[1]李昌响,赵 嘉*,韩龙哲,等.多通道CNN-BiLSTM的短时温度预测[J].江西师范大学学报(自然科学版),2023,(03):325-330.[doi:10.16357/j.cnki.issn1000-5862.2023.03.13]
　LI Changxiang,ZHAO Jia*,HAN Longzhe,et al.The Short-Time Temperature Prediction for Multi-Channel CNN-BiLSTM[J].Journal of Jiangxi Normal University:Natural Science Edition,2023,(03):325-330.[doi:10.16357/j.cnki.issn1000-5862.2023.03.13]
点击复制

多通道CNN-BiLSTM的短时温度预测()
分享到：

《江西师范大学学报》（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2023年03期
页码:
325-330
栏目:
出版日期:
2023-05-25

文章信息/Info

Title:
The Short-Time Temperature Prediction for Multi-Channel CNN-BiLSTM
文章编号:
1000-5862(2023)03-0325-06
作者:
李昌响; 赵 嘉*; 韩龙哲; 樊棠怀; 李桢桢
(南昌工程学院信息工程学院,江西 南昌 330099)
Author(s):
LI Changxiang; ZHAO Jia*; HAN Longzhe; FAN Tanghuai; LI Zhenzhen
(School of Information Engineering,Nanchang Institute of Technology,Nanchang Jiangxi 330099,China)
关键词:
温度预测;  卷积神经网络;  长短期记忆网络;  多通道;  多尺度特征
Keywords:
temperature prediction;  convolutional neural network;  long short-term memory;  multi-channel;  multi-scale feature
分类号:
TP 183
DOI:
10.16357/j.cnki.issn1000-5862.2023.03.13
文献标志码:
A
摘要:
温度数据具有明显的反向、时序相关性及多尺度特征,提升温度预测精度的关键在于能否有效提取温度数据的上述特征.为提取这些特征,该文提出一种多通道卷积双向长短期记忆网络(convolutional neural network-bidirection long short-term memory,CNN-BiLSTM)的短时温度预测模型.该模型首先利用双向长短期记忆网络(BiLSTM)提取数据的反向特征、时序相关性特征; 再利用多通道且不同尺寸、不同膨胀率的卷积神经网络(CNN)提取数据的多尺度特征,组成在学习多尺度特征后的数据,将其和原始数据作为BiLSTM层的多通道输入,输出的数据经过全连接层,形成最终的预测结果.实验结果表明:多通道CNN-BiLSTM的短时温度预测模型能有效地提取数据的时序相关性、反向及多尺度特征,可有效地提升温度预测精度,是一种行之有效的短时温度预测模型.
Abstract:
Temperature data have obvious reverse,temporal correlation and multi-scale features.The key to improve the accuracy of temperature prediction is to extract the above features from temperature data effectively.In order to extract these features,a short-time temperature prediction model is propsed for Convolutional Neural Network-Bidirection Long Short-Term Memory(CNN-BiLSTM).BiLSTM is used to extract reverse feature and temporal correlation feature from data.Multi-channel CNN with different sizes and expansion rates is used to extract multi-scale feature from the data and composed the data after learning multi-scale feature.The data and the original data are used as multi-channel input of BiLSTM layer,and the output data passes through the full connection layer to form the final prediction result.The experimental results show that the short-time temperature prediction model for multi-channel CNN-BiLSTM can effectively extract the reverse,temporal correlation and multi-scale features of the data,and can effectively improve the accuracy of temperature prediction.Therefore,it is an effective short-time temperature prediction model.

参考文献/References:

[1] 王玉洁,周波涛,任玉玉,等.全球气候变化对我国气候安全影响的思考 [J].应用气象学报,2016,27(6):750-758.
[2] 钱维宏,张宗婕.南方持续低温冻雨事件预测的前期信号 [J].地球物理学报,2012,55(5):1501-1512.
[3] 钱维宏.如何提高天气预报和气候预测的技巧?[J].地球物理学报,2012,55(5):1532-1540.
[4] BABU C N,REDDY B E.Predictive data mining on ave-rage global temperature using variants of ARIMA models [EB/OL].[2021-01-16].https://ieeexplore.ieee.org/document/6215607.
[5] NASUTION T H,HARAHAP L A.Predict the percentage error of LM35 temperature sensor readings using simple linear regression analysis[EB/OL].[2021-01-16].https://ieeexplore.ieee.org/document/9230472.
[6] 程鹏宇,赵嘉,韩龙哲,等.双向多尺度LSTM的短时温度预测 [J].江西师范大学学报(自然科学版),2022,46(2):134-139.
[7] XU Ting,GONG Xin,LENG Miao.Study on prediction model of cement precalciner outlet temperature [EB/OL].[2021-01-19]. https://ieeexplore.ieee.org/document/9326782.
[8] 肖勇,郑楷洪,郑镇境,等.基于多尺度跳跃深度长短期记忆网络的短期多变量负荷预测 [J].计算机应用,2021,41(1):231-236.
[9] ELMAN J L.Finding structure in time [J].Cognitive Science,1990,14(2):179-211.
[10] WANG Hongkang,LI Li,WU Yong,et al.Recurrent neural network model for prediction of microclimate in solar greenhouse [J].IFAC-Papers on Line,2018,51(17):790-795.
[11] HOCHREITER S,SCHMIDHUB J.Long Short-Term Memory [J].Neural Computation,1997,9(8):1735-1780.
[12] KHAN M,SIDDIQUE M,SAKIB S,et al.Prediction of temperature and rainfall in bangladesh using long short-term memory recurrent neural networks [EB/OL].[2021-01-26].https://ieeexplore.ieee.org/document/9254585.
[13] ZHANG Qin,WANG Hui,DONG Junyu,et al.Prediction of sea surface temperature using long short-term memory[J].IEEE Geoscience and Remote Sensing Letters,2017,14(10):1745-1749.
[14] MILAD A,ADWAN I,MAJEED S A,et al.Emerging technologies of deep learning models development for pavement temperature prediction [J].IEEE Access,2012,9(1):23840-23849.
[15] HAN Xiao,ZHANG Chunhong,JI Yang,et al.A dilated recurrent neural network-based model for graph embedding[J].IEEE Access,2019,7:32085-32092.
[16] CHEN Junbin,HUANG Ruyi,ZHAO Kun,et al.Multiscale convolutional neural network with feature alignment for bearing fault diagnosis [J].IEEE Transactions on Instrumentation and Measurement,2021,70:1-10.
[17] YAN Lecun,BOTTOU L,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[18] 王坤,殷明明,俞鸿飞,等.低资源维汉神经机器翻译研究 [J].江西师范大学学报(自然科学版),2019,43(6):638-642.
[19] 董永峰,孙跃华,高立超,等.基于改进一维卷积和双向长短期记忆神经网络的故障诊断方法 [J].计算机应用,2022,42(4):1207-1215.
[20] 赖金水,万中英,曾雪强.基于情感轮和多任务卷积神经网络的图像情感分布学习 [J].江西师范大学学报(自然科学版),2022,46(4):363-371.
[21] SUNNY M A I,MASWOOD M M S,ALHARBI A G.Deep learning-based stock price prediction using LSTM and bi-directional LSTM model[C]//NILES 2020 Committee. The 2nd Novel Intelligent and Leading Emerging Sciences Conference.Giza:IEEE Publishing,2020:87-92.
[22] LILLICRAP T P,SANTORO A.Backpropagation through time and the brain [J].Current Opinion in Neurobiology,2019,55:82-89.
[23] 王永志,刘博,李钰.一种基于LSTM神经网络的电力负荷预测方法 [J].实验室研究与探索,2020,39(5):41-45.
[24] CHEN Xiaohan,ZHANG Baike,GAO Dong.Bearing fault diagnosis base on multi-scale CNN and LSTM model [J].Journal of Intelligent Manufacturing,2021,32(4):971-987.
[25] JIN Ning,WU Jianxian,MA Xiang,et al.Multi-task learning model based on multi-scale CNN and LSTM for sentiment classification [J].IEEE Access,2020,8:77060-77072.

相似文献/References:

[1]翟煜锦,李培芸,项青宇,等.基于QE的机器翻译重排序方法研究[J].江西师范大学学报(自然科学版),2020,(01):46.[doi:10.16357/j.cnki.issn1000-5862.2020.01.08]
　ZHAI Yujin,LI Peiyun,XIANG Qingyu,et al.The Study on the Method of Machine Translation Reordering Based on QE[J].Journal of Jiangxi Normal University:Natural Science Edition,2020,(03):46.[doi:10.16357/j.cnki.issn1000-5862.2020.01.08]

备注/Memo

备注/Memo:
收稿日期:2022-12-10
基金项目:国家自然科学基金(62069014,61962036)和江西省重点研发计划课题(20192BBE50076,20203BBGL73225)资助项目.
通信作者:赵 嘉(1981—),男,安徽桐城人,教授,博士,主要从事大数据分析、人工智能理论和深度学习的研究.E-mail:zhaojia925@163.com
更新日期/Last Update: 2023-05-25