摘要
针对传统BP算法的神经网络易陷入局部极小,收敛慢的缺点,提出遗传算法GA优化的BP神经网络对影响高校毕业生就业心理问题的各项因素进行分析的模型。该模型可以预测高校毕业生的就业心理存在哪些不足。对因素量化采用了模糊数学中的综合评判法和专家打分的方法。仿真结果表明:该系统模型有效地避免BP神经网络陷入局部最优,具有较高的准确性。预测值与实际值的误差低于4%,可以将此模型应用于对高校毕业生就业心理问题成因的预测。
Aiming at the shortcomings of traditional BP neural network,which is easy to fall into local minima and slow convergence,this paper puts forward a model of combining genetic algorithm GA and BP algorithm to analyze various factors affecting the employment psychological problems of higher vocational graduates.This model can predict what shortcomings exist in the employment psychology of higher vocational graduates.The comprehensive evaluation method and expert scoring method in fuzzy mathematics are used to quantify the factors.The simulation results show that the system model can effectively avoid the BP neural network from falling into local optimum and has high accuracy.The error between the predicted value and the actual value is less than 4%,so this model can be applied to predict the causes of employment psychological problems of higher vocational graduates.
作者
董秀英
李泽军
沐娟
张佑春
DONG Xiuying;LI Zejun;MU Juan;ZHANG Youchun(College of Intelligent Manufacturing and Automotive,Anhui Business and Technology College,Hefei 231131,China;Department of Urban Rail Transit and Information Engineering,Anhui Communications Vocational&Technology College,Hefei 230051,China)
出处
《佳木斯大学学报（自然科学版）》
CAS
2024年第11期151-154,共4页
Journal of Jiamusi University：Natural Science Edition
基金
安徽省高校自然科学研究重点项目(2023AH052662,2024AH050138)
安徽省高校科研项目社科类(2022AH052788)
安徽省职业与成人教育学会教育教学研究规划课题(AZCJ2023117,Azcj2022008,zcj2022073)
安徽省质量工程项目(2023jnds010,2022jyxm153),安徽工商职业学院自然科学研究重点项目(ZK2024A001)。
关键词
遗传算法
BP神经网络
就业心理问题
预测
genetic algorithm
BP neural network
psychological problems in employment
prediction
