计算机科学 ›› 2020, Vol. 47 ›› Issue (6A): 294-298.doi: 10.11896/JsJkx.190700097

• 计算机网络 • 上一篇    下一篇

一种融合EMD分解和LSTM网络的频谱占用度预测模型

赵晓东1, 苏公瑾2, 李克利2, 成杰2, 徐江峰1   

  1. 1 郑州大学信息工程学院 郑州 450001;
    2 河南无线电管理信息系统备份中心 郑州 450000
  • 发布日期:2020-07-07
  • 通讯作者: 徐江峰(Jfxu@zzu.edu.cn)
  • 作者简介:1024729633@qq.com
  • 基金资助:
    国家重点研发计划

Spectrum Occupancy Prediction Model Based on EMD Decomposition and LSTM Networks

ZHAO Xiao-dong1, SU Gong-Jin2, LI Ke-li2, CHENG Jie2 and XU Jiang-feng1   

  1. 1 School of Information Engineering,Zhengzhou University,Zhengzhou 450001,China
    2 Henan Radio Management Information System Backup Center,Zhengzhou 450000,China
  • Published:2020-07-07
  • About author:ZHAO Xiao-dong, born in 1991, master.His main research interest include big data, artificial intelligence, deep lear-ning.
    XU Jiang-feng, born in 1965, Ph.D.professor.His main research interest include big data, cryptography, database.
  • Supported by:
    This work was supported by the National Key Research and Development Program of China.

摘要: 频谱占用度是衡量频谱利用率、反应频谱分配是否合理的重要依据,但是非稳态的频谱占用度序列为有效的预测带来了巨大的挑战。文中提出了融合EMD与LSTM的计算模型(EMD-LSTM),该模型首先对原始占用度序列进行经验模态分解(EMD),令其生成含有不同时间尺度的本征模函数(IMF),然后用Pearson相关系数选择出相关度高的IMF,并将其与频谱占用度序列进行融合,最后利用长短时记忆网络(LSTM)对融合序列进行占用度预测。仿真实验结果及分析表明,相比于普通的LSTM网络,新的模型在预测频谱占用度变化上有了较大的性能改善。

关键词: 长短时记忆, 分解EMD-LSTM, 频谱占用度, 网络经验模态

Abstract: Spectrum occupancy is an important basis to measure the spectrum utilization rate and reflect whether the spectrum allocation is reasonable.However,the unsteady spectrum occupancy sequence presents great challenges for effective prediction.In this paper,a new computing model (EMD-LSTM) combining EMD and LSTM is proposed.Firstly,the empirical mode decomposition (EMD) of the original occupancy sequence is used to generate the Intrinsic Mode Function (IMF) with different time scales,and then the highly correlated IMF is selected by Pearson correlation coefficient.Then,IMF and spectrum occupancy sequence are fused,and the occupancy sequence is predicted by using the long and short time memory network (LSTM).Simulation experiments and analysis show that,compared with the ordinary LSTM network,the new model has a great improvement in predicting the change of spectrum occupancy.

Key words: EMD, EMD-LSTM, Long-term and short-term memory network, Spectrum occupancy

中图分类号: 

  • TP183
[1] LPEZ-BENITEZ M,CASADEVALL F.Discrete-Time Spectrum Occupancy Model based on Markov Chain and Duty Cycle Models//2011 IEEE Symposium on New Frontiers in Dynamic Spectrum Access Networks (DySPAN).IEEE,2011.
[2] DALTA D,WYGLINSKI A M,M INDEN G J.A spectrum surveying framework for dynamic spectrum access network.IEEE Transactions on Vehicular Technology,2009,58(8):4158-4168.
[3] HAM ID E,SITHAMPARANATHAN K,BILL M,et al.Spectrum occupancy prediction using a hidden Markov model//Signal Processing and Communication Systems.Cairns,QLD,IEEE,2015:1-8.
[4] WANG L,XIE S G,SU D L,et al.An Autonomous Detectionand Robust Estimation Method of Spectrum Anomaly Based on Time Series Analysis.Acta Electronica Sinica,2014,42(6):1055-1060.
[5] WEI H H,JIA Y F.A Method for Analysis of Non-linear and Non-stationary Spectrum Occupancy Time Series.Acta Electronica Sinica,2017,45(8):2026-2030.
[6] GERS F A,SCHMIDHUBER,JRGEN,et al.Learning to Forget:Continual Prediction with LSTM.NeuralComputation,2000,12(10):2451-2471.
[7] HOCHREITER S,SCMIDHUBER J.Long Short-Term Memroy.Neural Computation,1997,9(8):1735-1780.
[8] NG Y H,HAUSKNECHT M,VIJAYANARASIMHAN S,et al.Beyond short snippets:Deep networks for video classification//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2015.
[9] KOK I,SIMSEK M U,OZDEMIR S.A deep learning model for air quality prediction in smart cities//2017 IEEE International Conference on Big Data (Big Data).IEEE,2017.
[10] ZENG Z,LI L,CHEN J.Deeply Hierarchical Bi-directional LSTM for Sentiment Classification.Computer Science,2018,45(8):213-217,252.
[11] HUANG,NORDEN E.The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non-Stationary Time Series Analysis.Proceedings:Mathematical.Physical and Engineering Sciences,1998(454):903-995.
[12] QI Y Y,YU M.Anti-Jamming Method for Frequency Hopping Communication Based on Single Channel BSS and EMD.Computer Science,2016,43(1):149-153.
[13] MOTIN M A,KARMAKAR C,PALANISWAMI M.Selection of Empirical Mode Decomposition Techniques for Extracting Breathing Rate from PPG.IEEE Signal Processing Letters,2019:1-1.
[14] ZHENG D,CUI G,CAO J,et al.Analysis of Brain-Death EEG Data Using 2T-EMD Algorithm//International Conference on Signal-image Technology & Internet-based Systems.IEEE,2016.
[15] GONG B M,WANG W B,ZHAO P.EMD-FSVM Prediction for Nonstationary Time Series.Computer Science,2014,41(S2):57-60.
[16] ELMAN J L.Finding Structure in Time.Cognitive Science,1990,14(2):179-211.
[17] International Telecommunication Union.Spectrum occupancy measurement and evaluaton.https://www.itu.int/rec/R-REC-SM.1880/en.
[1] 金方焱, 王秀利.
融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取
Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM
计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190
[2] 王杉, 徐楚怡, 师春香, 张瑛.
基于CNN-LSTM的卫星云图云分类方法研究
Study on Cloud Classification Method of Satellite Cloud Images Based on CNN-LSTM
计算机科学, 2022, 49(6A): 675-679. https://doi.org/10.11896/jsjkx.210300177
[3] 潘志豪, 曾碧, 廖文雄, 魏鹏飞, 文松.
基于交互注意力图卷积网络的方面情感分类
Interactive Attention Graph Convolutional Networks for Aspect-based Sentiment Classification
计算机科学, 2022, 49(3): 294-300. https://doi.org/10.11896/jsjkx.210100180
[4] 丁锋, 孙晓.
基于注意力机制和BiLSTM-CRF的消极情绪意见目标抽取
Negative-emotion Opinion Target Extraction Based on Attention and BiLSTM-CRF
计算机科学, 2022, 49(2): 223-230. https://doi.org/10.11896/jsjkx.210100046
[5] 敖天宇, 刘全.
一种快速收敛的最大置信上界探索方法
Upper Confidence Bound Exploration with Fast Convergence
计算机科学, 2022, 49(1): 298-305. https://doi.org/10.11896/jsjkx.201100194
[6] 林椹尠, 张梦凯, 吴成茂, 郑兴宁.
利用生成对抗网络的人脸图像分步补全法
Face Image Inpainting with Generative Adversarial Network
计算机科学, 2021, 48(9): 174-180. https://doi.org/10.11896/jsjkx.200800014
[7] 张宁, 方靖雯, 赵雨宣.
基于LSTM混合模型的比特币价格预测
Bitcoin Price Forecast Based on Mixed LSTM Model
计算机科学, 2021, 48(11A): 39-45. https://doi.org/10.11896/jsjkx.210600124
[8] 刘晓璇, 季怡, 刘纯平.
基于LSTM神经网络的声纹识别
Voiceprint Recognition Based on LSTM Neural Network
计算机科学, 2021, 48(11A): 270-274. https://doi.org/10.11896/jsjkx.210400041
[9] 刘云,尹传环,胡迪,赵田,梁宇.
基于循环神经网络的通信卫星故障检测
Communication Satellite Fault Detection Based on Recurrent Neural Network
计算机科学, 2020, 47(2): 227-232. https://doi.org/10.11896/jsjkx.190600147
[10] 孙国梓, 吕建伟, 李华康.
基于编辑距离的多实体可信确认算法
MeTCa:Multi-entity Trusted Confirmation Algorithm Based on Edit Distance
计算机科学, 2020, 47(12): 327-331. https://doi.org/10.11896/jsjkx.191100176
[11] 王启发, 王中卿, 李寿山, 周国栋.
基于交叉注意力机制和新闻正文的评论情感分类
Comment Sentiment Classification Using Cross-attention Mechanism and News Content
计算机科学, 2020, 47(10): 222-227. https://doi.org/10.11896/jsjkx.190900173
[12] 葛娜, 孙连英, 石晓达, 赵平.
Prophet-LSTM组合模型的销售量预测研究
Research on Sales Forecast of Prophet-LSTM Combination Model
计算机科学, 2019, 46(6A): 446-451.
[13] 郑诚, 洪彤彤, 薛满意.
用于短文本分类的BLSTM_MLPCNN模型
BLSTM_MLPCNN Model for Short Text Classification
计算机科学, 2019, 46(6): 206-211. https://doi.org/10.11896/j.issn.1002-137X.2019.06.031
[14] 刘佳慧, 王昱洁, 雷艺.
基于LSTM的CSI手势识别方法
CSI Gesture Recognition Method Based on LSTM
计算机科学, 2019, 46(11A): 283-288.
[15] 高忠石, 苏旸, 柳玉东.
基于PCA-LSTM的入侵检测研究
Study on Intrusion Detection Based on PCA-LSTM
计算机科学, 2019, 46(11A): 473-476.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!