基于互信息F统计量特征选择技术的地基气象云图分类

计算机与现代化 ›› 2021, Vol. 0 ›› Issue (02): 18-23.

基于互信息F统计量特征选择技术的地基气象云图分类

(1.山西大学数学科学学院,山西太原030006；2.山西大学现代教育技术学院,山西太原030006)

出版日期:2021-03-01 发布日期:2021-03-01
作者简介:杨秋良(1992—),女,河北邢台人,硕士研究生,研究方向:统计机器学习,E-mail: yangqiuliang31@163.com; 王钰,副教授,硕士生导师,研究方向:统计机器学习,数据挖掘,图像处理,E-mail: wangyu@sxu.edu.cn；杨杏丽,讲师,研究方向:统计机器学习; 李济洪,教授,博士生导师,研究方向:机器学习,中文信息处理,软件质量评测。
基金资助:
山西省应用基础研究计划项目(201901D111034,201801D211002); 统计与数据科学前沿理论及应用教育部重点实验室开放研究课题(KLATASDS2007); 国家自然科学基金资助项目(61806115)

Classification of Ground-based Meteorological Cloud Images Based on Feature Selection Technique of Mutual Information F-statistics

(1. School of Mathematical Sciences, Shanxi University, Taiyuan 030006, China;
2. School of Modern Educational Technology, Shanxi University, Taiyuan 030006, China)

Online:2021-03-01 Published:2021-03-01

摘要/Abstract

摘要： 在地基气象云图的云状（云类）识别研究中，基于局部二值模式（Local Binary Pattern, LBP）描述子的特征选择技术由于它的简单性和有效性成为最通用的方法。然而，LBP特征的高维特性使得云状识别的性能和计算开销不能令人满意。为此，本文提出一种基于互信息构造的F检验统计量的LBP特征选择算法，可以实现高维LBP特征的有效降维，同时保证云状识别的准确性，极大减少了特征选择过程的计算开销。

关键词: 地基气象云图, 高维特征选择, 互信息, F统计量, 分类

Abstract: In the study of cloud type recognition of ground-based meteorological cloud images, the feature selection technology based on Local Binary Pattern (LBP) descriptors is the most common method due to its simplicity and effectiveness. However, the high-dimensional property of LBP features makes the performance and computational overhead of cloud type recognition unsatisfactory. To the end, an LBP feature selection algorithm based on F-statistics constructed by mutual information is proposed, which can achieve effective dimensionality reduction of high-dimensional LBP features, while ensuring the accuracy of cloud type recognition, greatly reducing the computational cost of feature selection process.

Key words: ground-based meteorological cloud images, feature selection of high dimensional, mutual information, F-statistics, classification

杨秋良, 王钰, 杨杏丽, 李济洪. 基于互信息F统计量特征选择技术的地基气象云图分类[J]. 计算机与现代化, 2021, 0(02): 18-23.

YANG Qiu-liang, WANG Yu, YANG Xing-li, LI Ji-hong. Classification of Ground-based Meteorological Cloud Images Based on Feature Selection Technique of Mutual Information F-statistics [J]. Computer and Modernization, 2021, 0(02): 18-23.

参考文献［26］

［1］	中国气象局检测网络司. 气象仪器和观测方法指南［M］. 第6版. 北京:北京气象出版社, 2005.
［2］	陆雅君,陈刚毅,龚克坚,等. 测云方法研究进展［J］. 气象科技, 2012,40(5):689-697.
［3］	霍娟,吕达仁,王越. 全天空云识别阈值法的数值模拟初步研究［J］. 自然科学进展, 2006,16(4):98-102.
［4］	WANG Y, SHI C Z, WANG C H, et al. Ground-based cloud classification by learning stable local binary patterns［J］. Atmospheric Research, 2018,207:74-89.
［5］	OJALA T, PIETIKAINEN M, MAENPAA T. Multi resolution gray-scale and rotation invariant texture classification with local binary patterns［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001,24(7):971-987.
［6］	TAN X Y, TRIGGS B. Enhanced local texture feature sets for face recognition under difficult lighting conditions［J］. IEEE Transactions on Image Processing, 2010,19(6):1635-1650.
［7］	GUO Z H, ZHANG L, ZHANG D. A completed modeling of local binary pattern operator for texture classification［J］. IEEE Transactions on Image Processing, 2010,19(6):1657-1663.
［8］	LIAO S, LAW M W K, CHUNG A C S. Dominant local binary patterns for texture classification［J］. IEEE Transactions on Image Processing, 2009,18(5):1107-1118.
［9］	LIU S, LI M. Deep multimodal fusion for ground-based cloud classification in weather station networks［J］. Eurasip Journal on Wireless Communications and Networking, 2018,2018(1):48.
［10］	SHI C Z, WANG C H, WANG Y, et al. Deep convolutional activations-based features for ground-based cloud classification［J］. IEEE Geoscience and Remote Sensing Letters, 2017,14(6):816-820.
［11］	WANG Z, WANG Z H, CAO X Z, et al. Comparison of cloud top heights derived from FY-2 meteorological satellites with heights derived from ground-based millimeter wavelength cloud radar［J］. Atmospheric Research, 2018,199:113-127.
［12］	DEV S, LEE Y H, WINKLERS. Color-based segmentation of sky/cloud images from ground-based cameras［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017,10(1):231-242.
［13］	SHI C Z, WANG Y, WANG C H, et al. Ground-based cloud detection using graph model built upon superpixels［J］. IEEE Geoscience and Remote Sensing Letters, 2017,14(5):719-723.
［14］	DEV S, SAVOY F M, LEEY H, et al. Rough set based color channel selection［J］. IEEE Geoscience and Remote Sensing Letters, 2017,14(1):52-56.
［15］	FAN J Q, LI R Z. Variable selection via nonconcave penalized likelihood and its oracle properties［J］. Journal of the American Statistical Association, 2001,96(456):1348-1360.
［16］	CANDES E, TAO T. The dantzig selector: Statistical estimation when p is much large than n［J］. Annals of Statistics, 2007,35(6):2313-2351.
［17］	FAN J Q, LV J C. Sure independence screening for ultra-high-dimensional feature space［J］. Journal of the Royal Statistical Society Series B, 2008,70(5):849-911.
［18］	FAN J Q. Variable screening in high-dimensional feature space［C］// ICCM. 2007,2:735-747.
［19］	FAN J Q, LV J C. A selective overview of variable selection in high dimensional feature space［J］. Statistica Sinica, 2010,20(1):101-148.
［20］	李根,邹国华,张新雨. 高维模型选择方法综述［J］. 数理统计与管理, 2012,31(4):640-658.
［21］	PENG H C, LONG F H, DING C. Feature selection based on mutual information: Criteria of max-dependency, max-relevance, and min-redundancy［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005,27(8):1226-1238.
［22］	WANG Y, WANG R B, LI J H, et al. Blocked cross-validated t-test for comparing supervised classification learning algorithms［J］. Neural Computation, 2014,26(1):208-235.
［23］	SONG Q F, LIANG F M. A split-and-merge Bayesian variable selection approach for ultrahigh dimensional regression［J］. Journal of the Royal Statistical Society Series B, 2015,77(5):947-972.
［24］	CANNINGS T I, SAMWORTH R J. Random-projection ensemble classification［J］. Journal of the Royal Statistical Society Series B, 2017,79(4):959-1035.
［25］	WANG R B, WANG Y, LI J H, et al. Block-regularized m×2 cross-validated estimator of the generalization error［J］. Neural Computation, 2017,29(2):519-554.
［26］	DEV S, LEE Y H, WINKLER S. Categorization of cloud image patches using an improved texton-based approach［C］// 2015 IEEE International Conference on Image Processing. 2015:422-426.

[1]	孟娜, 方维维, 路红英. 一种面向微控制器上环境声音分类的DNN压缩方法[J]. 计算机与现代化, 2024, 0(01): 80-86.
[2]	邱凯星, 冯广. 基于双重特征注意力的多标签图像分类模型[J]. 计算机与现代化, 2023, 0(12): 41-47.
[3]	唐诗琪, 周瑞平, 谢仕斌, 刘梦赤, 肖文, . 基于栈式降噪编码器的跨语言多标签情感分类[J]. 计算机与现代化, 2023, 0(11): 6-12.
[4]	吴甜, 刘海华, 童顺延. 基于深度反馈的卷积神经网络的图像分类[J]. 计算机与现代化, 2023, 0(09): 82-86.
[5]	马国祥, 杨凌菲, 严传波, 张志豪, 孙彬, 王晓荣. 基于深度DenseNet网络的肝包虫病超声影像诊断方法[J]. 计算机与现代化, 2023, 0(09): 100-104.
[6]	欧阳飞, 吴旭, 向东升. 基于改进YOLOX的垃圾分类检测方法[J]. 计算机与现代化, 2023, 0(08): 68-73.
[7]	李兰兰, 高建龙, 朱晓, 穆培政. 基于区域内读数段分类的插入/缺失基因组变异检测方法[J]. 计算机与现代化, 2023, 0(07): 13-19.
[8]	秦竹媛, 吴浩忠, 谭代庆, 韩爱庆, 臧昊, 王选, 唐燕. 基于多尺度ResNet融合注意力机制的麦冬细粒度识别[J]. 计算机与现代化, 2023, 0(07): 105-111.
[9]	朱剑波, 葛明锋, 董文飞. 基于改进EfficientNet的阿尔兹海默症图像分类[J]. 计算机与现代化, 2023, 0(06): 56-61.
[10]	华昕宇, 祁云嵩. 一种基于CBAM和改进通道注意力的EfficientNet的混合脑肿瘤分类方法[J]. 计算机与现代化, 2023, 0(05): 1-7.
[11]	王杰, 潘凤, 张艳莎, 谭棉, 严晓波, 王林, . 融合带权非局部模块的铝型材表面缺陷分类[J]. 计算机与现代化, 2023, 0(05): 86-92.
[12]	徐涯昕, 何泽恩, 徐绪堪. 基于CNN-BiLSTM网络的数控机床故障文本自动分类[J]. 计算机与现代化, 2023, 0(04): 7-14.
[13]	魏鑫, 何小海, 滕奇志, 卿粼波, 陈洪刚. 基于BERT-BiLSTM-Attention混合模型的事件抽取方法[J]. 计算机与现代化, 2023, 0(04): 26-31.
[14]	朱原冶, 倪建军, 唐广翼. 一种基于改进卷积神经网络的RGB-D室内场景分类方法[J]. 计算机与现代化, 2023, 0(04): 73-77.
[15]	李晓峰, 马静, 周琰. 基于增强语义模型的货品名分类算法[J]. 计算机与现代化, 2023, 0(03): 71-78.