计算机与现代化 ›› 2022, Vol. 0 ›› Issue (06): 8-12.

• 算法设计与分析 • 上一篇    下一篇

基于PSO-KPLS的教师科研绩效预测

  

  1. (西安工程大学管理学院,陕西西安710048)
  • 出版日期:2022-06-23 发布日期:2022-06-23
  • 作者简介:黄玲(1983—),女,河南焦作人,工程师,硕士,研究方向:教育管理,跨文化交际,E-mail: jsz050401@163.com; 通信作者:白晓波(1983—),男,陕西勉县人,高级工程师,硕士,研究方向:智能信息处理,大数据分析与可视化,E-mail: baixiaobo@xpu.edu.cn。
  • 基金资助:
    国家自然科学基金资助项目(71802155); 陕西省教育厅重点研究计划项目(2020JT027); 西安工程大学哲学社会科学研究项目(2019ZXSK08)

Teachers’ Scientific Research Performance Prediction Based on PSO-KPLS 

  1. (School of Management, Xi’an Polytechnic University, Xi’an 710048, China)
  • Online:2022-06-23 Published:2022-06-23

摘要: 为了解决高校教师科研绩效难以预测的问题,首先,建立模型的优化目标,提出PSO-KPLS算法,其基本思想是:利用粒子群(Particle Swarm Optimization, PSO)算法作为寻优算法和均方根误差(RMSE)作为收敛判据,对核偏最小二乘法(Kernel-based Partial Least-Squares, KPLS)的参数进行群体寻优,以代替手动调参的寻优过程。然后,利用多维度的特征向量来表达教师的科研绩效,并利用综合法计算其科研分值。最后,以学院60个教师近6年的数据作为样本,利用PSO-KPLS训练模型并对模型进行拟合,并重点探究精度要求对PSO-KPLS运行效率的影响。通过和其他优化的KPLS算法的对比实验,结果表明:利用PSO-KPLS能够准确地预测老师在未来2~3年的科研绩效。

关键词: 科研绩效, 核偏最小二乘法, 均方根误差, 粒子群算法

Abstract: To resolve the problem that university teachers’ performance of science research is difficult to predict, firstly, the optimization target of model is built and PSO-KPLS algorithm is addressed, which base idea is that particle swarm optimization (PSO) algorithm is used as the optimization algorithm and root mean square error (RMSE) is used as the convergence criterion, which are utilized to optimize kernel based partial least squares(KPLS) . It is used to instead of finding suitable parameter by manual operation. Then, the multi-dimensional feature vector is used to express teachers’ research performance, and the comprehensive method is used to calculate their research score. Finally, taking the data of 6 years of 60 teachers as samples, the model is trained by PSO-KPLS and fitted, and the influence of accuracy requirements on the efficiency of PSO-KPLS is mainly explored. Through the comparative experiment with other optimized KPLS algorithms, the results show that PSO-KPLS can accurately predict teachers’ research performance in the next two or three years.

Key words: research performance, kernel-based partial least-squares, RMSE, particle swarm optimization