Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (5): 1394-1400.DOI: 10.11772/j.issn.1001-9081.2022030437
• China Conference on Data Mining 2022 (CCDM 2022) • Previous Articles
Rui XU1, Shuang LIANG1, Hang WAN2(), Yimin WEN1, Shiming SHEN3, Jian LI1
Received:
2022-04-06
Revised:
2022-06-02
Accepted:
2022-06-15
Online:
2023-05-08
Published:
2023-05-10
Contact:
Hang WAN
About author:
LIANG Shuang, born in 1994, M. S. candidate. Her research interests include environmental forecasting, deep learning and environmental big data.Supported by:
许睿1, 梁爽1, 万航2(), 文益民1, 沈世铭3, 李建1
通讯作者:
万航
作者简介:
许睿(1977—),男,四川成都人,副教授,博士,CCF会员,主要研究方向:人工智能、深度学习与环境大数据、环境监测仪器仪表、环境遥感与地理信息系统基金资助:
CLC Number:
Rui XU, Shuang LIANG, Hang WAN, Yimin WEN, Shiming SHEN, Jian LI. Extraction of PM2.5 diffusion characteristics based on candlestick pattern matching[J]. Journal of Computer Applications, 2023, 43(5): 1394-1400.
许睿, 梁爽, 万航, 文益民, 沈世铭, 李建. 基于烛台图模式匹配的PM2.5扩散特征的提取[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1394-1400.
Add to citation manager EndNote|Ris|BibTeX
URL: http://www.joca.cn/EN/10.11772/j.issn.1001-9081.2022030437
预测方法 | 资源使用 | 复杂度 | 预测精度 |
---|---|---|---|
基于物理模型的方法 | 高 | 高 | 低 |
基于机器学习的方法 | 高 | 高 | 一般 |
基于深度学习的方法 | 一般 | 一般 | 高 |
基于组合模型的方法 | 一般 | 一般 | 更高 |
Tab. 1 Comparison of characteristics of air pollutant concentration prediction methods
预测方法 | 资源使用 | 复杂度 | 预测精度 |
---|---|---|---|
基于物理模型的方法 | 高 | 高 | 低 |
基于机器学习的方法 | 高 | 高 | 一般 |
基于深度学习的方法 | 一般 | 一般 | 高 |
基于组合模型的方法 | 一般 | 一般 | 更高 |
匹配率 | 平均预测误差 | 匹配率 | 平均预测误差 |
---|---|---|---|
0.6 | 0.19 | 0.9 | 0.23 |
0.7 | 0.18 | 1.0 | 0.25 |
0.8 | 0.17 |
Tab. 2 Prediction error when matching rate changes
匹配率 | 平均预测误差 | 匹配率 | 平均预测误差 |
---|---|---|---|
0.6 | 0.19 | 0.9 | 0.23 |
0.7 | 0.18 | 1.0 | 0.25 |
0.8 | 0.17 |
方法 | 训练数据集 | 测试数据集 |
---|---|---|
基于AlexNet的方法 | 89.9 | 85.2 |
基于SVM的方法 | 91.3 | 91.4 |
基于VGG的方法 | 93.9 | 93.2 |
本文方法 | 97.8 | 95.1 |
Tab. 3 Accuracy comparison of different methods
方法 | 训练数据集 | 测试数据集 |
---|---|---|
基于AlexNet的方法 | 89.9 | 85.2 |
基于SVM的方法 | 91.3 | 91.4 |
基于VGG的方法 | 93.9 | 93.2 |
本文方法 | 97.8 | 95.1 |
方法 | PM2.5浓度上升 | PM2.5浓度下降 | PM2.5浓度未发生改变 | ||||||
---|---|---|---|---|---|---|---|---|---|
精确率 | 召回率 | F1分数 | 精确率 | 召回率 | F1分数 | 精确率 | 召回率 | F1分数 | |
基于AlexNet的方法 | 0.632 8 | 0.653 1 | 0.648 9 | 0.623 6 | 0.658 3 | 0.643 5 | 0.694 5 | 0.611 5 | 0.619 4 |
基于SVM的方法 | 0.670 9 | 0.608 1 | 0.638 2 | 0.691 2 | 0.604 4 | 0.627 2 | 0.708 4 | 0.600 7 | 0.604 8 |
基于VGG的方法 | 0.743 9 | 0.715 0 | 0.720 4 | 0.746 2 | 0.714 8 | 0.728 9 | 0.743 7 | 0.694 9 | 0.703 1 |
本文方法 | 0.800 7 | 0.843 2 | 0.812 7 | 0.820 7 | 0.853 9 | 0.829 5 | 0.710 8 | 0.623 2 | 0.637 5 |
Tab. 4 Comparison of different methods for predicting change of PM2.5 concentration
方法 | PM2.5浓度上升 | PM2.5浓度下降 | PM2.5浓度未发生改变 | ||||||
---|---|---|---|---|---|---|---|---|---|
精确率 | 召回率 | F1分数 | 精确率 | 召回率 | F1分数 | 精确率 | 召回率 | F1分数 | |
基于AlexNet的方法 | 0.632 8 | 0.653 1 | 0.648 9 | 0.623 6 | 0.658 3 | 0.643 5 | 0.694 5 | 0.611 5 | 0.619 4 |
基于SVM的方法 | 0.670 9 | 0.608 1 | 0.638 2 | 0.691 2 | 0.604 4 | 0.627 2 | 0.708 4 | 0.600 7 | 0.604 8 |
基于VGG的方法 | 0.743 9 | 0.715 0 | 0.720 4 | 0.746 2 | 0.714 8 | 0.728 9 | 0.743 7 | 0.694 9 | 0.703 1 |
本文方法 | 0.800 7 | 0.843 2 | 0.812 7 | 0.820 7 | 0.853 9 | 0.829 5 | 0.710 8 | 0.623 2 | 0.637 5 |
1 | ZHANG Y, BOCQUET M, MALLET V, et al. Real-time air quality forecasting, part Ⅰ: history, techniques, and current status[J]. Atmospheric Environment, 2012, 60:632-655. 10.1016/j.atmosenv.2012.06.031 |
2 | 李威凌,吴怀宇,陈洋. 基于高斯模型的武汉市区PM2.5扩散问题研究[J]. 高技术通讯, 2014, 24(11):1153-1159. 10.3772/j.issn.1002-0470.2014.11.009 |
LI W L, WU H Y, CHEN Y. PM2.5 diffusion problem research based on Gaussian model in Wuhan city[J]. Chinese High Technology Letters, 2014, 24(11): 1153-1159. 10.3772/j.issn.1002-0470.2014.11.009 | |
3 | SUN Q, ZHU Y M, CHEN X M, et al. A hybrid deep learning model with multi-source data for PM2.5 concentration forecast[J]. Air Quality, Atmosphere and Health, 2021, 14(4):503-513. 10.1007/s11869-020-00954-z |
4 | TAKEUCHI K, YOKOYAMA T, WADA K, et al. Modified K-line in neck extension is a prognostic indicator of the surgical outcome at 5 years after cervical laminoplasty for cervical spondylotic myelopathy[J]. Spine, 2021, 46(19):E1031-E1041. 10.1097/brs.0000000000003982 |
5 | LI Y P, FENG Z N, FENG L. Using candlestick charts to predict adolescent stress trend on micro-blog[J]. Procedia Computer Science, 2015, 63:221-228. 10.1016/j.procs.2015.08.337 |
6 | 魏连江,胡青伟,梁伟,等. 基于K线图理论的瓦斯异常模式诊断研究[J]. 煤矿安全, 2019, 50(6):24-27, 31. 10.13347/j.cnki.mkaq.2019.06.006 |
WEI L J, HU Q W, LIANG W, et al. Research on gas abnormal mode diagnosis based on K-line theory[J]. Safety in Coal Mines, 2019, 50(6):24-27, 31. 10.13347/j.cnki.mkaq.2019.06.006 | |
7 | HU G S, HU Y X, YANG K, et al. Deep stock representation learning: from candlestick charts to investment decisions[C]// Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2018:427-433. 10.1109/icassp.2018.8462215 |
8 | CHEN J H, TSAI Y C. Encoding candlesticks as images for patterns classification using convolutional neural networks[J]. Financial Innovation, 2020, 6: No.26. 10.1186/s40854-020-00187-0 |
9 | HUNG C C, CHEN Y J. DPP: deep predictor for price movement from candlestick charts[J]. PLoS ONE, 2021, 16(6): No.e0252404. 10.1371/journal.pone.0252404 |
10 | 华南理工大学. 一种基于深度学习的K线形态图像识别方法: 201811238452.8[P]. 2019-03-29. |
South China University of Technology. A K-line morphological image recognition method based on deep learning: 201811238452.8[P]. 2019-03-29. | |
11 | ONG B T, SUGIURA K, ZETTSU K. Dynamic pre-training of deep recurrent neural networks for predicting environmental monitoring data[C]// Proceedings of the 2014 IEEE International Conference on Big Data. Piscataway: IEEE, 2014:760-765. 10.1109/bigdata.2014.7004302 |
12 | MA J, LI Z, CHENG J C P, et al. Air quality prediction at new stations using spatially transferred bidirectional long short-term memory network[J]. The Science of the Total Environment, 2020, 705: No.135771. 10.1016/j.scitotenv.2019.135771 |
13 | MAO X, SHEN T, FENG X. Prediction of hourly ground-level PM2.5 concentrations 3 days in advance using neural networks with satellite data in eastern China[J]. Atmospheric Pollution Research, 2017, 8(6):1005-1015. 10.1016/j.apr.2017.04.002 |
14 | McKENDRY I G. Evaluation of artificial neural networks for fine particulate pollution (PM10 and PM2.5) forecasting[J]. Journal of the Air and Waste Management Association, 2002, 52(9):1096-1101. 10.1080/10473289.2002.10470836 |
15 | ORTIZ-GARCÍA E G, SALCEDO-SANZ S, PÉREZ-BELLIDO Á M, et al. Prediction of hourly O3 concentrations using support vector regression algorithms[J]. Atmospheric Environment, 2010, 44(35):4481-4488. 10.1016/j.atmosenv.2010.07.024 |
16 | ZHU S P, KINNON M J, ANDRE P, et al. Health benefits in California of strengthening the fine particulate matter standards[J]. Environmental Science and Technology, 2021, 55(18): 12223-12232. 10.1021/acs.est.1c03177 |
17 | LEE H J. Advancing exposure assessment of PM2.5 using satellite remote sensing: a review[J]. Asian Journal of Atmospheric Environment, 2020, 14(4): 319-334. 10.5572/ajae.2020.14.4.319 |
18 | GARCÍA NIETO P J, COMBARRO E F, DEL COZ DÍAZ J J, et al. A SVM-based regression model to study the air quality at a local scale in Oviedo urban area (Northern Spain): a case study[J]. Applied Mathematics and Computation, 2013, 219(17): 8923-8937. 10.1016/j.amc.2013.03.018 |
19 | YU W J, LIU R, ZHOU D S, et al. An improved GRU network for human motion prediction[C]// Proceedings of the IEEE 7th International Conference on Virtual Reality. Piscataway: IEEE, 2021:427-433. 10.1109/icvr51878.2021.9483851 |
20 | GUO S T, LUO Y X, SONG Y Z. Random forests and VGG-NET: an algorithm for the ISIC 2017 Skin Lesion Classification Challenge[EB/OL]. (2017-03-15) [2022-03-15].. |
21 | HU W L, SI Y W, FONG S, et al. A formal approach to candlestick pattern classification in financial time series[J]. Applied Soft Computing, 2019, 84: No.105700. 10.1016/j.asoc.2019.105700 |
22 | ANAND R, SOWMYA V, VIJAYKRISHNAMENON, et al. Modified VGG deep learning architecture for COVID-19 classification using bio-medical images[J]. IOP Conference Series: Materials Science and Engineering, 2021, 1084: No.012001. 10.1088/1757-899x/1084/1/012001 |
23 | ASTAWA I N G A, RADHITYA M L, ARDANA I W R, et al. Face images classification using VGG-CNN[J]. Knowledge Engineering and Data Science, 2021, 4(1):49-54. 10.17977/um018v4i12021p49-54 |
24 | WANG M, LI D H, LI T. A lung image classification method: a classifier constructed by combining improved VGG16 and gradient boosting decision tree[J]. Journal of Mechanics in Medicine and Biology, 2021, 21(4): No.2150042. 10.1142/s0219519421500421 |
[1] | Haiyu YANG, Wenpu GUO, Kai KANG. Signal modulation recognition method based on convolutional long short-term deep neural network [J]. Journal of Computer Applications, 2023, 43(4): 1318-1322. |
[2] | Jinyue LIU, Huiyu LI, Xiaohui JIA, Jiarui LI. Dynamic gait recognition method based on human model constraints [J]. Journal of Computer Applications, 2023, 43(3): 972-977. |
[3] | Haifeng LI, Fan ZHANG, Minnan PIAO, Huaichao WANG, Nansha LI, Zhongcheng GUI. Automatic detection of targets under airport pavement based on channel and spatial attention [J]. Journal of Computer Applications, 2023, 43(3): 930-935. |
[4] | Ranyan NI, Yi ZHANG. Action recognition method based on video spatio-temporal features [J]. Journal of Computer Applications, 2023, 43(2): 521-528. |
[5] | Ping WANG, Nan CHEN, Lei LU. Fall detection algorithm based on scene prior and attention guidance [J]. Journal of Computer Applications, 2023, 43(2): 529-535. |
[6] | Zhijun SHEN, Lina MU, Jing GAO, Yuanhang SHI, Zhiqiang LIU. Review of fine-grained image categorization [J]. Journal of Computer Applications, 2023, 43(1): 51-60. |
[7] | Jianzhuang LIN, Wenzhong YANG, Sixiang TAN, Lexin ZHOU, Danni CHEN. Fusing filter enhancement and reverse attention network for polyp segmentation [J]. Journal of Computer Applications, 2023, 43(1): 265-272. |
[8] | Hongjun HENG, Tianbao XU. Attention sentiment analysis model based on multi-scale convolution and gating mechanism [J]. Journal of Computer Applications, 2022, 42(9): 2674-2679. |
[9] | Yuhang WANG, Yongxia ZHOU, Liangwu WU. Pooling algorithm based on Gaussian function [J]. Journal of Computer Applications, 2022, 42(9): 2800-2806. |
[10] | Yuefeng LIU, Xiaoyan ZHANG, Wei GUO, Haodong BIAN, Yingjie HE. Remaining useful life prediction method of aero-engine based on optimized hybrid model [J]. Journal of Computer Applications, 2022, 42(9): 2960-2968. |
[11] | Chengxia XU, Qing YAN, Teng LI, Kaichao MIAO. De-raining algorithm based on joint attention mechanism for single image [J]. Journal of Computer Applications, 2022, 42(8): 2578-2585. |
[12] | Xianjie ZHANG, Zhiming ZHANG. Handwritten English text recognition based on convolutional neural network and Transformer [J]. Journal of Computer Applications, 2022, 42(8): 2394-2400. |
[13] | Nanjiang CHENG, Zhenxia YU, Lin CHEN, Hezhe QIAO. Multi-source and multi-label pedestrian attribute recognition based on domain adaptation [J]. Journal of Computer Applications, 2022, 42(8): 2401-2406. |
[14] | Jiehang DENG, Wenquan GUO, Hanjie CHEN, Guosheng GU, Jingjian LIU, Yukun DU, Chao LIU, Xiaodong KANG, Jian ZHAO. Few-shot diatom detection combining multi-scale multi-head self-attention and online hard example mining [J]. Journal of Computer Applications, 2022, 42(8): 2593-2600. |
[15] | Zhenhu LYU, Xinzheng XU, Fangyan ZHANG. Lightweight attention mechanism module based on squeeze and excitation [J]. Journal of Computer Applications, 2022, 42(8): 2353-2360. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||