基于优化BP神经网络的物理量回归方法

doi:10.11896／j.issn.1002-137X.2018.12.027

计算机科学 ›› 2018, Vol. 45 ›› Issue (12): 170-176.doi: 10.11896／j.issn.1002-137X.2018.12.027

基于优化BP神经网络的物理量回归方法

潘俊虹^1,2,3, 王宜怀^2,4, 吴薇^1,2,3

(武夷学院数学与计算机学院福建武夷山354300)¹
(苏州大学计算机科学与技术学院江苏苏州215006)²
(认知计算与智能信息处理福建省高校重点实验室福建武夷山354300)³
(软件新技术与产业化协同创新中心江苏苏州215006)⁴

收稿日期:2017-11-21 出版日期:2018-12-15 发布日期:2019-02-25
作者简介:潘俊虹(1980-),男,硕士,高级工程师,主要研究方向为嵌入式技术、物联网,E-mail:pjhtj1980@126.com(通信作者);王宜怀(1962-),男,博士,教授,主要研究方向为嵌入式系统、人工神经网络;吴薇(1978-),女,硕士,副教授,主要研究方向为嵌入式系统、计算机应用技术。
基金资助:
本文受国家自然科学基金(61672369),福建省教育厅科研基金(JAT160521),武夷学院校科研基金(XD201506)资助。

Physical Quantity Regression Method Based on Optimized BP Neural Network

PAN Jun-hong^1,2,3, WANG Yi-huai^2,4, WU Wei^1,2,3

(School of Mathematics and Computer,Wuyi University,Wuyishan,Fujian 354300,China)¹
(Department of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215006,China)²
(Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions,Wuyishan,Fujian 354300,China)³
(Collaborative Innovation Center of Novel Software Technology and Industrialization,Suzhou,Jiangsu 215006,China)⁴

Received:2017-11-21 Online:2018-12-15 Published:2019-02-25

摘要/Abstract

摘要： 在物联网实际应用系统的开发中,传统回归方法面对A/D转换物理量回归时存在表达方式不统一、非线性校正能力及动态适应性弱等问题。文中在分析A/D转换物理量回归要素的基础上,依据BP神经网络的非线性映射能力,提出了利用布谷鸟算法进行优化的BP神经网络,并利用其实现统一数学表达的A/D转换物理量回归方法。实践表明,该方法具有数学公式统一、非线性校正能力及动态适应性强等特点。该方法既适用于利用通信方式将A/D采集的数据直接送至PC机处理的物联网系统,也适用于利用PC机进行学习,将神经网络结构参数存储于MCU内的Flash中,在物联网终端直接将A/D值转为实际物理量的环境。

关键词: A/D转换, BP神经网络, 布谷鸟搜索算法, 动态校正, 物理量回归

Abstract: In the development of practical application system of Internet of Things(IoT),traditional regression methods have the problems of non-uniform expression,poor non-linear correction ability and dynamic adaptability for physical quantity regression of A/D conversion.Based on the analysis of the physical quantity regression elements of A/D conversion,and according to the non-linear mapping ability in BP artificial neural network,this paper proposed a BP neural network optimized by cuckoo search algorithm,and utilized it to realize physical quantity regression method of A/D conversion with unified mathematical expression.Practice shows that this method has the characteristics of uniform mathematical formula,strong nonlinear correction ability and dynamic adaptability.This method is not only suitable for IoT system using communication methods to send A/D acquisition data to PC directly,but also suitable for the environment in which PC is used to learn.The neural network structure parameters are stored in the Flash of MCU,and the A/D value is directly converted to the actual physical quantity at the terminal IoT.

Key words: A/D conversion, BP neural network, Cuckoo search algorithm, Dynamical correction, Physical quantity regression

中图分类号:

TP391

潘俊虹, 王宜怀, 吴薇. 基于优化BP神经网络的物理量回归方法[J]. 计算机科学, 2018, 45(12): 170-176. https://doi.org/10.11896／j.issn.1002-137X.2018.12.027

PAN Jun-hong, WANG Yi-huai, WU Wei. Physical Quantity Regression Method Based on Optimized BP Neural Network[J]. Computer Science, 2018, 45(12): 170-176. https://doi.org/10.11896／j.issn.1002-137X.2018.12.027

参考文献

[1]CAO J H,HE L X,WANG Y H.AD Conversion Technique of Online Dynamic Reviser Based on Kl25[J].Research and Exploration in Laboratory,2013,32(10):250-252.(in Chinese)
曹金华,贺黎潇,王宜怀.基于KL25的A/D转换动态在线校正技术[J].实验室研究与探索,2013,32(10):250-252.
[2]ZHANG G C,GAO Q,DU J Q,et al.Rockburst criterion based on artificial neural networks and nonlinear regression[J].Journal of Central South University (Science and Technology),2013,44(7):2977-2981.(in Chinese)
张光存,高谦,杜聚强,等.基于人工神经网络及非性回归的岩爆判据[J].中南大学学报(自然科学版),2013,44(7):2977-2981.
[3]HECHT-NIELSEN R.KOLMOGROV’s Mapping Neural Network Existence Theorem[C]∥International 1989 Joint Confe-rence on Neural Networks.1989:593-605.
[4]ITO Y.Approximate representation of a continuous function by a neural network with scaled or unscaled sigmoid units∥IJCNN-91-Seattle International Joint Conference on Neural Networks.1991:889.
[5]ORCIK L,VOZNAKM,ROZHON J,et al.Prediction of Speech Quality Based On Resilient Baclipropagation Artificial Neural Network[J].Wrieless Personal Communications,2016,96(4):1-15.
[6]PENG J W,LV W H,XING H Y,et al.Temperature compensation for humidity sensor based on improved AG-BP neural network[J].Chinese Journal of Scientific Instrument,2013,34(1):156-159.(in Chinese)
彭基伟,吕文华,行鸿彦,等.基于改进GA_BP神经网络的湿度传感器的温度补偿[J].仪器仪表学报,2013,34(1):156-159.
[7]CHEN Y H,CHANG F J.Evolutionary artificial neural net-works for hydrological systems forecasting[J].Hydrol,2009,367(1):125-137.
[8]LI Y,WU M Y,ZOU L.BP neural network for image restoration based on cuckoo algorithm[J].Journal of Computer Applications,2017,37(S1):173-175.(in Chinese)
李扬,吴敏渊,邹炼.基于布谷鸟算法的BP神经网络图像复原[J].计算机应用,2017,37(S1):173-175.
[9]YANG X S,DEB S.Cuckoo Search via Lévy flights∥Nature &Biologically Inspired Computing,2009.IEEE,2010:210-214.
[10]YANG H H,ZHANG X F,XIE P M,et al.Multiprocessor Task Scheduling Method Based on Cuckoo Search Algorithm[J].Computer Science,2015,42(1):86-89.(in Chinese)
杨辉华,张晓凤,谢谱模,等.基于布谷鸟搜索的多处理器任务调度算法[J].计算机科学,2015,42(1):86-89.
[11]NAWI N M,KHAN A,REHMAN M Z.A new back-propagation neural network optimized with cuckoo search algorithm[M]∥Computational Science and Its Applications－ICCSA2013.Springer Berlin Heidelberg,2013:413-426.
[12]VALIAN E,MOHANNA S,TAVAKOLI S.Improved cuckoo search algorithm for feedforward neural network training[J].International Journal of Artificial Intelligence & Applications,2011,2(3):36-43.
[13]WANG H S,WANG Y N,WANG Y C.Cost Estimation ofPlastic Injection Molding Parts through Integration of PSO and BP Neural Network[J].Expert Systems with Applications,2013,40(8):418-428.
[14]NURY A H,HASAN K,ALAM M J B.Comparative study of wavelet-ARIMA and wavelet－ANN models or temperature time series data in northeastern Bangladesh[J].Journal of King Saud University-Science,2017,29(1):47-61.
[15]NXP.KL25 Sub-Family Reference Manual[DB/OL].[2014-10-12].http://www.nxp.com.

相关文章 15

[1]	刘宝宝, 杨菁菁, 陶露, 王贺应. 基于DE-LSTM模型的教育统计数据预测研究 Study on Prediction of Educational Statistical Data Based on DE-LSTM Model 计算机科学, 2022, 49(6A): 261-266. https://doi.org/10.11896/jsjkx.220300120
[2]	田真真, 蒋维, 郑炳旭, 孟利民. 基于服务器集群的负载均衡优化调度算法 Load Balancing Optimization Scheduling Algorithm Based on Server Cluster 计算机科学, 2022, 49(6A): 639-644. https://doi.org/10.11896/jsjkx.210800071
[3]	徐佳楠, 张天瑞, 赵伟博, 贾泽轩. 面向供应链风险评估的改进BP小波神经网络研究 Study on Improved BP Wavelet Neural Network for Supply Chain Risk Assessment 计算机科学, 2022, 49(6A): 654-660. https://doi.org/10.11896/jsjkx.210800049
[4]	朱旭辉, 沈国娇, 夏平凡, 倪志伟. 基于螺旋进化萤火虫算法和BP神经网络的模型及其在PPP融资风险预测中的应用 Model Based on Spirally Evolution Glowworm Swarm Optimization and Back Propagation Neural Network and Its Application in PPP Financing Risk Prediction 计算机科学, 2022, 49(6A): 667-674. https://doi.org/10.11896/jsjkx.210800088
[5]	夏静, 马中, 戴新发, 胡哲琨. 基于BP神经网络的智能云效能模型 Efficiency Model of Intelligent Cloud Based on BP Neural Network 计算机科学, 2022, 49(2): 353-367. https://doi.org/10.11896/jsjkx.201100140
[6]	程铁军, 王曼. 基于变权组合的突发事件网络舆情趋势预测 Network Public Opinion Trend Prediction of Emergencies Based on Variable Weight Combination 计算机科学, 2021, 48(6A): 190-195. https://doi.org/10.11896/jsjkx.200600094
[7]	郭福民, 张华, 胡瑢华, 宋岩. 一种基于表面肌电信号的腕部肌力估计方法研究 Study on Method for Estimating Wrist Muscle Force Based on Surface EMG Signals 计算机科学, 2021, 48(6A): 317-320. https://doi.org/10.11896/jsjkx.200600021
[8]	石琳姗, 马创, 杨云, 靳敏. 基于SSC-BP神经网络的异常检测算法 Anomaly Detection Algorithm Based on SSC-BP Neural Network 计算机科学, 2021, 48(12): 357-363. https://doi.org/10.11896/jsjkx.201000086
[9]	焦东来, 王浩翔, 吕海洋, 徐轲. 基于手机传感器轨迹的路面地物检测方法 Road Surface Object Detection from Mobile Phone Based Sensor Trajectories 计算机科学, 2021, 48(11A): 283-289. https://doi.org/10.11896/jsjkx.210200145
[10]	周俊, 尹悦, 夏斌. 基于LSTM神经网络的声发射信号识别研究 Acoustic Emission Signal Recognition Based on Long Short Time Memory Neural Network 计算机科学, 2021, 48(11A): 319-326. https://doi.org/10.11896/jsjkx.210700034
[11]	曹素娥, 杨泽民. 基于聚类分析算法和优化支持向量机的无线网络流量预测 Prediction of Wireless Network Traffic Based on Clustering Analysis and Optimized Support Vector Machine 计算机科学, 2020, 47(8): 319-322. https://doi.org/10.11896/jsjkx.190800075
[12]	宋岩, 胡瑢华, 郭福民, 袁新亮, 熊睿洋. 基于sEMG的改进SVM+BP肌力预测分层算法 Improved SVM+BP Algorithm for Muscle Force Prediction Based on sEMG 计算机科学, 2020, 47(6A): 75-78. https://doi.org/10.11896/JsJkx.190900143
[13]	诸珺文. 基于改进BP神经网络的SQL注入识别 SQL InJection Recognition Based on Improved BP Neural Network 计算机科学, 2020, 47(6A): 352-359. https://doi.org/10.11896/JsJkx.191200054
[14]	周立鹏, 孟利民, 周磊, 蒋维, 董建平. 基于BP神经网络的摔倒检测算法 Fall Detection Algorithm Based on BP Neural Network 计算机科学, 2020, 47(6A): 242-246. https://doi.org/10.11896/JsJkx.191000077
[15]	陈燕文,李坤,韩焱,王燕平. 基于MFCC和常数Q变换的乐器音符识别 Musical Note Recognition of Musical Instruments Based on MFCC and Constant Q Transform 计算机科学, 2020, 47(3): 149-155. https://doi.org/10.11896/jsjkx.190100224

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于优化BP神经网络的物理量回归方法

Physical Quantity Regression Method Based on Optimized BP Neural Network

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0