基于多机器学习竞争策略的短时雷电预报

doi:10.11772/j.issn.1001-9081.2016.09.2555

计算机应用 ›› 2016, Vol. 36 ›› Issue (9): 2555-2559.DOI: 10.11772/j.issn.1001-9081.2016.09.2555

基于多机器学习竞争策略的短时雷电预报

孙丽华¹, 严军峰¹, 徐健锋^1,2

1. 南昌大学软件学院, 南昌 330047;
2. 同济大学电子与信息工程学院, 上海 201804

收稿日期:2016-04-12 修回日期:2016-05-21 出版日期:2016-09-10 发布日期:2016-09-08
通讯作者: 徐健锋
作者简介:孙丽华(1955-),女,江西南昌人,教授,主要研究方向:信息处理、人工智能、粒计算;严军峰(1987-),男,陕西宝鸡人,硕士研究生,主要研究方向:数据挖掘、机器学习;徐健锋(1973-),男,江西南昌人,副教授,博士研究生,主要研究方向:智能信息处理、数据挖掘、粒计算、机器学习。
基金资助:
国家自然科学基金资助项目（61070139，61273304）；南昌市科技支撑计划项目（nckjj2014），南昌大学研究生创新资金资助项目（cx2015097）。

Short-term lightning prediction based on multi-machine learning competitive strategy

SUN LiHua¹, YAN Junfeng¹, XU Jianfeng^1,2

1. College of software, Nanchang University, Nanchang Jiangxi 330047, China;
2. College of Electronics and Information Engineering, Tongji University, Shanghai 201804, China

Received:2016-04-12 Revised:2016-05-21 Online:2016-09-10 Published:2016-09-08
Supported by:
This work is partially supported by the National Natural Science Foundation of China(61070139, 61273304); the Science and Technology Supported Programme (nckjj2014) of Nanchang City; the Graduate Student Creative Research Funds for the Nanchang University (cx2015097).

摘要/Abstract

摘要： 传统的雷电数据预测方法往往采用单一最优机器学习算法，较少考虑气象数据的时空变化等现象。针对该现象，提出一种基于集成策略的多机器学习短时雷电预报算法。首先，对气象数据进行属性约简，降低数据维度；其次，在数据集上训练多种异构机器学习分类器，并基于预测质量筛选最优基分类器；最后，通过对最优基分类器训练权重，并结合集成策略产生最终分类器。实验表明，该方法优于传统单最优方法，其平均预测准确率提高了9.5%。

关键词: 雷电预报, 属性约简, 集成学习, 机器学习

Abstract: The traditional lightning data forecasting methods often use single optimal machine learning algorithm to forecast, not considering the spatial and temporal variations of meteorological data. For this phenomenon, an ensemble learning based multi-machine learning model was put forward. Firstly, attribute reduction was conducted for meteorological data to reduce dimension; secondly, multiple heterogeneous machine learning classifiers were trained on data set and optimal base classifier was screened based on predictive quality; finally, the final classifier was generated after weighted training for optimal base classifier by using ensemble strategy. The experimental results show that, compared with the traditional single optimal algorithm, the prediction accuracy of the proposed model is increased by 9.5% on average.

Key words: lightning forecast, attribute reduction, ensemble learning, machine learning

中图分类号:

TP181

孙丽华, 严军峰, 徐健锋. 基于多机器学习竞争策略的短时雷电预报[J]. 计算机应用, 2016, 36(9): 2555-2559.

SUN LiHua, YAN Junfeng, XU Jianfeng. Short-term lightning prediction based on multi-machine learning competitive strategy[J]. Journal of Computer Applications, 2016, 36(9): 2555-2559.

参考文献

[1] 李准,杨慧民,林春.南昌地区雷电灾害易损性分析及区划[J].气象研究与应用,2013,34(3):78-82.(LI Z, YANG H M, LIN C. Regionalization and analysis of lighting disaster vulnerability in Nanchang [J]. Journal of Meteorological Research and Application, 2013, 34(3): 78-82.)
[2] 吕振东,李玉塔,王怀清.江西省雷电时空分布特征及其区域易损性分析[J].能源研究与管理,2016(1):51-57.(LYU Z D, LI Y T, WANG H Q. Analysis of temporal and spatial distribution characteristics of lighting activity and vulnerability in Jiangxi [J]. Energy Research and Management, 2016(1): 51-57.)
[3] 靳小兵,卜俊伟,李一丁,等.四川省雷电监测预警预报系统及其应用研究[J].高原山地气象研究,2012,32(3):54-57.(JIN X B, BU J W, LI Y D, et al. The research of lightning monitoring and early warning forecast system of Sichuan province and its application [J]. Plateau and Mountain Meteorology Research, 2012, 32(3): 54-57.)
[4] 刘达新,来志云,吉平,等.能抵抗粗差的雷电定位算法研究与仿真[J].科学技术与工程,2013,13(28):8399-8403.(LIU D X, LAI Z Y, JI P, et al. Algorithms and simulation for robust lightning location [J]. Science Technology and Engineering, 2013, 13(28): 8399-8043.)
[5] 刘冲,李向军,沈华,等.基于基数排序及属性约简的雷电预报因子提取方法[J].南昌大学学报(理科版),2013,37(4):344-349.(LIU C, LI X J, SHENG H, et al. Extraction method of lightning forecast factors based on radix sort and attribute reduction [J]. Journal of Nanchang University (Natural Science), 2013, 37(4): 344-349.)
[6] 彭永供,邱桃荣,林于渊,等.基于哈夫曼树的雷电数据采样算法[J].计算机工程,2013,39(5):174-177.(PENG Y G, QIU T R, LIN Y Y, et al. Lightning data sampling algorithm based on Huffman tree [J]. Computer Engineering, 2013, 39(5): 174-177.)
[7] 滕少华,樊继慧,陈潇,等.SVM多分类器协同挖掘局域气象数据[J].广西大学学报(自然科学版),2014,39(5):1131-1137.(TENG S H, FAN J H, CHEN X, et al. Application of SVM-based multi-classifiers in miningcooperatively local area meteorological data [J]. Journal of Guanxi University (Natural Science Edition), 2014, 39(5): 1131-1137.)
[8] 周浩,刘萍,邱桃荣,等.基于粒计算的决策树并行算法的应用[J].计算机工程与设计,2015,36(6):1504-1509.(ZHOU H, LIU P, QIU T R, et al. Parallel decision tree algorithm based on granular computing [J]. Computer Engineering and Design, 2015, 36(6): 1504-1509.)
[9] VALIANT L G. A theory of the learnable [J]. Communications of the ACM, 1984, 27(11): 1134-1142.
[10] NAKAMURA M, NOMIYA H, UEHARA K. Improvement of boosting algorithm by modifying the weighting rule [J]. Annals of Mathematics and Artificial Intelligence, 2004, 41(1): 95-109.
[11] LOZANO A C, ABE N. Multi-class cost-sensitive boosting with p-norm loss functions [C]// KDD '08: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2008: 506-514.
[12] 廖红文,周德龙.AdaBoost及其改进算法综述[J].计算机系统应用,2012,21(5):240-244.(LIAO H W, ZHOU D L. Review of AdaBoost and its improvement [J]. Computer System and Applications, 2012, 21(5): 240-244.)
[13] 刘宏杰,冯博琴,李文捷,等.粗糙集属性约简判别分析方法及其应用[J].西安交通大学学报,2007,41(8):939-943.(LIU H J, FENG B Q, LI W J, et al. Discrimination method of rough set attribute reduction and its applications [J]. Journal of Xi'an JiaoTong University, 2007, 41(8): 939-943.)
[14] PAWLAK Z. Rough sets [J]. International Journal of Computer and Information Sciences, 1982, 11(5): 341-356.

[1]	郭棉, 张锦友. 移动边缘计算环境中面向机器学习的计算迁移策略[J]. 计算机应用, 2021, 41(9): 2639-2645.
[2]	毛铭泽, 曹芮浩, 闫春钢. 基于权值多样性的半监督分类算法[J]. 计算机应用, 2021, 41(9): 2473-2480.
[3]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[4]	余东昌, 赵文芳, 聂凯, 张舸. 基于LightGBM算法的能见度预测模型[J]. 计算机应用, 2021, 41(4): 1035-1041.
[5]	秦静, 左长青, 汪祖民, 季长清, 王宝凤. 基于堆叠分类器的心电异常监测模型设计[J]. 计算机应用, 2021, 41(3): 887-890.
[6]	姜倩玉, 王凤英, 贾立鹏. 基于感知哈希算法和特征融合的恶意代码检测方法[J]. 计算机应用, 2021, 41(3): 780-785.
[7]	罗长银, 陈学斌, 马春地, 王君宇. 面向区块链的在线联邦增量学习算法[J]. 计算机应用, 2021, 41(2): 363-371.
[8]	孟祥瑞, 杨文忠, 王婷. 基于图文融合的情感分析研究综述[J]. 计算机应用, 2021, 41(2): 307-317.
[9]	刘晓龙, 王士同. 渐进式分离的开放集模糊域自适应算法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3127-3131.
[10]	楼豪杰, 郑元林, 廖开阳, 雷浩, 李佳. 基于Siamese-YOLOv4的印刷品缺陷目标检测[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3206-3212.
[11]	王雅辉, 钱宇华, 刘郭庆. 基于模糊优势互补互信息的有序决策树算法[J]. 计算机应用, 2021, 41(10): 2785-2792.
[12]	蒋阳升, 王胜男, 涂家祺, 李莎, 王红军. 面向高铁站的热舒适度和能耗综合预测[J]. 计算机应用, 2021, 41(1): 249-257.
[13]	周超然, 赵建平, 马太, 周欣. 基于注意力机制和集成学习的网页黑名单判别方法[J]. 计算机应用, 2021, 41(1): 133-138.
[14]	顾桐, 许国良, 李万林, 李家浩, 王志愿, 雒江涛. 基于集成LightGBM和贝叶斯优化策略的房价智能评估模型[J]. 计算机应用, 2020, 40(9): 2762-2767.
[15]	朱琳, 于海涛, 雷新宇, 刘静, 王若凡. 基于MRI图像的阿尔茨海默症患者脑网络特征识别算法[J]. 计算机应用, 2020, 40(8): 2455-2459.

基于多机器学习竞争策略的短时雷电预报

Short-term lightning prediction based on multi-machine learning competitive strategy

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics