[1]顾海艳,曹 林,朱 涛,等.神经网络二次集成预测算法研究[J].南京师大学报(自然科学版),2022,(02):136-141.[doi:10.3969/j.issn.1001-4616.2022.02.017]
 Gu Haiyan,Cao Lin,Zhu Tao,et al.Research on Quadratic Integration Prediction Algorithm of Neural Network[J].Journal of Nanjing Normal University(Natural Science Edition),2022,(02):136-141.[doi:10.3969/j.issn.1001-4616.2022.02.017]
点击复制

神经网络二次集成预测算法研究()
分享到:

《南京师大学报(自然科学版)》[ISSN:1001-4616/CN:32-1239/N]

卷:
期数:
2022年02期
页码:
136-141
栏目:
·计算机科学与技术·
出版日期:
2022-05-15

文章信息/Info

Title:
Research on Quadratic Integration Prediction Algorithm of Neural Network
文章编号:
1001-4616(2022)02-0136-06
作者:
顾海艳1曹 林2朱 涛1袁 明1
(1.江苏警官学院,江苏 南京 210031)(2.中国人民解放军第66072部队,北京 100144)
Author(s):
Gu Haiyan1Cao Lin2Zhu Tao1Yuan Ming1
(1.Jiangsu Police Institute,Nanjing 210031,China)(2.PLA 66072 Troops,Beijing 100144,China)
关键词:
神经网络二次集成量子粒子群算法量子免疫算法数据预测
Keywords:
two-level neural network ensemblequantum particle swarm optimization algorithmquantum immune algorithmdata forecasting
分类号:
TP18
DOI:
10.3969/j.issn.1001-4616.2022.02.017
文献标志码:
A
摘要:
针对常用预测算法不同程度地存在泛化能力不足的缺陷,提出了基于神经网络二次集成的优化算法(NNE2-QQ). 该算法在第一次集成时采用量子粒子群算法进行个体网络的选择优化,在第二次集成时采用量子免疫算法进行集成结论生成优化,并通过多次迭代自适应寻求个体和权值的最佳组合,实现神经网络二次集成模型的性能最优,最后实验验证了NNE2-QQ算法的有效性和实用性. NNE2-QQ可从海量数据中发现各种因素之间的联系及其规律,为预测判断提供支持.
Abstract:
The common prediction algorithms of data mining have the defect of insufficient generalization ability,so this paper proposes an optimization algorithm based on two-level neural network ensemble(NNE2-QQ). The first ensemble uses quantum particle swarm optimization algorithm to select individuals,the second ensemble uses quantum immune algorithm to optimize the result,and then the best ability of the ensemble model is obtained by finding the best selection and weights through multiple iterations. Finally,simulation results demonstrate the practicality and efficiency of NNE2-QQ algorithm. NNE2-QQ can find the relationship between various factors and their laws from massive data,and provide support for prediction and judgment.

参考文献/References:

[1] HANSEN L K,PETER S. Neural network ensembles[J]. Institute of Electrical and electronic Engineers transactions on pattern analysis & machine intelligence,1990,12(10):993-1001.
[2]LI H,WANG X S,DING S F. Research and development of neural network ensembles:a survey[J]. Artificial intelligence review,2018,49(4):455-479.
[3]李晓峰,刘刚,卫晋,等. 基于卷积神经网络与特征选择的医疗图像误差预测算法[J]. 湖南大学学报(自然科学版),2021,48(4):90-99.
[4]张兴挥,樊秀梅,阿喜达,等. 反向学习的灰狼算法优化及其在交通流预测中的应用[J]. 电子学报,2021,49(5):879-886.
[5]CHOI J Y,LEE B. Ensemble of deep convolution neural networks with Gabor face representations for face recognition[J]. Institute of Electrical and Electronic Engineers transactions on image processing,2020,29:3270-3281.
[6]王洁,乔艺璇,彭岩,等. 基于深度学习的美国媒体"一带一路"舆情的情感分析[J]. 计算机技术与应用,2018,44(11):102-110.
[7]LEE M,LEE J,CHANG J H. Ensemble of jointly trained deep neural network-based acoustic models for reverberant speech recognition[J]. Digital signal processing,2019,85:1-9.
[8]韩兆宇,周勇,刘兵. 基于差异性神经网络集成的命名实体识别方法[J]. 计算机工程与设计,2019,40(4):994-1000.
[9]KITAMURA G,CHUNG C Y,MOORE B E. Ankle fracture detection utilizing a convolutional neural network ensemble implemented with a small sample,De Novo Training,and Multiview Incorporation[J]. Journal of digital imaging,2019,32:672-677.
[10]朱俊,刘天羽,王致杰,等. 基于蜂群算法的选择性神经网络集成的风机齿轮箱轴承故障诊断[J]. 电机与控制应用,2017,4401:6-11.
[11]谢琪,程耕国,徐旭. 基于神经网络集成学习股票预测模型的研究[J]. 计算机工程与应用,2019,55(8):238-243.
[12]赵辉,周杰,王红君,等. 基于 CEEMDAN-PE 和 QGA-BP的短期风速预测[J]. 电子技术应用,2018,44(12):60-64.
[13]闫瑞姣,尹四清. 选择性神经网络集成的微博用户信用评估模型[J]. 计算机工程与设计,2018,39(5):1478-1483.
[14]施彦. 群体智能预测与优化[M]. 北京:国防工业出版社,2012.
[15]CHAKRABORTY M,BISWAS S K,PURKAYASTHA B. A novel ensembling method to boost performance of neural net-works[J]. Journal of experimental & theoretical artificial intelligence,2020,32(1):17-29.
[16]曹林,王之腾,陈亮,等. 基于改进量子免疫算法的神经网络集成[J]. 计算机工程与应用,2020,56(22):142-147.
[17]KURNAZ T F,KAYA Y. A novel ensemble model based on GMDH-type neural network for the prediction of CPT-based soil liquefaction[J]. Environmental earth sciences,2019,78(11):339.1-339.14
[18]RRAGAGNOLO L,SILVA R V D,GRZYBOWSKI J M V. Artificial neural network ensembles applied to the mapping of landslide susceptibility[J]. Catena,2019,184:104240.
[19]金建海,孙俊,张安通,等. 基于量子粒子群优化算法的无人艇航线规划[J]. 船舶力学,2020,24(3):352-361.

备注/Memo

备注/Memo:
基金项目:国家自然科学基金资助项目(61802155)、江苏省教改课题(2019JSJG595).
通讯作者:顾海艳,副教授,研究方向:信息安全、大数据技术和智能优化. E-mail:ghy7388@126.com
更新日期/Last Update: 1900-01-01