无线网络信号传输建模：一种区间二型模糊集成深度学习方法

doi:10.11959/j.issn.2096-6652.202043

智能科学与技术学报 ›› 2020, Vol. 2 ›› Issue (4): 401-411.doi: 10.11959/j.issn.2096-6652.202043

• 专刊：深度强化学习 • 上一篇

无线网络信号传输建模：一种区间二型模糊集成深度学习方法

赵亮, 谢志峰, 张坤鹏, 郑玉卿, 付园坤

河南工业大学电气工程学院，河南郑州 450001

修回日期:2020-11-30 出版日期:2020-12-15 发布日期:2020-12-01
作者简介:赵亮（1978- ），男，博士，河南工业大学电气工程学院副教授，主要研究方向为智能通信、智慧医疗、平行学习等。
谢志峰（1996- ），男，河南工业大学电气工程学院硕士生，主要研究方向为深度学习、智能通信等。
张坤鹏（1987- ），男，博士，河南工业大学电气工程学院讲师，主要研究方向为智能交通、智能通信等。
郑玉卿（1987- ），男，博士，河南工业大学电气工程学院讲师，主要研究方向为智能通信、智能控制。
付园坤（1995- ），男，河南工业大学电气工程学院硕士生，主要研究方向为智慧医疗、智能通信等。
基金资助:
国家自然科学基金资助项目(61105079);国家自然科学基金资助项目(61473114);国家自然科学基金资助项目(62002101);河南省自然科学基金资助项目(162300410059);河南工业大学省属高校基本科研业务费专项资金资助项目(2018RCJH16);河南工业大学高层次人才科研基金资助项目(2019BS044)

Modeling signal propagation in wireless network:an interval type-2 fuzzy ensemble deep learning approach

Liang ZHAO, Zhifeng XIE, Kunpeng ZHANG, Yuqing ZHENG, Yuankun FU

College of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, China

Revised:2020-11-30 Online:2020-12-15 Published:2020-12-01
Supported by:
The National Natural Science Foundation of China(61105079);The National Natural Science Foundation of China(61473114);The National Natural Science Foundation of China(62002101);The Natural Science Foundation of Henan Province of China(162300410059);Fundamental Research Funds for the Henan Provincial Col-leges and Universities in Henan University of Technology(2018RCJH16);High-level Talent Research Fund of Henan University of Technology(2019BS044)

摘要/Abstract

摘要：

针对常用的信号传输模型存在使用场景单一、预测精度不佳的问题，提出一种适用于多场景的数据驱动无线信号传输模型。首先根据先验知识从预处理后的数据构造初始特征，接着进行特征选择，以得到输入特征集合。然后分析建模需求，选择深度置信网络（DBN）、残差网络（ResNet）和堆叠自编码器（SAE）作为区间二型模糊规则的后件（个体深度学习器），经过区间二型模糊推理进行集成。最后采用5G网络信号传输实测数据，并进行实验验证。结果表明，3种个体深度学习器在测试集上的表现均优于Cost231-Hata模型和反向传播神经网络（BPNN）模型，其中ResNet的准确度高于DBN和SAE模型。区间二型模糊集成深度学习模型的性能与其个体深度学习器的性能以及模糊规则数目呈正相关，同时异质集成在测试集上的表现优于同质集成。

关键词: 信号传输模型, 特征工程, 区间二型模糊推理, 集成学习, 深度学习

Abstract:

There exist some problems in the commonly used signal propagation models, such as single usage scenario and poor prediction accuracy.A data-driven wireless signal propagation model suitable for multiple scenarios was proposed.Firstly, the initial features were constructed from the preprocessed data according to the prior knowledge, and then the input feature set was obtained by using feature selection technique.Then analyzing the modeling requirements, selecting the deep belief network (DBN), residual network (ResNet) and stacked auto encoder (SAE) as the consequents (individual learners) of the interval type-2 fuzzy rules, and leveraged interval type-2 fuzzy inference to ensemble them.Finally, the actual measurement data of 5G signal propagation was applied for experimental verification.The results demonstrate that the performance of the three individual learners for the test set is better than those of the Cost231-Hata and back propagation neural network (BPNN), as well as the accuracy of ResNet is higher than those of DBN and SAE.Moreover, the performance of the interval type-2 fuzzy ensemble deep learning model is positively correlated with those of its individual learners and the number of fuzzy rules.Meanwhile, the heterogeneous ensemble is superior to the homogeneous counterpart for the test set.

Key words: signal propagation model, feature engineering, interval type-2 fuzzy inference, ensemble learning, deep learning

中图分类号:

TP391

赵亮, 谢志峰, 张坤鹏, 等. 无线网络信号传输建模：一种区间二型模糊集成深度学习方法[J]. 智能科学与技术学报, 2020, 2(4): 401-411.

Liang ZHAO, Zhifeng XIE, Kunpeng ZHANG, et al. Modeling signal propagation in wireless network:an interval type-2 fuzzy ensemble deep learning approach[J]. Chinese Journal of Intelligent Science and Technology, 2020, 2(4): 401-411.

图/表 12

表1

图1

图2

图3

图4

图5

图6

表2

表3

表4

图7

表5

参考文献 32

[1]	SHAFI M , MOLISCH A F , SMITH P J ,et al. 5G:a tutorial overview of standards,trials,challenges,deployment,and practice[J]. IEEE Journal on Selected Areas in Communications, 2017,35(6): 1201-1221.
[2]	RAPPAPORT T S , MACCARTNEY G R , SAMIMI M K ,et al. Wideband millimeter-wave propagation measurements and channel models for future wireless communication system design[J]. IEEE Transactions on Communications, 2015,63(9): 3029-3056.
[3]	RAPPAPORT T S . Wireless communications:principles and practice[M]. New Jersey: Prentice Hall PTR, 1996.
[4]	ZAPPONE A , DI RENZO M , DEBBAH M . Wireless networks design in the era of deep learning:model-based,AI-based,or both?[J]. IEEE Transactions on Communications, 2019,67(10): 7331-7376.
[5]	HATA M . Empirical formula for propagation loss in land mobile radio services[J]. IEEE Transactions on Vehicular Technology, 1980,29(3): 317-325.
[6]	MEDEISIS A , KAJACKAS A . On the use of the universal Okumura-Hata propagation prediction model in rural areas[C]// 2000 IEEE 51st Vehicular Technology Conference. Piscataway:IEEE Press, 2000: 1815-1818.
[7]	WERNER-ALLEN G , LORINCZ K , RUIZ M ,et al. Deploying a wireless sensor network on an active volcano[J]. IEEE Internet Computing, 2006,10(2): 18-25.
[8]	DUNCAN C A . Finite difference time domain analysis of fractal antennas used in wireless communications[D]. Miami:Florida International University, 2004.
[9]	POPOOLA S I , ATAYERO A A , FARUK N ,et al. Standard propagation model tuning for path loss predictions in built-up environments[C]// International Conference on Computational Science and Its Applications. Cham:Springer, 2017: 363-375.
[10]	SUN Y H , PENG M , ZHOU Y C ,et al. Application of machine learning in wireless networks:key techniques and open issues[J]. IEEE Communications Surveys ＆ Tutorials, 2019,21(4): 3072-3108.
[11]	ALDOSSARI S M , CHEN K C . Machine learning for wireless communication channel modeling:an overview[J]. Wireless Personal Communications, 2019,106(1): 41-70.
[12]	POPESCU I , NIKITOPOULOS D , CONSTANTINOU P ,et al. ANN prediction models for outdoor environment[C]// 2006 IEEE 17th International Symposium on Personal,Indoor and Mobile Radio Communications. Piscataway:IEEE Press, 2006: 1-5.
[13]	ZHAO X N , HOU C P , WANG Q . A new SVM-based modeling method of cabin path loss prediction[J]. International Journal of Antennas and Propagation, 2013(2): 718-720.
[14]	ZINEB A B , AYADI M . A multi-wall and multi-frequency indoor path loss prediction model using artificial neural networks[J]. Arabian Journal for Science and Engineering, 2016,41(3): 987-996.
[15]	HERATH J D , SEETHARAM A , RAMESH A . A deep learning model for wireless channel quality prediction[C]// 2019 IEEE International Conference on Communications. Piscataway:IEEE Press, 2019: 1-6.
[16]	SOTIROUDIS S P , GOUDOS S K , SIAKAVARA K . Deep learning for radio propagation:using image-driven regression to estimate path loss in urban areas[J]. ICT Express, 2020,6(3): 160-165.
[17]	THRANE J , ZIBAR D , CHRISTIANSEN H L . Model-aided deep learning method for path loss prediction in mobile communication systems at 2.6 GHz[J]. IEEE Access, 2020,8: 7925-7936.
[18]	YUN Z Q , ISKANDER M F . Ray tracing for radio propagation modeling:principles and applications[J]. IEEE Access, 2015,3: 1089-1100.
[19]	KHALID S , KHALIL T , NASREEN S . A survey of feature selection and feature extraction techniques in machine learning[C]// 2014 Science and Information Conference. Piscataway:IEEE Press, 2014: 372-378.
[20]	CHANDRASHEKAR G , SAHIN F . A survey on feature selection methods[J]. Computers ＆ Electrical Engineering, 2014,40(1): 16-28.
[21]	HINTON G E , SALAKHUTDINOV R R . Reducing the dimensionality of data with neural networks[J]. Science, 2006,313(5786): 504-507.
[22]	HE K M , ZHANG X Y , REN S Q ,et al. Deep residual learning for image recognition[C]// The IEEE Conference On Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2016: 770-778.
[23]	ZADEH L A . The concept of a linguistic variable and its application on approximate reasoning-I[J]. Information Sciences, 1975,8(3): 199-249.
[24]	MENDEL J M . Uncertain rule-based fuzzy systems:introduction and new directions (second edition)[M]. Berlin: Springer, 2017: 684.
[25]	伍冬睿, 曾志刚, 莫红 ,等. 区间二型模糊集和模糊系统:综述与展望[J]. 自动化学报, 2020,46(8): 1539-1556.
	WU D R , ZENG Z G , MO H ,et al. Interval type-2 fuzzy sets and system:overview and outlook[J]. Acta Automatica Sinica, 2020,46(8): 1539-1556.
[26]	DONG X B , YU Z W , CAO W M ,et al. A survey on ensemble learning[J]. Frontiers of Computer Science, 2020: 1-18.
[27]	KRAWCZYK B , MINKU L L , GAMA J ,et al. Ensemble learning for data stream analysis:a survey[J]. Information Fusion, 2017,37: 132-156.
[28]	BREIMAN L . Stacked regressions[J]. Machine learning, 1996,24(1): 49-64.
[29]	WOLPERT D H . Stacked generalization[J]. Neural networks, 1992,5(2): 241-259.
[30]	GARIBALDI JONATHAN M, 陈虹宇, 李小双, . 差异与学习:模糊系统与模糊推理[J]. 智能科学与技术学报, 2019,1(4): 319-326.
	GARIBALDI JONATHAN M , CHEN H Y , LI X S . Variation and learning:fuzzy system and fuzzy inference[J]. Chinese Journal of Intelligent Science and Technology, 2019,1(4): 319-326.
[31]	陈德旺, 蔡际杰, 黄允浒 . 面向可解释性人工智能与大数据的模糊系统发展展望[J]. 智能科学与技术学报, 2019,1(4): 327-334.
	CHEN D W , CAI J J , HUANG Y H . Development prospect of fuzzy system oriented to interpretable artificial intelligence and big data[J]. Chinese Journal of Intelligent Science and Technology, 2019,1(4): 327-334.
[32]	杜宏庆, 陈德旺, 黄允浒 ,等. 基于改进遗传算法与支持度的模糊系统优化建模方法[J]. 智能科学与技术学报, 2020,2(2): 179-185.
	DU H Q , CHEN D W , HUANG Y H ,et al. A fuzzy system optimization modeling method based on improved genetic algorithm and support degree[J]. Chinese Journal of Intelligent Science and Technology, 2020,2(2): 179-185.

特征名称	特征含义
dis_2d	信号接收端与信号发射端之间的二维距离
dis_2d_log	信号接收端与信号发射端之间二维距离的对数形式
dis_3d	信号接收端与信号发射端之间的三维距离
dis_3d_log	信号接收端与信号发射端之间三维距离的对数形式
h	基站发射机的有效高度
h_log	基站发射机有效高度的对数形式
hori_beta	信号接收端和信号发射端的连线与发射机信号发射方向之间的二维夹角
spare_beta	信号接收端和信号发射端的连线与发射机信号发射方向之间的三维夹角

模型	MaxPE/dBm	MAE/dBm	MAPE	RMSE/dBm
Cost231-Hata	118.799	19.289	21.655%	25.952
BPNN	52.028	10.263	12.097%	12.557
ResNet	43.545	7.112	7.946%	9.025
SAE	42.889	7.445	8.303%	9.397
DBN	47.012	7.419	8.413%	9.352

模型	MaxPE/dBm	MAE/dBm	MAPE	RMSE/dBm
IT2_ResNet3	42.727	6.923	7.732%	8.794
IT2_ResNet4	43.010	6.907	7.715%	8.772
IT2_ResNet5	43.344	6.904	7.711%	8.770
IT2_DBN3	42.018	7.332	8.213%	9.264
IT2_DBN4	42.545	7.249	8.117%	9.167
IT2_DBN5	45.084	7.127	7.976%	9.034
IT2_SAE3	42.995	7.454	8.357%	9.404
IT2_SAE4	43.096	7.429	8.331%	9.377
IT2_SAE5	41.643	7.387	8.278%	9.324

模型	MaxPE/dBm	MAE/dBm	MAPE	RMSE/dBm
IT2_RSD	41.628	6.959	7.778%	8.836
IT2_2RSD	41.742	6.909	7.722%	8.775
IT2_R2SD	41.895	6.947	7.753%	8.827
IT2_RS2D	41.910	6.955	7.778%	8.828
IT2_3RSD	42.153	6.883	7.663%	8.758
IT2_2R2SD	41.809	6.906	7.713%	8.775
IT2_2RS2D	42.676	6.891	7.679%	8.763
IT2_R3SD	43.464	6.951	7.767%	8.827
IT2_R2S2D	41.057	6.949	7.763%	8.825

个体深度学习器	评价标准	集成方法
个体深度学习器	评价标准	FSE	FCE	BE	IT2FE
ResNet3	MaxPE/dBm	43.344	43.250	43.450	42.727
	MAE/dBm	7.011	6.969	6.999	6.923
	MAPE	7.838%	7.768%	7.820%	7.732%
	RMSE/dBm	8.899	8.850	8.885	8.794
RSD	MaxPE/dBm	42.553	41.596	43.318	41.628
	MAE/dBm	7.025	6.969	7.010	6.959
	MAPE	7.858%	7.792%	7.842%	7.778%
	RMSE/dBm	8.915	8.846	8.895	8.836

无线网络信号传输建模：一种区间二型模糊集成深度学习方法

Modeling signal propagation in wireless network:an interval type-2 fuzzy ensemble deep learning approach

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 32

相关文章 15

Metrics

推荐阅读 0

[1]	黄哲, 王永才, 李德英. 3D目标检测方法研究综述[J]. 智能科学与技术学报, 2023, 5(1): 7-31.
[2]	卢经纬, 程相, 王飞跃. 求解微分方程的人工智能与深度学习方法：现状及展望[J]. 智能科学与技术学报, 2022, 4(4): 461-476.
[3]	张俊, 许沛东, 陈思远, 高天露, 戴宇欣, 张科, 赵杭, 高杰迈, 白昱阳, 李金星, 张浩然, 李湘, 陈玖香. 物理-数据-知识混合驱动的人机混合增强智能系统管控方法[J]. 智能科学与技术学报, 2022, 4(4): 571-583.
[4]	陈妍, 罗雪琴, 梁伟, 谢永芳. 基于情感信息融合注意力机制的抑郁症识别[J]. 智能科学与技术学报, 2022, 4(4): 600-609.
[5]	栗仁武, 张凌霄, 高林, 李淳芃, 蒋浩. 基于点云的类级别物体姿态估计[J]. 智能科学与技术学报, 2022, 4(2): 246-254.
[6]	李琳辉, 周彬, 任威威, 连静. 行人轨迹预测方法综述[J]. 智能科学与技术学报, 2021, 3(4): 399-411.
[7]	李颖, 陈龙, 黄钊宏, 孙杨, 蔡国榕. 基于多尺度卷积神经网络特征融合的植株叶片检测技术[J]. 智能科学与技术学报, 2021, 3(3): 304-311.
[8]	田庆, 胡蓉, 李佐勇, 蔡远征, 余兆钗. 基于SE-YOLOv5s的绝缘子检测[J]. 智能科学与技术学报, 2021, 3(3): 312-321.
[9]	刘文, 胡琨林, 李岩, 刘钊. 移动目标轨迹预测方法研究综述[J]. 智能科学与技术学报, 2021, 3(2): 149-160.
[10]	张阳, 胡月, 辛东嵘. 一种考虑时空关联的深度学习短时交通流预测方法[J]. 智能科学与技术学报, 2021, 3(2): 172-178.
[11]	胡毅, 瞿博阳, 梁静, 王杰, 王艳丽. 进化集成学习算法综述[J]. 智能科学与技术学报, 2021, 3(1): 18-35.
[12]	刘栋军, 王宇涵, 凌文芬, 彭勇, 孔万增. 基于脑机协同智能的情绪识别[J]. 智能科学与技术学报, 2021, 3(1): 65-75.
[13]	田思佳,顾强,胡蓉,李锐戈,何顶新. 一种基于深度学习的机械臂分拣方法[J]. 智能科学与技术学报, 2020, 2(3): 268-274.
[14]	王飞跃,曹东璞,魏庆来. 强化学习：迈向知行合一的智能机制与算法[J]. 智能科学与技术学报, 2020, 2(2): 101-106.
[15]	袁小锋,王雅琳,阳春华,桂卫华. 深度学习在流程工业过程数据建模中的应用[J]. 智能科学与技术学报, 2020, 2(2): 107-115.