Research on POI quality prediction based on KPCA-GA-BP neural network

Lu LIU; Dan YANG; Ruijie CHEN; Jia LI; Xi ZHOU

doi:10.11959/j.issn.1000-0801.2023004

您当前的位置：

首页 >

文章列表页 >

Research on POI quality prediction based on KPCA-GA-BP neural network

Research and Development | 更新时间：2024-06-05

- Research on POI quality prediction based on KPCA-GA-BP neural network
- Telecommunications Science Vol. 39, Issue 1, Pages: 108-116(2023)
- 作者机构：
  
  1. 中国移动通信集团设计院有限公司重庆分公司，重庆401121
  2. 中国移动通信集团云南有限公司，云南昆明 650228
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2023004
  CLC： TN92
- Published Online：2023-01，
  
  Published：20 January 2023
- 稿件说明：
移动端阅览
Lu LIU, Dan YANG, Ruijie CHEN, et al. Research on POI quality prediction based on KPCA-GA-BP neural network[J]. Telecommunications science, 2023, 39(1): 108-116.
DOI：

Lu LIU, Dan YANG, Ruijie CHEN, et al. Research on POI quality prediction based on KPCA-GA-BP neural network[J]. Telecommunications science, 2023, 39(1): 108-116. DOI： 10.11959/j.issn.1000-0801.2023004.

摘要

目前移动网络优化一般基于小区进行网络质量评估及预测，遵循“升维研究，降维实施”的研究思路，提出了兴趣点（point of interest，POI）网络质量的柔性评价体系，但其涉及较多网络关键绩效指标（key performance indicator，KPI），导致POI网络综合质量评价体系较为庞杂且预测精度不高，为提高POI网络质量预测精准性，采用核主成分分析（kernel principal component analysis，KPCA）算法对反向传播（back propagation，BP）神经网络的输入变量进行相关性压缩，简化了BP神经网络结构，然后通过遗传算法（genetic algorithm，GA）优化了BP神经网络连接权值及阈值参数。与传统BP神经网络预测结果进行对比，在预测准确度方面提高了10.90%，均方误差性能显著降低，对研究POI网络质量的预测可起到较好的支撑作用。

Abstract

At present

in network optimization

network quality evaluation and prediction are generally based on communities

and a flexible evaluation system for POI network quality was proposed following the research idea of “research on dimensionality increase and implementation of dimensionality reduction”.However

it involves many network KPI

resulting in a relatively complex evaluation system for POI network comprehensive quality and low prediction accuracy.In order to improve the prediction accuracy of POI network quality

KPCA was used to compress the correlation of input variables of BP neural network

the structure of BP neural network was simplified

and then the connection weights and threshold parameters of BP neural network were optimized through GA.Compared with the prediction results of traditional BP neural network

the prediction accuracy is improved by 10.9%

and the mean square error performance is significantly reduced

it can play a better supporting role in the prediction of POI network quality.

关键词

Keywords

references

丁彦文 , 许捍卫 , 汪成昊 . 融合OSM路网与POI数据的城市功能区识别研究 [J ] . 地理与地理信息科学 , 2020 , 36 ( 4 ): 57 - 63 .

DING Y W , XU H W , WANG C H . Research on urban functional area recognition integrating OSM road network and POI data [J ] . Geography and Geo-Information Science , 2020 , 36 ( 4 ): 57 - 63 .

刘璐 , 陈睿杰 , 李嘉 . 基于 MDT 重叠覆盖度数据的KNN-DBSCAN 参数自适应调优研究 [J ] . 电信科学 , 2022 , 38 ( 2 ): 119 - 129 .

LIU L , CHEN R J , LI J . Research on adaptive optimization of KNN-DBSCAN parameters based on MDT overlapping coverage data [J ] . Telecommunications Science , 2022 , 38 ( 2 ): 119 - 129 .

苏灿 . 移动通信网络优化实证研究 [J ] . 电信技术 , 2019 ( S1 ): 19 - 21 .

SU C . An empirical study on mobile communication network optimization [J ] . Telecommunications Technology , 2019 ( S1 ): 19 - 21 .

刘伟涛 , 顾鸿 , 李春洪 . 基于德尔菲法的专家评估方法 [J ] . 计算机工程 , 2011 , 37 ( S1 ): 189 - 191 , 204 .

LIU W T , GU H , LI C H . Expert evaluation method based on Delphi method [J ] . Computer Engineering , 2011 , 37 ( S1 ): 189 - 191 , 204 .

彭令 , 牛瑞卿 , 赵艳南 , 等 . 基于核主成分分析和粒子群优化支持向量机的滑坡位移预测 [J ] . 武汉大学学报·信息科学版 , 2013 , 38 ( 2 ): 148 - 152 , 161 .

PENG L , NIU R Q , ZHAO Y N , et al . Prediction of landslide displacement based on KPCA and PSO-SVR [J ] . Geomatics and Information Science of Wuhan University , 2013 , 38 ( 2 ): 148 - 152 , 161 .

李新春 , 房梽斅 , 张春华 . 基于KPCA和改进GBRT的室内定位算法 [J ] . 传感技术学报 , 2019 , 32 ( 3 ): 430 - 437 .

LI X C , FANG Z X , ZHANG C H . Indoor positioning algorithm based on KPCA and improved GBRT [J ] . Chinese Journal of Sensors and Actuators , 2019 , 32 ( 3 ): 430 - 437 .

董鸽 , 闵建中 , 陈立范 , 等 . 基于 MATLAB 的中药主成分分析数学实验教学案例 [J ] . 现代商贸工业 , 2021 , 42 ( 34 ): 142 - 144 .

DONG G , MIN J Z , CHEN L F , et al . Math experiment teaching case of principal component analysis of traditional Chinese medicine based on MATLAB [J ] . Modern Business Trade Industry , 2021 , 42 ( 34 ): 142 - 144 .

冯玉芳 , 卢厚清 , 殷宏 , 等 . 基于BP神经网络的故障诊断模型研究 [J ] . 计算机工程与应用 , 2019 , 55 ( 6 ): 24 - 30 .

FENG Y F , LU H Q , YIN H , et al . Study on fault diagnosis model based on BP neural network [J ] . Computer Engineering and Applications , 2019 , 55 ( 6 ): 24 - 30 .

温廷新 , 孔祥博 . 基于 KPCA-GA-BP 的煤矿瓦斯爆炸风险模式识别 [J ] . 安全与环境学报 , 2021 , 21 ( 1 ): 19 - 26 .

WEN T X , KONG X B . Risk pattern recognition of the coal mine gas explosion based on the KPCA-GA-BP [J ] . Journal of Safety and Environment , 2021 , 21 ( 1 ): 19 - 26 .

宋超 , 宋娟 . 基于遗传算法优化和 BP 神经网络的短期天然气负荷预测 [J ] . 工业控制计算机 , 2012 , 25 ( 10 ): 82 - 84 .

SONG C , SONG J . Parameter optimazation for BP neural network with GA on short-term gas load prediction [J ] . Industrial Control Computer , 2012 , 25 ( 10 ): 82 - 84 .

庞尔军 , 于虹 , 唐贵基 , 等 . 基于遗传算法优化的BP网络变压器可靠度计算 [J ] . 机电工程 , 2013 , 30 ( 8 ): 997 - 1000 , 1028 .

PANG E J , YU H , TANG G J , et al . Reliability calculation of transformer based on GA optimized BP [J ] . Journal of Mechanical ＆ Electrical Engineering , 2013 , 30 ( 8 ): 997 - 1000 , 1028 .

Views

179

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on control strategy of bidirectional DC-DC converter based on improved genetic algorithm

Task urgency-based resource allocation algorithm in industrial Internet of things

A genetic algorithm based method of optimizing dispersion matrix for RDSM system

Virtual machine scheduling model based on Shapley value modified genetic algorithm in cloud computing

Joint optimization of dispersion matrix and 3D constellation for STSK system based on improved genetic algorithm

Related Author

ZHOU Hongxi

LIU Yang

CHEN Zhuaixia

GAO Feifan

LI Can

CHEN Can

LI Li

ZHUO Sai

Related Institution

State Grid Information & Telecommunication Co., Ltd.

School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications

Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China

Chongqing Key Laboratory of Ubiquitous Sensing and Networking

Jiaxing Vocational Technical College

⁰