugate gradient method[J].Neurocomputing,2015,167:243-253.
[9] MA Meng,SUN Chuang,CHEN Xuefeng.Discriminative deep belief networks with ant colony optimization for health status assessment of machine[J].IEEE Transactions on Instrumentation and Measurement,2017,66(12):3115-3125.
[10] QIAO Junfei,WANG Gongming,LI Xiaoli,et al.Design and application of deep belief network with adaptive learning rate[J].Acta Automatica Sinica,2017,43(8):1339-1349.(in Chinese) 乔俊飞,王功明,李晓理,等.基于自适应学习率的深度信念网设计与应用[J].自动化学报,2017,43(8):1339-1349.
[11] HINTON G E.A practical guide to training restricted Boltzmann machines[J].Momentum,2012,9(1):599-619.
[12] WANG S,LIU Y,ZHANG X.A differentiated DBN model based on CRBM for time series forecasting technology[C]//Proceedings of ICCT'17.Washington D.C.,USA:IEEE Press,2017:1926-1931.
[13] GENG Zhiqiang,ZHANG Yikang.An improved deep belief network inspired by glia chains[J].Acta Automatica Sinica,2016,42(6):943-952.(in Chinese) 耿志强,张怡康.一种基于胶质细胞链的改进深度信念网络模型[J].自动化学报,2016,42(6):943-952.
[14] SHAO Haidong,JIANG Hongkai,ZHANG Xun,et al.Rolling bearing fault diagnosis using an optimization deep belief network[J].Measurement Science and Technology,2015,26(11):1-5.
[15] HINTON G E,OSINDERO S,TEH Y W.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18(7):1527-1554.
[16] ZHENG J,FU X,ZHANG G.Research on exchange rate forecasting based on deep belief network[J].Neural Computing and Applications,2017,10(8):1-10.
[17] GEEM Z W,KIM J H,LOGANATHAN G V.A new heuristic optimization algorithm:harmony search[J].Simulation,2001,76(2):60-68.
[18] ZHANG Jie,ZHANG Ping.A study on harmony search algo-rithm and applications[C]//Proceedings of 2018 Chinese Control And Decision Conference.Washington D.C.,USA:IEEE Press,2018:736-739.
[19] HU Pianpian,ZENG Biqing.Cognitive radio spectrum prediction technology based on HS-BP neural network[J].Computer Engineering,2017,43(7):146-150,155.(in Chinese) 胡翩翩,曾碧卿.基于HS-BP神经网络的认知无线电频谱预测技术[J].计算机工程,2017,43(7):146-150,155.
[20] JI T,YANG Y,FU M,et al.Optimum design of reactive powder concrete mixture proportion based on artificial neural and harmony search algorithm[J].ACI Materials Journal,2017,114(1):41-47.
[21] YU Hongtao,ZHU Shangzhen,LEI Yanhua.Improvement and application of harmony search algorithm[C]//Proceedings of the 10th International Conference on Computer Science and Education.Washington D.C.,USA:IEEE Press,2015:967-970.

选择文件类型/文献管理软件名称

选择包含的内容

深度置信网络优化模型在人才评价中的应用

Application of Optimized Deep Belief Network Model in Talent Evaluation

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	舒斐, 陈涛, 王斌, 杨慧婷, 李明轩. 一种基于DBN-RF的电网工控系统异常识别方法[J]. 计算机工程, 2020, 46(11): 35-41.
[2]	钱青,唐桂忠,张广明,邓歆,尹海培. 基于AR-DBN的建筑分项能耗短期预测[J]. 计算机工程, 2019, 45(6): 290-296.
[3]	窦方正,孙汉昌,孙显,刁文辉,付琨. 基于DBN与对象融合的遥感图像变化检测方法[J]. 计算机工程, 2018, 44(4): 294-298,304.
[4]	袁凤强,王晓晨,王中元,陈丹,姜林. 基于音调调整的AVS-P10带宽扩展优化方案[J]. 计算机工程, 2018, 44(10): 286-291.
[5]	郑晓飞,郭创,姚斌,冯华鑫. 基于深度学习的航空传感器故障诊断方法[J]. 计算机工程, 2017, 43(7): 281-287.
[6]	胡翩翩,曾碧卿. 基于HS-BP神经网络的认知无线电频谱预测技术[J]. 计算机工程, 2017, 43(7): 146-150,155.
[7]	许庆勇,江顺亮,黄伟,李菁,徐少平,叶发茂. 基于多特征融合的深度置信网络图像分类算法[J]. 计算机工程, 2015, 41(11): 245-252.
[8]	路世昌，袁铎宁，杨晓陶. 基于IHSA_LSSVM的供应链绩效评估研究[J]. 计算机工程, 2014, 40(6): 291-294.
[9]	尹玉萍,刘万军,魏林. 基于和声蚁群耦合算法的风电机组齿轮箱故障诊断[J]. 计算机工程, 2014, 40(12): 172-176,181.
[10]	乔英, 高岳林, 江巧永. 改进的多目标和声搜索算法[J]. 计算机工程, 2012, 38(18): 144-146.
[11]	李宁, 贺毅朝, 田海燕. 混合编码和声搜索算法在动态优化中的应用[J]. 计算机工程, 2012, 38(12): 149-151.
[12]	何宗耀, 郝伟. 求解函数优化问题的反向自适应和声搜索算法[J]. 计算机工程, 2012, 38(10): 157-160.
[13]	韩红燕, 潘全科. 求解批量流水线调度问题的改进和声搜索算法[J]. 计算机工程, 2011, 37(6): 178-180.
[14]	李超燕?, 赖红辉, 周建良. 基于极大熵和声搜索算法的非线性方程组求解[J]. 计算机工程, 2011, 37(20): 189-190.
[15]	代军;李国;徐晨;陶艾. 一种新的粒子群优化算法[J]. 计算机工程, 2010, 36(9): 192-194.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

深度置信网络优化模型在人才评价中的应用

Application of Optimized Deep Belief Network Model in Talent Evaluation

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献

相关文章 15

编辑推荐

Metrics

本文评价